We Keep Coding

sklearn image.PatchExtractor in a pipeline throws ValueError

I want to train my image classifier on extracted patches, so I developed the following pipeline, but I keep getting a ValueError and I'm not sure how can I solve it:
mlp_pipeline = pipeline.make_pipeline(
image.PatchExtractor(),
DictVectorizer(),
preprocessing.MinMaxScaler(**hyperparameters),
neural_network.MLPClassifier(**hyperparameters))
When I attempt to fit the model:
_ = mlp_pipeline.fit(train_features, train_target)
I get the following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [18], in <cell line: 1>()
----> 1 _ = mlp_pipeline.fit(train_features, train_target)
3 _predi = mlp_pipeline.predict(train_features)
5 _report = metrics.classification_report(
6 train_target,
7 _predi,
8 )
File ~/anaconda3/envs/DSA/lib/python3.10/site-packages/sklearn/pipeline.py:378, in Pipeline.fit(self, X, y, **fit_params)
352 """Fit the model.
353
354 Fit all the transformers one after the other and transform the
(...)
375 Pipeline with fitted steps.
376 """
377 fit_params_steps = self._check_fit_params(**fit_params)
--> 378 Xt = self._fit(X, y, **fit_params_steps)
379 with _print_elapsed_time("Pipeline", self._log_message(len(self.steps) - 1)):
380 if self._final_estimator != "passthrough":
File ~/anaconda3/envs/DSA/lib/python3.10/site-packages/sklearn/pipeline.py:336, in Pipeline._fit(self, X, y, **fit_params_steps)
334 cloned_transformer = clone(transformer)
335 # Fit or load from cache the current transformer
--> 336 X, fitted_transformer = fit_transform_one_cached(
337 cloned_transformer,
338 X,
339 y,
340 None,
341 message_clsname="Pipeline",
342 message=self._log_message(step_idx),
343 **fit_params_steps[name],
344 )
345 # Replace the transformer of the step with the fitted
346 # transformer. This is necessary when loading the transformer
347 # from the cache.
348 self.steps[step_idx] = (name, fitted_transformer)
File ~/anaconda3/envs/DSA/lib/python3.10/site-packages/joblib/memory.py:349, in NotMemorizedFunc.__call__(self, *args, **kwargs)
348 def __call__(self, *args, **kwargs):
--> 349 return self.func(*args, **kwargs)
File ~/anaconda3/envs/DSA/lib/python3.10/site-packages/sklearn/pipeline.py:872, in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
870 res = transformer.fit_transform(X, y, **fit_params)
871 else:
--> 872 res = transformer.fit(X, y, **fit_params).transform(X)
874 if weight is None:
875 return res, transformer
File ~/anaconda3/envs/DSA/lib/python3.10/site-packages/sklearn/feature_extraction/image.py:551, in PatchExtractor.transform(self, X)
532 """Transform the image samples in `X` into a matrix of patch data.
533
534 Parameters
(...)
548 number of patches that can be extracted.
549 """
550 self.random_state = check_random_state(self.random_state)
--> 551 n_images, i_h, i_w = X.shape[:3]
552 X = np.reshape(X, (n_images, i_h, i_w, -1))
553 n_channels = X.shape[-1]
ValueError: not enough values to unpack (expected 3, got 2)

