stock.py

#Stock Prediction using machine learning


# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
from matplotlib import style
import datetime as dt1
from datetime import datetime as dt
# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory
import subprocess
#print(check_output(["ls", "../input"]).decode("utf8"))

df=pd.read_csv('prices.csv')
df.tail()
df=df.loc[df['symbol'] == 'BBY']
print(df.tail())

from sklearn import preprocessing, cross_validation, svm
from sklearn.linear_model import LinearRegression
import math

forecast_col = 'close'
df.fillna(value=-99999, inplace=True)
forecast_out = int(math.ceil(0.01 * len(df)))
print(forecast_out)
df['label'] = df[forecast_col].shift(-forecast_out)
print(df.head())

#X = np.array(df.drop(['label'], 1)
X=np.array(df.drop(['label','symbol','date'], axis=1))
#print(X)
X = preprocessing.scale(X)
#print(X)
X_lately = X[-forecast_out:]
#print(X_lately)
X = X[:-forecast_out]
df.dropna(inplace=True)
y = np.array(df['label'])
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.fit(X_train, y_train)
confidence = clf.score(X_test, y_test)
print(confidence)

forecast_set = clf.predict(X_lately)
print(forecast_set)
df['Forecast'] = np.nan
last_date = df.iloc[-1].date
print(last_date)
last_date=dt.strptime(last_date, '%Y-%m-%d').timestamp()
last_unix = last_date
one_day = 86400
next_unix = last_unix + one_day
for i in forecast_set:
    next_date = dt.fromtimestamp(next_unix)
    next_unix += 86400
    df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+[i]
print(df.tail())
df['close'].plot()
df['Forecast'].plot()
#plt.legend(loc=4)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()