progress

configuration/equity.cfg

@@ -2,7 +2,7 @@
     "security_type": "EQUITY",
     "data_directory": "./data/equity",
     "datafiles": [
-        "202505*.alpaca_sim_md.db",
+        "202506*.mktdata.ohlcv.db",
     ],
     "db_table_name": "md_1min_bars",
     "exchange_id": "ALPACA",
@@ -19,8 +19,8 @@
     "dis-equilibrium_close_trshld": 1.0,
     "training_minutes": 120,
     "funding_per_pair": 2000.0,
-    # "strategy_class": "strategies.StaticFitStrategy"
+    "strategy_class": "strategies.StaticFitStrategy"
-    "strategy_class": "strategies.SlidingFitStrategy"
+    # "strategy_class": "strategies.SlidingFitStrategy"
     "exclude_instruments": ["CAN"]
     
 }

requirements.txt

@@ -25,6 +25,7 @@ httplib2>=0.20.2
 idna>=3.3
 ifaddr>=0.1.7
 IMDbPY>=2021.4.18
+ipykernel>=6.29.5
 jeepney>=0.7.1
 jsonschema>=3.2.0
 keyring>=23.5.0
@@ -35,6 +36,7 @@ lxml>=4.8.0
 Mako>=1.1.3
 Markdown>=3.3.6
 MarkupSafe>=2.0.1
+matplotlib>=3.10.3
 more-itertools>=8.10.0
 multidict>=6.0.4
 mypy>=0.942
@@ -64,6 +66,7 @@ PyYAML>=6.0
 reportlab>=3.6.8
 requests>=2.25.1
 requests-file>=1.5.1
+seaborn>=0.13.2
 SecretStorage>=3.3.1
 setproctitle>=1.2.2
 six>=1.16.0

scripts/load_equity_1min.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+
+usage() {
+    echo "Usage: $0 [DatePattern]"
+    echo "DatePattern: YYYYMM or YYYYM or YYYYMMD"
+    exit 1
+}
+
+DatePattern="${1}"
+if [ -z "${DatePattern}" ]; then
+    usage
+fi
+FilePattern="${DatePattern}*.alpaca_sim_md.db.gz"
+
+pushd ./data/equity
+Cmd="rsync -ahvv cvtt@hs01.cvtt.vpn:/works/cvtt/md_archive/equity/alpaca_md/sim/${FilePattern} ./"
+echo ${Cmd}
+eval ${Cmd}
+# -------------------------------------
+
+for srcfname in $(ls *.db.gz); do
+    dt="${srcfname:0:8}"
+    tgtfile=${dt}.mktdata.ohlcv.db
+    echo "${srcfname} -> ${tgtfile}"
+
+    gunzip -c $srcfname > temp.db
+    rm -f ${tgtfile} && sqlite3 temp.db ".dump md_1min_bars" | sqlite3  ${tgtfile} && rm ${srcfname}
+done
+rm temp.db
+popd

src/tools/trading_pair.py

@@ -93,15 +93,30 @@ class TradingPair:
         # print(f"{self}: {self.vecm_fit_.summary()}")
         pass
 
-    def check_cointegration(self):
+    def check_cointegration_johansen(self):
         from statsmodels.tsa.vector_ar.vecm import coint_johansen
         df = self.training_df_[self.colnames()].reset_index(drop=True)
         result = coint_johansen(df, det_order=0, k_ar_diff=1)
-        # print(f"{self}: lr1={result.lr1[0]} cvt={result.cvt[0, 1]}.")
+        print(f"{self}: lr1={result.lr1[0]} cvt={result.cvt[0, 1]}.")
         is_cointegrated = result.lr1[0] > result.cvt[0, 1]
 
         return is_cointegrated
 
+
+    def check_cointegration(self):
+        from statsmodels.tsa.stattools import coint
+        col1, col2 = self.colnames()
+        series1 = self.training_df_[col1].reset_index(drop=True)
+        series2 = self.training_df_[col2].reset_index(drop=True)
+
+        # Run Engle-Granger cointegration test
+        pvalue = coint(series1, series2)[1]
+        # Define cointegration if p-value < 0.05 (i.e., reject null of no cointegration)
+        is_cointegrated = pvalue < 0.05
+        print(f"{self}: is_cointegrated={is_cointegrated} pvalue={pvalue}")
+        return is_cointegrated
+
+
     def train_pair(self) -> bool:
         is_cointegrated = self.check_cointegration()
         if not is_cointegrated: