Compare commits
No commits in common. "0ded87a0fb099ffa669a222ed648fbf81ad2d022" and "aa4bc26c533d63dc9845dd7941329670eaa9f782" have entirely different histories.
0ded87a0fb
...
aa4bc26c53
3
.gitignore
vendored
3
.gitignore
vendored
@ -199,5 +199,4 @@ artifacts/
|
||||
lightning_logs/
|
||||
wne-masters-thesis-testing/
|
||||
notebooks/cache/
|
||||
notebooks/images/
|
||||
.DS_Store
|
||||
notebooks/images/
|
||||
119
README.md
119
README.md
@ -1,48 +1,93 @@
|
||||
# WNE Masters Thesis
|
||||
|
||||
The repository contains the implementation of evaluation framework and strategies for master's thesis: "Informer In Algorithmic Investment
|
||||
Strategies on High Frequency Bitcoin Data"
|
||||
|
||||
The implementation uses [PytorchForecasting](https://pytorch-forecasting.readthedocs.io/en/stable/) framework, and the Informer implementation is taken from the following [Github repository](https://github.com/martinwhl/Informer-PyTorch-Lightning). Experiment management is done using [Weights&Biases](https://wandb.ai/site).
|
||||
|
||||
## Repository structure
|
||||
Thre repository is organized in the following way:
|
||||
- `src/ml`: contains the code that implements utilities for training the machine learning models.
|
||||
- `src/informer`: contains the implementation of the Informer.
|
||||
- `src/strategy`: contains the implementation of the strategies, as well as the methods for efficient evaluation and hyperparameter serach.
|
||||
- `notebooks/`: contains the evaluations of various srategies and methods for generating the visualistions used in the publication.
|
||||
- `scripts/`: contains the main training script.
|
||||
- `configs/`: contains configurations for different experiments of ml models, that can be passed to the main training script.
|
||||
## Getting started
|
||||
|
||||
To make it easy for you to get started with GitLab, here's a list of recommended next steps.
|
||||
|
||||
Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
|
||||
|
||||
## Add your files
|
||||
|
||||
- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
|
||||
- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
|
||||
|
||||
```
|
||||
cd existing_repo
|
||||
git remote add origin https://gitlab.com/FilipStefaniuk/wne-msc-thesis.git
|
||||
git branch -M main
|
||||
git push -uf origin main
|
||||
```
|
||||
|
||||
## Integrate with your tools
|
||||
|
||||
- [ ] [Set up project integrations](https://gitlab.com/FilipStefaniuk/wne-msc-thesis/-/settings/integrations)
|
||||
|
||||
## Collaborate with your team
|
||||
|
||||
- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
|
||||
- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
|
||||
- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
|
||||
- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
|
||||
- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
|
||||
|
||||
## Test and Deploy
|
||||
|
||||
Use the built-in continuous integration in GitLab.
|
||||
|
||||
- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html)
|
||||
- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
|
||||
- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
|
||||
- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
|
||||
- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
|
||||
|
||||
***
|
||||
|
||||
# Editing this README
|
||||
|
||||
When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
|
||||
|
||||
## Suggestions for a good README
|
||||
|
||||
Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
|
||||
|
||||
## Name
|
||||
Choose a self-explaining name for your project.
|
||||
|
||||
## Description
|
||||
Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
|
||||
|
||||
## Badges
|
||||
On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
|
||||
|
||||
## Visuals
|
||||
Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
|
||||
|
||||
## Installation
|
||||
Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
|
||||
|
||||
Install package with the following command:
|
||||
```
|
||||
pip install -e .
|
||||
```
|
||||
## Usage
|
||||
Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
|
||||
|
||||
## Training
|
||||
## Support
|
||||
Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
|
||||
|
||||
Usage of the training script:
|
||||
```
|
||||
usage: train.py [-h] [-p PROJECT] [-l LOG_LEVEL] [-s SEED] [-n LOG_INTERVAL] [-v VAL_CHECK_INTERVAL] [-t PATIENCE] [--no-wandb] [--store-predictions] config
|
||||
## Roadmap
|
||||
If you have ideas for releases in the future, it is a good idea to list them in the README.
|
||||
|
||||
positional arguments:
|
||||
config Experiment configuration file in yaml format.
|
||||
## Contributing
|
||||
State if you are open to contributions and what your requirements are for accepting them.
|
||||
|
||||
optional arguments:
|
||||
-h, --help show this help message and exit
|
||||
-p PROJECT, --project PROJECT
|
||||
W&B project name. (default: wne-masters-thesis-testing)
|
||||
-l LOG_LEVEL, --log-level LOG_LEVEL
|
||||
Sets the log level. (default: 20)
|
||||
-s SEED, --seed SEED Random seed for the training. (default: 42)
|
||||
-n LOG_INTERVAL, --log-interval LOG_INTERVAL
|
||||
Log every n steps. (default: 100)
|
||||
-v VAL_CHECK_INTERVAL, --val-check-interval VAL_CHECK_INTERVAL
|
||||
Run validation every n batches. (default: 300)
|
||||
-t PATIENCE, --patience PATIENCE
|
||||
Patience for early stopping. (default: 5)
|
||||
--no-wandb Disables wandb, for testing. (default: False)
|
||||
--store-predictions Whether to store predictions of the best run. (default: False)
|
||||
```
|
||||
For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
|
||||
|
||||
You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
|
||||
|
||||
## Authors and acknowledgment
|
||||
Show your appreciation to those who have contributed to the project.
|
||||
|
||||
## License
|
||||
For open source projects, say how it is licensed.
|
||||
|
||||
## Project status
|
||||
If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
|
||||
|
||||
@ -1,11 +1,11 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-15m-rmse-eval
|
||||
name: informer-btcusdt-15m-gmadl-eval
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-15m-rmse.yaml"
|
||||
- "./configs/experiments/informer-btcusdt-15m-gmadl2.yaml"
|
||||
- "--patience"
|
||||
- "20"
|
||||
- "--store-predictions"
|
||||
@ -1,25 +0,0 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-1m-gmadl-eval
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-1m-gmadl.yaml"
|
||||
- "--patience"
|
||||
- "20"
|
||||
- "--store-predictions"
|
||||
method: grid
|
||||
metric:
|
||||
goal: minimize
|
||||
name: val_loss
|
||||
parameters:
|
||||
data:
|
||||
parameters:
|
||||
dataset:
|
||||
value: "btc-usdt-1m:latest"
|
||||
validation:
|
||||
value: 0.2
|
||||
sliding_window:
|
||||
min: 0
|
||||
max: 5
|
||||
@ -1,11 +1,11 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-30m-rmse-eval
|
||||
name: informer-btcusdt-30m-gmadl-eval
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-30m-rmse.yaml"
|
||||
- "./configs/experiments/informer-btcusdt-30m-gmadl2.yaml"
|
||||
- "--patience"
|
||||
- "20"
|
||||
- "--store-predictions"
|
||||
@ -1,11 +1,11 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-5m-rmse-eval
|
||||
name: informer-btcusdt-5m-quantile-eval
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-5m-rmse.yaml"
|
||||
- "./configs/experiments/informer-btcusdt-5m-quantile-returns.yaml"
|
||||
- "--patience"
|
||||
- "20"
|
||||
- "--store-predictions"
|
||||
@ -22,31 +22,12 @@ fields:
|
||||
- "open_price"
|
||||
- "close_price"
|
||||
- "volume"
|
||||
- "open_to_close_price"
|
||||
- "high_to_close_price"
|
||||
- "low_to_close_price"
|
||||
- "high_to_low_price"
|
||||
- "returns"
|
||||
- "log_returns"
|
||||
- "vol_1h"
|
||||
- "macd"
|
||||
- "macd_signal"
|
||||
- "rsi"
|
||||
- "low_bband_to_close_price"
|
||||
- "up_bband_to_close_price"
|
||||
- "mid_bband_to_close_price"
|
||||
- "sma_1h_to_close_price"
|
||||
- "sma_1d_to_close_price"
|
||||
- "sma_7d_to_close_price"
|
||||
- "ema_1h_to_close_price"
|
||||
- "ema_1d_to_close_price"
|
||||
dynamic_unknown_cat: []
|
||||
dynamic_known_real:
|
||||
- "effective_rates"
|
||||
- "vix_close_price"
|
||||
- "fear_greed_index"
|
||||
- "vol_1d"
|
||||
- "vol_7d"
|
||||
dynamic_known_cat:
|
||||
- "hour"
|
||||
- "weekday"
|
||||
|
||||
@ -1,14 +1,14 @@
|
||||
future_window:
|
||||
value: 2
|
||||
past_window:
|
||||
value: 28
|
||||
value: 30
|
||||
batch_size:
|
||||
value: 256
|
||||
value: 128
|
||||
max_epochs:
|
||||
value: 40
|
||||
data:
|
||||
value:
|
||||
dataset: "btc-usdt-1m:latest"
|
||||
dataset: "btc-usdt-15m:latest"
|
||||
sliding_window: 0
|
||||
validation: 0.2
|
||||
fields:
|
||||
@ -63,8 +63,8 @@ model:
|
||||
d_model: 256
|
||||
d_fully_connected: 256
|
||||
n_attention_heads: 2
|
||||
dropout: 0.01
|
||||
n_encoder_layers: 1
|
||||
n_decoder_layers: 3
|
||||
dropout: 0.1
|
||||
n_encoder_layers: 2
|
||||
n_decoder_layers: 1
|
||||
learning_rate: 0.0001
|
||||
optimizer: "Adam"
|
||||
@ -14,7 +14,7 @@ data:
|
||||
fields:
|
||||
value:
|
||||
time_index: "time_index"
|
||||
target: "returns"
|
||||
target: "close_price"
|
||||
group_ids: ["group_id"]
|
||||
dynamic_unknown_real:
|
||||
- "high_price"
|
||||
|
||||
@ -1,68 +0,0 @@
|
||||
future_window:
|
||||
value: 2
|
||||
past_window:
|
||||
value: 110
|
||||
batch_size:
|
||||
value: 64
|
||||
max_epochs:
|
||||
value: 30
|
||||
data:
|
||||
value:
|
||||
dataset: "btc-usdt-15m:latest"
|
||||
sliding_window: 0
|
||||
validation: 0.2
|
||||
fields:
|
||||
value:
|
||||
time_index: "time_index"
|
||||
target: "returns"
|
||||
group_ids: ["group_id"]
|
||||
dynamic_unknown_real:
|
||||
- "high_price"
|
||||
- "low_price"
|
||||
- "open_price"
|
||||
- "close_price"
|
||||
- "volume"
|
||||
- "open_to_close_price"
|
||||
- "high_to_close_price"
|
||||
- "low_to_close_price"
|
||||
- "high_to_low_price"
|
||||
- "returns"
|
||||
- "log_returns"
|
||||
- "vol_1h"
|
||||
- "macd"
|
||||
- "macd_signal"
|
||||
- "rsi"
|
||||
- "low_bband_to_close_price"
|
||||
- "up_bband_to_close_price"
|
||||
- "mid_bband_to_close_price"
|
||||
- "sma_1h_to_close_price"
|
||||
- "sma_1d_to_close_price"
|
||||
- "sma_7d_to_close_price"
|
||||
- "ema_1h_to_close_price"
|
||||
- "ema_1d_to_close_price"
|
||||
dynamic_unknown_cat: []
|
||||
dynamic_known_real:
|
||||
- "effective_rates"
|
||||
- "vix_close_price"
|
||||
- "fear_greed_index"
|
||||
- "vol_1d"
|
||||
- "vol_7d"
|
||||
dynamic_known_cat:
|
||||
- "hour"
|
||||
- "weekday"
|
||||
static_real: []
|
||||
static_cat: []
|
||||
loss:
|
||||
value:
|
||||
name: "RMSE"
|
||||
model:
|
||||
value:
|
||||
name: "Informer"
|
||||
d_model: 512
|
||||
d_fully_connected: 256
|
||||
n_attention_heads: 4
|
||||
dropout: 0.1
|
||||
n_encoder_layers: 3
|
||||
n_decoder_layers: 2
|
||||
learning_rate: 0.0005
|
||||
optimizer: "Adam"
|
||||
@ -1,11 +1,11 @@
|
||||
future_window:
|
||||
value: 2
|
||||
past_window:
|
||||
value: 115
|
||||
value: 26
|
||||
batch_size:
|
||||
value: 64
|
||||
value: 128
|
||||
max_epochs:
|
||||
value: 50
|
||||
value: 40
|
||||
data:
|
||||
value:
|
||||
dataset: "btc-usdt-30m:latest"
|
||||
@ -54,15 +54,17 @@ fields:
|
||||
static_cat: []
|
||||
loss:
|
||||
value:
|
||||
name: "RMSE"
|
||||
name: "GMADL"
|
||||
a: 1000
|
||||
b: 2
|
||||
model:
|
||||
value:
|
||||
name: "Informer"
|
||||
d_model: 256
|
||||
d_fully_connected: 512
|
||||
n_attention_heads: 2
|
||||
dropout: 0.2
|
||||
d_fully_connected: 256
|
||||
n_attention_heads: 4
|
||||
dropout: 0.1
|
||||
n_encoder_layers: 2
|
||||
n_decoder_layers: 2
|
||||
learning_rate: 0.0005
|
||||
n_decoder_layers: 1
|
||||
learning_rate: 0.001
|
||||
optimizer: "Adam"
|
||||
@ -14,7 +14,7 @@ data:
|
||||
fields:
|
||||
value:
|
||||
time_index: "time_index"
|
||||
target: "returns"
|
||||
target: "close_price"
|
||||
group_ids: ["group_id"]
|
||||
dynamic_unknown_real:
|
||||
- "high_price"
|
||||
|
||||
@ -22,31 +22,12 @@ fields:
|
||||
- "open_price"
|
||||
- "close_price"
|
||||
- "volume"
|
||||
- "open_to_close_price"
|
||||
- "high_to_close_price"
|
||||
- "low_to_close_price"
|
||||
- "high_to_low_price"
|
||||
- "returns"
|
||||
- "log_returns"
|
||||
- "vol_1h"
|
||||
- "macd"
|
||||
- "macd_signal"
|
||||
- "rsi"
|
||||
- "low_bband_to_close_price"
|
||||
- "up_bband_to_close_price"
|
||||
- "mid_bband_to_close_price"
|
||||
- "sma_1h_to_close_price"
|
||||
- "sma_1d_to_close_price"
|
||||
- "sma_7d_to_close_price"
|
||||
- "ema_1h_to_close_price"
|
||||
- "ema_1d_to_close_price"
|
||||
dynamic_unknown_cat: []
|
||||
dynamic_known_real:
|
||||
- "effective_rates"
|
||||
- "vix_close_price"
|
||||
- "fear_greed_index"
|
||||
- "vol_1d"
|
||||
- "vol_7d"
|
||||
dynamic_known_cat:
|
||||
- "hour"
|
||||
- "weekday"
|
||||
|
||||
@ -14,7 +14,7 @@ data:
|
||||
fields:
|
||||
value:
|
||||
time_index: "time_index"
|
||||
target: "returns"
|
||||
target: "close_price"
|
||||
group_ids: ["group_id"]
|
||||
dynamic_unknown_real:
|
||||
- "high_price"
|
||||
|
||||
@ -1,68 +0,0 @@
|
||||
future_window:
|
||||
value: 2
|
||||
past_window:
|
||||
value: 102
|
||||
batch_size:
|
||||
value: 64
|
||||
max_epochs:
|
||||
value: 30
|
||||
data:
|
||||
value:
|
||||
dataset: "btc-usdt-5m:latest"
|
||||
sliding_window: 0
|
||||
validation: 0.2
|
||||
fields:
|
||||
value:
|
||||
time_index: "time_index"
|
||||
target: "returns"
|
||||
group_ids: ["group_id"]
|
||||
dynamic_unknown_real:
|
||||
- "high_price"
|
||||
- "low_price"
|
||||
- "open_price"
|
||||
- "close_price"
|
||||
- "volume"
|
||||
- "open_to_close_price"
|
||||
- "high_to_close_price"
|
||||
- "low_to_close_price"
|
||||
- "high_to_low_price"
|
||||
- "returns"
|
||||
- "log_returns"
|
||||
- "vol_1h"
|
||||
- "macd"
|
||||
- "macd_signal"
|
||||
- "rsi"
|
||||
- "low_bband_to_close_price"
|
||||
- "up_bband_to_close_price"
|
||||
- "mid_bband_to_close_price"
|
||||
- "sma_1h_to_close_price"
|
||||
- "sma_1d_to_close_price"
|
||||
- "sma_7d_to_close_price"
|
||||
- "ema_1h_to_close_price"
|
||||
- "ema_1d_to_close_price"
|
||||
dynamic_unknown_cat: []
|
||||
dynamic_known_real:
|
||||
- "effective_rates"
|
||||
- "vix_close_price"
|
||||
- "fear_greed_index"
|
||||
- "vol_1d"
|
||||
- "vol_7d"
|
||||
dynamic_known_cat:
|
||||
- "hour"
|
||||
- "weekday"
|
||||
static_real: []
|
||||
static_cat: []
|
||||
loss:
|
||||
value:
|
||||
name: "RMSE"
|
||||
model:
|
||||
value:
|
||||
name: "Informer"
|
||||
d_model: 512
|
||||
d_fully_connected: 512
|
||||
n_attention_heads: 4
|
||||
dropout: 0.3
|
||||
n_encoder_layers: 2
|
||||
n_decoder_layers: 3
|
||||
learning_rate: 0.0005
|
||||
optimizer: "Adam"
|
||||
@ -1,41 +0,0 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-15m-rmse-sweep
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-15m-rmse.yaml"
|
||||
- "--patience"
|
||||
- "15"
|
||||
method: random
|
||||
metric:
|
||||
goal: minimize
|
||||
name: val_loss
|
||||
parameters:
|
||||
past_window:
|
||||
distribution: int_uniform
|
||||
min: 20
|
||||
max: 120
|
||||
batch_size:
|
||||
values: [64, 128, 256]
|
||||
model:
|
||||
parameters:
|
||||
name:
|
||||
value: "Informer"
|
||||
d_model:
|
||||
values: [256, 512, 1024]
|
||||
d_fully_connected:
|
||||
values: [256, 512, 1024]
|
||||
n_attention_heads:
|
||||
values: [1, 2, 4]
|
||||
dropout:
|
||||
values: [0.05, 0.1, 0.2, 0.3]
|
||||
n_encoder_layers:
|
||||
values: [1, 2, 3]
|
||||
n_decoder_layers:
|
||||
values: [1, 2, 3]
|
||||
learning_rate:
|
||||
values: [0.001, 0.0005, 0.0001]
|
||||
optimizer:
|
||||
value: "Adam"
|
||||
@ -1,43 +0,0 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-30m-rmse-sweep
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-30m-rmse.yaml"
|
||||
- "--patience"
|
||||
- "15"
|
||||
- "--val-check-interval"
|
||||
- "100"
|
||||
method: random
|
||||
metric:
|
||||
goal: minimize
|
||||
name: val_loss
|
||||
parameters:
|
||||
past_window:
|
||||
distribution: int_uniform
|
||||
min: 20
|
||||
max: 120
|
||||
batch_size:
|
||||
values: [64, 128, 256]
|
||||
model:
|
||||
parameters:
|
||||
name:
|
||||
value: "Informer"
|
||||
d_model:
|
||||
values: [256, 512, 1024]
|
||||
d_fully_connected:
|
||||
values: [256, 512, 1024]
|
||||
n_attention_heads:
|
||||
values: [1, 2, 4]
|
||||
dropout:
|
||||
values: [0.05, 0.1, 0.2, 0.3]
|
||||
n_encoder_layers:
|
||||
values: [1, 2, 3]
|
||||
n_decoder_layers:
|
||||
values: [1, 2, 3]
|
||||
learning_rate:
|
||||
values: [0.001, 0.0005, 0.0001]
|
||||
optimizer:
|
||||
value: "Adam"
|
||||
@ -1,41 +0,0 @@
|
||||
program: ./scripts/train.py
|
||||
name: informer-btcusdt-5m-rmse-sweep
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/informer-btcusdt-5m-rmse.yaml"
|
||||
- "--patience"
|
||||
- "15"
|
||||
method: random
|
||||
metric:
|
||||
goal: minimize
|
||||
name: val_loss
|
||||
parameters:
|
||||
past_window:
|
||||
distribution: int_uniform
|
||||
min: 20
|
||||
max: 120
|
||||
batch_size:
|
||||
values: [64, 128, 256]
|
||||
model:
|
||||
parameters:
|
||||
name:
|
||||
value: "Informer"
|
||||
d_model:
|
||||
values: [256, 512, 1024]
|
