zhenpengyao / supramolecular_vae Goto Github PK

train_mof = model.df_to_tuples(df.loc[train_index], smiles_column)
test_mof = model.df_to_tuples(df.loc[test_index], smiles_column)
prop_train = model.df_to_tuples(prop_df.loc[prop_train_index], smiles_column)
prop_test = model.df_to_tuples(prop_df.loc[prop_test_index], smiles_column)
train_data = train_mof + prop_train
test_data = test_mof + prop_tes

ValueError                                Traceback (most recent call last)

<ipython-input-101-e9059b196f9e> in <module>()
----> 1 train_mof = model.df_to_tuples(df.loc[train_index], smiles_column)
      2 test_mof = model.df_to_tuples(df.loc[test_index], smiles_column)
      3 prop_train = model.df_to_tuples(prop_df.loc[prop_train_index], smiles_column)
      4 prop_test = model.df_to_tuples(prop_df.loc[prop_test_index], smiles_column)
      5 train_data = train_mof + prop_train

11 frames

/content/drive/My Drive/research/Supramolecular_VAE/vaemof/model.py in df_to_tuples(self, df, smiles_column)
    316     def df_to_tuples(self, df: pd.DataFrame, smiles_column: Text) -> List[DataTuple]:
    317         n = len(df)
--> 318         smi_ids = self.vocab.df_to_ids(df, smiles_column)
    319         mof_ids = self.vocab_mof.df_to_ids(df)
    320         has_y = all(i in df.columns.tolist() for i in self.vocab_y.labels)

/content/drive/My Drive/research/Supramolecular_VAE/vaemof/vocabs.py in df_to_ids(self, df, column, batch)
    155             print("column:", column)
    156             strings = df.iloc[list(indexes)][column].tolist()
--> 157             ids = Parallel(n_jobs=n_jobs)(delayed(self.string_to_ids)(s) for s in strings)
    158             ids_list.extend(ids)
    159         return ids_list

/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in __call__(self, iterable)
   1030                 self._iterating = self._original_iterator is not None
   1031 
-> 1032             while self.dispatch_one_batch(iterator):
   1033                 pass
   1034 

/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
    845                 return False
    846             else:
--> 847                 self._dispatch(tasks)
    848                 return True
    849 

/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in _dispatch(self, batch)
    763         with self._lock:
    764             job_idx = len(self._jobs)
--> 765             job = self._backend.apply_async(batch, callback=cb)
    766             # A job can complete so quickly than its callback is
    767             # called before we get here, causing self._jobs to

/usr/local/lib/python3.6/dist-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
    206     def apply_async(self, func, callback=None):
    207         """Schedule a func to be run"""
--> 208         result = ImmediateResult(func)
    209         if callback:
    210             callback(result)

/usr/local/lib/python3.6/dist-packages/joblib/_parallel_backends.py in __init__(self, batch)
    570         # Don't delay the application, to avoid keeping the input
    571         # arguments in memory
--> 572         self.results = batch()
    573 
    574     def get(self):

/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in __call__(self)
    251         with parallel_backend(self._backend, n_jobs=self._n_jobs):
    252             return [func(*args, **kwargs)
--> 253                     for func, args, kwargs in self.items]
    254 
    255     def __reduce__(self):

/usr/local/lib/python3.6/dist-packages/joblib/parallel.py in <listcomp>(.0)
    251         with parallel_backend(self._backend, n_jobs=self._n_jobs):
    252             return [func(*args, **kwargs)
--> 253                     for func, args, kwargs in self.items]
    254 
    255     def __reduce__(self):

/content/drive/My Drive/research/Supramolecular_VAE/vaemof/vocabs.py in string_to_ids(self, string, pad_seq, max_len)
    125     def string_to_ids(self, string, pad_seq=False, max_len=0):
    126         print("String:",self.string_preprocess(string))
--> 127         ids = [self.char_to_id(c) for c in self.string_preprocess(string)]
    128         max_len = self.max_len if max_len == 0 else max_len
    129         ids = self.add_bos_eos(ids)

/content/drive/My Drive/research/Supramolecular_VAE/vaemof/vocabs.py in <listcomp>(.0)
    125     def string_to_ids(self, string, pad_seq=False, max_len=0):
    126         print("String:",self.string_preprocess(string))
--> 127         ids = [self.char_to_id(c) for c in self.string_preprocess(string)]
    128         max_len = self.max_len if max_len == 0 else max_len
    129         ids = self.add_bos_eos(ids)

/content/drive/My Drive/research/Supramolecular_VAE/vaemof/vocabs.py in char_to_id(self, char)
    111         #print(self.c2i)
    112         if char not in self.c2i:
--> 113             raise ValueError(f'{char} not in dictionary!')
    114 
    115         return self.c2i[char]

ValueError: \Lrexpl not in dictionary!