Finalize the AI model

WebServer/AIPython/aipredictor.py

@@ -21,8 +21,10 @@ def Predict():
     # Pull 1 month of current data to make prediction against | for volatility 20
     df = yf.download(Symbol, period="2mo", auto_adjust=True)
     if not df.empty:
-        # Remove the ticker column
+        # Remove the horizontal ticker column
         df.columns = df.columns.get_level_values(0)
+        # Add in the Vertical ticker column
+        df['Ticker'] = Symbol
         # Make the feature set
         df = features.MakeFeatures(df)
 
@@ -61,10 +63,10 @@ def Predict():
 
     # Set the movement indicator
     movement_indicator = 0
-    averagePrediction = np.mean(flat_predictions)
+    averagePrediction = np.mean(flat_predictions) + predictionTrend
-    if (averagePrediction > 0.005): # as in 3% swing up
+    if (averagePrediction > 0.3): # as in 3% swing up
         movement_indicator = 1
-    elif (averagePrediction < -0.005): # as in 3% swing down
+    elif (averagePrediction < -0.3): # as in 3% swing down
         movement_indicator = -1
     else:
         movement_indicator = 0

WebServer/AIPython/datapuller.py

@@ -17,8 +17,10 @@ def pull():
     for i, symbol in enumerate(tickers):
         df = yf.download(symbol, period="max", auto_adjust=True)
         if not df.empty:
-            # Remove the ticker column
+            # Remove the Horizontal ticker column
             df.columns = df.columns.get_level_values(0)
+            # Add in the Vertical ticker column
+            df['Ticker'] = symbol
             # add to master list
             all_data.append(df)
 

WebServer/AIPython/features.py

@@ -5,6 +5,9 @@ def MakeFeatures(df):
     # Convert all F64 to F32 to save ram
     df = df.astype({col: 'float32' for col in df.select_dtypes('float64').columns})
 
+    # Create Grouped columns by ticker
+    grouped = df.groupby('Ticker')
+
     # Candle Wick's
     df['Spread'] = (df['High'] - df['Low']) / df['Close'] # in percentage of price
     candle_top = df[['Open', 'Close']].max(axis=1)
@@ -12,45 +15,45 @@ def MakeFeatures(df):
     df['Upper_Shadow'] = (df['High'] - candle_top) / (df['High'] - df['Low'])
 
      # Is volume 2x higher than the 20-day average?
-    df['Vol_Intensity'] = df['Volume'] / df['Volume'].shift(1).rolling(20).mean()
+    df['Vol_Intensity'] = df['Volume'] / grouped['Volume'].transform(lambda x: x.rolling(20).mean())
     # Volume Change
-    df['Volume_Chg'] = df['Volume'].pct_change()
+    df['Volume_Chg'] = grouped['Volume'].pct_change()
 
     # Moving Average Crossover (Golden/Death Cross logic)
-    df['Moving_Average_5'] = df['Close'].rolling(window=5).mean()
+    df['Moving_Average_5'] = grouped['Close'].transform(lambda x: x.rolling(5).mean())
-    df['Moving_Average_20'] = df['Close'].rolling(window=20).mean()
+    df['Moving_Average_20'] = grouped['Close'].transform(lambda x: x.rolling(20).mean())
     # if short term > long term (bullish), else 0
-    df['Trend_Signal'] = (df['Moving_Average_5'] > df['Moving_Average_20']).astype(int)
+    df['Trend_Signal'] = (df['Moving_Average_5'] > df['Moving_Average_20']).astype(np.float32)
     # Distance from MA (How overextended are we?)
     df['Dist_From_MA20'] = (df['Close'] / df['Moving_Average_20']) - 1
 
     # Bollinger Band Position (Where are we relative to volatility?)
-    std_20 = df['Close'].rolling(20).std()
+    std_20 = grouped['Close'].transform(lambda x: x.rolling(20).std())
     upper_band = df['Moving_Average_20'] + (std_20 * 2)
     lower_band = df['Moving_Average_20'] - (std_20 * 2)
-    df['BB_Pos'] = (df['Close'] - lower_band) / (upper_band - lower_band)
+    df['BB_Pos'] = (df['Close'] - lower_band) / (upper_band - lower_band).replace(0, 1e-6)
 
     # Add feature for Returns
-    df['Return'] = df['Close'].pct_change()
+    df['Return'] = grouped['Close'].pct_change()
     # Log Returns (Better for AI than pct_change for statistical normality)
-    df['Log_Return'] = np.log(df['Close'] / df['Close'].shift(1))
+    df['Log_Return'] = np.log(df['Close'] / grouped['Close'].shift(1))
 
     # Add feature for volitility last 5
-    df['Volatility_5'] = df['Return'].transform(lambda x: x.shift(1).rolling(5).std())
+    df['Volatility_5'] = grouped['Return'].transform(lambda x: x.rolling(5).std())
     # Add feature for volitility last 20
-    df['Volatility_20'] = df['Return'].transform(lambda x: x.shift(1).rolling(20).std())
+    df['Volatility_20'] = grouped['Return'].transform(lambda x: x.rolling(20).std())
 
     # RSI (Relative Strength Index)
-    delta = df['Close'].diff()
+    delta = grouped['Close'].diff()
-    gain = (delta.where(delta > 0, 0)).shift(1).rolling(window=14).mean()
+    gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()
-    loss = (-delta.where(delta < 0, 0)).shift(1).rolling(window=14).mean()
+    loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()
     rs = gain / loss
     df['RSI'] = 100 - (100 / (1 + rs))
 
     # Return lagged
     for lag in range(1, 4):
-        df[f'Return_Lag_{lag}'] = df['Return'].shift(lag)
+        df[f'Return_Lag_{lag}'] = grouped['Return'].shift(lag)
-        df[f'Vol_Lag_{lag}'] = df['Volume_Chg'].shift(lag)
+        df[f'Vol_Lag_{lag}'] = grouped['Volume_Chg'].shift(lag)
 
     # This is our training metric of price difference 5 days ahead
     df['Target_Close'] = (np.log(df['Close'].shift(-5) / df['Close']) / df['Volatility_5']).clip(-10, 10)
@@ -59,8 +62,17 @@ def MakeFeatures(df):
     with open("Target_Close_Average.txt", "w") as file:
         file.write(str(df["Target_Close"].mean()))
 
+    # Make a feature for the S&P500 average for the day
+    df['SP500_Market_Log_Return'] = df.groupby('Date')['Log_Return'].transform('mean')
+    # Relative Strength agains the S&P500
+    df['SP500_Relative_Performance'] = df['Log_Return'] - df['SP500_Market_Log_Return']
+    # S&P500 market trend
+    daily_trend = df.groupby('Date')['SP500_Market_Log_Return'].first().rolling(window=20).mean()
+    daily_trend.name = 'SP500_Market_Trend_20'
+    df = df.merge(daily_trend, on='Date', how='left')
+
     # Drop every column that is a raw price or an unscaled average
-    cols_to_drop = ['Open', 'High', 'Low', 'Volume', 'Close', 'Moving_Average_5', 'Moving_Average_20']
+    cols_to_drop = ['Open', 'High', 'Low', 'Volume', 'Close', 'Moving_Average_5', 'Moving_Average_20', 'Ticker']
     for col in cols_to_drop:
         if col in df.columns:
             df.drop(col, axis=1, inplace=True)