label_encode_dict['cat116']
# output
OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=-99)
label_encode_dict['cat116'].transform(np.array([xq['cat116']]).reshape(-1,1))
stack trace
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/sklearn/utils/_encode.py in _encode(values, uniques, check_unknown)
177 try:
--> 178 return _map_to_integer(values, uniques)
179 except KeyError as e:
6 frames
/usr/local/lib/python3.7/dist-packages/sklearn/utils/_encode.py in _map_to_integer(values, uniques)
122 table = _nandict({val: i for i, val in enumerate(uniques)})
--> 123 return np.array([table[v] for v in values])
124
/usr/local/lib/python3.7/dist-packages/sklearn/utils/_encode.py in <listcomp>(.0)
122 table = _nandict({val: i for i, val in enumerate(uniques)})
--> 123 return np.array([table[v] for v in values])
124
/usr/local/lib/python3.7/dist-packages/sklearn/utils/_encode.py in __missing__(self, key)
116 return self.nan_value
--> 117 raise KeyError(key)
118
KeyError: 'A'
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-120-25237eb44032> in <module>()
----> 1 label_encode_dict['cat116'].transform(np.array([xq['cat116']]).reshape(-1,1))
/usr/local/lib/python3.7/dist-packages/sklearn/preprocessing/_encoders.py in transform(self, X)
785 Transformed input.
786 """
--> 787 X_int, X_mask = self._transform(X, handle_unknown=self.handle_unknown)
788 X_trans = X_int.astype(self.dtype, copy=False)
789
/usr/local/lib/python3.7/dist-packages/sklearn/preprocessing/_encoders.py in _transform(self, X, handle_unknown, force_all_finite)
152 # already called above.
153 X_int[:, i] = _encode(Xi, uniques=self.categories_[i],
--> 154 check_unknown=False)
155
156 return X_int, X_mask
/usr/local/lib/python3.7/dist-packages/sklearn/utils/_encode.py in _encode(values, uniques, check_unknown)
178 return _map_to_integer(values, uniques)
179 except KeyError as e:
--> 180 raise ValueError(f"y contains previously unseen labels: {str(e)}")
181 else:
182 if check_unknown:
ValueError: y contains previously unseen labels: 'A'
Why this unseen label error came as handle_unknown is already specified in Ordinal Encoder.
Sk learn version = 0.24.1
**Edited: short example **
from sklearn.preprocessing import OrdinalEncoder
enc = OrdinalEncoder(handle_unknown = 'use_encoded_value', unknown_value = -9)
PP = [['AA','B']]
enc.fit(PP)
print(enc.categories_)
enc.transform(np.array(['A','B']).reshape(1,-1)) # gives the same ValueError: y contains previously unseen labels: 'A'
enc.transform(np.array(['AC','B']).reshape(1,-1)) # this works as expected
I am now thinking that it handles unkown_values higher than alphabetical order. In above example as 'A' is smaller than 'AA'. It resulted in error. Any turnaround for this?