Test a linar regression

A small test to get jupyter to know. It loads data from quandl, calculates the percent daily change.

This is then used to train a liniear regression model which are used to plot a prediction

In [30]:
import numpy as np
import matplotlib.pyplot as plt

%matplotlib inline

Use quandl to load the actual stock data

In [52]:
import quandl
df = quandl.get("WIKI/GOOGL")

df = df[['Adj. Open',  'Adj. High',  'Adj. Low',  'Adj. Close', 'Adj. Volume']]
In [53]:
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']]
print(df.head())
            Adj. Close    HL_PCT  PCT_change  Adj. Volume
Date                                                     
2004-08-19   50.322842  8.072956    0.324968   44659000.0
2004-08-20   54.322689  7.921706    7.227007   22834300.0
2004-08-23   54.869377  4.049360   -1.227880   18256100.0
2004-08-24   52.597363  7.657099   -5.726357   15247300.0
2004-08-25   53.164113  3.886792    1.183658    9188600.0

The percentage change in price over time

In [33]:
plt.plot(df)
plt.show()
In [34]:
import numpy as np
import math
import pandas as pd
from sklearn import preprocessing, svm
from sklearn.linear_model import LinearRegression
In [35]:
forecast_col = 'Adj. Close'
df.fillna(value=-99999, inplace=True)
forecast_out = int(math.ceil(0.01 * len(df)))
In [36]:
df['label'] = df[forecast_col].shift(-forecast_out)
df.dropna(inplace=True)
In [47]:
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'])
In [38]:
X = preprocessing.scale(X)
y = np.array(df['label'])
In [39]:
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)
In [44]:
clf = LinearRegression(n_jobs=-1)
clf.fit(X_train, y_train)
Out[44]:
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=-1, normalize=False)
In [45]:
confidence = clf.score(X_test, y_test)
print(confidence)
0.976888544493
In [49]:
import datetime

forecast_set = clf.predict(X_lately)
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 += 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()