model.py 文件源码

def kde_opt2c(df_cell_train_feats, y_train, df_cell_test_feats):
    def prepare_feats(df):
        df_new = pd.DataFrame()
        df_new["hour"] = df["hour"]
        df_new["weekday"] = df["weekday"] + df["hour"] / 24.
        df_new["accuracy"] = df["accuracy"].apply(lambda x: np.log10(x))
        df_new["x"] = df["x"]
        df_new["y"] = df["y"]
        return df_new
    logging.info("train kde_opt2c model")
    df_cell_train_feats_kde = prepare_feats(df_cell_train_feats)
    df_cell_test_feats_kde = prepare_feats(df_cell_test_feats)
    n_class = len(np.unique(y_train))
    y_test_pred = np.zeros((len(df_cell_test_feats_kde), n_class), "d")
    for i in range(n_class):
        X = df_cell_train_feats_kde[y_train == i]
        y_test_pred_i = np.ones(len(df_cell_test_feats_kde), "d")
        for feat in df_cell_train_feats_kde.columns.values:
            X_feat = X[feat].values
            kde = gaussian_kde(X_feat, "scott")
            y_test_pred_i *= kde.evaluate(df_cell_test_feats_kde[feat].values)
        y_test_pred[:, i] += y_test_pred_i
    return y_test_pred