I ran into the same problem and got it working by applying the workaround specified in the book's Github repo.
Warning: earlier versions of the book used the LabelBinarizer class at
this point. Again, this was incorrect: just like the LabelEncoder
class, the LabelBinarizer class was designed to preprocess labels, not
input features. A better solution is to use Scikit-Learn's upcoming
CategoricalEncoder class: it will soon be added to Scikit-Learn, and
in the meantime you can use the code below (copied from Pull Request
#9151).
To save you some grepping here's the workaround, just paste and run it in a previous cell:
# Definition of the CategoricalEncoder class, copied from PR #9151.
# Just run this cell, or copy it to your code, do not try to understand it (yet).
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.utils import check_array
from sklearn.preprocessing import LabelEncoder
from scipy import sparse
class CategoricalEncoder(BaseEstimator, TransformerMixin):
def __init__(self, encoding='onehot', categories='auto', dtype=np.float64,
handle_unknown='error'):
self.encoding = encoding
self.categories = categories
self.dtype = dtype
self.handle_unknown = handle_unknown
def fit(self, X, y=None):
"""Fit the CategoricalEncoder to X.
Parameters
----------
X : array-like, shape [n_samples, n_feature]
The data to determine the categories of each feature.
Returns
-------
self
"""
if self.encoding not in ['onehot', 'onehot-dense', 'ordinal']:
template = ("encoding should be either 'onehot', 'onehot-dense' "
"or 'ordinal', got %s")
raise ValueError(template % self.handle_unknown)
if self.handle_unknown not in ['error', 'ignore']:
template = ("handle_unknown should be either 'error' or "
"'ignore', got %s")
raise ValueError(template % self.handle_unknown)
if self.encoding == 'ordinal' and self.handle_unknown == 'ignore':
raise ValueError("handle_unknown='ignore' is not supported for"
" encoding='ordinal'")
X = check_array(X, dtype=np.object, accept_sparse='csc', copy=True)
n_samples, n_features = X.shape
self._label_encoders_ = [LabelEncoder() for _ in range(n_features)]
for i in range(n_features):
le = self._label_encoders_[i]
Xi = X[:, i]
if self.categories == 'auto':
le.fit(Xi)
else:
valid_mask = np.in1d(Xi, self.categories[i])
if not np.all(valid_mask):
if self.handle_unknown == 'error':
diff = np.unique(Xi[~valid_mask])
msg = ("Found unknown categories {0} in column {1}"
" during fit".format(diff, i))
raise ValueError(msg)
le.classes_ = np.array(np.sort(self.categories[i]))
self.categories_ = [le.classes_ for le in self._label_encoders_]
return self
def transform(self, X):
"""Transform X using one-hot encoding.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data to encode.
Returns
-------
X_out : sparse matrix or a 2-d array
Transformed input.
"""
X = check_array(X, accept_sparse='csc', dtype=np.object, copy=True)
n_samples, n_features = X.shape
X_int = np.zeros_like(X, dtype=np.int)
X_mask = np.ones_like(X, dtype=np.bool)
for i in range(n_features):
valid_mask = np.in1d(X[:, i], self.categories_[i])
if not np.all(valid_mask):
if self.handle_unknown == 'error':
diff = np.unique(X[~valid_mask, i])
msg = ("Found unknown categories {0} in column {1}"
" during transform".format(diff, i))
raise ValueError(msg)
else:
# Set the problematic rows to an acceptable value and
# continue `The rows are marked `X_mask` and will be
# removed later.
X_mask[:, i] = valid_mask
X[:, i][~valid_mask] = self.categories_[i][0]
X_int[:, i] = self._label_encoders_[i].transform(X[:, i])
if self.encoding == 'ordinal':
return X_int.astype(self.dtype, copy=False)
mask = X_mask.ravel()
n_values = [cats.shape[0] for cats in self.categories_]
n_values = np.array([0] + n_values)
indices = np.cumsum(n_values)
column_indices = (X_int + indices[:-1]).ravel()[mask]
row_indices = np.repeat(np.arange(n_samples, dtype=np.int32),
n_features)[mask]
data = np.ones(n_samples * n_features)[mask]
out = sparse.csc_matrix((data, (row_indices, column_indices)),
shape=(n_samples, indices[-1]),
dtype=self.dtype).tocsr()
if self.encoding == 'onehot-dense':
return out.toarray()
else:
return out
pandas.get_dummies(). – Nucleotidase