wzchen / stock_market_prediction Goto Github PK

import pandas as pd
import numpy as np
from Score import auc
from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier,VotingClassifier
from sklearn.metrics import accuracy_score,classification_report
def MakeDataframe(csv,reverse):
    df = pd.read_csv(csv)
    if reverse:
        df = df[::-1]
    df = df[['open','close']]
    #print df.head(12)
    return df.values

def Window(dataset):
    dataX,dataY = [],[]
    for i in range(len(dataset) - 9):
        item = dataset[i:(i+10),0:2]
        item = item.ravel()
        if item[19] >= item[18]:
            target = 1
        else:
            target = 0
        dataY.append(target)
        item = item[:19]
        item = item / item[0]
        dataX.append(item)

    return np.array(dataX), np.array(dataY)

reverse = True
train = MakeDataframe('./CSV/EURUSD-2016-10-1W_1M.csv',reverse)
test = MakeDataframe('./CSV/EURUSD-2016-10-2W_1M.csv',reverse)

X,Y = Window(train)
X_test,Y_test = Window(test)

Y = Y.astype('int')
Y_test = Y_test.astype('int')
model = RandomForestClassifier(n_jobs=-1,n_estimators=100,oob_score=True,verbose=False)
#model2 = AdaBoostClassifier()

#model = VotingClassifier([('RF',model1),('Ada',model2)],n_jobs=-1,voting='soft')
model.fit(X,Y)

Y_pred = model.predict_proba(X_test)[:,1]
predicted = model.predict(X_test)
score = accuracy_score(Y_test,predicted)
report = classification_report(Y_test,predicted)
print score
print auc(Y_test,Y_pred)
print report
print model.oob_score_