||||
d_fully_connected:
|
||||
values: [256, 512, 1024]
|
||||
n_attention_heads:
|
||||
values: [1, 2, 4]
|
||||
dropout:
|
||||
values: [0.05, 0.1, 0.2, 0.3]
|
||||
n_encoder_layers:
|
||||
values: [1, 2, 3]
|
||||
n_decoder_layers:
|
||||
values: [1, 2, 3]
|
||||
learning_rate:
|
||||
values: [0.001, 0.0005, 0.0001]
|
||||
optimizer:
|
||||
value: "Adam"
|
||||
38
configs/sweeps/temporal-fusion-btcusdt-gmadl.yaml
Normal file
38
configs/sweeps/temporal-fusion-btcusdt-gmadl.yaml
Normal file
@ -0,0 +1,38 @@
|
||||
program: ./scripts/train.py
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/temporal-fusion-btcusdt-gmadl.yaml"
|
||||
- "--patience"
|
||||
- "10"
|
||||
method: random
|
||||
metric:
|
||||
goal: minimize
|
||||
name: val_loss
|
||||
parameters:
|
||||
past_window:
|
||||
distribution: int_uniform
|
||||
min: 20
|
||||
max: 100
|
||||
batch_size:
|
||||
values: [64, 128, 256]
|
||||
model:
|
||||
parameters:
|
||||
name:
|
||||
value: "TemporalFusionTransformer"
|
||||
share_single_variable_networks:
|
||||
value: false
|
||||
hidden_size:
|
||||
values: [128, 256, 512, 1024]
|
||||
dropout:
|
||||
values: [0.0, 0.1, 0.2, 0.3]
|
||||
attention_head_size:
|
||||
values: [1, 2, 4, 6]
|
||||
hidden_continuous_size:
|
||||
values: [4, 8, 16, 32]
|
||||
learning_rate:
|
||||
value: 0.001
|
||||
optimizer:
|
||||
value: "Adam"
|
||||
36
configs/sweeps/temporal-fusion-btcusdt-quantile.yaml
Normal file
36
configs/sweeps/temporal-fusion-btcusdt-quantile.yaml
Normal file
@ -0,0 +1,36 @@
|
||||
program: ./scripts/train.py
|
||||
project: wne-masters-thesis-testing
|
||||
command:
|
||||
- ${env}
|
||||
- ${interpreter}
|
||||
- ${program}
|
||||
- "./configs/experiments/temporal-fusion-btcusdt-quantile.yaml"
|
||||
method: random
|
||||
metric:
|
||||
goal: minimize
|
||||
name: val_loss
|
||||
parameters:
|
||||
past_window:
|
||||
distribution: int_uniform
|
||||
min: 5
|
||||
max: 100
|
||||
batch_size:
|
||||
values: [64, 128, 256]
|
||||
model:
|
||||
parameters:
|
||||
name:
|
||||
value: "TemporalFusionTransformer"
|
||||
share_single_variable_networks:
|
||||
value: false
|
||||
hidden_size:
|
||||
values: [128, 256, 512, 1024]
|
||||
dropout:
|
||||
values: [0.0, 0.1, 0.2, 0.3, 0.4]
|
||||
attention_head_size:
|
||||
values: [1, 2, 4, 6]
|
||||
hidden_continuous_size:
|
||||
values: [4, 8, 16, 32]
|
||||
learning_rate:
|
||||
values: [0.01, 0.001, 0.0005, 0.0001]
|
||||
optimizer:
|
||||
values: ["Adam", "RMSProp", "Adagrad"]
|
||||
@ -2,7 +2,7 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -42,7 +42,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -52,7 +52,7 @@
|
||||
"Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-15m:latest, 248.65MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:0.8\n"
|
||||
"Done. 0:0:0.5\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -67,7 +67,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -81,7 +81,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -90,19 +90,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 639.58it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:05<00:00, 658.38it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 624.58it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:05<00:00, 649.63it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 627.23it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 633.46it/s]\n"
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 614.41it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:08<00:00, 479.05it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 554.94it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 575.21it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 571.03it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 576.86it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -136,19 +136,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 11088/11088 [00:19<00:00, 560.36it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:22<00:00, 495.98it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:19<00:00, 556.67it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:19<00:00, 554.79it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:18<00:00, 590.13it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:17<00:00, 650.44it/s]\n"
|
||||
"100%|██████████| 11088/11088 [00:19<00:00, 580.54it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:17<00:00, 627.38it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:17<00:00, 624.72it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:18<00:00, 586.62it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:17<00:00, 618.44it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:18<00:00, 597.40it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -179,95 +179,6 @@
|
||||
"# plot_sweep_results(pd.DataFrame([result for result, _ in rsi_sweep_results[0]]), parameters=RSI_PARAMS.keys())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Model with rmse loss\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/inpvjdsp'\n",
|
||||
"train_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"valid_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'valid')\n",
|
||||
"test_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'test')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [00:39<00:00, 29.69it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:41<00:00, 28.17it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:40<00:00, 29.34it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:40<00:00, 29.28it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:40<00:00, 29.11it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:40<00:00, 29.39it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"MODEL_RMSE_LOSS_FILTER = lambda p: (\n",
|
||||
" ((p['enter_long'] is not None and (p['enter_short'] is not None or p['exit_long'] is not None))\n",
|
||||
" or (p['enter_short'] is not None and (p['exit_short'] is not None or p['enter_long'] is not None)))\n",
|
||||
" and (p['enter_short'] is None or p['exit_long'] is None or (p['exit_long'] > p['enter_short']))\n",
|
||||
" and (p['enter_long'] is None or p['exit_short'] is None or (p['exit_short'] < p['enter_long'])))\n",
|
||||
"\n",
|
||||
"rmse_model_sweep_results = []\n",
|
||||
"for (in_sample, _), train_preds, valid_preds, test_preds in zip(data_windows, train_pred_windows, valid_pred_windows, test_pred_windows):\n",
|
||||
" data_part = int((1 - VALID_PART) * len(in_sample))\n",
|
||||
" params={\n",
|
||||
" 'predictions': [get_predictions_dataframe(train_preds, valid_preds, test_preds)],\n",
|
||||
" 'enter_long': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" 'exit_long': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'enter_short': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'exit_short': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" # 'enter_short': [None],\n",
|
||||
" # 'exit_short': [None],\n",
|
||||
" }\n",
|
||||
" \n",
|
||||
" rmse_model_sweep_results.append(parameter_sweep(\n",
|
||||
" in_sample[data_part-PADDING:],\n",
|
||||
" ModelGmadlPredictionsStrategy,\n",
|
||||
" params,\n",
|
||||
" params_filter=MODEL_RMSE_LOSS_FILTER,\n",
|
||||
" padding=PADDING,\n",
|
||||
" interval=INTERVAL,\n",
|
||||
" sort_by=METRIC))\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"rmse_model_best_strategies = [[strat for _, strat in results[:TOP_N]] for results in rmse_model_sweep_results]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
@ -275,7 +186,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -320,12 +231,12 @@
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1125/1125 [00:25<00:00, 44.03it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:20<00:00, 53.68it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:20<00:00, 54.38it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:20<00:00, 54.70it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:20<00:00, 54.23it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:21<00:00, 53.31it/s]\n"
|
||||
"100%|██████████| 1125/1125 [00:21<00:00, 51.66it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:20<00:00, 53.98it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:22<00:00, 49.63it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:24<00:00, 45.57it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 47.76it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:24<00:00, 46.33it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -412,19 +323,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [00:22<00:00, 53.42it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:19<00:00, 59.87it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 66.89it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 65.52it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 67.44it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 67.15it/s]\n"
|
||||
"100%|██████████| 1176/1176 [00:19<00:00, 60.00it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:19<00:00, 61.63it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:16<00:00, 69.59it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 65.37it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 66.33it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:17<00:00, 67.86it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -461,7 +372,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -470,12 +381,11 @@
|
||||
" 'buy_and_hold': buyandhold_best_strategies,\n",
|
||||
" 'macd_strategies': macd_best_strategies,\n",
|
||||
" 'rsi_strategies': rsi_best_strategies,\n",
|
||||
" 'rmse_model': rmse_model_best_strategies,\n",
|
||||
" 'quantile_model': quantile_model_best_strategies,\n",
|
||||
" 'gmadl_model': gmadl_model_best_strategies\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"with open('cache/15min-best-strategies-v2.pkl', 'wb') as outp:\n",
|
||||
"with open('cache/15min-best-strategies.pkl', 'wb') as outp:\n",
|
||||
" pickle.dump(best_strategies, outp, pickle.HIGHEST_PROTOCOL)"
|
||||
]
|
||||
},
|
||||
@ -488,11 +398,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('cache/15min-best-strategies-v2.pkl', 'rb') as inpt:\n",
|
||||
"with open('cache/15min-best-strategies.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies = pickle.load(inpt)"
|
||||
]
|
||||
},
|
||||
@ -606,56 +516,6 @@
|
||||
"print(latextable.draw_latex(table_rsi_params))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lcccc}\n",
|
||||
"\t\t\t\\textbf{Window} & \\textbf{\\textit{enter long}} & \\textbf{\\textit{exit Long}} & \\textbf{\\textit{enter Short}} & \\textbf{\\textit{exit Short}} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tW1-15min & 0.002 & - & -0.001 & - \\\\\n",
|
||||
"\t\t\tW2-15min & - & - & -0.002 & 0.002 \\\\\n",
|
||||
"\t\t\tW3-15min & - & - & -0.001 & 0.002 \\\\\n",
|
||||
"\t\t\tW4-15min & 0.001 & - & -0.002 & - \\\\\n",
|
||||
"\t\t\tW5-15min & - & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\tW6-15min & - & - & -0.002 & 0.001 \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"table_rmse_params = Texttable()\n",
|
||||
"table_rmse_params.set_deco(Texttable.HEADER)\n",
|
||||
"table_rmse_params.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\"])\n",
|
||||
"table_rmse_params.header([\n",
|
||||
" \"\\\\textbf{Window}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{enter long}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{exit Long}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{enter Short}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{exit Short}}\",\n",
|
||||
"])\n",
|
||||
"\n",
|
||||
"for i, rmse_strategy in enumerate(best_strategies['rmse_model']):\n",
|
||||
" rmse_strategy_info = rmse_strategy[0].info()\n",
|
||||
" table_rmse_params.add_row([\n",
|
||||
" f\"W{i+1}-{INTERVAL}\",\n",
|
||||
" rmse_strategy_info['enter_long'] or '-',\n",
|
||||
" rmse_strategy_info['exit_long'] or '-',\n",
|
||||
" rmse_strategy_info['enter_short'] or '-',\n",
|
||||
" rmse_strategy_info['exit_short'] or '-'\n",
|
||||
" ])\n",
|
||||
"print(latextable.draw_latex(table_rmse_params))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
@ -767,32 +627,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def results_plot(idx, result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model, width=850, height=500, notitle=False, v_lines=None):\n",
|
||||
"def results_plot(idx, result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model, width=850, height=500, notitle=False):\n",
|
||||
"\n",
|
||||
" fig = go.Figure([\n",
|
||||
" go.Scatter(y=result_buyandhold['portfolio_value'], x=result_buyandhold['time'], name=\"Buy and Hold\"),\n",
|
||||
" go.Scatter(y=result_macd['portfolio_value'], x=result_macd['time'], name=\"MACD Strategy\"),\n",
|
||||
" go.Scatter(y=result_rsi['portfolio_value'], x=result_rsi['time'], name=\"RSI Strategy\"),\n",
|
||||
" go.Scatter(y=result_rmse_model['portfolio_value'], x=result_rmse_model['time'], name='RMSE Informer Strategy'),\n",
|
||||
" go.Scatter(y=result_quantile_model['portfolio_value'], x=result_quantile_model['time'], name='Quantile Informer Strategy'),\n",
|
||||
" go.Scatter(y=result_gmadl_model['portfolio_value'], x=result_gmadl_model['time'], name='GMADL Informer Strategy')\n",
|
||||
" ])\n",
|
||||
" \n",
|
||||
" if v_lines:\n",
|
||||
" for v_line in v_lines:\n",
|
||||
" fig.add_shape(\n",
|
||||
" go.layout.Shape(type=\"line\",\n",
|
||||
" yref=\"paper\",\n",
|
||||
" xref=\"x\",\n",
|
||||
" x0=v_line,\n",
|
||||
" x1=v_line,\n",
|
||||
" y0=0,\n",
|
||||
" y1=1,\n",
|
||||
" line=dict(dash='dash', color='rgb(140,140,140)')))\n",
|
||||
" fig.update_layout(\n",
|
||||
" title={\n",
|
||||
" 'text': f\"W{idx}-{INTERVAL}\",\n",
|
||||
@ -836,7 +683,7 @@
|
||||
" fig.write_image(f\"images/eval-w{idx}-{INTERVAL}.png\")\n",
|
||||
" fig.show()\n",
|
||||
" \n",
|
||||
"def results_table(result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model):\n",
|
||||
"def results_table(result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model):\n",
|
||||
" table_eval_windows = Texttable()\n",
|
||||
" table_eval_windows.set_deco(Texttable.HEADER)\n",
|
||||
" table_eval_windows.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\"])\n",
|
||||
@ -859,7 +706,6 @@
|
||||
" ('Buy and Hold', result_buyandhold),\n",
|
||||
" ('MACD Strategy', result_macd),\n",
|
||||
" ('RSI Strategy', result_rsi),\n",
|
||||
" ('RMSE Informer', result_rmse_model),\n",
|
||||
" ('Quantile Informer', result_quantile_model),\n",
|
||||
" ('GMADL Informer', result_gmadl_model)\n",
|
||||
" ]\n",
|
||||
@ -867,10 +713,10 @@
|
||||
" table_eval_windows.add_row([\n",
|
||||
" strategy_name,\n",
|
||||
" result['value'],\n",
|
||||
" f\"{result['arc']*100:.2f}\\%\",\n",
|
||||
" f\"{result['asd']*100:.2f}\\%\",\n",
|
||||
" result['arc'],\n",
|
||||
" result['asd'],\n",
|
||||
" result['ir'],\n",
|
||||
" f\"{result['md']*100:.2f}\\%\",\n",
|
||||
" result['md'],\n",
|
||||
" result['mod_ir'],\n",
|
||||
" result['n_trades'],\n",
|
||||
" f\"{result['long_pos']*100:.2f}\\%\",\n",
|
||||
