bugfixing

app/cron_ai_score.py

@@ -80,7 +80,7 @@ def top_uncorrelated_features(df, target_col='Target', top_n=10, threshold=0.75)
             selected_features.append(feature)
     return selected_features
 
-async def download_data(ticker, con, start_date, end_date, skip_downloading):
+async def download_data(ticker, con, start_date, end_date, skip_downloading, save_data):
 
     file_path = f"ml_models/training_data/ai-score/{ticker}.json"
 
@@ -200,6 +200,7 @@ async def download_data(ticker, con, start_date, end_date, skip_downloading):
                 'operatingCashFlow','cashAndCashEquivalents', 'totalEquity','otherCurrentLiabilities', 'totalCurrentLiabilities', 'totalDebt',
                 'totalLiabilitiesAndStockholdersEquity', 'totalStockholdersEquity', 'totalInvestments','totalAssets',
             ]
+            
 
             # Function to compute combinations within a group
             def compute_column_ratios(columns, df, new_columns):
@@ -240,7 +241,7 @@ async def download_data(ticker, con, start_date, end_date, skip_downloading):
             df_copy = df_combined.copy().map(lambda x: round(x, 2) if isinstance(x, float) else x)
 
             # Save to a file if there are rows in the DataFrame
-            if not df_copy.empty:
+            if not df_copy.empty and save_data == True:
                 with open(file_path, 'wb') as file:
                     file.write(orjson.dumps(df_copy.to_dict(orient='records')))
 
@@ -251,7 +252,7 @@ async def download_data(ticker, con, start_date, end_date, skip_downloading):
             pass
 
 
-async def chunked_gather(tickers, con, skip_downloading, chunk_size):
+async def chunked_gather(tickers, con, skip_downloading, save_data, chunk_size):
     test_size = 0.2
     start_date = datetime(1995, 1, 1).strftime("%Y-%m-%d")
     end_date = datetime.today().strftime("%Y-%m-%d")
@@ -267,7 +268,7 @@ async def chunked_gather(tickers, con, skip_downloading, chunk_size):
     for chunk in tqdm(chunks(tickers, chunk_size)):
         # Create tasks for each chunk
         print(f"chunk size: {len(chunk)}")
-        tasks = [download_data(ticker, con, start_date, end_date, skip_downloading) for ticker in chunk]
+        tasks = [download_data(ticker, con, start_date, end_date, skip_downloading, save_data) for ticker in chunk]
         # Await the results for the current chunk
         chunk_results = await asyncio.gather(*tasks)
         
@@ -309,18 +310,18 @@ async def chunked_gather(tickers, con, skip_downloading, chunk_size):
         print(f'Overall Evaluation Metrics: {data}')
 
         
-async def warm_start_training(tickers, con, skip_downloading):
+async def warm_start_training(tickers, con, skip_downloading, save_data):
     
-    dfs = await chunked_gather(tickers, con, skip_downloading, chunk_size=100)
+    dfs = await chunked_gather(tickers, con, skip_downloading, save_data, chunk_size=100)
 
 
-async def fine_tune_and_evaluate(ticker, con, start_date, end_date, test_size, skip_downloading):
+async def fine_tune_and_evaluate(ticker, con, start_date, end_date, test_size, skip_downloading, save_data):
     try:
         df_train = pd.DataFrame()
         df_test_dict = {}  # Store test data for each ticker
         all_test_data = []  # Store all test data for overall evaluation
 
-        df = await download_data(ticker, con, start_date, end_date, skip_downloading)
+        df = await download_data(ticker, con, start_date, end_date, skip_downloading, save_data)
         split_size = int(len(df) * (1 - test_size))
         df_train = df.iloc[:split_size]
         df_test = df.iloc[split_size:]
@@ -345,22 +346,24 @@ async def fine_tune_and_evaluate(ticker, con, start_date, end_date, test_size, s
         # Save the evaluation data to a JSON file
             await save_json(ticker, data)
             print(f"Saved results for {ticker}")
-    except:
+    except Exception as e:
+        print(e)
         pass
 
