import quandl
import pandas as pd
import numpy as np
import pandas_datareader as pdr 
#from datetime import datetime
import datetime
from __future__ import division
import math
from sklearn import preprocessing, cross_validation, svm
from sklearn.linear_model import LinearRegression
import pickle

import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')
%matplotlib inline

#Set times, -1 = yearg ago from now
end = datetime.now()
print (end)

start = datetime(end.year -1, end.month, end.day)
print (start)

#Import data from yahoo and assign it to IRBT
IRBT = pdr.DataReader('IRBT', 'yahoo', start, end)

IRBT.info()

#View historical trend of the closing price Adj Close column
IRBT['Adj Close'].plot(legend=True, figsize=(10,4))

IRBT.head()

IRBT.tail()

df = IRBT[['Open','High','Low','Close', 'Volume']]

df['HL_PCT'] = (df['High']-df['Close'])/ df['Close'] * 100.0

df['PCT_Change'] = (df['Close']-df['Open'])/ df['Open'] * 100.0

df = df [['Close','HL_PCT','PCT_Change','Volume']]

df.tail()

#Define a label -- Adj Price in the future
forecast_col = 'Close' 
df.fillna(-99999, inplace=True)
forecast_out = int(math.ceil(0.01*len(df)))

df['Label'] = df[forecast_col].shift(-forecast_out)
df.dropna(inplace=True)

df.head()

df[['Close','Label']].plot(subplots=False,legend=True, figsize=(10,4))

#Define features X and labels y

X = np.array(df.drop(['Label'],1))

y = np.array(df['Label'])

#Scale X
X = preprocessing.scale(X)
y = np.array(df['Label'])
print(len(X),len(y))

#Create training and testing sets
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)

#Define a classifier and test it .fit=train / .score=test
classf = LinearRegression()
classf.fit(X_train, y_train)
accuracy = classf.score(X_test, y_test)

print(forecast_out)
print(accuracy)

#Using the Support Vector Machine algo

classf = svm.SVR()
classf.fit(X_train, y_train)
accuracy = classf.score(X_test, y_test)

print(forecast_out)
print(accuracy)

#Forecasting into the future...
df['Label'] = df[forecast_col].shift(-forecast_out)
X = np.array(df.drop(['Label'],1))
X = preprocessing.scale(X)
X_lately = X[-forecast_out:]
X = X[:-forecast_out]

df.dropna(inplace=True)
y = np.array(df['Label'])


#Create training and testing sets
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)

#Define a classifier and test it .fit=train / .score=test
classf = LinearRegression()
classf.fit(X_train, y_train)
accuracy = classf.score(X_test, y_test)

print(forecast_out)
print(accuracy)

forecast_set = classf.predict(X_lately)
print (forecast_set, accuracy, forecast_out)

df['Forecast']= np.nan

last_date = df.iloc[-1].name
last_unix = last_date.timestamp()
one_day = 86400
next_unix = last_unix + one_day

for i in forecast_set:
    next_date = datetime.datetime.fromtimestamp(next_unix)
    next_unix += one_day
    df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+ [i]
   

df['Close'].plot()
df['Forecast'].plot()
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()

df[['Close','Forecast']].plot(subplots=False,legend=True, figsize=(10,4))

df