@ -882,154 +728,61 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.933 & -13.15\\% & 66.69\\% & -0.197 & 51.81\\% & -0.050 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.357 & -87.59\\% & 66.96\\% & -1.308 & 73.46\\% & -1.559 & 852 & 52.49\\% & 47.51\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 0.621 & -61.93\\% & 66.94\\% & -0.925 & 48.44\\% & -1.183 & 882 & 58.61\\% & 41.39\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.498 & 127.03\\% & 52.56\\% & 2.417 & 22.20\\% & 13.827 & 3 & 0.00\\% & 61.05\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.715 & -49.34\\% & 66.74\\% & -0.739 & 40.17\\% & -0.908 & 182 & 52.75\\% & 47.25\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 2.173 & 382.27\\% & 66.83\\% & 5.720 & 29.76\\% & 73.474 & 146 & 36.88\\% & 63.12\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.548 & -70.48\\% & 72.12\\% & -0.977 & 63.18\\% & -1.090 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.714 & -49.48\\% & 72.07\\% & -0.687 & 50.67\\% & -0.670 & 118 & 57.61\\% & 42.39\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.141 & 30.61\\% & 72.05\\% & 0.425 & 49.51\\% & 0.263 & 58 & 19.64\\% & 80.36\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.903 & -18.73\\% & 15.66\\% & -1.196 & 14.91\\% & -1.503 & 202 & 4.74\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 0.885 & -21.88\\% & 72.10\\% & -0.303 & 43.48\\% & -0.153 & 54 & 35.85\\% & 64.15\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.016 & 3.26\\% & 50.58\\% & 0.065 & 37.76\\% & 0.006 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.060 & 12.62\\% & 50.57\\% & 0.250 & 38.35\\% & 0.082 & 55 & 66.38\\% & 32.66\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 0.898 & -19.62\\% & 50.65\\% & -0.387 & 25.20\\% & -0.302 & 174 & 23.30\\% & 76.70\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.982 & -3.55\\% & 50.69\\% & -0.070 & 34.60\\% & -0.007 & 2 & 0.00\\% & 100.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.081 & 17.17\\% & 40.53\\% & 0.424 & 31.82\\% & 0.229 & 103 & 0.00\\% & 53.36\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.158 & 34.60\\% & 31.80\\% & 1.088 & 18.06\\% & 2.085 & 32 & 0.00\\% & 59.07\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.231 & 52.34\\% & 44.11\\% & 1.186 & 22.01\\% & 2.822 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.020 & 4.03\\% & 44.11\\% & 0.091 & 25.36\\% & 0.015 & 74 & 34.59\\% & 65.41\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 0.794 & -37.41\\% & 44.15\\% & -0.848 & 43.03\\% & -0.737 & 86 & 39.98\\% & 60.02\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.232 & 52.63\\% & 42.30\\% & 1.244 & 22.01\\% & 2.975 & 3 & 91.43\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.122 & 26.21\\% & 21.18\\% & 1.238 & 9.32\\% & 3.481 & 106 & 24.72\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 0.718 & -48.86\\% & 44.08\\% & -1.108 & 41.58\\% & -1.302 & 10 & 60.34\\% & 39.66\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.440 & 109.38\\% & 44.60\\% & 2.452 & 20.31\\% & 13.204 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.218 & 49.24\\% & 33.63\\% & 1.464 & 13.88\\% & 5.195 & 118 & 50.76\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.440 & 109.38\\% & 44.60\\% & 2.452 & 20.31\\% & 13.204 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.832 & -31.06\\% & 13.66\\% & -2.274 & 19.29\\% & -3.662 & 4 & 0.00\\% & 4.56\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.206 & 46.21\\% & 37.95\\% & 1.218 & 19.49\\% & 2.887 & 147 & 78.97\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.398 & 97.31\\% & 44.61\\% & 2.181 & 22.22\\% & 9.554 & 26 & 99.64\\% & 0.36\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.558 & 145.73\\% & 51.90\\% & 2.808 & 26.76\\% & 15.290 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.402 & 98.29\\% & 34.32\\% & 2.864 & 20.22\\% & 13.925 & 93 & 48.96\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.104 & 22.18\\% & 49.12\\% & 0.452 & 26.76\\% & 0.374 & 3 & 82.57\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.000 & 0.04\\% & 18.06\\% & 0.002 & 9.32\\% & 0.000 & 81 & 9.73\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.463 & 116.41\\% & 45.31\\% & 2.569 & 21.45\\% & 13.942 & 94 & 63.52\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
" padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
" result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_macd = evaluate_strategy(padded_window, [s[0] for s in best_strategies['macd_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_rsi = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rsi_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_rmse_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rmse_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_quantile_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['quantile_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
"# padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
"# result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_macd = evaluate_strategy(padded_window, [s[0] for s in best_strategies['macd_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_rsi = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rsi_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_quantile_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['quantile_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
" results_table(result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model)\n",
|
||||
" # results_plot(i+1, result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model)\n",
|
||||
"# results_table(result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model)\n",
|
||||
"# results_plot(i+1, result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model)\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.440 & 13.10\\% & 56.03\\% & 0.234 & 77.23\\% & 0.040 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.468 & -22.64\\% & 52.43\\% & -0.432 & 83.18\\% & -0.118 & 1311 & 51.80\\% & 31.33\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 0.800 & -7.28\\% & 55.66\\% & -0.131 & 66.67\\% & -0.014 & 1206 & 54.02\\% & 43.08\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.509 & 14.93\\% & 34.90\\% & 0.428 & 45.54\\% & 0.140 & 16 & 15.24\\% & 27.60\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.945 & -1.91\\% & 37.77\\% & -0.051 & 48.30\\% & -0.002 & 824 & 28.48\\% & 16.77\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 3.296 & 49.65\\% & 52.70\\% & 0.942 & 47.39\\% & 0.987 & 362 & 49.37\\% & 37.72\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval=INTERVAL)\n",
|
||||
"macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"rmse_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rmse_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"# buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
"# v_lines=[data_window[1]['close_time'].iloc[-1] for data_window in data_windows][:-1]\n",
|
||||
"# results_table(buy_and_hold_concat, macd_concat, rsi_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, quantile_model_concat, gmadl_model_concat, width=1200, notitle=True)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
"# padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
"# result_buyandhold = evaluate_strategy(padded_window, buyandhold_best_strategies[i], padding=PADDING, interval='15min')\n",
|
||||
"# result_macd = evaluate_strategy(padded_window, macd_best_strategies[i], padding=PADDING, interval='15min')\n",
|
||||
"# result_rsi = evaluate_strategy(padded_window, rsi_best_strategies[i], padding=PADDING, interval='15min')\n",
|
||||
"# result_quantile_model = evaluate_strategy(padded_window, quantile_model_best_strategies[i], padding=PADDING, interval='15min')\n",
|
||||
"# result_gmadl_model = evaluate_strategy(padded_window, gmadl_model_best_strategies[i], padding=PADDING, interval='15min')\n",
|
||||
"\n",
|
||||
"results_table(buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat, width=1300, height=500, notitle=True)\n"
|
||||
"# go.Figure([\n",
|
||||
"# go.Scatter(y=result_buyandhold['portfolio_value'], x=result_buyandhold['time'], name=result_buyandhold['strategy_name']),\n",
|
||||
"# go.Scatter(y=result_macd['portfolio_value'], x=result_macd['time'], name=result_macd['strategy_name']),\n",
|
||||
"# go.Scatter(y=result_rsi['portfolio_value'], x=result_rsi['time'], name=result_rsi['strategy_name']),\n",
|
||||
"# go.Scatter(y=result_quantile_model['portfolio_value'], x=result_quantile_model['time'], name='Quantile Model'),\n",
|
||||
"# go.Scatter(y=result_gmadl_model['portfolio_value'], x=result_gmadl_model['time'], name='GMADL model')\n",
|
||||
"# ]).show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@ -1,507 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import pickle\n",
|
||||
"import plotly.graph_objs as go\n",
|
||||
"import latextable\n",
|
||||
"from texttable import Texttable\n",
|
||||
"from strategy.strategy import (\n",
|
||||
" BuyAndHoldStrategy,\n",
|
||||
" MACDStrategy,\n",
|
||||
" RSIStrategy,\n",
|
||||
" ModelQuantilePredictionsStrategy,\n",
|
||||
" ModelGmadlPredictionsStrategy,\n",
|
||||
" ConcatenatedStrategies\n",
|
||||
")\n",
|
||||
"from strategy.util import (\n",
|
||||
" get_data_windows,\n",
|
||||
" get_sweep_window_predictions,\n",
|
||||
" get_predictions_dataframe\n",
|
||||
")\n",
|
||||
"from strategy.evaluation import (\n",
|
||||
" parameter_sweep,\n",
|
||||
" evaluate_strategy\n",
|
||||
")\n",
|
||||
"from strategy.plotting import (\n",
|
||||
" plot_sweep_results\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"PADDING=5000\n",
|
||||
"VALID_PART=0.2\n",
|
||||
"INTERVAL='min'\n",
|
||||
"METRIC='mod_ir'\n",
|
||||
"TOP_N=10"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-1m:latest, 3717.80MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:4.7\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data_windows = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-1m:latest',\n",
|
||||
" min_window=0, \n",
|
||||
" max_window=5\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def sweeps_on_all_windows(data_windows, strategy_class, params, **kwargs):\n",
|
||||
" result = []\n",
|
||||
" for in_sample, _ in data_windows:\n",
|
||||
" data_part = int((1 - VALID_PART) * len(in_sample))\n",
|
||||
" result.append(parameter_sweep(in_sample[data_part-PADDING:], strategy_class, params, padding=PADDING, interval=INTERVAL, **kwargs))\n",
|
||||
" return result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"buyandhold_best_strategies = [BuyAndHoldStrategy() for _ in data_windows] "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Model with gmadl loss\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/s8goxcbz'\n",
|
||||
"# SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/v3epl3qk'\n",
|
||||
"# train_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"valid_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'valid')\n",
|
||||
"test_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'test')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# y = test_gmadl_pred_windows[0][2][:, 0, 0]\n",
|
||||
"# fig = go.Figure([\n",
|
||||
"# go.Scatter(y=y[::100]),\n",
|
||||
"# ])\n",
|
||||
"# fig.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [04:40<00:00, 4.20it/s]\n",
|
||||
"100%|██████████| 1176/1176 [04:40<00:00, 4.20it/s]\n",
|
||||
"100%|██████████| 1176/1176 [04:36<00:00, 4.26it/s]\n",
|
||||
"100%|██████████| 1176/1176 [04:35<00:00, 4.28it/s]\n",
|
||||
"100%|██████████| 1176/1176 [04:36<00:00, 4.26it/s]\n",
|
||||
"100%|██████████| 1176/1176 [04:30<00:00, 4.35it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"MODEL_GMADL_LOSS_FILTER = lambda p: (\n",
|
||||
" ((p['enter_long'] is not None and (p['enter_short'] is not None or p['exit_long'] is not None))\n",
|
||||
" or (p['enter_short'] is not None and (p['exit_short'] is not None or p['enter_long'] is not None)))\n",
|
||||
" and (p['enter_short'] is None or p['exit_long'] is None or (p['exit_long'] > p['enter_short']))\n",
|
||||
" and (p['enter_long'] is None or p['exit_short'] is None or (p['exit_short'] < p['enter_long'])))\n",
|
||||
"\n",
|
||||
"gmadl_model_sweep_results = []\n",
|
||||
"for (in_sample, _), valid_preds, test_preds in zip(data_windows, valid_gmadl_pred_windows, test_gmadl_pred_windows):\n",
|
||||
" data_part = int((1 - VALID_PART) * len(in_sample))\n",
|
||||
" params={\n",
|
||||
" 'predictions': [get_predictions_dataframe(valid_preds, test_preds)],\n",
|
||||
" 'enter_long': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" 'exit_long': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'enter_short': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'exit_short': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" }\n",
|
||||
" \n",
|
||||
" gmadl_model_sweep_results.append(parameter_sweep(\n",
|
||||
" in_sample[data_part-PADDING:],\n",
|
||||
" ModelGmadlPredictionsStrategy,\n",
|
||||
" params,\n",
|
||||
" params_filter=MODEL_GMADL_LOSS_FILTER,\n",
|
||||
" padding=PADDING,\n",
|
||||
" interval=INTERVAL,\n",
|
||||
" sort_by=METRIC))\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"gmadl_model_best_strategies = [[strat for _, strat in results[:TOP_N]] for results in gmadl_model_sweep_results]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "NameError",
|
||||
"evalue": "name 'buyandhold_best_strategies' is not defined",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[0;32mIn[3], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# Persist best strategies, so that they don't have to be recomputed every time\u001b[39;00m\n\u001b[1;32m 2\u001b[0m best_strategies \u001b[38;5;241m=\u001b[39m {\n\u001b[0;32m----> 3\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbuy_and_hold\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[43mbuyandhold_best_strategies\u001b[49m,\n\u001b[1;32m 4\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgmadl_model\u001b[39m\u001b[38;5;124m'\u001b[39m: gmadl_model_best_strategies\n\u001b[1;32m 5\u001b[0m }\n\u001b[1;32m 7\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcache/1min-best-strategies-v1.pkl\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mwb\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m outp:\n\u001b[1;32m 8\u001b[0m pickle\u001b[38;5;241m.\u001b[39mdump(best_strategies, outp, pickle\u001b[38;5;241m.\u001b[39mHIGHEST_PROTOCOL)\n",
|
||||
"\u001b[0;31mNameError\u001b[0m: name 'buyandhold_best_strategies' is not defined"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Persist best strategies, so that they don't have to be recomputed every time\n",
|
||||
"best_strategies = {\n",
|
||||
" 'buy_and_hold': buyandhold_best_strategies,\n",
|
||||
" 'gmadl_model': gmadl_model_best_strategies\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"with open('cache/1min-best-strategies-v1.pkl', 'wb') as outp:\n",
|
||||
" pickle.dump(best_strategies, outp, pickle.HIGHEST_PROTOCOL)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('cache/1min-best-strategies-v1.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies = pickle.load(inpt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# plot_sweep_results(pd.DataFrame([result for result, _ in gmadl_model_sweep_results[0]]), parameters=['enter_long', 'exit_long', 'enter_short', 'exit_short'], round=5, objective='mod_ir')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def results_plot(idx, result_buyandhold, result_gmadl_model, width=850, height=500, notitle=False, v_lines=None):\n",
|
||||
"\n",
|
||||
" fig = go.Figure([\n",
|
||||
" go.Scatter(y=result_buyandhold['portfolio_value'], x=result_buyandhold['time'], name=\"Buy and Hold\"),\n",
|
||||
" go.Scatter(y=result_gmadl_model['portfolio_value'], x=result_gmadl_model['time'], name='GMADL Informer Strategy')\n",
|
||||
" ])\n",
|
||||
" \n",
|
||||
" if v_lines:\n",
|
||||
" for v_line in v_lines:\n",
|
||||
" fig.add_shape(\n",
|
||||
" go.layout.Shape(type=\"line\",\n",
|
||||
" yref=\"paper\",\n",
|
||||
" xref=\"x\",\n",
|
||||
" x0=v_line,\n",
|
||||
" x1=v_line,\n",
|
||||
" y0=0,\n",
|
||||
" y1=1,\n",
|
||||
" line=dict(dash='dash', color='rgb(140,140,140)')))\n",
|
||||
" fig.update_layout(\n",
|
||||
" title={\n",
|
||||
" 'text': f\"W{idx}-{INTERVAL}\",\n",
|
||||
" 'y':0.97,\n",
|
||||
" 'x':0.5,\n",
|
||||
" 'xanchor': 'center',\n",
|
||||
" 'yanchor': 'top'} if not notitle else None,\n",
|
||||
" yaxis_title=\"Portfolio Value\",\n",
|
||||
" xaxis_title=\"Date\",\n",
|
||||
" font=dict(\n",
|
||||
" # family=\"Courier New, monospace\",\n",
|
||||
" size=14,\n",
|
||||
" ),\n",
|
||||
" autosize=False,\n",
|
||||
" width=width,\n",
|
||||
" height=height,\n",
|
||||
" margin=dict(l=20, r=20, t=20 if notitle else 110, b=20),\n",
|
||||
" plot_bgcolor='white',\n",
|
||||
" legend=dict(\n",
|
||||
" orientation=\"h\",\n",
|
||||
" yanchor=\"bottom\",\n",
|
||||
" y=1.02,\n",
|
||||
" xanchor=\"left\",\n",
|
||||
" x=0.02\n",
|
||||
" )\n",
|
||||
" )\n",
|
||||
" fig.update_xaxes(\n",
|
||||
" mirror=True,\n",
|
||||
" ticks='outside',\n",
|
||||
" showline=True,\n",
|
||||
" linecolor='black',\n",
|
||||
" gridcolor='lightgrey'\n",
|
||||
" )\n",
|
||||
" fig.update_yaxes(\n",
|
||||
" mirror=True,\n",
|
||||
" ticks='outside',\n",
|
||||
" showline=True,\n",
|
||||
" linecolor='black',\n",
|
||||
" gridcolor='lightgrey'\n",
|
||||
" )\n",
|
||||
" fig.write_image(f\"images/eval-w{idx}-{INTERVAL}.png\")\n",
|
||||
" fig.show()\n",
|
||||
" \n",
|
||||
"def results_table(result_buyandhold, result_gmadl_model):\n",
|
||||
" table_eval_windows = Texttable()\n",
|
||||
" table_eval_windows.set_deco(Texttable.HEADER)\n",
|
||||
" table_eval_windows.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\"])\n",
|
||||
" table_eval_windows.set_precision(3)\n",
|
||||
"\n",
|
||||
" table_eval_windows.header([\n",
|
||||
" \"\\\\textbf{Strategy}\",\n",
|
||||
" \"\\\\textbf{VAL}\",\n",
|
||||
" \"\\\\textbf{ARC}\",\n",
|
||||
" \"\\\\textbf{ASD}\",\n",
|
||||
" \"\\\\textbf{IR*}\",\n",
|
||||
" \"\\\\textbf{MD}\",\n",
|
||||
" \"\\\\textbf{IR**}\",\n",
|
||||
" \"\\\\textbf{N}\",\n",
|
||||
" \"\\\\textbf{LONG}\",\n",
|
||||
" \"\\\\textbf{SHORT}\",\n",
|
||||
" ])\n",
|
||||
"\n",
|
||||
" strategy_name_result = [\n",
|
||||
" ('Buy and Hold', result_buyandhold),\n",
|
||||
" ('GMADL Informer', result_gmadl_model)\n",
|
||||
" ]\n",
|
||||
" for strategy_name, result in strategy_name_result:\n",
|
||||
" table_eval_windows.add_row([\n",
|
||||
" strategy_name,\n",
|
||||
" result['value'],\n",
|
||||
" f\"{result['arc']*100:.2f}\\%\",\n",
|
||||
" f\"{result['asd']*100:.2f}\\%\",\n",
|
||||
" result['ir'],\n",
|
||||
" f\"{result['md']*100:.2f}\\%\",\n",
|
||||
" result['mod_ir'],\n",
|
||||
" result['n_trades'],\n",
|
||||
" f\"{result['long_pos']*100:.2f}\\%\",\n",
|
||||
" f\"{result['short_pos']*100:.2f}\\%\",\n",
|
||||
" ])\n",
|
||||