 async def run():
     train_mode = False  # Set this to False for fine-tuning and evaluation
     skip_downloading = False
+    save_data = train_mode
     con = sqlite3.connect('stocks.db')
     cursor = con.cursor()
     cursor.execute("PRAGMA journal_mode = wal")
     
     if train_mode:
         # Warm start training
-        warm_start_symbols = list(set(['APO','UNM','CVS','SAVE','SIRI','EA','TTWO','NTDOY','GRC','ODP','IMAX','YUM','UPS','FI','DE','MDT','INFY','ICE','SNY','HON','BSX','C','ADP','CB','LOW','PFE','RTX','DIS','MS','BHP','BAC','PG','BABA','ACN','TMO','LLY','XOM','JPM','UNH','COST','HD','ASML','BRK-A','BRK-B','CAT','TT','SAP','APH','CVS','NOG','DVN','COP','OXY','MRO','MU','AVGO','INTC','LRCX','PLD','AMT','JNJ','ACN','TSM','V','ORCL','MA','BAC','BA','NFLX','ADBE','IBM','GME','NKE','ANGO','PNW','SHEL','XOM','WMT','BUD','AMZN','PEP','AMD','NVDA','AWR','TM','AAPL','GOOGL','META','MSFT','LMT','TSLA','DOV','PG','KO']))
+        warm_start_symbols = list(set(['CB','LOW','PFE','RTX','DIS','MS','BHP','BAC','PG','BABA','ACN','TMO','LLY','XOM','JPM','UNH','COST','HD','ASML','BRK-A','BRK-B','CAT','TT','SAP','APH','CVS','NOG','DVN','COP','OXY','MRO','MU','AVGO','INTC','LRCX','PLD','AMT','JNJ','ACN','TSM','V','ORCL','MA','BAC','BA','NFLX','ADBE','IBM','GME','NKE','ANGO','PNW','SHEL','XOM','WMT','BUD','AMZN','PEP','AMD','NVDA','AWR','TM','AAPL','GOOGL','META','MSFT','LMT','TSLA','DOV','PG','KO']))
 
         print(f'Warm Start Training: Total Tickers {len(warm_start_symbols)}')
-        await warm_start_training(warm_start_symbols, con, skip_downloading)
+        await warm_start_training(warm_start_symbols, con, skip_downloading, save_data)
     else:
         start_date = datetime(1995, 1, 1).strftime("%Y-%m-%d")
         end_date = datetime.today().strftime("%Y-%m-%d")
@@ -374,7 +377,7 @@ async def run():
         """)
         stock_symbols = [row[0] for row in cursor.fetchall()]
         for ticker in tqdm(stock_symbols):
-            await fine_tune_and_evaluate(ticker, con, start_date, end_date, test_size, skip_downloading)
+            await fine_tune_and_evaluate(ticker, con, start_date, end_date, test_size, skip_downloading, save_data)
     
 
     con.close()

app/cron_options_gex.py

@@ -367,7 +367,7 @@ etf_cursor.execute("PRAGMA journal_mode = wal")
 etf_cursor.execute("SELECT DISTINCT symbol FROM etfs")
 etf_symbols = [row[0] for row in etf_cursor.fetchall()]
 
-total_symbols = ['SPY'] #stock_symbols + etf_symbols
+total_symbols = stock_symbols + etf_symbols
 
 query_template = """
     SELECT date, close,change_percent

app/ml_models/score_model.py

@@ -1,14 +1,8 @@
 import pandas as pd
 from datetime import datetime, timedelta
 import numpy as np
-from xgboost import XGBClassifier
-from sklearn.ensemble import StackingClassifier, RandomForestClassifier
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.naive_bayes import GaussianNB
-from sklearn.svm import SVC
-from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import precision_score, recall_score, f1_score, roc_auc_score, accuracy_score
-from sklearn.preprocessing import MinMaxScaler, StandardScaler
+from sklearn.preprocessing import MinMaxScaler
 from sklearn.decomposition import PCA
 import lightgbm as lgb
 
@@ -24,52 +18,19 @@ import os
 
 class ScorePredictor:
     def __init__(self):
-        self.scaler = StandardScaler()
+        self.scaler = MinMaxScaler()
         self.pca = PCA(n_components=0.95)
 
