Lets go

main.py

@@ -1,9 +1,11 @@
 import pandas as pd
-from sklearn.model_selection import GridSearchCV
-from sklearn.ensemble import RandomForestRegressor
 import time
 from datetime import datetime, timezone, timedelta
 import calendar
+#from sklearnex import patch_sklearn # broken :(
+#patch_sklearn()
+from sklearn.model_selection import GridSearchCV
+from sklearn.ensemble import RandomForestRegressor
 
 rf_reg_grid = {
     'bootstrap': [True],
@@ -17,6 +19,9 @@ rf_reg_grid = {
 best_params = {
     'bootstrap': [True], 'max_depth': [90], 'max_features': ['auto'], 'min_samples_leaf': [4], 'min_samples_split': [10], 'n_estimators': [100]
 }
+
+report_file = '/results/report.txt'
+
 def get_data_and_store_csv(symbol, interval, start, end = None, limit=1000):
     """
     start and end must be isoformat YYYY-MM-DD
@@ -74,8 +79,8 @@ def get_stored_data(symbol, interval, start, end):
     start = calendar.timegm(datetime.fromisoformat(start).timetuple()) * 1000
     end = calendar.timegm(datetime.fromisoformat(end).timetuple()) * 1000
     df = pd.read_csv(
-        #f'/crypto_prediction/data/{symbol}--interval-{interval}--start-{start}--end-{end}.csv',
-        f'data/{symbol}--interval-{interval}--start-{start}--end-{end}.csv',
+        f'/crypto_prediction/data/{symbol}--interval-{interval}--start-{start}--end-{end}.csv',
+        #'data/{symbol}--interval-{interval}--start-{start}--end-{end}.csv',
         parse_dates=['Opentime']
     )
     return df
@@ -113,10 +118,11 @@ def split_data(df, split_value):
 
 def find_best_hyperparameters_and_train(X_train, y_train):
     global rf_reg_grid
+    global report_file
 
     gs_rf_reg = GridSearchCV(
         RandomForestRegressor(),
-        param_grid=best_params,
+        param_grid=rf_reg_grid,
         cv=5,
         refit=True,
         n_jobs=-1
@@ -124,19 +130,27 @@ def find_best_hyperparameters_and_train(X_train, y_train):
 
     gs_rf_reg.fit(X_train, y_train)
 
-    print("Best hyperparameters: ", gs_rf_reg.best_params_)
+    report(report_file, f'Best hyperparams:\n{gs_rf_reg.best_params_}')
 
     return gs_rf_reg
 
+def report(f_name, report_data):
+    with open(f_name, 'a') as f:
+        f.write(report_data)
+        f.write('\n')
+        f.flush()
+        f.close()
+
+
 def main():
-    global models
+    global report_file
     # Read data into panda dataframe
     #df = get_data_and_store_csv('XMRUSDT', '1m', '2020-01-01', '2022-09-04')
     df = get_stored_data('XMRUSDT', '1m', '2020-01-01', '2022-09-04')
     # Prepare data for moddeling
     df = process_data(df=df)
     # Split data into train and test sets
-    X_train, X_test, y_train, y_test = split_data(df=df, split_value=0.9999) 
+    X_train, X_test, y_train, y_test = split_data(df=df, split_value=0.99999) 
 
     # Model the data
     model = find_best_hyperparameters_and_train(
@@ -144,15 +158,18 @@ def main():
          y_train=y_train
     )
 
-    # Score our modello
-    print("Test data:\n", X_test)
-    print("Prediction results:\n", model.predict(X_test))
-    print("Correct values:\n", y_test)
-    print('Model scored:\n', model.score(X_test, y_test))
+    # Do a report
+    report(report_file, f'Test data:\n{X_test}')
+    report(report_file, f'Prediction results:\n{model.predict(X_test)}')
+    report(report_file, f'Correct values:\n{y_test}')
+    report(report_file, f'Model scored:\n{model.score(X_test, y_test)}')
 
 
 if __name__ == "__main__":
     start_time = time.time()
+    prettified_time = datetime.now().strftime("%H:%M:%S")
+    report(report_file, f"\n Starting! {prettified_time}")
     main()
     end_time = time.time() - start_time
     print(f'\n\nCompleted...\t\t\t\t\t{end_time // 3600} h {(end_time // 60) % 60} m {int(end_time % 60)}s')
+    report(report_file, f'\n\nCompleted...\t\t\t\t\t{end_time // 3600} h {(end_time // 60) % 60} m {int(end_time % 60)}s')