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 pickle
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)))
print("当前天数 =")
print(forecast_out)
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=0.4)
#COMMENTED OUT:
#clf = svm.SVR(kernel='linear')
#clf.fit(X_train, y_train)
#with open('linearregresssion.pickle','wb')as f:
#pickle.dump(clf,f)
pickle_in = open('linearregresssion.pickle','rb')
clf = pickle.load(pickle_in)
confidence = clf.score(X_test, y_test)
print(confidence)
forecast_set = clf.predict(X_lately)
print(df.tail())
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()
Its the first machine learning project i've done on python
We use a dataset of Google Stock from 2012 - 2016 ,aim to predict the Google stock price of next (0.01* len (df)) days
several Questions you may ask
1.The preprocessing of data is mainly about to add a column of the price of the day after (0.01* len (df)) prepare to the current day ,like :
price(current) adv ............. price(the day after (0.01* len (df)))
27.5 8 37.5
27.9 6 38.7
The Column of { price(the day after (0.01* len (df))) } is what we add
2.basicly we use the sklearn linerfit function. you learned it in your high school.
3The interesting point is we got a 97.6% acurracy