         # Define base models
-        self.xgb_model = XGBClassifier(
-            n_estimators=100,
-            max_depth=10,
-            learning_rate=0.001,
-            random_state=42,
-            n_jobs=10,
-            tree_method='gpu_hist',
-        )
-        '''
         self.lgb_model = lgb.LGBMClassifier(
-            n_estimators=100,
+            n_estimators=2000,
             learning_rate=0.001,
-            max_depth=10,
+            max_depth=5,
+            num_leaves=2**5-1,
             n_jobs=10
         )
-        '''
-        self.rf_model = RandomForestClassifier(
-            n_estimators=100,
-            max_depth=10,
-            random_state=42,
-            n_jobs=10
-        )
-
-        self.svc_model = SVC(probability=True, kernel='rbf')
-        self.knn_model = KNeighborsClassifier(n_neighbors=5)
-        self.nb_model = GaussianNB()
     
 
-        # Stacking ensemble (XGBoost + LightGBM) with Logistic Regression as meta-learner
-        self.model = StackingClassifier(
-            estimators=[
-                ('xgb', self.xgb_model),
-                #('lgb', self.lgb_model),
-                ('rf', self.rf_model),
-                ('svc', self.svc_model),
-                ('knn', self.knn_model),
-                ('nb', self.nb_model)
-            ],
-            final_estimator=LogisticRegression(),
-            n_jobs=10
-        )
-
         self.warm_start_model_path = 'ml_models/weights/ai-score/stacking_weights.pkl'
 
     def preprocess_train_data(self, X):
@@ -87,8 +48,8 @@ class ScorePredictor:
     def warm_start_training(self, X_train, y_train):
         X_train = self.preprocess_train_data(X_train)
         if os.path.exists(self.warm_start_model_path):
-            with open(self.warm_start_model_path, 'rb') as f:
+            os.remove(self.warm_start_model_path)
-                self.model = pickle.load(f)
+        
         self.model.fit(X_train, y_train)
         pickle.dump(self.model, open(self.warm_start_model_path, 'wb'))
         print("Warm start model saved.")
@@ -121,6 +82,7 @@ class ScorePredictor:
         print(f"ROC AUC: {round(test_roc_auc_score * 100)}%")
 
         last_prediction_prob = class_1_probabilities[-1]
+        print(pd.DataFrame({'y_test': y_test, 'y_pred': binary_predictions}))
         print(f"Last prediction probability: {last_prediction_prob}")
 
         thresholds = [0.8, 0.75, 0.7, 0.6, 0.5, 0.45, 0.4, 0.35, 0.3, 0]

app/utils/feature_engineering.py

@@ -177,33 +177,6 @@ def generate_statistical_features(df, windows=[20,50,200], price_col='close',
         df_features[f'volume_skew_{window}'] = df[volume_col].rolling(window=window).skew()
         df_features[f'volume_kurt_{window}'] = df[volume_col].rolling(window=window).kurt()
         
-        # Price-volume correlations
-        df_features[f'price_volume_corr_{window}'] = (
-            df[price_col].rolling(window=window)
-            .corr(df[volume_col]))
-        
-        # Higher-order moments of returns
-        returns = df[price_col].pct_change()
-        df_features[f'returns_skew_{window}'] = returns.rolling(window=window).skew()
-        df_features[f'returns_kurt_{window}'] = returns.rolling(window=window).kurt()
-        
-    # Cross-sectional statistics
-    df_features['price_acceleration'] = df[price_col].diff().diff()
-    df_features['returns_acceleration'] = df[price_col].pct_change().diff()
-    
-    # Advanced volatility estimators
-    df_features['parkinson_vol'] = np.sqrt(
-        1/(4*np.log(2)) * (np.log(df[high_col]/df[low_col])**2))
-    
-    df_features['garman_klass_vol'] = np.sqrt(
-        0.5 * np.log(df[high_col]/df[low_col])**2 -
-        (2*np.log(2)-1) * np.log(df[price_col]/df['open'])**2
-    )
-    
-    # Dispersion measures
-    df_features['price_range'] = df[high_col] - df[low_col]
-    df_features['price_range_pct'] = df_features['price_range'] / df[price_col]
-    
     # Clean up any NaN values
     df_features = df_features.dropna()