" print(latextable.draw_latex(table_eval_windows))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.929 & -13.87\\% & 69.66\\% & -0.199 & 52.09\\% & -0.053 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.306 & 71.83\\% & 69.69\\% & 1.031 & 41.57\\% & 1.781 & 50 & 7.29\\% & 92.71\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.549 & -70.35\\% & 73.36\\% & -0.959 & 63.40\\% & -1.064 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.837 & 243.15\\% & 73.38\\% & 3.314 & 25.16\\% & 32.024 & 186 & 18.19\\% & 81.81\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.016 & 3.33\\% & 52.45\\% & 0.064 & 38.42\\% & 0.006 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 0.739 & -45.82\\% & 52.21\\% & -0.878 & 42.46\\% & -0.947 & 35 & 4.70\\% & 93.05\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.230 & 52.29\\% & 44.30\\% & 1.180 & 22.35\\% & 2.761 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.086 & 18.12\\% & 40.58\\% & 0.446 & 26.30\\% & 0.308 & 11 & 60.03\\% & 23.82\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.439 & 109.31\\% & 43.75\\% & 2.498 & 21.12\\% & 12.930 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.010 & 1.98\\% & 43.47\\% & 0.046 & 31.96\\% & 0.003 & 67 & 80.24\\% & 15.37\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.561 & 146.58\\% & 53.72\\% & 2.729 & 27.11\\% & 14.756 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.178 & 39.32\\% & 43.06\\% & 0.913 & 18.63\\% & 1.927 & 92 & 54.86\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
" padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
" result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
" results_table(result_buyandhold, result_gmadl_model)\n",
|
||||
" # results_plot(i+1, result_buyandhold, result_gmadl_model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"# buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
"# v_lines=[data_window[1]['close_time'].iloc[-1] for data_window in data_windows][:-1]\n",
|
||||
"# results_table(buy_and_hold_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, gmadl_model_concat, width=1300, height=500, notitle=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import plotly.figure_factory as ff\n",
|
||||
"\n",
|
||||
"def results_for_strats(\n",
|
||||
" data_windows, \n",
|
||||
" best_strategies,\n",
|
||||
" top_n=10):\n",
|
||||
" test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"\n",
|
||||
" buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval='min')\n",
|
||||
" gmadl_1min_model_concat = [evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[x] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval='min') for x in range(top_n)]\n",
|
||||
"\n",
|
||||
" z = list(reversed([\n",
|
||||
" list(reversed([round(buy_and_hold_concat['mod_ir'], 3)]*top_n)),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in gmadl_1min_model_concat])),\n",
|
||||
" ]))\n",
|
||||
" x = list(reversed(range(1, top_n+1)))\n",
|
||||
" y = list(reversed([\n",
|
||||
" \"Buy and Hold\",\n",
|
||||
" \"Gmadl Informer (1 min)\"\n",
|
||||
" ]))\n",
|
||||
" # 'Portland'\n",
|
||||
" fig = ff.create_annotated_heatmap(z, x=x, y=y, colorscale='thermal', zmid=buy_and_hold_concat['mod_ir'])\n",
|
||||
" fig.update_layout(\n",
|
||||
" margin=dict(l=20, r=20, b=20, t=20),\n",
|
||||
" width=1100,\n",
|
||||
" height=650,\n",
|
||||
" font=dict(\n",
|
||||
" # family=\"Courier New, monospace\",\n",
|
||||
" size=16, # Set the font size here\n",
|
||||
" # color=\"RebeccaPurple\"\n",
|
||||
" )\n",
|
||||
" )\n",
|
||||
" fig.show()\n",
|
||||
"\n",
|
||||
"# results_for_strats(data_windows, best_strategies, top_n=10) "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "wnemsc",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.19"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@ -2,7 +2,7 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 107,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -34,7 +34,7 @@
|
||||
")\n",
|
||||
"\n",
|
||||
"PADDING=5000\n",
|
||||
"VALID_PART=0.2\n",
|
||||
"VALID_PART=0.4\n",
|
||||
"INTERVAL='30min'\n",
|
||||
"METRIC='mod_ir'\n",
|
||||
"TOP_N=10"
|
||||
@ -42,17 +42,16 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 101,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-30m:latest, 124.19MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:0.5\n"
|
||||
"Done. 0:0:0.6\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -67,7 +66,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 40,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -81,7 +80,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 41,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -90,19 +89,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 44,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 3840/3840 [00:05<00:00, 762.16it/s] \n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 937.71it/s] \n",
|
||||
"100%|██████████| 3840/3840 [00:03<00:00, 990.52it/s] \n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 956.93it/s] \n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 931.01it/s] \n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 951.89it/s] \n"
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 769.13it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 779.61it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:05<00:00, 754.69it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:06<00:00, 579.24it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 777.65it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:04<00:00, 782.54it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -127,7 +126,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -136,19 +135,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 108,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 11088/11088 [00:13<00:00, 838.13it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:10<00:00, 1054.57it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:10<00:00, 1032.31it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:11<00:00, 967.27it/s] \n",
|
||||
"100%|██████████| 11088/11088 [00:11<00:00, 995.52it/s] \n",
|
||||
"100%|██████████| 11088/11088 [00:10<00:00, 1023.57it/s]\n"
|
||||
"100%|██████████| 11088/11088 [00:18<00:00, 611.54it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:17<00:00, 644.30it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:16<00:00, 653.15it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:17<00:00, 640.80it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:14<00:00, 762.97it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:15<00:00, 737.06it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -174,7 +173,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 89,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -196,7 +195,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 90,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -205,105 +204,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Model with rmse loss\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/j9d5r6tg'\n",
|
||||
"train_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"valid_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'valid')\n",
|
||||
"test_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'test')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.99it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 58.14it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.39it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.46it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:22<00:00, 52.43it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.39it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"MODEL_RMSE_LOSS_FILTER = lambda p: (\n",
|
||||
" ((p['enter_long'] is not None and (p['enter_short'] is not None or p['exit_long'] is not None))\n",
|
||||
" or (p['enter_short'] is not None and (p['exit_short'] is not None or p['enter_long'] is not None)))\n",
|
||||
" and (p['enter_short'] is None or p['exit_long'] is None or (p['exit_long'] > p['enter_short']))\n",
|
||||
" and (p['enter_long'] is None or p['exit_short'] is None or (p['exit_short'] < p['enter_long'])))\n",
|
||||
"\n",
|
||||
"rmse_model_sweep_results = []\n",
|
||||
"for (in_sample, _), train_preds, valid_preds, test_preds in zip(data_windows, train_pred_windows, valid_pred_windows, test_pred_windows):\n",
|
||||
" data_part = int((1 - VALID_PART) * len(in_sample))\n",
|
||||
" params={\n",
|
||||
" 'predictions': [get_predictions_dataframe(train_preds, valid_preds, test_preds)],\n",
|
||||
" 'enter_long': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" 'exit_long': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'enter_short': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'exit_short': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" # 'enter_short': [None],\n",
|
||||
" # 'exit_short': [None],\n",
|
||||
" }\n",
|
||||
" \n",
|
||||
" rmse_model_sweep_results.append(parameter_sweep(\n",
|
||||
" in_sample[data_part-PADDING:],\n",
|
||||
" ModelGmadlPredictionsStrategy,\n",
|
||||
" params,\n",
|
||||
" params_filter=MODEL_RMSE_LOSS_FILTER,\n",
|
||||
" padding=PADDING,\n",
|
||||
" interval=INTERVAL,\n",
|
||||
" sort_by=METRIC))\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"rmse_model_best_strategies = [[strat for _, strat in results[:TOP_N]] for results in rmse_model_sweep_results]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# plot_sweep_results(pd.DataFrame([result for result, _ in rmse_model_sweep_results[0]]), parameters=['enter_long', 'exit_long', 'enter_short', 'exit_short'], round=5)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 46,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -341,19 +242,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 48,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 47.74it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 48.10it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 47.79it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 47.27it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 47.82it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:23<00:00, 47.74it/s]\n"
|
||||
"100%|██████████| 1125/1125 [00:28<00:00, 40.16it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:27<00:00, 41.37it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:27<00:00, 41.47it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:27<00:00, 40.47it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:25<00:00, 44.84it/s]\n",
|
||||
"100%|██████████| 1125/1125 [00:25<00:00, 44.11it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -395,7 +296,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -404,7 +305,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 50,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -435,9 +336,7 @@
|
||||
"source": [
|
||||
"# Model with gmadl loss\n",
|
||||
"# SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/tmqx4epx'\n",
|
||||
"# SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/7p7tdxbn' (old)\n",
|
||||
"# SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/7x42xn5j'\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/z776cpvj'\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/7p7tdxbn'\n",
|
||||
"train_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"valid_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'valid')\n",
|
||||
"test_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'test')"
|
||||
@ -445,19 +344,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 51,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 58.39it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.42it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.34it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.48it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 58.43it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:20<00:00, 57.45it/s]\n"
|
||||
"100%|██████████| 1176/1176 [00:22<00:00, 51.45it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:24<00:00, 48.45it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:21<00:00, 53.53it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:24<00:00, 48.36it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:22<00:00, 51.90it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:21<00:00, 54.04it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -505,21 +404,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 109,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Persist best strategies, so that they don't have to be recomputed every time\n",
|
||||
"best_strategies = {\n",
|
||||
" 'buy_and_hold': buyandhold_best_strategies,\n",
|
||||
" 'macd_strategies': macd_best_strategies,\n",
|
||||
" # 'buy_and_hold': buyandhold_best_strategies,\n",
|
||||
" # 'macd_strategies': macd_best_strategies,\n",
|
||||
" 'rsi_strategies': rsi_best_strategies,\n",
|
||||
" 'rmse_model': rmse_model_best_strategies,\n",
|
||||
" 'quantile_model': quantile_model_best_strategies,\n",
|
||||
" 'gmadl_model': gmadl_model_best_strategies\n",
|
||||
" # 'quantile_model': quantile_model_best_strategies,\n",
|
||||
" # 'gmadl_model': gmadl_model_best_strategies\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"with open('cache/30min-best-strategies-v6.pkl', 'wb') as outp:\n",
|
||||
"with open('cache/30min-best-strategies-04.pkl', 'wb') as outp:\n",
|
||||
" pickle.dump(best_strategies, outp, pickle.HIGHEST_PROTOCOL)"
|
||||
]
|
||||
},
|
||||
@ -532,18 +430,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 53,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('cache/30min-best-strategies-v6.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies = pickle.load(inpt)\n",
|
||||
" buyandhold_best_strategies = best_strategies['buy_and_hold']\n",
|
||||
" macd_best_strategies = best_strategies['macd_strategies']\n",
|
||||
" rsi_best_strategies = best_strategies['rsi_strategies']\n",
|
||||
" rmse_model_best_strategies = best_strategies['rmse_model']\n",
|
||||
" quantile_model_best_strategies = best_strategies['quantile_model']\n",
|
||||
" gmadl_model_best_strategies = best_strategies['gmadl_model']"
|
||||
"with open('cache/30min-best-strategies.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies = pickle.load(inpt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -710,7 +602,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 60,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -722,62 +614,12 @@
|
||||
"\t\t\\begin{tabular}{lcccc}\n",
|
||||
"\t\t\t\\textbf{Window} & \\textbf{\\textit{enter long}} & \\textbf{\\textit{exit Long}} & \\textbf{\\textit{enter Short}} & \\textbf{\\textit{exit Short}} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tW1-30min & 0.002 & - & -0.003 & - \\\\\n",
|
||||
"\t\t\tW2-30min & - & - & -0.002 & 0.001 \\\\\n",
|
||||
"\t\t\tW3-30min & - & - & -0.001 & 0.002 \\\\\n",
|
||||
"\t\t\tW4-30min & 0.001 & - & -0.002 & - \\\\\n",
|
||||
"\t\t\tW5-30min & 0.001 & - & -0.002 & - \\\\\n",
|
||||
"\t\t\tW6-30min & 0.001 & - & -0.002 & - \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"table_rmse_params = Texttable()\n",
|
||||
"table_rmse_params.set_deco(Texttable.HEADER)\n",
|
||||
"table_rmse_params.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\"])\n",
|
||||
"table_rmse_params.header([\n",
|
||||
" \"\\\\textbf{Window}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{enter long}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{exit Long}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{enter Short}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{exit Short}}\",\n",
|
||||
"])\n",
|
||||
"\n",
|
||||
"for i, rmse_strategy in enumerate(best_strategies['rmse_model']):\n",
|
||||
" rmse_strategy_info = rmse_strategy[0].info()\n",
|
||||
" table_rmse_params.add_row([\n",
|
||||
" f\"W{i+1}-{INTERVAL}\",\n",
|
||||
" rmse_strategy_info['enter_long'] or '-',\n",
|
||||
" rmse_strategy_info['exit_long'] or '-',\n",
|
||||
" rmse_strategy_info['enter_short'] or '-',\n",
|
||||
" rmse_strategy_info['exit_short'] or '-'\n",
|
||||
" ])\n",
|
||||
"print(latextable.draw_latex(table_rmse_params))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lcccc}\n",
|
||||
"\t\t\t\\textbf{Window} & \\textbf{\\textit{enter long}} & \\textbf{\\textit{exit Long}} & \\textbf{\\textit{enter Short}} & \\textbf{\\textit{exit Short}} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tW1-30min & - & - & -0.007 & 0.005 \\\\\n",
|
||||
"\t\t\tW2-30min & - & -0.006 & -0.007 & 0.004 \\\\\n",
|
||||
"\t\t\tW3-30min & - & - & -0.004 & 0.007 \\\\\n",
|
||||
"\t\t\tW4-30min & 0.003 & -0.007 & - & - \\\\\n",
|
||||
"\t\t\tW5-30min & 0.006 & - & -0.004 & - \\\\\n",
|
||||
"\t\t\tW6-30min & 0.001 & - & -0.005 & - \\\\\n",
|
||||
"\t\t\tW1-30min & 0.007 & - & -0.001 & - \\\\\n",
|
||||
"\t\t\tW2-30min & 0.003 & - & -0.007 & - \\\\\n",
|
||||
"\t\t\tW3-30min & - & - & -0.001 & 0.005 \\\\\n",
|
||||
"\t\t\tW4-30min & 0.002 & - & -0.006 & - \\\\\n",
|
||||
"\t\t\tW5-30min & 0.005 & -0.001 & - & - \\\\\n",
|
||||
"\t\t\tW6-30min & 0.003 & - & -0.004 & - \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
@ -817,32 +659,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 98,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def results_plot(idx, result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model, width=850, height=500, notitle=False, v_lines=None):\n",