TypeError, Hands on ML With Sci-Kit Learn Regression

Trying to work through the project in Chapter 2 of Hands-on ML with Sci-Kit Learn and Tensorflow, I am being given a type error when trying to run the data through a pipeline prior to building a model.
I keep getting a TypeError telling me that fit_transform() takes 2 positional arguments and yet 3 are given. Not sure what I am doing wrong as I am following along the best I can with the exercise. Please advise, let me know or if more information is needed as I tried to stick to the minimum amount of code required to generate the error sustained. Thanks for what insight you may be able to kindly provide.
Code is as follows
#Load the Data
import os
import tarfile
from six.moves import urllib
download_root = "https://raw.githubusercontent.com/ageron/handson-ml/master/"
housing_path = os.path.join('datasets', 'housing')
housing_url = download_root + "datasets/housing/housing.tgz"
def fetch_housing_data(housing_url=housing_url, housing_path = housing_path):
if not os.path.isdir(housing_path):
os.makedirs(housing_path)
tgz_path = os.path.join(housing_path, 'housing.tgz')
urllib.request.urlretrieve(housing_url, tgz_path)
housing_tgz = tarfile.open(tgz_path)
housing_tgz.extractall(path=housing_path)
housing_tgz.close()
# Pipeline Build
from sklearn.preprocessing import Imputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, LabelBinarizer
from sklearn.base import BaseEstimator, TransformerMixin
class DataFrameSelector(BaseEstimator, TransformerMixin):
def __init__(self, attribute_names):
self.attribute_names = attribute_names
def fit(self, x, y=None):
return self
def transform(self, x):
return x[self.attribute_names].values
from sklearn.base import BaseEstimator, TransformerMixin
rooms_ix, bedrooms_ix, population_ix, household_ix = 3, 4, 5, 6
class CombinedAttributesAdder(BaseEstimator, TransformerMixin):
def __init__(self, add_bedrooms_per_room=True):
self.add_bedrooms_per_room = add_bedrooms_per_room
def fit(self, X, y=None):
return self
def transform(self, X, y=None):
rooms_per_house = X[:, rooms_ix] / X[:, household_ix]
pop_per_house = X[:, population_ix] / X[:, household_ix]
if self.add_bedrooms_per_room:
bedrooms_per_room = X[:, bedrooms_ix]/X[:, rooms_ix]
return np.c_[X, rooms_per_house, pop_per_house,
bedrooms_per_room]
else:
return np.c_[X, rooms_per_house, pop_per_house]
num_attribs = list(house_num)
cat_attribs = ['ocean_proximity']
num_pipeline = Pipeline([
('selector', DataFrameSelector(num_attribs)),
('imputer', Imputer(strategy='median')),
('attribs_adder', CombinedAttributesAdder()),
('std_scaler', StandardScaler())
])
cat_pipeline = Pipeline([
('selector', DataFrameSelector(cat_attribs)),
('label_binarizer', LabelBinarizer())
])
from sklearn.compose import ColumnTransformer
full_pipeline = ColumnTransformer([
('num_pipeline', num_pipeline, num_attribs),
('cat_pipeline', cat_pipeline, cat_attribs),
])
Type Error encountered is as follows
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-50-925e65d2e69a> in <module>
----> 1 house_prep = full_pipeline.fit_transform(house)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in fit_transform(self, X, y)
474 self._validate_remainder(X)
475
--> 476 result = self._fit_transform(X, y, _fit_transform_one)
477
478 if not result:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in _fit_transform(self, X, y, func, fitted)
418 message=self._log_message(name, idx, len(transformers)))
419 for idx, (name, trans, column, weight) in enumerate(
--> 420 self._iter(fitted=fitted, replace_strings=True), 1))
421 except ValueError as e:
422 if "Expected 2D array, got 1D array instead" in str(e):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
922 self._iterating = self._original_iterator is not None
923
--> 924 while self.dispatch_one_batch(iterator):
925 pass
926
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
714 with self._lock:
715 job_idx = len(self._jobs)
--> 716 job = self._backend.apply_async(batch, callback=cb)
717 # A job can complete so quickly than its callback is
718 # called before we get here, causing self._jobs to
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback)
180 def apply_async(self, func, callback=None):
181 """Schedule a func to be run"""
--> 182 result = ImmediateResult(func)
183 if callback:
184 callback(result)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch)
547 # Don't delay the application, to avoid keeping the input
548 # arguments in memory
--> 549 self.results = batch()
550
551 def get(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
714 with _print_elapsed_time(message_clsname, message):
715 if hasattr(transformer, 'fit_transform'):
--> 716 res = transformer.fit_transform(X, y, **fit_params)
717 else:
718 res = transformer.fit(X, y, **fit_params).transform(X)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py in fit_transform(self, X, y, **fit_params)
391 return Xt
392 if hasattr(last_step, 'fit_transform'):
--> 393 return last_step.fit_transform(Xt, y, **fit_params)
394 else:
395 return last_step.fit(Xt, y, **fit_params).transform(Xt)
TypeError: fit_transform() takes 2 positional arguments but 3 were given

