advanced-algorithmic-trading

293
Figure 20.5: Test MSE curves for multiple k-fold cross-validation folds for a Linear Regression
with polynomial features of increasing degree
import datetime
import pprint
import numpy as np
import pandas as pd
import pandas_datareader.data as web
import pylab as plt
import sklearn
from sklearn.cross_validation import train_test_split, KFold
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
def create_lagged_series(symbol, start_date, end_date, lags=5):
"""
This creates a pandas DataFrame that stores
the percentage returns of the adjusted closing
value of a stock obtained from Yahoo Finance,
along with a number of lagged returns from the
prior trading days (lags defaults to 5 days).