|
||||
"def results_plot(idx, result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model, width=850, height=500, notitle=False):\n",
|
||||
"\n",
|
||||
" fig = go.Figure([\n",
|
||||
" go.Scatter(y=result_buyandhold['portfolio_value'], x=result_buyandhold['time'], name=\"Buy and Hold\"),\n",
|
||||
" go.Scatter(y=result_macd['portfolio_value'], x=result_macd['time'], name=\"MACD Strategy\"),\n",
|
||||
" go.Scatter(y=result_rsi['portfolio_value'], x=result_rsi['time'], name=\"RSI Strategy\"),\n",
|
||||
" go.Scatter(y=result_rmse_model['portfolio_value'], x=result_rmse_model['time'], name='RMSE Informer Strategy'),\n",
|
||||
" go.Scatter(y=result_quantile_model['portfolio_value'], x=result_quantile_model['time'], name='Quantile Informer Strategy'),\n",
|
||||
" go.Scatter(y=result_gmadl_model['portfolio_value'], x=result_gmadl_model['time'], name='GMADL Informer Strategy')\n",
|
||||
" ])\n",
|
||||
" \n",
|
||||
" if v_lines:\n",
|
||||
" for v_line in v_lines:\n",
|
||||
" fig.add_shape(\n",
|
||||
" go.layout.Shape(type=\"line\",\n",
|
||||
" yref=\"paper\",\n",
|
||||
" xref=\"x\",\n",
|
||||
" x0=v_line,\n",
|
||||
" x1=v_line,\n",
|
||||
" y0=0,\n",
|
||||
" y1=1,\n",
|
||||
" line=dict(width=1.5, dash='dash', color='rgb(140,140,140)')))\n",
|
||||
" fig.update_layout(\n",
|
||||
" title={\n",
|
||||
" 'text': f\"W{idx}-{INTERVAL}\",\n",
|
||||
@ -886,7 +715,7 @@
|
||||
" fig.write_image(f\"images/eval-w{idx}-{INTERVAL}.png\")\n",
|
||||
" fig.show()\n",
|
||||
" \n",
|
||||
"def results_table(result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model):\n",
|
||||
"def results_table(result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model):\n",
|
||||
" table_eval_windows = Texttable()\n",
|
||||
" table_eval_windows.set_deco(Texttable.HEADER)\n",
|
||||
" table_eval_windows.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\"])\n",
|
||||
@ -909,7 +738,6 @@
|
||||
" ('Buy and Hold', result_buyandhold),\n",
|
||||
" ('MACD Strategy', result_macd),\n",
|
||||
" ('RSI Strategy', result_rsi),\n",
|
||||
" ('RMSE Informer', result_rmse_model),\n",
|
||||
" ('Quantile Informer', result_quantile_model),\n",
|
||||
" ('GMADL Informer', result_gmadl_model)\n",
|
||||
" ]\n",
|
||||
@ -917,10 +745,10 @@
|
||||
" table_eval_windows.add_row([\n",
|
||||
" strategy_name,\n",
|
||||
" result['value'],\n",
|
||||
" f\"{result['arc']*100:.2f}\\%\",\n",
|
||||
" f\"{result['asd']*100:.2f}\\%\",\n",
|
||||
" result['arc'],\n",
|
||||
" result['asd'],\n",
|
||||
" result['ir'],\n",
|
||||
" f\"{result['md']*100:.2f}\\%\",\n",
|
||||
" result['md'],\n",
|
||||
" result['mod_ir'],\n",
|
||||
" result['n_trades'],\n",
|
||||
" f\"{result['long_pos']*100:.2f}\\%\",\n",
|
||||
@ -932,112 +760,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.924 & -14.84\\% & 66.12\\% & -0.225 & 51.75\\% & -0.064 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.269 & 62.19\\% & 65.90\\% & 0.944 & 31.81\\% & 1.845 & 15 & 50.36\\% & 47.71\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.843 & 245.59\\% & 66.51\\% & 3.693 & 35.02\\% & 25.897 & 26 & 42.40\\% & 57.60\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.924 & -14.84\\% & 66.12\\% & -0.225 & 51.75\\% & -0.064 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.743 & -45.20\\% & 60.57\\% & -0.746 & 29.11\\% & -1.159 & 443 & 30.43\\% & 53.98\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.030 & 6.23\\% & 19.98\\% & 0.312 & 10.01\\% & 0.194 & 39 & 0.00\\% & 8.72\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.548 & -70.51\\% & 72.38\\% & -0.974 & 63.18\\% & -1.087 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.303 & 70.93\\% & 71.82\\% & 0.988 & 36.06\\% & 1.943 & 19 & 57.32\\% & 40.76\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.703 & 194.24\\% & 72.36\\% & 2.684 & 34.89\\% & 14.945 & 106 & 39.96\\% & 60.04\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.387 & 94.09\\% & 41.55\\% & 2.264 & 16.34\\% & 13.037 & 8 & 0.00\\% & 34.41\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.403 & 98.74\\% & 27.62\\% & 3.575 & 9.44\\% & 37.393 & 255 & 0.00\\% & 18.79\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.050 & 10.44\\% & 23.40\\% & 0.446 & 14.45\\% & 0.322 & 90 & 0.00\\% & 5.98\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.018 & 3.75\\% & 51.25\\% & 0.073 & 37.47\\% & 0.007 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.673 & -55.16\\% & 51.01\\% & -1.081 & 59.24\\% & -1.007 & 95 & 81.60\\% & 16.48\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 0.988 & -2.50\\% & 38.04\\% & -0.066 & 30.42\\% & -0.005 & 238 & 2.34\\% & 50.54\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.980 & -4.00\\% & 51.36\\% & -0.078 & 34.51\\% & -0.009 & 2 & 0.00\\% & 100.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.884 & -22.19\\% & 23.41\\% & -0.948 & 18.39\\% & -1.144 & 171 & 0.00\\% & 18.83\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 0.737 & -46.11\\% & 42.58\\% & -1.083 & 42.71\\% & -1.169 & 302 & 0.00\\% & 81.21\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.229 & 51.90\\% & 45.01\\% & 1.153 & 21.74\\% & 2.753 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.031 & 6.45\\% & 45.08\\% & 0.143 & 30.15\\% & 0.031 & 94 & 35.18\\% & 64.82\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.010 & 2.03\\% & 1.87\\% & 1.084 & 0.30\\% & 7.410 & 4 & 0.02\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.414 & 101.80\\% & 45.03\\% & 2.260 & 21.74\\% & 10.584 & 10 & 92.95\\% & 7.05\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.629 & -60.99\\% & 28.76\\% & -2.121 & 39.23\\% & -3.297 & 448 & 36.32\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.054 & 11.31\\% & 28.25\\% & 0.400 & 24.18\\% & 0.187 & 345 & 34.69\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.439 & 109.30\\% & 41.49\\% & 2.634 & 20.18\\% & 14.265 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.393 & 95.71\\% & 31.47\\% & 3.041 & 15.00\\% & 19.407 & 90 & 48.66\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.439 & 109.30\\% & 41.49\\% & 2.634 & 20.18\\% & 14.265 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.439 & 109.30\\% & 41.49\\% & 2.634 & 20.18\\% & 14.265 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.277 & 64.08\\% & 34.28\\% & 1.869 & 16.61\\% & 7.212 & 311 & 76.90\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.672 & 183.71\\% & 41.56\\% & 4.420 & 20.18\\% & 40.230 & 22 & 78.48\\% & 21.52\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.559 & 145.95\\% & 52.85\\% & 2.762 & 26.69\\% & 15.103 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.227 & 51.44\\% & 36.38\\% & 1.414 & 18.55\\% & 3.921 & 11 & 40.69\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1.059 & 12.32\\% & 52.86\\% & 0.233 & 41.44\\% & 0.069 & 10 & 93.44\\% & 6.56\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.855 & -27.14\\% & 34.50\\% & -0.787 & 35.23\\% & -0.606 & 150 & 37.79\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.617 & 165.10\\% & 52.85\\% & 3.124 & 24.64\\% & 20.929 & 10 & 99.88\\% & 0.12\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
" padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
" result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_macd = evaluate_strategy(padded_window, [s[0] for s in best_strategies['macd_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_rsi = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rsi_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_rmse_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rmse_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_quantile_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['quantile_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
"# padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
"# result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_macd = evaluate_strategy(padded_window, [s[0] for s in best_strategies['macd_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_rsi = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rsi_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_quantile_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['quantile_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
" results_table(result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model)\n",
|
||||
" # results_plot(i+1, result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model)\n",
|
||||
"# results_table(result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model)\n",
|
||||
"# results_plot(i+1, result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model)\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
@ -1050,51 +786,20 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.440 & 13.12\\% & 55.95\\% & 0.235 & 77.20\\% & 0.040 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.952 & 25.37\\% & 52.36\\% & 0.485 & 59.24\\% & 0.207 & 327 & 52.30\\% & 28.30\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 4.542 & 66.77\\% & 46.25\\% & 1.444 & 39.91\\% & 2.415 & 377 & 30.79\\% & 28.03\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 2.727 & 40.37\\% & 50.47\\% & 0.800 & 51.75\\% & 0.624 & 34 & 64.40\\% & 24.67\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.629 & -14.51\\% & 36.91\\% & -0.393 & 55.09\\% & -0.104 & 1783 & 30.24\\% & 15.27\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 2.263 & 31.79\\% & 36.70\\% & 0.866 & 53.35\\% & 0.516 & 811 & 35.51\\% & 19.59\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval=INTERVAL)\n",
|
||||
"macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"rmse_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rmse_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
"# v_lines=[data_window[1]['close_time'].iloc[-1] for data_window in data_windows][:-1]\n",
|
||||
"\n",
|
||||
"results_table(buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat, width=1200, height=500, notitle=True)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
"source": [
|
||||
"# test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"# buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
"# results_table(buy_and_hold_concat, macd_concat, rsi_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, quantile_model_concat, gmadl_model_concat, width=1200, notitle=True)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
@ -2,7 +2,7 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 109,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -33,7 +33,7 @@
|
||||
")\n",
|
||||
"\n",
|
||||
"PADDING=5000\n",
|
||||
"VALID_PART=0.2\n",
|
||||
"VALID_PART=0.4\n",
|
||||
"INTERVAL='5min'\n",
|
||||
"METRIC='mod_ir'\n",
|
||||
"TOP_N=10"
|
||||
@ -41,17 +41,16 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 94,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-5m:latest, 745.12MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:1.3\n"
|
||||
"Done. 0:0:0.8\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -66,7 +65,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 95,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -80,7 +79,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 96,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -89,19 +88,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 97,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 3840/3840 [00:18<00:00, 206.53it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:18<00:00, 205.12it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:18<00:00, 205.54it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:18<00:00, 204.08it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:18<00:00, 202.37it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:18<00:00, 202.96it/s]\n"
|
||||
"100%|██████████| 3840/3840 [00:25<00:00, 148.93it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:25<00:00, 149.05it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:27<00:00, 138.86it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:28<00:00, 133.50it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:25<00:00, 152.79it/s]\n",
|
||||
"100%|██████████| 3840/3840 [00:22<00:00, 168.94it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -137,19 +136,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 99,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 11088/11088 [00:51<00:00, 216.64it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:52<00:00, 210.53it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:52<00:00, 210.59it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:52<00:00, 210.06it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:52<00:00, 209.24it/s]\n",
|
||||
"100%|██████████| 11088/11088 [00:52<00:00, 209.32it/s]\n"
|
||||
"100%|██████████| 11088/11088 [01:14<00:00, 149.71it/s]\n",
|
||||
"100%|██████████| 11088/11088 [01:18<00:00, 140.49it/s]\n",
|
||||
"100%|██████████| 11088/11088 [01:14<00:00, 148.45it/s]\n",
|
||||
"100%|██████████| 11088/11088 [01:15<00:00, 147.54it/s]\n",
|
||||
"100%|██████████| 11088/11088 [01:09<00:00, 160.15it/s]\n",
|
||||
"100%|██████████| 11088/11088 [01:10<00:00, 158.01it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -182,96 +181,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Model with rmse loss\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/9afp99kz'\n",
|
||||
"train_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"valid_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'valid')\n",
|
||||
"test_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'test')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [02:10<00:00, 9.04it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:07<00:00, 9.19it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:10<00:00, 9.02it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:16<00:00, 8.59it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:13<00:00, 8.82it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:12<00:00, 8.85it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"MODEL_RMSE_LOSS_FILTER = lambda p: (\n",
|
||||
" ((p['enter_long'] is not None and (p['enter_short'] is not None or p['exit_long'] is not None))\n",
|
||||
" or (p['enter_short'] is not None and (p['exit_short'] is not None or p['enter_long'] is not None)))\n",
|
||||
" and (p['enter_short'] is None or p['exit_long'] is None or (p['exit_long'] > p['enter_short']))\n",
|
||||
" and (p['enter_long'] is None or p['exit_short'] is None or (p['exit_short'] < p['enter_long'])))\n",
|
||||
"\n",
|
||||
"rmse_model_sweep_results = []\n",
|
||||
"for (in_sample, _), train_preds, valid_preds, test_preds in zip(data_windows, train_pred_windows, valid_pred_windows, test_pred_windows):\n",
|
||||
" data_part = int((1 - VALID_PART) * len(in_sample))\n",
|
||||
" params={\n",
|
||||
" 'predictions': [get_predictions_dataframe(train_preds, valid_preds, test_preds)],\n",
|
||||
" 'enter_long': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" 'exit_long': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'enter_short': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'exit_short': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" # 'enter_short': [None],\n",
|
||||
" # 'exit_short': [None],\n",
|
||||
" }\n",
|
||||
" \n",
|
||||
" rmse_model_sweep_results.append(parameter_sweep(\n",
|
||||
" in_sample[data_part-PADDING:],\n",
|
||||
" ModelGmadlPredictionsStrategy,\n",
|
||||
" params,\n",
|
||||
" params_filter=MODEL_RMSE_LOSS_FILTER,\n",
|
||||
" padding=PADDING,\n",
|
||||
" interval=INTERVAL,\n",
|
||||
" sort_by=METRIC))\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"rmse_model_best_strategies = [[strat for _, strat in results[:TOP_N]] for results in rmse_model_sweep_results]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 101,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -309,19 +219,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 102,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1125/1125 [02:35<00:00, 7.23it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:28<00:00, 7.56it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:35<00:00, 7.22it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:47<00:00, 6.71it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:39<00:00, 7.06it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:35<00:00, 7.25it/s]\n"
|
||||
"100%|██████████| 1125/1125 [02:49<00:00, 6.65it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:51<00:00, 6.55it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:56<00:00, 6.36it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:50<00:00, 6.61it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:47<00:00, 6.72it/s]\n",
|
||||
"100%|██████████| 1125/1125 [02:48<00:00, 6.66it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -369,14 +279,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 104,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 2 of 2 files downloaded. \n",
|
||||
@ -395,27 +310,26 @@
|
||||
"source": [
|
||||
"# Model with gmadl loss\n",
|
||||
"SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/0pro3i5i'\n",
|
