def doOneHot(X_train, X_test):
res = X_test[['instanceID']]
X_test.drop('instanceID', axis=1, inplace=True)
data = X_train.append(X_test, ignore_index=True)
del X_train, X_test
gc.collect()
features_trans = ['gender','appCategory_main','connectionType']
data = pd.get_dummies(data, columns=features_trans)
X_train = data.loc[data['label'] != -1, :]
X_test = data.loc[data['label'] == -1, :]
X_test.loc[:, 'instanceID'] = res.values
del data
gc.collect()
return X_train, X_test
评论列表
文章目录