features_kmeans_1.py 文件源码

def build(self):
        train, y, test, _ = data.get()

        ntrain = len(train)
        df = pd.concat([train, test], axis=0)
        to_drop = df.columns

        dcn = []
        for n in [2, 5, 10, 15, 25]:
            cname = 'kmeans_' + str(n)
            dcn.append(cname)
            df[cname] = cluster.KMeans(n_clusters=n).fit_predict(df)

        df = pd.get_dummies(df, columns=dcn)

        df = df.drop(to_drop, axis=1)
        train = df[:ntrain]
        test = df[ntrain:].copy()

        return train.astype('int32'), test.astype('int32'), None