||||
"# SWEEP_ID = 'filipstefaniuk/wne-masters-thesis-testing/v3epl3qk'\n",
|
||||
"# train_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"train_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'train')\n",
|
||||
"valid_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'valid')\n",
|
||||
"test_gmadl_pred_windows = get_sweep_window_predictions(SWEEP_ID, 'test')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 110,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"100%|██████████| 1176/1176 [00:58<00:00, 20.16it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:55<00:00, 21.38it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:54<00:00, 21.43it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:54<00:00, 21.38it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:55<00:00, 21.29it/s]\n",
|
||||
"100%|██████████| 1176/1176 [00:55<00:00, 21.03it/s]\n"
|
||||
"100%|██████████| 1176/1176 [02:30<00:00, 7.82it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:31<00:00, 7.78it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:31<00:00, 7.77it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:32<00:00, 7.72it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:30<00:00, 7.84it/s]\n",
|
||||
"100%|██████████| 1176/1176 [02:30<00:00, 7.80it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -427,10 +341,10 @@
|
||||
" and (p['enter_long'] is None or p['exit_short'] is None or (p['exit_short'] < p['enter_long'])))\n",
|
||||
"\n",
|
||||
"gmadl_model_sweep_results = []\n",
|
||||
"for (in_sample, _), valid_preds, test_preds in zip(data_windows, valid_gmadl_pred_windows, test_gmadl_pred_windows):\n",
|
||||
"for (in_sample, _), train_preds, valid_preds, test_preds in zip(data_windows, train_gmadl_pred_windows, valid_gmadl_pred_windows, test_gmadl_pred_windows):\n",
|
||||
" data_part = int((1 - VALID_PART) * len(in_sample))\n",
|
||||
" params={\n",
|
||||
" 'predictions': [get_predictions_dataframe(valid_preds, test_preds)],\n",
|
||||
" 'predictions': [get_predictions_dataframe(train_preds, valid_preds, test_preds)],\n",
|
||||
" 'enter_long': [None, 0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007],\n",
|
||||
" 'exit_long': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
" 'enter_short': [None, -0.001, -0.002, -0.003, -0.004, -0.005, -0.006, -0.007],\n",
|
||||
@ -452,7 +366,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": 111,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -461,12 +375,11 @@
|
||||
" 'buy_and_hold': buyandhold_best_strategies,\n",
|
||||
" 'macd_strategies': macd_best_strategies,\n",
|
||||
" 'rsi_strategies': rsi_best_strategies,\n",
|
||||
" 'rmse_model': rmse_model_best_strategies,\n",
|
||||
" 'quantile_model': quantile_model_best_strategies,\n",
|
||||
" 'gmadl_model': gmadl_model_best_strategies\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"with open('cache/5min-best-strategies-v2.pkl', 'wb') as outp:\n",
|
||||
"with open('cache/5min-best-strategies-04.pkl', 'wb') as outp:\n",
|
||||
" pickle.dump(best_strategies, outp, pickle.HIGHEST_PROTOCOL)"
|
||||
]
|
||||
},
|
||||
@ -479,11 +392,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 52,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('cache/5min-best-strategies-v2.pkl', 'rb') as inpt:\n",
|
||||
"with open('cache/5min-best-strategies.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies = pickle.load(inpt)"
|
||||
]
|
||||
},
|
||||
@ -597,56 +510,6 @@
|
||||
"print(latextable.draw_latex(table_rsi_params))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lcccc}\n",
|
||||
"\t\t\t\\textbf{Window} & \\textbf{\\textit{enter long}} & \\textbf{\\textit{exit Long}} & \\textbf{\\textit{enter Short}} & \\textbf{\\textit{exit Short}} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tW1-5min & 0.002 & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\tW2-5min & - & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\tW3-5min & - & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\tW4-5min & - & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\tW5-5min & - & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\tW6-5min & - & - & -0.001 & 0.001 \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"table_rmse_params = Texttable()\n",
|
||||
"table_rmse_params.set_deco(Texttable.HEADER)\n",
|
||||
"table_rmse_params.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\"])\n",
|
||||
"table_rmse_params.header([\n",
|
||||
" \"\\\\textbf{Window}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{enter long}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{exit Long}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{enter Short}}\",\n",
|
||||
" \"\\\\textbf{\\\\textit{exit Short}}\",\n",
|
||||
"])\n",
|
||||
"\n",
|
||||
"for i, rmse_strategy in enumerate(best_strategies['rmse_model']):\n",
|
||||
" rmse_strategy_info = rmse_strategy[0].info()\n",
|
||||
" table_rmse_params.add_row([\n",
|
||||
" f\"W{i+1}-{INTERVAL}\",\n",
|
||||
" rmse_strategy_info['enter_long'] or '-',\n",
|
||||
" rmse_strategy_info['exit_long'] or '-',\n",
|
||||
" rmse_strategy_info['enter_short'] or '-',\n",
|
||||
" rmse_strategy_info['exit_short'] or '-'\n",
|
||||
" ])\n",
|
||||
"print(latextable.draw_latex(table_rmse_params))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 56,
|
||||
@ -758,32 +621,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 61,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def results_plot(idx, result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model, width=850, height=500, notitle=False, v_lines=None):\n",
|
||||
"def results_plot(idx, result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model, width=850, height=500, notitle=False):\n",
|
||||
"\n",
|
||||
" fig = go.Figure([\n",
|
||||
" go.Scatter(y=result_buyandhold['portfolio_value'], x=result_buyandhold['time'], name=\"Buy and Hold\"),\n",
|
||||
" go.Scatter(y=result_macd['portfolio_value'], x=result_macd['time'], name=\"MACD Strategy\"),\n",
|
||||
" go.Scatter(y=result_rsi['portfolio_value'], x=result_rsi['time'], name=\"RSI Strategy\"),\n",
|
||||
" go.Scatter(y=result_rmse_model['portfolio_value'], x=result_rmse_model['time'], name='RMSE Informer Strategy'),\n",
|
||||
" go.Scatter(y=result_quantile_model['portfolio_value'], x=result_quantile_model['time'], name='Quantile Informer Strategy'),\n",
|
||||
" go.Scatter(y=result_gmadl_model['portfolio_value'], x=result_gmadl_model['time'], name='GMADL Informer Strategy')\n",
|
||||
" ])\n",
|
||||
" \n",
|
||||
" if v_lines:\n",
|
||||
" for v_line in v_lines:\n",
|
||||
" fig.add_shape(\n",
|
||||
" go.layout.Shape(type=\"line\",\n",
|
||||
" yref=\"paper\",\n",
|
||||
" xref=\"x\",\n",
|
||||
" x0=v_line,\n",
|
||||
" x1=v_line,\n",
|
||||
" y0=0,\n",
|
||||
" y1=1,\n",
|
||||
" line=dict(dash='dash', color='rgb(140,140,140)')))\n",
|
||||
" fig.update_layout(\n",
|
||||
" title={\n",
|
||||
" 'text': f\"W{idx}-{INTERVAL}\",\n",
|
||||
@ -827,7 +677,7 @@
|
||||
" fig.write_image(f\"images/eval-w{idx}-{INTERVAL}.png\")\n",
|
||||
" fig.show()\n",
|
||||
" \n",
|
||||
"def results_table(result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model):\n",
|
||||
"def results_table(result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model):\n",
|
||||
" table_eval_windows = Texttable()\n",
|
||||
" table_eval_windows.set_deco(Texttable.HEADER)\n",
|
||||
" table_eval_windows.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\"])\n",
|
||||
@ -850,7 +700,6 @@
|
||||
" ('Buy and Hold', result_buyandhold),\n",
|
||||
" ('MACD Strategy', result_macd),\n",
|
||||
" ('RSI Strategy', result_rsi),\n",
|
||||
" ('RMSE Informer', result_rmse_model),\n",
|
||||
" ('Quantile Informer', result_quantile_model),\n",
|
||||
" ('GMADL Informer', result_gmadl_model)\n",
|
||||
" ]\n",
|
||||
@ -858,10 +707,10 @@
|
||||
" table_eval_windows.add_row([\n",
|
||||
" strategy_name,\n",
|
||||
" result['value'],\n",
|
||||
" f\"{result['arc']*100:.2f}\\%\",\n",
|
||||
" f\"{result['asd']*100:.2f}\\%\",\n",
|
||||
" result['arc'],\n",
|
||||
" result['asd'],\n",
|
||||
" result['ir'],\n",
|
||||
" f\"{result['md']*100:.2f}\\%\",\n",
|
||||
" result['md'],\n",
|
||||
" result['mod_ir'],\n",
|
||||
" result['n_trades'],\n",
|
||||
" f\"{result['long_pos']*100:.2f}\\%\",\n",
|
||||
@ -873,195 +722,38 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.930 & -13.76\\% & 70.24\\% & -0.196 & 51.87\\% & -0.052 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.375 & -86.35\\% & 70.71\\% & -1.221 & 71.90\\% & -1.467 & 1542 & 52.05\\% & 47.95\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.428 & 106.05\\% & 70.55\\% & 1.503 & 26.24\\% & 6.074 & 114 & 26.31\\% & 73.69\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.965 & -6.93\\% & 3.11\\% & -2.227 & 3.54\\% & -4.361 & 12 & 0.02\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.117 & 25.15\\% & 43.69\\% & 0.576 & 16.27\\% & 0.889 & 365 & 0.00\\% & 45.14\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.502 & 128.10\\% & 70.54\\% & 1.816 & 30.70\\% & 7.576 & 82 & 41.54\\% & 58.46\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 0.549 & -70.37\\% & 74.61\\% & -0.943 & 63.35\\% & -1.048 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.498 & -75.63\\% & 74.63\\% & -1.013 & 62.97\\% & -1.217 & 446 & 50.72\\% & 49.28\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.368 & 88.76\\% & 74.58\\% & 1.190 & 27.34\\% & 3.864 & 78 & 61.40\\% & 38.60\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.941 & -11.54\\% & 74.69\\% & -0.154 & 44.84\\% & -0.040 & 990 & 50.50\\% & 49.50\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.635 & 170.94\\% & 74.67\\% & 2.289 & 30.47\\% & 12.844 & 522 & 20.20\\% & 79.80\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.016 & 3.23\\% & 51.77\\% & 0.062 & 37.98\\% & 0.005 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.081 & 17.10\\% & 51.79\\% & 0.330 & 20.87\\% & 0.270 & 154 & 58.24\\% & 41.76\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.127 & 27.41\\% & 51.92\\% & 0.528 & 22.30\\% & 0.649 & 398 & 11.48\\% & 88.52\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.057 & 11.93\\% & 51.90\\% & 0.230 & 30.10\\% & 0.091 & 894 & 27.62\\% & 72.38\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.198 & 44.15\\% & 19.18\\% & 2.302 & 7.68\\% & 13.227 & 16 & 0.00\\% & 17.86\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.231 & 52.35\\% & 45.25\\% & 1.157 & 22.29\\% & 2.718 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.612 & 163.18\\% & 45.34\\% & 3.599 & 21.23\\% & 27.660 & 190 & 44.69\\% & 55.31\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 0.866 & -25.30\\% & 19.03\\% & -1.330 & 15.65\\% & -2.150 & 205 & 23.63\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.825 & -32.24\\% & 27.88\\% & -1.156 & 22.72\\% & -1.641 & 290 & 44.45\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.673 & 183.80\\% & 45.26\\% & 4.061 & 24.78\\% & 30.125 & 62 & 65.14\\% & 34.86\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.439 & 109.23\\% & 44.72\\% & 2.443 & 21.07\\% & 12.664 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.346 & 82.57\\% & 32.85\\% & 2.514 & 15.44\\% & 13.447 & 94 & 49.06\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.169 & 37.33\\% & 13.86\\% & 2.692 & 4.73\\% & 21.237 & 42 & 5.67\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.667 & -56.06\\% & 36.94\\% & -1.518 & 42.77\\% & -1.989 & 3 & 0.00\\% & 57.45\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.984 & -3.12\\% & 33.97\\% & -0.092 & 20.63\\% & -0.014 & 578 & 59.26\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.582 & 153.60\\% & 45.11\\% & 3.405 & 14.37\\% & 36.394 & 130 & 44.70\\% & 55.30\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n",
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.560 & 146.27\\% & 52.72\\% & 2.775 & 26.96\\% & 15.054 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.179 & 39.63\\% & 34.65\\% & 1.144 & 28.87\\% & 1.570 & 111 & 47.58\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 1.507 & 129.58\\% & 38.15\\% & 3.396 & 17.97\\% & 24.493 & 7 & 41.29\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 1 & 0.00\\% & 0.00\\% & 0 & 0.00\\% & 0 & 0 & 0.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 1.056 & 11.76\\% & 40.73\\% & 0.289 & 30.60\\% & 0.111 & 280 & 59.60\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 1.253 & 57.92\\% & 52.71\\% & 1.099 & 32.66\\% & 1.949 & 34 & 97.21\\% & 2.79\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
" padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
" result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_macd = evaluate_strategy(padded_window, [s[0] for s in best_strategies['macd_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_rsi = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rsi_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_rmse_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rmse_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_quantile_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['quantile_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
" result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# for i, (in_sample, out_of_sample) in enumerate(data_windows):\n",
|
||||
"# padded_window = pd.concat([in_sample.iloc[-PADDING:], out_of_sample])\n",
|
||||
"# result_buyandhold = evaluate_strategy(padded_window, best_strategies['buy_and_hold'][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_macd = evaluate_strategy(padded_window, [s[0] for s in best_strategies['macd_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_rsi = evaluate_strategy(padded_window, [s[0] for s in best_strategies['rsi_strategies']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_quantile_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['quantile_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"# result_gmadl_model = evaluate_strategy(padded_window, [s[0] for s in best_strategies['gmadl_model']][i], padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
" results_table(result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model)\n",
|
||||
" # results_plot(i+1, result_buyandhold, result_macd, result_rsi, result_rmse_model, result_quantile_model, result_gmadl_model)\n",
|
||||
"# results_table(result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model)\n",
|
||||
"# results_plot(i+1, result_buyandhold, result_macd, result_rsi, result_quantile_model, result_gmadl_model)\n",
|
||||
" \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.441 & 13.14\\% & 57.74\\% & 0.228 & 77.31\\% & 0.039 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 0.516 & -20.04\\% & 54.14\\% & -0.370 & 85.77\\% & -0.087 & 2535 & 50.39\\% & 32.38\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 3.341 & 50.34\\% & 50.41\\% & 0.999 & 29.99\\% & 1.676 & 846 & 28.29\\% & 33.47\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.643 & -13.88\\% & 15.13\\% & -0.917 & 44.61\\% & -0.285 & 16 & 0.00\\% & 9.58\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 0.956 & -1.52\\% & 47.91\\% & -0.032 & 53.96\\% & -0.001 & 3395 & 40.24\\% & 27.84\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 9.747 & 115.88\\% & 54.44\\% & 2.129 & 32.66\\% & 7.552 & 846 & 44.80\\% & 41.51\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING)\n",
|
||||
"macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"rmse_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rmse_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"# buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING)\n",
|
||||
"# macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"# gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL)\n",
|
||||
"\n",
|
||||
"v_lines=[data_window[1]['close_time'].iloc[-1] for data_window in data_windows][:-1]\n",
|
||||
"results_table(buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat, width=1300, height=500, notitle=True)\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\\begin{table}\n",
|
||||
"\t\\begin{center}\n",
|
||||
"\t\t\\begin{tabular}{lccccccccc}\n",
|
||||
"\t\t\t\\textbf{Strategy} & \\textbf{VAL} & \\textbf{ARC} & \\textbf{ASD} & \\textbf{IR*} & \\textbf{MD} & \\textbf{IR**} & \\textbf{N} & \\textbf{LONG} & \\textbf{SHORT} \\\\\n",
|
||||
"\t\t\t\\hline\n",
|
||||
"\t\t\tBuy and Hold & 1.441 & 13.14\\% & 57.74\\% & 0.228 & 77.31\\% & 0.039 & 2 & 100.00\\% & 0.00\\% \\\\\n",
|
||||
"\t\t\tMACD Strategy & 1.918 & 24.63\\% & 54.07\\% & 0.456 & 67.19\\% & 0.167 & 2535 & 50.39\\% & 32.38\\% \\\\\n",
|
||||
"\t\t\tRSI Strategy & 5.154 & 74.05\\% & 50.37\\% & 1.470 & 26.46\\% & 4.113 & 846 & 28.29\\% & 33.47\\% \\\\\n",
|
||||
"\t\t\tRMSE Informer & 0.650 & -13.53\\% & 15.13\\% & -0.894 & 44.05\\% & -0.275 & 16 & 0.00\\% & 9.58\\% \\\\\n",
|
||||
"\t\t\tQuantile Informer & 5.404 & 76.86\\% & 47.83\\% & 1.607 & 37.34\\% & 3.307 & 3395 & 40.24\\% & 27.84\\% \\\\\n",
|
||||
"\t\t\tGMADL Informer & 14.946 & 149.43\\% & 54.42\\% & 2.746 & 31.57\\% & 12.994 & 846 & 44.80\\% & 41.51\\% \\\\\n",
|
||||
"\t\t\\end{tabular}\n",
|
||||
"\t\\end{center}\n",
|
