统计模型应用--基本预测手法

分类器：

import sklearn
from sklearn.ensemble import RandomFoerestClassifier
from sklearn.linear.linear_model import LogisticRegression
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
from sklearn.metrics import confusion_matrix
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis as QDA
from sklearn.svm import LinearSVC, SVC

def create_lagged_series(symbol, start_date, end_date, lags=5):
    ts = web.DataReader(
    symbol, "quandl",
    start_date-datetime.timedelta(days=365),
    end_date
    ).sort_index()
    tslag = pd.DataFrame(index=ts.index)
    tslag["Today"] = ts["AdjClose"]
    tslag['Volume'] = ts['Volume']
    for i in range(0, lags):
       tslag["lag%s"% str(i+1)] = ts['AdjClose'].shift(i+1)
       tsret = pd.DataFrame(index=tslag.index)
       tsret["Volume"] = tslag["Vloume"]
       tsret["Today"] = talag["Today"].pct_change()*100.0
    for i,x in enumerate(tsret['Today']):
       if (abs(x) < 0.0001):
          tsret['Today'][i] = 0.0001
    for i in range(0,lags):
       tsret['lag%s'% str(i+1)] = 
       tsret['lag%s'% str(i+1)].pct_change()*100.0
    tsret["Direction"] = np.sign(tsret['Today'])
    tsret = tsret[tsret.index >= start_date]
    return tsret
if __name__ == '__main__':
   snpret = create_lagged_series(
   "AAPL.US", datetime.datetime(2001,1,10),
   datetime.datetime(2005,12,31), lags=5
   )
   x= snpret[['Lag1', 'Lag2']]
   y = snpret["Direction"]
   start_test = datetime.datetime(2005,1,1)
   X_train = X[X.index < start_test]
   X_test = X[X.index >= start_test]
   Y_train = Y[Y.index < start_test]
   Y_test = Y[Y.index >= start_test]
   print("Hit Rates/Confusion Matrices:
")
   models = [
   ('LR', LogisticRegression()),
   ('LDA',LDA()),
   ('QDA',QDA()),
   ("LSVC",LinearSVC()),
   ("RSVM",SVC(
    C=1000000.0, cache_size=200, class_weight=None,
    coef0=0.0, degree=3, gamma=0.0001, kernel='rbf',
    max_iter=-1, probability=False,random_state=None,
    shrinkinf=True, tol=0.001,verbose=False
    )),
    ('RF', RandomForestClassifier(
    n_estimators=1000,criterion='gini',
    max_depth=None, min_samples_split=2,
    min_samples_leaf=1, max_features='auto',
    bootstrap=True, oob_score=False, n_jobs=1,
    random_state=None, verbose=0)
    )]
    for m in models:
       m[1].fit(X_train, Y_train)
       pred = m[1].predict(X_test)
       print("%s:
%0.3f" % (m[0],m[1].score(X_test,Y_test)))
       print("%s
" % confusion_matrix(pred, Y_test))