grouping_data.py

import pandas as pd

df = pd.read_csv('new_events_data.csv')
grouped_data = df.groupby('user_id')['product_id'].agg(list).reset_index()

user_product_dict = dict(zip(grouped_data['user_id'], grouped_data['product_id']))

for key, value in user_product_dict.items():
    print(key, value)
    break

user_id_list = list(user_product_dict.keys())
print(len(user_id_list))
print(len(user_product_dict))

import pickle

def save_obj(obj, name):
    with open(name, 'wb') as f:
        pickle.dump(obj, f)
        

save_obj(user_product_dict, 'user_product_dict.pkl')
save_obj(user_id_list, 'user_id_list.pkl')