||||
"\\end{table}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# No transaction fees\n",
|
||||
"test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING)\n",
|
||||
"macd_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL, exchange_fee=0)\n",
|
||||
"rsi_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=INTERVAL, exchange_fee=0)\n",
|
||||
"rmse_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['rmse_model']], padding=PADDING), padding=PADDING, interval=INTERVAL, exchange_fee=0)\n",
|
||||
"quantile_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=INTERVAL, exchange_fee=0)\n",
|
||||
"gmadl_model_concat = evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=INTERVAL, exchange_fee=0)\n",
|
||||
"\n",
|
||||
"v_lines=[data_window[1]['close_time'].iloc[-1] for data_window in data_windows][:-1]\n",
|
||||
"results_table(buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, rmse_model_concat, quantile_model_concat, gmadl_model_concat, width=1300, height=500, notitle=True)\n",
|
||||
"# results_table(buy_and_hold_concat, macd_concat, rsi_concat, quantile_model_concat, gmadl_model_concat)\n",
|
||||
"# results_plot(0, buy_and_hold_concat, macd_concat, rsi_concat, quantile_model_concat, gmadl_model_concat, width=1200, notitle=True)\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
21766
notebooks/gmadl.ipynb
21766
notebooks/gmadl.ipynb
File diff suppressed because it is too large
Load Diff
@ -2,7 +2,7 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -39,36 +39,26 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 48,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-1m:latest, 3717.80MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:5.3\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-5m:latest, 745.12MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:0.8\n",
|
||||
"Done. 0:0:0.9\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-15m:latest, 248.65MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:0.5\n",
|
||||
"Done. 0:0:0.7\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-30m:latest, 124.19MB. 12 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 12 of 12 files downloaded. \n",
|
||||
"Done. 0:0:0.5\n"
|
||||
"Done. 0:0:0.6\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data_windows_1min = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-1m:latest',\n",
|
||||
" min_window=0, \n",
|
||||
" max_window=5\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data_windows_5min = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-5m:latest',\n",
|
||||
@ -93,20 +83,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 49,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('cache/1min-best-strategies-v1.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_1min = pickle.load(inpt)\n",
|
||||
"\n",
|
||||
"with open('cache/5min-best-strategies-v2.pkl', 'rb') as inpt:\n",
|
||||
"with open('cache/5min-best-strategies.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_5min = pickle.load(inpt)\n",
|
||||
"\n",
|
||||
"with open('cache/15min-best-strategies-v2.pkl', 'rb') as inpt:\n",
|
||||
"with open('cache/15min-best-strategies.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_15min = pickle.load(inpt)\n",
|
||||
"\n",
|
||||
"with open('cache/30min-best-strategies-v6.pkl', 'rb') as inpt:\n",
|
||||
"with open('cache/30min-best-strategies.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_30min = pickle.load(inpt)"
|
||||
]
|
||||
},
|
||||
@ -119,34 +106,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def results_plot(\n",
|
||||
" buy_and_hold_concat,\n",
|
||||
" # macd_30min_concat,\n",
|
||||
" # rsi_30min_concat,\n",
|
||||
" # rsi_5_min_concat,\n",
|
||||
" # rmse_30min_model_concat,\n",
|
||||
" # rmse_15min_model_concat,\n",
|
||||
" gmadl_30min_model_concat,\n",
|
||||
" gmadl_15min_model_concat,\n",
|
||||
" gmadl_5min_model_concat, \n",
|
||||
" gmadl_1min_model_concat, \n",
|
||||
" width=850, height=500, notitle=False):\n",
|
||||
"def results_plot(buy_and_hold_concat, gmadl_5min_model_concat, rsi_5_min_concat, gmadl_15min_model_concat, rsi_30min_concat, macd_30min_concat, width=850, height=500, notitle=False):\n",
|
||||
"\n",
|
||||
" fig = go.Figure([\n",
|
||||
" go.Scatter(y=buy_and_hold_concat['portfolio_value'], x=buy_and_hold_concat['time'], name=\"Buy and Hold\"),\n",
|
||||
" # go.Scatter(y=macd_30min_concat['portfolio_value'], x=macd_30min_concat['time'], name='MACD Strategy (30min)'),\n",
|
||||
" # go.Scatter(y=rsi_30min_concat['portfolio_value'], x=rsi_30min_concat['time'], name='RSI Strategy (30min)'),\n",
|
||||
" # go.Scatter(y=rsi_5_min_concat['portfolio_value'], x=rsi_5_min_concat['time'], name=\"RSI Strategy (5min)\"),\n",
|
||||
" # go.Scatter(y=rmse_30min_model_concat['portfolio_value'], x=rmse_30min_model_concat['time'], name='RMSE Informer Strategy (30min)'),\n",
|
||||
" # go.Scatter(y=rmse_15min_model_concat['portfolio_value'], x=rmse_15min_model_concat['time'], name='RMSE Informer Strategy (15min)'),\n",
|
||||
" go.Scatter(y=gmadl_30min_model_concat['portfolio_value'], x=gmadl_30min_model_concat['time'], name='GMADL Informer Strategy (30min)'),\n",
|
||||
" go.Scatter(y=gmadl_15min_model_concat['portfolio_value'], x=gmadl_15min_model_concat['time'], name='GMADL Informer Strategy (15min)'),\n",
|
||||
" go.Scatter(y=gmadl_5min_model_concat['portfolio_value'], x=gmadl_5min_model_concat['time'], name=\"GMADL Informer Strategy (5min)\"),\n",
|
||||
" go.Scatter(y=gmadl_1min_model_concat['portfolio_value'], x=gmadl_1min_model_concat['time'], name=\"GMADL Informer Strategy (1min)\")\n",
|
||||
" go.Scatter(y=rsi_5_min_concat['portfolio_value'], x=rsi_5_min_concat['time'], name=\"RSI Strategy (5min)\"),\n",
|
||||
" go.Scatter(y=gmadl_15min_model_concat['portfolio_value'], x=gmadl_15min_model_concat['time'], name='GNADL Informer Strategy (15min)'),\n",
|
||||
" go.Scatter(y=rsi_30min_concat['portfolio_value'], x=rsi_30min_concat['time'], name='RSI Strategy (30min)'),\n",
|
||||
" go.Scatter(y=macd_30min_concat['portfolio_value'], x=macd_30min_concat['time'], name='MACD Strategy (30min)')\n",
|
||||
" ])\n",
|
||||
" fig.update_layout(\n",
|
||||
" # title={\n",
|
||||
@ -164,7 +136,7 @@
|
||||
" autosize=False,\n",
|
||||
" width=width,\n",
|
||||
" height=height,\n",
|
||||
" margin=dict(l=20, r=20, t=50, b=20),\n",
|
||||
" margin=dict(l=20, r=20, t=20, b=20),\n",
|
||||
" plot_bgcolor='white',\n",
|
||||
" legend=dict(\n",
|
||||
" orientation=\"h\",\n",
|
||||
@ -191,19 +163,7 @@
|
||||
" # fig.write_image(f\"images/eval-w{idx}-{INTERVAL}.png\")\n",
|
||||
" fig.show()\n",
|
||||
" \n",
|
||||
"def results_table(\n",
|
||||
" buy_and_hold_concat,\n",
|
||||
" # macd_30min_concat,\n",
|
||||
" # rsi_30min_concat,\n",
|
||||
" # rsi_5_min_concat,\n",
|
||||
" # rmse_30min_model_concat,\n",
|
||||
" # rmse_15min_model_concat,\n",
|
||||
" gmadl_30min_model_concat,\n",
|
||||
" gmadl_15min_model_concat,\n",
|
||||
" gmadl_5min_model_concat,\n",
|
||||
" gmadl_1min_model_concat\n",
|
||||
" ):\n",
|
||||
"\n",
|
||||
"def results_table(buy_and_hold_concat, gmadl_5min_model_concat, rsi_5_min_concat, gmadl_15min_model_concat, rsi_30min_concat, macd_30min_concat):\n",
|
||||
" table_eval_windows = Texttable()\n",
|
||||
" table_eval_windows.set_deco(Texttable.HEADER)\n",
|
||||
" table_eval_windows.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\"])\n",
|
||||
@ -224,15 +184,11 @@
|
||||
"\n",
|
||||
" strategy_name_result = [\n",
|
||||
" ('Buy and Hold', buy_and_hold_concat),\n",
|
||||
" # ('MACD Strategy (30min)', macd_30min_concat),\n",
|
||||
" # ('RSI Strategy (30min)', rsi_30min_concat),\n",
|
||||
" # ('RSI Strategy (5min)', rsi_5_min_concat),\n",
|
||||
" # ('RMSE Informer (30min)', rmse_30min_model_concat),\n",
|
||||
" # ('RMSE Informer (15min)', rmse_15min_model_concat),\n",
|
||||
" ('GMADL Informer (30min)', gmadl_30min_model_concat),\n",
|
||||
" ('GMADL Informer (15min)', gmadl_15min_model_concat),\n",
|
||||
" ('GMADL Informer (5min)', gmadl_5min_model_concat),\n",
|
||||
" ('GMADL Informer (1min)', gmadl_1min_model_concat),\n",
|
||||
" ('RSI Strategy (5min)', rsi_5_min_concat),\n",
|
||||
" ('GMADL Informer (15min)', gmadl_15min_model_concat),\n",
|
||||
" ('RSI Strategy (30min)', rsi_30min_concat),\n",
|
||||
" ('MACD Strategy (30min)', macd_30min_concat)\n",
|
||||
" ]\n",
|
||||
" for strategy_name, result in strategy_name_result:\n",
|
||||
" table_eval_windows.add_row([\n",
|
||||
@ -254,146 +210,21 @@
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "NameError",
|
||||
"evalue": "name 'pd' is not defined",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m test_data_1min \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241m.\u001b[39mconcat([data_windows_1min[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m-\u001b[39mPADDING:]] \u001b[38;5;241m+\u001b[39m [data_window[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m data_window \u001b[38;5;129;01min\u001b[39;00m data_windows_1min])\n\u001b[1;32m 2\u001b[0m test_data_5min \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat([data_windows_5min[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m-\u001b[39mPADDING:]] \u001b[38;5;241m+\u001b[39m [data_window[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m data_window \u001b[38;5;129;01min\u001b[39;00m data_windows_5min])\n\u001b[1;32m 3\u001b[0m test_data_15min \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat([data_windows_15min[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m0\u001b[39m][\u001b[38;5;241m-\u001b[39mPADDING:]] \u001b[38;5;241m+\u001b[39m [data_window[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mfor\u001b[39;00m data_window \u001b[38;5;129;01min\u001b[39;00m data_windows_15min])\n",
|
||||
"\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"test_data_1min = pd.concat([data_windows_1min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_1min])\n",
|
||||
"test_data_5min = pd.concat([data_windows_5min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_5min])\n",
|
||||
"test_data_15min = pd.concat([data_windows_15min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_15min])\n",
|
||||
"test_data_30min = pd.concat([data_windows_30min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_30min])\n",
|
||||
"\n",
|
||||
"buy_and_hold_concat = evaluate_strategy(test_data_5min, BuyAndHoldStrategy(), padding=PADDING, interval='5min')\n",
|
||||
"# macd_30min_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['macd_strategies']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"# rsi_30min_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"# rsi_5_min_concat = evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[0] for s in best_strategies_5min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='5min')\n",
|
||||
"# rmse_30min_model_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['rmse_model']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"# rmse_15min_model_concat = evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[0] for s in best_strategies_15min['rmse_model']], padding=PADDING), padding=PADDING, interval='15min')\n",
|
||||
"gmadl_30min_model_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['gmadl_model']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"gmadl_15min_model_concat = evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[0] for s in best_strategies_15min['gmadl_model']], padding=PADDING), padding=PADDING, interval='15min')\n",
|
||||
"gmadl_1min_model_concat = evaluate_strategy(test_data_1min, ConcatenatedStrategies(len(data_windows_1min[0][1]), [s[0] for s in best_strategies_1min['gmadl_model']], padding=PADDING), padding=PADDING, interval='min')\n",
|
||||
"gmadl_5min_model_concat = evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[0] for s in best_strategies_5min['gmadl_model']], padding=PADDING), padding=PADDING, interval='5min')\n",
|
||||
"\n",
|
||||
"# results_table(\n",
|
||||
"# buy_and_hold_concat,\n",
|
||||
" # macd_30min_concat,\n",
|
||||
" # rsi_30min_concat,\n",
|
||||
" # rsi_5_min_concat,\n",
|
||||
" # rmse_30min_model_concat,\n",
|
||||
" # rmse_15min_model_concat,\n",
|
||||
" # gmadl_30min_model_concat,\n",
|
||||
" # gmadl_15min_model_concat,\n",
|
||||
" # gmadl_5min_model_concat,\n",
|
||||
" # gmadl_1min_model_concat\n",
|
||||
" # )\n",
|
||||
"\n",
|
||||
"# results_plot(\n",
|
||||
"# buy_and_hold_concat,\n",
|
||||
"# macd_30min_concat,\n",
|
||||
"# rsi_30min_concat,\n",
|
||||
"# rsi_5_min_concat,\n",
|
||||
"# rmse_30min_model_concat,\n",
|
||||
"# rmse_15min_model_concat,\n",
|
||||
" # gmadl_30min_model_concat,\n",
|
||||
" # gmadl_15min_model_concat,\n",
|
||||
" # gmadl_5min_model_concat, \n",
|
||||
" # gmadl_1min_model_concat, \n",
|
||||
" # width=1200, notitle=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Statistical significance"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"test_data_5min = pd.concat([data_windows_5min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_5min])\n",
|
||||
"test_data_15min = pd.concat([data_windows_15min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_15min])\n",
|
||||
"test_data_30min = pd.concat([data_windows_30min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_30min])\n",
|
||||
"# test_data_5min = pd.concat([data_windows_5min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_5min])\n",
|
||||
"# test_data_15min = pd.concat([data_windows_15min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_15min])\n",
|
||||
"# test_data_30min = pd.concat([data_windows_30min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_30min])\n",
|
||||
"\n",
|
||||
"buy_and_hold_5min = evaluate_strategy(test_data_5min, BuyAndHoldStrategy(), padding=PADDING, interval='5min')\n",
|
||||
"buy_and_hold_15min = evaluate_strategy(test_data_15min, BuyAndHoldStrategy(), padding=PADDING, interval='15min')\n",
|
||||
"buy_and_hold_30min = evaluate_strategy(test_data_30min, BuyAndHoldStrategy(), padding=PADDING, interval='30min')\n",
|
||||
"macd_30min_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['macd_strategies']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"rsi_30min_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"rsi_5_min_concat = evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[0] for s in best_strategies_5min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='5min')\n",
|
||||
"rmse_30min_model_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['rmse_model']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"rmse_15min_model_concat = evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[0] for s in best_strategies_15min['rmse_model']], padding=PADDING), padding=PADDING, interval='15min')\n",
|
||||
"gmadl_30min_model_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['gmadl_model']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"gmadl_15min_model_concat = evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[0] for s in best_strategies_15min['gmadl_model']], padding=PADDING), padding=PADDING, interval='15min')\n",
|
||||
"gmadl_5min_model_concat = evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[0] for s in best_strategies_5min['gmadl_model']], padding=PADDING), padding=PADDING, interval='5min')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"MACD (30 min) & 51840 & 0.326504 & 174.34 & 0.000000*** \\\\\n",
|
||||
"RSI (30 min) & 51840 & 1.065079 & 258.49 & 0.000000*** \\\\\n",
|
||||
"RSI (5 min) & 311040 & 0.648741 & 662.77 & 0.000000*** \\\\\n",
|
||||
"RMSE (30 min) & 51840 & 0.796647 & 161.58 & 0.000000*** \\\\\n",
|
||||
"RMSE (15 min) & 103680 & 0.541611 & 115.29 & 0.000000*** \\\\\n",
|
||||
"GMADL (30 min) & 51840 & 0.320689 & 448.49 & 0.000000*** \\\\\n",
|
||||
"GMADL (15 min) & 103680 & 0.558743 & 408.13 & 0.000000*** \\\\\n",
|
||||
"GMADL (5min) & 311040 & 2.820834 & 375.84 & 0.000000*** \\\\\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import scipy.stats\n",
|
||||
"# buy_and_hold_concat = evaluate_strategy(test_data_5min, BuyAndHoldStrategy(), padding=PADDING, interval='5min')\n",
|
||||
"# gmadl_5min_model_concat = evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[0] for s in best_strategies_5min['gmadl_model']], padding=PADDING), padding=PADDING, interval='5min')\n",
|
||||
"# gmadl_15min_model_concat = evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[0] for s in best_strategies_15min['gmadl_model']], padding=PADDING), padding=PADDING, interval='15min')\n",
|
||||
"# rsi_5_min_concat = evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[0] for s in best_strategies_5min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='5min')\n",
|
||||
"# rsi_30min_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"# macd_30min_concat = evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[0] for s in best_strategies_30min['macd_strategies']], padding=PADDING), padding=PADDING, interval='30min')\n",
|
||||
"\n",
|
||||
"def ttest(benchmark, strategy):\n",
|
||||
" sigma = np.std(strategy['portfolio_value'] - benchmark['portfolio_value'])\n",
|
||||
