Stock_Prediction_Data_Processing.py 文件源码

def preprocessing_train_data(paras, df, LabelColumnName, ticker, train_tickers_dict, one_hot_label_proc, array_format=True):
    day_list=train_tickers_dict[ticker]
    index_df=np.vectorize(lambda s: s.strftime('%Y-%m-%d'))(df.index.to_pydatetime())
    df.index=index_df
    common_day=list(set(day_list).intersection(set(index_df)))
    df=df.loc[common_day]
    X = df.drop(LabelColumnName, 1)
    y = np.array(df[LabelColumnName])
    #print(X.head())

    # print("ticker", ticker)
    # print(X)

    if one_hot_label_proc == True:
        # generate one hot output
        y_normalized_T = one_hot_processing(y, paras.n_out_class)
    else:
        y_normalized_T = y.astype(int)  # np.repeat(float('nan'), len(y))

    if array_format: return X.values, y_normalized_T

    return X, y_normalized_T