Transform dataframe data to the ffmlib datatype

pandas2ffmlib.py

## for category columns
def category_feature2FFM(data, category_list):
    previous_len = 0
    for i in range(len(category_list)):
        
        category_name = category_list[i]
        
        dic = data[category_name].unique()
        dic = dict(zip(dic, range(len(dic))))

        def data2ffm(x):
            return (i, dic.get(x)+previous_len, 1)

        data[category_name] = data[category_name].map(data2ffm)
        
        previous_len += len(dic)
        print('%s转换完成'%category_name)
    return data


## for numerical columns
def numeric_feature2FFM(data, numeric_list, start_num):
    
    for i in range(len(numeric_list)):
        numeric_name = numeric_list[i]
        
        field_id = start_num + i
        
        def numeric2ffm(x):
            return (field_id, int(1), x)
        
        scaler = MinMaxScaler()
        scaler.fit(data[numeric_name])
        data[numeric_name] = scaler.transform(data[numeric_name])
        
        data[numeric_name] = data[numeric_name].map(numeric2ffm)
        print('%s转换完成'%numeric_name)
    return data