Building and implementing a Random Forest Algorithm

Now we’ll be implementing a simple Random Forest algorithm into code using Python 3.

Let’s get started!

Importing the necessary packages and dependencies:

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
%matplotlib inline

from zipline.data.data_portal import DataPortal
from zipline.data import bundles
from zipline.utils.calendars import get_calendar

Getting the data

Now we have to import the data, we’ll import it from Quandl. We’ll specify the dates from start and finish as follows:

end date: 2019-01-01

start date: The first trading day available in Quandl. (If we run this line, it will output a Timestamp: “Timestamp(‘1990-01-02 00:00:00+0000′, tz=’UTC’)“

bundle_data = bundles.load("quandl")

end_date = pd.Timestamp("2019-01-01", tz="utc")

bundle_data.equity_daily_bar_reader.first_trading_day


				

Then we initiate the DataPortal object:

data_por = DataPortal(
    asset_finder=bundle_data.asset_finder, 
    trading_calendar=get_calendar("NYSE"),
    first_trading_day=bundle_data.equity_daily_bar_reader.first_trading_day,
    equity_daily_reader=bundle_data.equity_daily_bar_reader
)

				

We’ll be using the NETFLIX stock data:

NFLX = data_por.asset_finder.lookup_symbol(
    "NFLX",
    as_of_date = None
)

df = data_por.get_history_window(
    assets = [NFLX],
    end_dt = end_date,
    bar_count = 5000,
    frequency = '1d',
    data_frequency = 'daily',
    field = "close"
)