" N = len(strategy['strategy_returns'])\n",
|
||||
" tt = (strategy['ir'] - benchmark['ir']) / (sigma / np.sqrt(N))\n",
|
||||
"\n",
|
||||
" pval = scipy.stats.t.sf(np.abs(tt), N-1)*2\n",
|
||||
"\n",
|
||||
" return tt, pval, sigma, N\n",
|
||||
"\n",
|
||||
"macd_30min_ttest = ttest(buy_and_hold_30min, macd_30min_concat)\n",
|
||||
"rsi_30min_ttest = ttest(buy_and_hold_30min, rsi_30min_concat)\n",
|
||||
"rsi_5min_ttest = ttest(buy_and_hold_5min, rsi_5_min_concat)\n",
|
||||
"rmse_30min_ttest = ttest(buy_and_hold_30min, rmse_30min_model_concat)\n",
|
||||
"rmse_15min_ttest = ttest(buy_and_hold_15min, rmse_15min_model_concat)\n",
|
||||
"gmadl_30min_ttest = ttest(buy_and_hold_30min, gmadl_30min_model_concat)\n",
|
||||
"gmadl_15min_ttest = ttest(buy_and_hold_15min, gmadl_15min_model_concat)\n",
|
||||
"gmadl_5min_ttest = ttest(buy_and_hold_5min, gmadl_5min_model_concat)\n",
|
||||
"\n",
|
||||
"for name, result in [\n",
|
||||
" (\"MACD (30 min)\", macd_30min_ttest),\n",
|
||||
" (\"RSI (30 min)\", rsi_30min_ttest),\n",
|
||||
" (\"RSI (5 min)\", rsi_5min_ttest),\n",
|
||||
" (\"RMSE (30 min)\", rmse_30min_ttest),\n",
|
||||
" (\"RMSE (15 min)\", rmse_15min_ttest),\n",
|
||||
" (\"GMADL (30 min)\", gmadl_30min_ttest),\n",
|
||||
" (\"GMADL (15 min)\", gmadl_15min_ttest),\n",
|
||||
" (\"GMADL (5min)\", gmadl_5min_ttest),\n",
|
||||
"]:\n",
|
||||
" print(f\"{name} & {result[3]} & {result[2]:.6f} & {result[0]:.2f} & {result[1]:.6f}*** \\\\\\\\\")"
|
||||
"# results_table(buy_and_hold_concat, gmadl_5min_model_concat, rsi_5_min_concat, gmadl_15min_model_concat, rsi_30min_concat, macd_30min_concat)\n",
|
||||
"# results_plot(buy_and_hold_concat, gmadl_5min_model_concat, gmadl_15min_model_concat, rsi_5_min_concat, rsi_30min_concat, macd_30min_concat, width=1200, notitle=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -405,88 +236,52 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def results_for_strats(\n",
|
||||
" data_windows_5min, data_windows_15min, data_windows_30min, \n",
|
||||
" best_strategies_5min, best_strategies_15min, best_strategies_30min,\n",
|
||||
" top_n=10):\n",
|
||||
" test_data_5min = pd.concat([data_windows_5min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_5min])\n",
|
||||
" test_data_15min = pd.concat([data_windows_15min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_15min])\n",
|
||||
" test_data_30min = pd.concat([data_windows_30min[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows_30min])\n",
|
||||
"def results_for_strats(data_windows, best_strategies, interval='5min', top_n=10):\n",
|
||||
" test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"\n",
|
||||
" buy_and_hold_concat = evaluate_strategy(test_data_5min, BuyAndHoldStrategy(), padding=PADDING, interval='5min')\n",
|
||||
" macd_30min_concat = [evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[x] for s in best_strategies_30min['macd_strategies']], padding=PADDING), padding=PADDING, interval='30min') for x in range(top_n)]\n",
|
||||
" macd_15min_concat = [evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[x] for s in best_strategies_15min['macd_strategies']], padding=PADDING), padding=PADDING, interval='15min') for x in range(top_n)]\n",
|
||||
" macd_5min_concat = [evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[x] for s in best_strategies_5min['macd_strategies']], padding=PADDING), padding=PADDING, interval='5min') for x in range(top_n)]\n",
|
||||
" rsi_30min_concat = [evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[x] for s in best_strategies_30min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='30min') for x in range(top_n)]\n",
|
||||
" rsi_15min_concat = [evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[x] for s in best_strategies_15min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='15min') for x in range(top_n)]\n",
|
||||
" rsi_5_min_concat = [evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[x] for s in best_strategies_5min['rsi_strategies']], padding=PADDING), padding=PADDING, interval='5min') for x in range(top_n)]\n",
|
||||
" rmse_30min_model_concat = [evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[x] for s in best_strategies_30min['rmse_model']], padding=PADDING), padding=PADDING, interval='30min') for x in range(top_n)]\n",
|
||||
" rmse_15min_model_concat = [evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[x] for s in best_strategies_15min['rmse_model']], padding=PADDING), padding=PADDING, interval='15min') for x in range(top_n)]\n",
|
||||
" rmse_5min_model_concat = [evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[x] for s in best_strategies_5min['rmse_model']], padding=PADDING), padding=PADDING, interval='5min') for x in range(top_n)]\n",
|
||||
" quantile_30min_model_concat = [evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[x] for s in best_strategies_30min['quantile_model']], padding=PADDING), padding=PADDING, interval='30min') for x in range(top_n)]\n",
|
||||
" quantile_15min_model_concat = [evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[x] for s in best_strategies_15min['quantile_model']], padding=PADDING), padding=PADDING, interval='15min') for x in range(top_n)]\n",
|
||||
" quantile_5min_model_concat = [evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[x] for s in best_strategies_5min['quantile_model']], padding=PADDING), padding=PADDING, interval='5min') for x in range(top_n)]\n",
|
||||
" gmadl_30min_model_concat = [evaluate_strategy(test_data_30min, ConcatenatedStrategies(len(data_windows_30min[0][1]), [s[x] for s in best_strategies_30min['gmadl_model']], padding=PADDING), padding=PADDING, interval='30min') for x in range(top_n)]\n",
|
||||
" gmadl_15min_model_concat = [evaluate_strategy(test_data_15min, ConcatenatedStrategies(len(data_windows_15min[0][1]), [s[x] for s in best_strategies_15min['gmadl_model']], padding=PADDING), padding=PADDING, interval='15min') for x in range(top_n)]\n",
|
||||
" gmadl_5min_model_concat = [evaluate_strategy(test_data_5min, ConcatenatedStrategies(len(data_windows_5min[0][1]), [s[x] for s in best_strategies_5min['gmadl_model']], padding=PADDING), padding=PADDING, interval='5min') for x in range(top_n)]\n",
|
||||
" buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING)\n",
|
||||
" \n",
|
||||
" macd_concat = [evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[x] for s in best_strategies['macd_strategies']], padding=PADDING), padding=PADDING, interval=interval) for x in range(top_n)]\n",
|
||||
" rsi_concat = [evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[x] for s in best_strategies['rsi_strategies']], padding=PADDING), padding=PADDING, interval=interval) for x in range(top_n)]\n",
|
||||
" quantile_model_concat = [evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[x] for s in best_strategies['quantile_model']], padding=PADDING), padding=PADDING, interval=interval) for x in range(top_n)]\n",
|
||||
" gmadl_model_concat = [evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[x] for s in best_strategies['gmadl_model']], padding=PADDING), padding=PADDING, interval=interval) for x in range(top_n)]\n",
|
||||
"\n",
|
||||
" z = list(reversed([\n",
|
||||
" list(reversed([round(buy_and_hold_concat['mod_ir'], 3)]*top_n)),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in macd_30min_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in macd_15min_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in macd_5min_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rsi_30min_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rsi_15min_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rsi_5_min_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rmse_30min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rmse_15min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rmse_5min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in quantile_30min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in quantile_15min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in quantile_5min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in gmadl_30min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in gmadl_15min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in gmadl_5min_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in macd_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in rsi_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in quantile_model_concat])),\n",
|
||||
" list(reversed([round(x['mod_ir'], 3) for x in gmadl_model_concat])),\n",
|
||||
" ]))\n",
|
||||
" x = list(reversed(range(1, top_n+1)))\n",
|
||||
" y = list(reversed([\n",
|
||||
" \"Buy and Hold\",\n",
|
||||
" \"MACD Strategy (30 min)\",\n",
|
||||
" \"MACD Strategy (15 min)\",\n",
|
||||
" \"MACD Strategy (5 min)\",\n",
|
||||
" \"RSI Strategy (30 min)\",\n",
|
||||
" \"RSI Strategy (15 min)\",\n",
|
||||
" \"RSI Strategy (5 min)\",\n",
|
||||
" \"RMSE Informer (30 min)\",\n",
|
||||
" \"RMSE Informer (15 min)\",\n",
|
||||
" \"RMSE Informer (5 min)\",\n",
|
||||
" \"Quantile Informer (30 min)\",\n",
|
||||
" \"Quantile Informer (15 min)\",\n",
|
||||
" \"Quantile Informer (5 min)\",\n",
|
||||
" \"Gmadl Informer (30 min)\",\n",
|
||||
" \"Gmadl Informer (15 min)\",\n",
|
||||
" \"Gmadl Informer (5 min)\"\n",
|
||||
" \"MACD Strategy\",\n",
|
||||
" \"RSI Strategy\",\n",
|
||||
" \"Quantile Informer\",\n",
|
||||
" \"Gmadl Informer\"\n",
|
||||
" ]))\n",
|
||||
" # 'Portland'\n",
|
||||
" fig = ff.create_annotated_heatmap(z, x=x, y=y, colorscale='thermal', zmid=buy_and_hold_concat['mod_ir'])\n",
|
||||
" fig.update_layout(\n",
|
||||
" margin=dict(l=20, r=20, b=20, t=20),\n",
|
||||
" width=1100,\n",
|
||||
" height=650,\n",
|
||||
" height=450,\n",
|
||||
" font=dict(\n",
|
||||
" # family=\"Courier New, monospace\",\n",
|
||||
" size=16, # Set the font size here\n",
|
||||
" size=18, # Set the font size here\n",
|
||||
" # color=\"RebeccaPurple\"\n",
|
||||
" )\n",
|
||||
" )\n",
|
||||
" fig.show()\n",
|
||||
"\n",
|
||||
"# results_for_strats(data_windows_5min, data_windows_15min, data_windows_30min,\n",
|
||||
"# best_strategies_5min, best_strategies_15min, best_strategies_30min, top_n=10) "
|
||||
"# results_for_strats(data_windows_5min, best_strategies_5min, interval='5min', top_n=10) \n",
|
||||
"# results_for_strats(data_windows_15min, best_strategies_15min, interval='15min', top_n=10) \n",
|
||||
"# results_for_strats(data_windows_30min, best_strategies_30min, interval='30min', top_n=10) \n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -536,7 +331,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 48,
|
||||
"execution_count": 37,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -591,7 +386,7 @@
|
||||
" table_eval_windows = Texttable()\n",
|
||||
" table_eval_windows.set_deco(Texttable.HEADER)\n",
|
||||
" table_eval_windows.set_cols_align([\"l\", \"c\",\"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\", \"c\"])\n",
|
||||
" table_eval_windows.set_precision(2)\n",
|
||||
" table_eval_windows.set_precision(3)\n",
|
||||
"\n",
|
||||
" table_eval_windows.header([\n",
|
||||
" \"\\\\textbf{Strategy}\",\n",
|
||||
@ -612,21 +407,21 @@
|
||||
" table_eval_windows.add_row([\n",
|
||||
" strategy_name,\n",
|
||||
" result['value'],\n",
|
||||
" f\"{result['arc']*100:.1f}\\%\",\n",
|
||||
" f\"{result['asd']*100:.1f}\\%\",\n",
|
||||
" result['arc'],\n",
|
||||
" result['asd'],\n",
|
||||
" result['ir'],\n",
|
||||
" f\"{result['md']*100:.1f}\\%\",\n",
|
||||
" result['md'],\n",
|
||||
" result['mod_ir'],\n",
|
||||
" result['n_trades'],\n",
|
||||
" f\"{result['long_pos']*100:.1f}\\%\",\n",
|
||||
" f\"{result['short_pos']*100:.1f}\\%\",\n",
|
||||
" f\"{result['long_pos']*100:.2f}\\%\",\n",
|
||||
" f\"{result['short_pos']*100:.2f}\\%\",\n",
|
||||
" ])\n",
|
||||
" print(latextable.draw_latex(table_eval_windows))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 37,
|
||||
"execution_count": 46,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -708,125 +503,6 @@
|
||||
"# results_plot(buy_and_hold_concat, [res], width=1200)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Different number of test windows"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open('cache/5min-best-strategies-short.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_5min_short = pickle.load(inpt)\n",
|
||||
"\n",
|
||||
"with open('cache/5min-best-strategies-long.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_5min_long = pickle.load(inpt)\n",
|
||||
"\n",
|
||||
"with open('cache/30min-best-strategies-short.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_30min_short = pickle.load(inpt)\n",
|
||||
"\n",
|
||||
"with open('cache/30min-best-strategies-long.pkl', 'rb') as inpt:\n",
|
||||
" best_strategies_30min_long = pickle.load(inpt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 39,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-5m-short:latest, 1341.36MB. 24 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 24 of 24 files downloaded. \n",
|
||||
"Done. 0:0:0.7\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-5m-long:latest, 446.99MB. 6 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 6 of 6 files downloaded. \n",
|
||||
"Done. 0:0:1.1\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-30m-short:latest, 223.56MB. 24 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 24 of 24 files downloaded. \n",
|
||||
"Done. 0:0:0.7\n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact btc-usdt-30m-long:latest, 74.51MB. 6 files... \n",
|
||||
"\u001b[34m\u001b[1mwandb\u001b[0m: 6 of 6 files downloaded. \n",
|
||||
"Done. 0:0:0.4\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data_windows_5min_short = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-5m-short:latest',\n",
|
||||
" min_window=0, \n",
|
||||
" max_window=11\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data_windows_5min_long = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-5m-long:latest',\n",
|
||||
" min_window=0, \n",
|
||||
" max_window=2\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data_windows_30min_short = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-30m-short:latest',\n",
|
||||
" min_window=0, \n",
|
||||
" max_window=11\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data_windows_30min_long = get_data_windows(\n",
|
||||
" 'wne-masters-thesis-testing',\n",
|
||||
" 'btc-usdt-30m-long:latest',\n",
|
||||
" min_window=0, \n",
|
||||
" max_window=2\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 57,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# def results_for_strats_different_windows(buy_and_hold_data_windows, *args, interval='5min'):\n",
|
||||
"# evaluation_results = []\n",
|
||||
"# names = []\n",
|
||||
"# buy_and_hold_data = pd.concat([buy_and_hold_data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in buy_and_hold_data_windows])\n",
|
||||
"# buy_and_hold_concat = evaluate_strategy(buy_and_hold_data, BuyAndHoldStrategy(), padding=PADDING, interval=interval)\n",
|
||||
"# for data_windows, strategy, name in args:\n",
|
||||
"# test_data = pd.concat([data_windows[0][0][-PADDING:]] + [data_window[1] for data_window in data_windows])\n",
|
||||
"# # buy_and_hold_concat = evaluate_strategy(test_data, BuyAndHoldStrategy(), padding=PADDING, interval=interval)\n",
|
||||
"# evaluation_results.append(\n",
|
||||
"# evaluate_strategy(test_data, ConcatenatedStrategies(len(data_windows[0][1]), [s[0] for s in strategy], padding=PADDING), padding=PADDING, interval=interval\n",
|
||||
"# ))\n",
|
||||
"# names.append(name)\n",
|
||||
" \n",
|
||||
"# results_plot2(buy_and_hold_concat, evaluation_results, names, width=1200)\n",
|
||||
"# results_table2(buy_and_hold_concat, evaluation_results, names)\n",
|
||||
"\n",
|
||||
"# results_for_strats_different_windows(\n",
|
||||
"# data_windows_30min,\n",
|
||||
"# (data_windows_30min_short, best_strategies_30min_short['rsi_strategies'], '12 windows'),\n",
|
||||
"# (data_windows_30min, best_strategies_30min['rsi_strategies'], '6 windows'),\n",
|
||||
"# (data_windows_30min_long, best_strategies_30min_long['rsi_strategies'], '3 windows'),\n",
|
||||
"# interval='30min'\n",
|
||||
"# )\n",
|
||||
"\n",
|
||||
"# results_for_strats_different_windows(\n",
|
||||
"# data_windows_5min,\n",
|
||||
"# (data_windows_5min_short, best_strategies_5min_short['gmadl_model'], '12 windows'),\n",
|
||||
"# (data_windows_5min, best_strategies_5min['gmadl_model'], '6 windows'),\n",
|
||||
"# (data_windows_5min_long, best_strategies_5min_long['gmadl_model'], '3 windows'),\n",
|
||||
"# interval='5min'\n",
|
||||
"# )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import torch
|
||||
|
||||
from pytorch_forecasting import QuantileLoss, RMSE
|
||||
from pytorch_forecasting import QuantileLoss
|
||||
from pytorch_forecasting.metrics.base_metrics import MultiHorizonMetric
|
||||
|
||||
|
||||
@ -15,9 +15,6 @@ def get_loss(config):
|
||||
a=config['loss']['a'],
|
||||
b=config['loss']['b']
|
||||
)
|
||||
|
||||
if loss_name == 'RMSE':
|
||||
return RMSE()
|
||||
|
||||
raise ValueError("Unknown loss")
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user