42 lines
1.1 KiB
Python
42 lines
1.1 KiB
Python
import pandas as pd
|
|
|
|
def MakeFeatures(df, i):
|
|
# Remove the ticker column
|
|
df.columns = df.columns.get_level_values(0)
|
|
|
|
# Make sure Date is a number object
|
|
df = df.reset_index()
|
|
df['Date'] = pd.to_numeric(pd.to_datetime(df['Date']))
|
|
|
|
# Add the Symbol column for tracking | as an int 1 hot encoded
|
|
df['Symbol'] = i
|
|
|
|
# Add feature Spread
|
|
df['Spread'] = abs( df['High'] - df['Low'] )
|
|
|
|
# Add feature for Returns
|
|
df['Return'] = df['Close'].pct_change()
|
|
|
|
# Add feature for volitility last 5
|
|
df['Volatility_5'] = df['Return'].transform(lambda x: x.rolling(5).std())
|
|
|
|
# Add feature for volitility last 20
|
|
df['Volatility_20'] = df['Return'].transform(lambda x: x.rolling(20).std())
|
|
|
|
# This is our training metric
|
|
df['Target_Close_Tomorrow'] = df['Close'].shift(-1).pct_change()
|
|
|
|
# Return new df with new features
|
|
return df
|
|
|
|
|
|
def CleanDF(df):
|
|
# Make date the index so it doesnt influence the training
|
|
df.set_index('Date', inplace=True)
|
|
|
|
# Drop rows with null values
|
|
df.dropna(inplace=True)
|
|
|
|
# Return new df thats cleaned
|
|
return df
|