model1_ml.py

"""
Important notes about model

Training Machine-Learning model is trained every Monday (I found that if I train my model every-day it shows less returns)

Trading is happening after each 10 minutes 

Machine_learning Model: 

I am using two independent Features: '5 minutes price change' and '15 minutes price change' 
Dependent Feature: '10 minutes returns' (if -ve buy the stock, if +ve or 0 sell the stock)

Machine_learning Algorithm: Random-Forest(Ensemble-Learning)

Returns: around 110%
Sharp Ratio: 0.91
"""
from sklearn.ensemble import RandomForestClassifier
from sklearn import tree
from sklearn import preprocessing
import numpy as np
import pandas as pd

def initialize(context):
    context.assets = sid(8554) 
    context.model = RandomForestClassifier()
    schedule_function(create_model, date_rules.week_start(),time_rules.market_open(minutes=1)) 
    total_minutes = 6*60 + 30
    for i in range(1, total_minutes):
    # Every 10 minutes run schedule
        if i % 10 == 0:
            schedule_function(trade,
                              date_rules.every_day(),
                              time_rules.market_open(minutes=i),True)
def create_model(context, data):
    hello_price = data.history(context.assets, "price", 10000, "1m") 
    my_df =  pd.DataFrame(index=hello_price.index)
    my_df['price'] = hello_price.values
    my_df['15mins_return'] = my_df['price'].pct_change(15)
    my_df['15_mins_return_filled'] = my_df['15mins_return'].fillna(my_df['15mins_return'].mean())         
    my_df['5mins_return'] = my_df['price'].pct_change(5)
    my_df['5_mins_return_filled'] = my_df['5mins_return'].fillna(my_df['5mins_return'].mean())         
    my_df['returns_per_10_minutes'] = my_df['price'].pct_change(10)
    my_df['10minutes_direction'] = np.sign(my_df['returns_per_10_minutes'][10:])   
    X = my_df[['5_mins_return_filled','15_mins_return_filled']] 
    X_scaled = preprocessing.scale(X)
    Y = my_df['10minutes_direction'] 
    context.model.fit(X_scaled, Y)
def trade(context, data):
    if context.model: 
        hello_hello = data.history(context.assets, "price",30, "1m") 
        my_df =  pd.DataFrame(index=hello_hello.index)
        my_df['price'] = hello_hello.values
        my_df['15mins_return'] = my_df['price'].pct_change(15)
        my_df['5mins_return'] = my_df['price'].pct_change(5)
        X = [(my_df['15mins_return'][15:]).mean(),my_df['5mins_return'][5:].mean()]
        X_scaled = preprocessing.scale(X)       
        prediction = context.model.predict(X_scaled)    
        if prediction < 0:
            order_target_percent(context.assets, 1.0)
        elif prediction > 0 and prediction==0:
            order_target_percent(context.assets, -1.0)
        else:
            pass        
def handle_data(context, data):
    pass