109 lines
4.5 KiB
Python
109 lines
4.5 KiB
Python
from sklearn.preprocessing import MinMaxScaler
|
|
import numpy as np
|
|
|
|
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)
|
|
df['Body_Size'] = (df['Close'] - df['Open']).abs() / (df['High'] - df['Low'])
|
|
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'] / grouped['Volume'].transform(lambda x: x.rolling(20).mean())
|
|
# Volume Change
|
|
df['Volume_Chg'] = grouped['Volume'].pct_change()
|
|
|
|
# Moving Average Crossover (Golden/Death Cross logic)
|
|
df['Moving_Average_5'] = grouped['Close'].transform(lambda x: x.rolling(5).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(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 = 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).replace(0, 1e-6)
|
|
|
|
# Add feature for Returns
|
|
df['Return'] = grouped['Close'].pct_change()
|
|
# Log Returns (Better for AI than pct_change for statistical normality)
|
|
df['Log_Return'] = np.log(df['Close'] / grouped['Close'].shift(1))
|
|
|
|
# Add feature for volitility last 5
|
|
df['Volatility_5'] = grouped['Return'].transform(lambda x: x.rolling(5).std())
|
|
# Add feature for volitility last 20
|
|
df['Volatility_20'] = grouped['Return'].transform(lambda x: x.rolling(20).std())
|
|
|
|
# RSI (Relative Strength Index)
|
|
delta = grouped['Close'].diff()
|
|
gain = (delta.where(delta > 0, 0)).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}'] = grouped['Return'].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)
|
|
|
|
# Save the overall trend to predict based off of later
|
|
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', 'Ticker']
|
|
for col in cols_to_drop:
|
|
if col in df.columns:
|
|
df.drop(col, axis=1, inplace=True)
|
|
|
|
# Drop rows with null values
|
|
df.dropna(inplace=True)
|
|
|
|
# Replace Infinity with 0 -> This fixes the AI mental breakdown
|
|
df = df.replace([np.inf, -np.inf], 0)
|
|
|
|
# Replace Infinity with 0 -> This fixes the AI mental breakdown
|
|
df['Volume_Chg'] = df['Volume_Chg'].replace([np.inf, -np.inf], 0)
|
|
|
|
# Return new df with new features
|
|
return df
|
|
|
|
def Prepare(df):
|
|
|
|
df = df.replace([np.inf, -np.inf], 0)
|
|
|
|
# Remove indicators and set the target
|
|
X = df.drop('Target_Close', axis=1)
|
|
Y = df['Target_Close']
|
|
|
|
# Scale the features to the same size
|
|
feature_scaler = MinMaxScaler()
|
|
X_scaled = feature_scaler.fit_transform(X)
|
|
|
|
# Safe for the Y
|
|
target_scaler = MinMaxScaler()
|
|
y_scaled = target_scaler.fit_transform(Y.values.reshape(-1, 1))
|
|
|
|
return X_scaled, y_scaled, feature_scaler, target_scaler
|