regression_sentdex_part1.py

# # make sure you have installed sklearn , pandas and quandl . 
# # quandl is like a finance api thing . 

# import pandas as pd 
# import quandl 
# import math
# import numpy as np 
# from sklearn import preprocessing, cross_validation, svm
# from sklearn.linear_model import LinearRegression
# from numpy._distributor_init import NUMPY_MKL
# import matplotlib.pyplot as plt
# from matplotlib import style
# import datetime
# import time



# quandl.ApiConfig.api_key='6x-3xWJzAfcwXPpXWZs2'
# df = quandl.get('WIKI/GOOGL')
# # here , you get stuff like open , high , low etc . These are your features . 
# # a feature is basically a column , in terms of excel . 

# # we don't need all of these , so let's tone them down . 

# df = df[['Adj. Open',  'Adj. High',  'Adj. Low',  'Adj. Close', 'Adj. Volume',]]
# df['HL_PCT'] = ((df['Adj. High'] - df['Adj. Close']) / df['Adj. Close'])*100
# df['PCT_change'] = ((df['Adj. Close'] - df['Adj. Open']) / df['Adj. Open'])*100 
 
# # change the df to reflect the columns we need 
# df = df[['Adj. Close', 'Adj. Volume', 'HL_PCT', 'PCT_change']]

# # an input you give is a feature , the variable u r trying to predict is ur label 

# """
# an example I got from stackoverflow is this : if you are trying to predict what kind of pet 
# a person would buy , the features will be salary , gender , age etc 
# the label will be animal ( dog , cat , fish  etc )
# """
# # let's do this for what we have 

# """
# When inplace=True is passed, the data is renamed in place (it returns nothing)
# When inlace=False is passed (this is the default value, so isn't necessary), performs the operation and returns a copy of the object

# """
# 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)
# # not entirely sure what df.dropna does here , but eh . 
# df.dropna(inplace=True)

# # usually , X ( capital X ) is our features , y ( small y ) is our labels 
# # put all inputs & outputs in two np arrays 
# X = np.array(df.drop(['label'], 1))

# y = np.array(df['label'])

# # split into training and testing 

# X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)
# X_lately = X[-forecast_out:]

# # try for linear regression 
# clf = LinearRegression()
# clf.fit(X_train,y_train)
# accuracy = clf.score(X_test,y_test)
# print(accuracy)



# # try for regression in svm 
# clf = svm.SVR()
# clf.fit(X_train,y_train)
# accuracy = clf.score(X_test,y_test)
# print(accuracy)





# # for k in ['linear','poly','rbf','sigmoid']:
# #     clf = svm.SVR(kernel=k)
# #     clf.fit(X_train, y_train)
# #     confidence = clf.score(X_test, y_test)
# #     print(k,confidence)





# forecast_set = clf.predict(X_lately)
# df['Forecast'] = np.nan

# last_date = df.iloc[-1].name
# last_unix = time.mktime(last_date.timetuple())
# one_day = 86400
# next_unix = last_unix + one_day

# for i in forecast_set:
#     next_date = datetime.datetime.fromtimestamp(next_unix)
#     next_unix += 86400
#     df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+[i]

# df['Adj. Close'].plot()
# df['Forecast'].plot()
# plt.legend(loc=4)
# plt.xlabel('Date')
# plt.ylabel('Price')
# plt.show()

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 matplotlib.pyplot as plt
from matplotlib import style
import datetime
import time 
quandl.ApiConfig.api_key='6x-3xWJzAfcwXPpXWZs2'
style.use('ggplot')

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)

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'])

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)

forecast_set = clf.predict(X_lately)
df['Forecast'] = np.nan

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

for i in forecast_set:
    next_date = datetime.datetime.fromtimestamp(next_unix)
    next_unix += 86400
    df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+[i]

df['Adj. Close'].plot()
df['Forecast'].plot()
plt.legend(loc=4)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()