mengtingwan/grocery

models for grocery shopping behavior (Wan et al, CIKM'18, Wan et al, WWW'17)

grocery's Issues

Problem with preprocessing

Hi, when I run the preprocessing py file, here comes the error:
Traceback (most recent call last):
File "./src/parser.py", line 98, in
parse_instacart(thr_i = args.thr_item, thr_u = args.thr_user, subset_user = args.subset_user)
File "./src/parser.py", line 80, in parse_instacart
item_descr['PID'] = item_descr['PID'].apply(lambda x: [item_dict[k] for k in x])
File "/opt/anaconda3/lib/python3.7/site-packages/pandas/core/series.py", line 4042, in apply
mapped = lib.map_infer(values, f, convert=convert_dtype)
File "pandas/_libs/lib.pyx", line 2228, in pandas._libs.lib.map_infer
File "./src/parser.py", line 80, in
item_descr['PID'] = item_descr['PID'].apply(lambda x: [item_dict[k] for k in x])
TypeError: 'int' object is not iterable

Actually I don't know why here comes this error? Thanks.

how to do With-in basket recommendation

hi, thank you very much for the fabulous work!!!

I have a question...

Do you know how to do With-in basket recommendation

for next-basek recommendation, it seems like you do the

s = np.dot(self.item_emb, self.user_emb[u,:]) + self.item_bias.copy()

I guess for the with-in recommendation.
given item j , user u
it would be

s = np.dot(self.item_emb1,self.item_emb2[j,:]+np.dot(self.item_emb, self.user_emb[u,:]) + self.item_bias.copy()

however... it does not seem to work....

would you help me out on this??

Thanks!!

Dataset & code share issue

Hi! thanks for sharing.

1. I cannot access the link https://www.instacart.com/datasets/grocery-shopping-2017. How can I download data?
2. Could you also share the code for the Paper Mengting Wan, Di Wang, Matt Goldman, Matt Taddy, Justin Rao, Jie Liu, Dimitrios Lymberopoulos, Julian McAuley, "Modeling Consumer Preferences and Price Sensitivities from Large-Scale Grocery Shopping Transaction Logs", in WWW'17 ?

Thanks!

About difference between item_embedding1.csv and item_embedding2.csv

Hello, I wonder what's the difference between item_embedding1.csv and item_embedding2.csv?