Process the dataset and use labelencoder to convert all IDs to start from 0

Data sets in the field of recommended algorithms always start from 1 Start , Or a string of numbers , Every time you deal with it, you need one more user2id The operation of , It's a real hassle
Simply handle it before using the dataset , And save it user2id Dictionaries , Convenient for follow-up query

Pay attention to the ：

• sep To change to the separator of the current dataset （’ ‘,’\t’）
• names Change to the column name of the current dataset

The code is as follows ：

import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder


def load_mat():
    data_path = '../dataset/ml-100k/u.data'
    df_data = pd.read_csv(data_path, header = None, sep='\t', names =['user_id', 'item_id', 'rating','time'])

    lbe_user = LabelEncoder()
    lbe_user.fit(df_data['user_id'].unique())
    converted_user = lbe_user.transform(df_data['user_id'])

    lbe_item = LabelEncoder()  #  Make it discrete 
    lbe_item.fit(df_data['item_id'].unique())
    converted_item = lbe_item.transform(df_data['item_id'])

    converted_data = pd.DataFrame()
    converted_data['user_id'] = converted_user
    converted_data['item_id'] = converted_item
    converted_data['rating'] = df_data['rating']

    #  Corresponding relation 
    user2id = {
    }
    for user in lbe_user.classes_:
        user2id.update({
    user: lbe_user.transform([user])[0]})

    item2id = {
    }
    for item in lbe_item.classes_:
        item2id.update({
    item: lbe_item.transform([item])[0]})

    return converted_data,user2id,item2id

def save(converted_data,user2id,item2id):
    sort = converted_data.sort_values(by=['user_id'])
    sort.to_csv('../dataset/ml-100k/data_converted', header=None, index=False)
    np.save('../dataset/ml-100k/user2id.npy', user2id)
    np.save('../dataset/ml-100k/item2id.npy', item2id)
    print('successfully saved')


if __name__ == '__main__':
    converted_data,user2id,item2id = load_mat()
    save(converted_data,user2id,item2id)