[ASK] Error in NCFDataset creation

Description

Hello all, i'm trying to use the NCF_deep_dive notebook with my own data. With the following structure

	usr_id	code_id	amt_trx	bestelldatum
0	0	35	1	2022-03-01
1	0	2	1	2022-03-01
2	0	18	1	2022-03-01
3	0	9	1	2022-03-01
4	0	0	1	2022-03-01

when I try to create the dataset i get the following error

data = NCFDataset(train_file=train_file, test_file=leave_one_out_test_file, seed=SEED, overwrite_test_file_full=True, col_user='usr_id', col_item='code_id', col_rating='amt_trx', binary=False)

---------------------------------------------------------------------------
MissingUserException                      Traceback (most recent call last)
Cell In [39], line 1
----> 1 data = NCFDataset(train_file=train_file,
      2                     test_file=leave_one_out_test_file,
      3                     seed=SEED,
      4                     overwrite_test_file_full=True,
      5                     col_user='usr_id',
      6                     col_item='code_id',
      7                     col_rating='amt_trx',
      8                     binary=False)

File /anaconda/envs/recsys/lib/python3.8/site-packages/recommenders/models/ncf/dataset.py:376, in Dataset.__init__(self, train_file, test_file, test_file_full, overwrite_test_file_full, n_neg, n_neg_test, col_user, col_item, col_rating, binary, seed, sample_with_replacement, print_warnings)
    374         self.test_file_full = os.path.splitext(self.test_file)[0] + "_full.csv"
    375     if self.overwrite_test_file_full or not os.path.isfile(self.test_file_full):
--> 376         self._create_test_file()
    377     self.test_full_datafile = DataFile(
    378         filename=self.test_file_full,
    379         col_user=self.col_user,
   (...)
    383         binary=self.binary,
    384     )
    385 # set random seed

File /anaconda/envs/recsys/lib/python3.8/site-packages/recommenders/models/ncf/dataset.py:417, in Dataset._create_test_file(self)
    415 if user in train_datafile.users:
    416     user_test_data = test_datafile.load_data(user)
--> 417     user_train_data = train_datafile.load_data(user)
    418     # for leave-one-out evaluation, exclude items seen in both training and test sets
    419     # when sampling negatives
    420     user_positive_item_pool = set(
    421         user_test_data[self.col_item].unique()
    422     ).union(user_train_data[self.col_item].unique())

File /anaconda/envs/recsys/lib/python3.8/site-packages/recommenders/models/ncf/dataset.py:194, in DataFile.load_data(self, key, by_user)
    192 while (self.line_num == 0) or (self.row[key_col] != key):
    193     if self.end_of_file:
--> 194         raise MissingUserException("User {} not in file {}".format(key, self.filename))
    195     next(self)
    196 # collect user/test batch data

MissingUserException: User 58422 not in file ./train_new.csv

I made some checks print(train.usr_id.nunique()) --> output: 81062 print(test.usr_id.nunique()) --> output: 81062 print(leave.usr_id.nunique()) --> output: 81062

also checked by hand and the user 58422 is in all the files. Also the types are the same i'm using int64 for usr_id, code_id and amt_trx like movielens dataset

I can't understand the error, could you help me please?

Update

If i remove the parameter overwrite_test_file_full it creates the dataset but then I can't make predictions because the dataset object didn't create the user2id mapping

data = NCFDataset(train_file=train_file,
                    test_file=leave_one_out_test_file,
                    seed=SEED,
                    col_user='usr_id',
                    col_item='code_id',
                    col_rating='amt_trx',
                    print_warnings=True)

model = NCF (
    n_users=data.n_users, 
    n_items=data.n_items,
    model_type="NeuMF",
    n_factors=4,
    layer_sizes=[16,8,4],
    n_epochs=EPOCHS,
    batch_size=BATCH_SIZE,
    learning_rate=1e-3,
    verbose=99,
    seed=SEED
)

predictions = [[row.usr_id, row.code_id, model.predict(row.usr_id, row.code_id)]
               for (_, row) in test.iterrows()]


predictions = pd.DataFrame(predictions, columns=['usr_id', 'code_id', 'prediction'])
predictions.head()

AttributeError                            Traceback (most recent call last)
Cell In [38], line 1
----> 1 predictions = [[row.usr_id, row.code_id, model.predict(row.usr_id, row.code_id)]
      2                for (_, row) in test.iterrows()]
      5 predictions = pd.DataFrame(predictions, columns=['usr_id', 'code_id', 'prediction'])
      6 predictions.head()

Cell In [38], line 1, in <listcomp>(.0)
----> 1 predictions = [[row.usr_id, row.code_id, model.predict(row.usr_id, row.code_id)]
      2                for (_, row) in test.iterrows()]
      5 predictions = pd.DataFrame(predictions, columns=['usr_id', 'code_id', 'prediction'])
      6 predictions.head()

File /anaconda/envs/recsys/lib/python3.8/site-packages/recommenders/models/ncf/ncf_singlenode.py:434, in NCF.predict(self, user_input, item_input, is_list)
    431     return list(output.reshape(-1))
    433 else:
--> 434     output = self._predict(np.array([user_input]), np.array([item_input]))
    435     return float(output.reshape(-1)[0])

File /anaconda/envs/recsys/lib/python3.8/site-packages/recommenders/models/ncf/ncf_singlenode.py:440, in NCF._predict(self, user_input, item_input)
    437 def _predict(self, user_input, item_input):
    438 
    439     # index converting
--> 440     user_input = np.array([self.user2id[x] for x in user_input])
    441     item_input = np.array([self.item2id[x] for x in item_input])
    443     # get feed dict

File /anaconda/envs/recsys/lib/python3.8/site-packages/recommenders/models/ncf/ncf_singlenode.py:440, in <listcomp>(.0)
    437 def _predict(self, user_input, item_input):
    438 
    439     # index converting
--> 440     user_input = np.array([self.user2id[x] for x in user_input])
    441     item_input = np.array([self.item2id[x] for x in item_input])
    443     # get feed dict

AttributeError: 'NCF' object has no attribute 'user2id'