Algo_w_PriceFall.py

#!/usr/bin/bash
import numpy as np
import pandas as pd
from tensorflow import keras


dataset = pd.read_csv('/Users/King/SPY_NN1.csv')
dataset = dataset.dropna()
dataset = dataset[['ref_Num', 'Close_Price', 'Tick', 'Liq_Tick', 'new_Strength', 'Diff', 'Liq_change_div_Avg', 'MIV_Index', 'Type', 'LiqDividedByREGLiq', 'LFP', 'LFPC']]

dataset['ref_Num'] = dataset['ref_Num']
dataset['Close_Price'] = dataset['Close_Price']
dataset['Tick'] = dataset['Tick']
dataset['Liq_Tick'] = dataset['Liq_Tick']
dataset['new_Strength'] = dataset['new_Strength']
dataset['Diff'] = dataset['Diff']
dataset['Liq_change_div_Avg'] = dataset['Liq_change_div_Avg']
dataset['MIV_Index'] = dataset['MIV_Index']
dataset['Type'] = dataset['Type']
dataset['LiqDividedByREGLiq'] = dataset['LiqDividedByREGLiq']
dataset['LFP'] = dataset['LFP']
dataset['LFPC'] = dataset['LFPC']

dataset['Price_Rise'] = np.where(dataset['Close_Price'].shift(-240) > dataset['Close_Price'], 1, 0)
dataset['Price_Fall'] = np.where(dataset['Close_Price'].shift(-240) < dataset['Close_Price'], 1, 0)

dataset = dataset.dropna()
X = dataset.iloc[:, 4:-1]
y = dataset.iloc[:, -1]

split = int(len(dataset)*0.5)
X_train, X_test, y_train, y_test = X[:split], X[split:], y[:split], y[split:]

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Dropout
classifier = Sequential()

classifier.add(Dense(units = 128, kernel_initializer = 'uniform', activation = 'relu', input_dim = X.shape[1]))
classifier.add(Dense(units = 128, kernel_initializer = 'uniform', activation = 'relu'))
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
classifier.compile(optimizer = 'adam', loss = 'mean_squared_error', metrics = ['accuracy'])
classifier.fit(X_train, y_train, batch_size = 10, epochs = 100)
y_pred = classifier.predict(X_test)
y_pred = (y_pred > 0.5)
dataset['y_pred'] = np.NaN
dataset.iloc[(len(dataset) - len(y_pred)):,-1:] = y_pred
trade_dataset = dataset.dropna()

trade_dataset['4 Hour Return'] = 0.
trade_dataset['4 Hour Return'] = np.log(trade_dataset['Close_Price']/trade_dataset['Close_Price'].shift(1))
trade_dataset['4 Hour Return'] = trade_dataset['4 Hour Return'].shift(-240)
trade_dataset['Strategy Returns'] = 0.
trade_dataset['Strategy Returns'] = np.where(trade_dataset['y_pred'] == True, trade_dataset['4 Hour Return'], - trade_dataset['4 Hour Return'])
trade_dataset['Cumulative Market Returns'] = np.cumsum(trade_dataset['4 Hour Return'])
trade_dataset['Cumulative Strategy Returns'] = np.cumsum(trade_dataset['Strategy Returns'])
import matplotlib.pyplot as plt
plt.figure(figsize=(10,5))
plt.plot(trade_dataset['Cumulative Market Returns'], color='r', label='Market Returns')
plt.plot(trade_dataset['Cumulative Strategy Returns'], color='g', label='Strategy Returns')
plt.legend()
plt.show()