Pickle vs. Joblib, some ML with update features, DF, predict GOOGL from Quandl

python_ML_intro_regression.py

import quandl, pickle, math, datetime
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn import preprocessing, cross_validation
from sklearn.externals import joblib
import matplotlib.pyplot as plt
from matplotlib import style
one_day = 86400
one_week = one_day*7
# READ DATA
try:
	df = pickle.load(open('df.pkl', 'rb'))
	if datetime.datetime.now().timestamp()-df.iloc[-1].name.timestamp()>one_week:
		raise
except:
	print('Getting new data from Quandl...')
	df = quandl.get('WIKI/GOOGL', api_key='GxHxjaX1EiVzszDc1CQt')
	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']]
	df.fillna(value=-99999, inplace=True)
	pickle.dump(df, open('df.pkl', 'wb'))
# BACKUP DF
df_orig = pd.DataFrame()
df_orig = df_orig.append(df)
# SETTING
forecast_col = 'Adj. Close'
forecast_out = math.ceil(0.01*len(df))
X = np.array(df)
X = preprocessing.scale(X)
X_predict = X[-forecast_out:]
X = X[:-forecast_out]
df['label'] = df[forecast_col].shift(-forecast_out)
df.dropna(inplace=True)
Y = np.array(df['label'])
# DO_IT
X_train, X_test, Y_train, Y_test = cross_validation.train_test_split(X, Y, test_size=0.2)
confidence = 0
try:
	clf = joblib.load('clf.pkl')
	confidence = clf.score(X_test, Y_test)
	if confidence < 0.9:
		raise
except:
	print('Re-fitting the line...')
	clf = LinearRegression()
	clf.fit(X_train, Y_train)
	joblib.dump(clf, 'clf.pkl')
confidence = clf.score(X_test, Y_test) if confidence==0 else confidence
forecast_set = clf.predict(X_predict)
# Prepare for VISUAL
df = df_orig
df['Forecast'] = np.nan
last_date = df.iloc[-1]
last_date['Forecast'] = last_date['Adj. Close']
df.iloc[-1] = last_date
next_unix = df.iloc[-1].name.timestamp() + one_day
for i in forecast_set:
	next_date = datetime.datetime.fromtimestamp(next_unix)
	df.loc[next_date] = [np.nan]*(len(df.columns)-1)+[i]
	next_unix += one_day
# PLOT_IT
style.use('ggplot')
df['Adj. Close'].plot()
df['Forecast'].plot()
plt.legend(loc=4) # Locate legend in IV part
plt.xlabel('Time')
plt.ylabel('Price')
plt.show()