linearregression.py

import quandl, math
import numpy as np
import pandas as pd
from sklearn import preprocessing, cross_validation, svm
from sklearn.linear_model import LinearRegression
import pickle
df = quandl.get("WIKI/GOOGL")
df = df[['Adj. Open',  'Adj. High',  'Adj. Low',  'Adj. Close', 'Adj. Volume']]
df['HL_PCT'] = (df['Adj. High'] - df['Adj. Low']) / df['Adj. Close'] * 100.0
df['PCT_change'] = (df['Adj. Close'] - df['Adj. Open']) / df['Adj. Open'] * 100.0
df = df[['Adj. Close', 'HL_PCT', 'PCT_change', 'Adj. Volume']]
forecast_col = 'Adj. Close'
df.fillna(value=-99999, inplace=True)
forecast_out = int(math.ceil(0.01 * len(df)))
df['label'] = df[forecast_col].shift(-forecast_out)
df.dropna(inplace=True)
X = np.array(df.drop(['label'],1))
y = np.array(df['label'])
X = preprocessing.scale(X)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)
clf = LinearRegression(n_jobs = -1)
# clf = svm.SVR()
clf.fit(X_train,y_train)
with open('linearregression.pickle','wb') as f:
	pickle.dump(clf, f)
pickle_in = open('linearregression.pickle','rb')
clf = pickle.load(pickle_in)
confidence = clf.score(X_test,y_test)
print(confidence)