mainPEP.py 文件源码

def parametered_single(x_train,y_train,x_test,y_test,thresh_opt):
    print("samples: %d %d %d %d" % (x_train.shape[0],x_train.shape[1],x_test.shape[0],x_test.shape[1]))

    metrics = np.zeros((1,5),dtype="float32")
    thresh = 0.5

    # estimate the threshold
    if thresh_opt==1:
        thresh = threshold_estimate(x_train,y_train)

    clf = xgb.XGBClassifier(max_depth=10, learning_rate=0.1, n_estimators=500, nthread=50)
    weight = float(sum(y_train<1))/float(sum(y_train==1))
    w1 = np.array([1]*y_train.shape[0])
    w1[y_train==1]=weight
    clf.fit(x_train, y_train, sample_weight=w1)

    prob = clf.predict_proba(x_test)
    yfit = (prob[:,1]>thresh)

    precision, recall, f1, mcc = score_function(y_test,yfit)
    metrics = np.array((thresh,precision,recall,f1,mcc))
    print metrics

    importances = clf.feature_importances_
    indices1 = np.argsort(importances)[::-1]
    features1 = np.transpose(np.array((indices1,importances[indices1])))

    pred = np.transpose(np.array((y_test,yfit)))
    return metrics, pred, prob, features1

# Cross validation for PEP-Word