predict_2017_06_16_4.py 文件源码

def gen_features(train, y, test):
    for c in ['active', 'alco', 'smoke']:
        le = preprocessing.LabelEncoder()
        le.fit(train[c].values.tolist() + test[c].values.tolist())
        train[c] = le.transform(train[c])
        test[c] = le.transform(test[c])

    train['ap_dif'] = train.ap_hi - train.ap_lo
    test['ap_dif'] = test.ap_hi - test.ap_lo

    h = train['height'] / 100
    train['BWI'] = train['weight'] / (h * h)
    h = test['height'] / 100
    test['BWI'] = test['weight'] / (h * h)

    imp = preprocessing.Imputer()
    train = imp.fit_transform(train)
    test = imp.transform(test)

    return train, y, test