scikit-learn FeatureUnion not working to combine text & numeric features

I'm trying to combine a textual column of movie plots I have in a dataset with a categorical column of each movie's rating (the MPAA rating - G, PG, PG-13, R; not an IMDb user's score). I'm using sklearn's FeatureUnion object, but I keep getting en error about the fit_transform method being called with too many named arguments. Here's my code:
# create training and testing sets
X_train, X_test, y_train, y_test = train_test_split(movie_ratings[['Genre', 'Plot']], pd.get_dummies(movie_ratings['Rated']), random_state=56)
''' create a processing pipeline and feature union '''
# create function transformers
get_genre_data = FunctionTransformer(lambda x: x['Genre'], validate=False)
get_plot_data = FunctionTransformer(lambda x: x['Plot'], validate=False)
# obtain the data
genres = get_genre_data.fit_transform(movie_ratings)
plots = get_plot_data.fit_transform(movie_ratings)
# # join the processing in a feature union
join_data_formats = FeatureUnion(
transformer_list = [
('genres', Pipeline([
('selector', get_genre_data),
('one_hot_encoder', LabelEncoder())
])),
('plots', Pipeline([
('selector', get_plot_data),
('count_vectorizer', CountVectorizer(tokenizer=nltk.tokenize)),
('tfidf_transformer', TfidfTransformer())
]))
]
)
# # instantiate a nested pipeline
pipeline = Pipeline([
('feature_union', join_data_formats),
('neural_network', MLPClassifier(alpha=0.01, hidden_layer_sizes=(100,), early_stopping=False, verbose=True))
])
# # fit the pipeline to the training data
pipeline.fit(X_train, y_train)
...and the error being thrown is:
34 # # fit the pipeline to the training data
---> 35 pipeline.fit(X_train, y_train)
...
TypeError: fit_transform() takes 2 positional arguments but 3 were given
Where am I going wrong? Thanks much for the help!
UPDATE: here's the full stack trace:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-171-f57d9b24a9c8> in <module>()
28 # print(y_test.shape)
29
---> 30 pipeline.fit(X_train, y_train)
31 y_pred = pipeline.predict(X_test)
32
~\Anaconda3\lib\site-packages\sklearn\pipeline.py in fit(self, X, y, **fit_params)
246 This estimator
247 """
--> 248 Xt, fit_params = self._fit(X, y, **fit_params)
249 if self._final_estimator is not None:
250 self._final_estimator.fit(Xt, y, **fit_params)
~\Anaconda3\lib\site-packages\sklearn\pipeline.py in _fit(self, X, y, **fit_params)
211 Xt, fitted_transformer = fit_transform_one_cached(
212 cloned_transformer, None, Xt, y,
--> 213 **fit_params_steps[name])
214 # Replace the transformer of the step with the fitted
215 # transformer. This is necessary when loading the transformer
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\memory.py in __call__(self, *args, **kwargs)
360
361 def __call__(self, *args, **kwargs):
--> 362 return self.func(*args, **kwargs)
363
364 def call_and_shelve(self, *args, **kwargs):
~\Anaconda3\lib\site-packages\sklearn\pipeline.py in _fit_transform_one(transformer, weight, X, y, **fit_params)
579 **fit_params):
580 if hasattr(transformer, 'fit_transform'):
--> 581 res = transformer.fit_transform(X, y, **fit_params)
582 else:
583 res = transformer.fit(X, y, **fit_params).transform(X)
~\Anaconda3\lib\site-packages\sklearn\pipeline.py in fit_transform(self, X, y, **fit_params)
737 delayed(_fit_transform_one)(trans, weight, X, y,
738 **fit_params)
--> 739 for name, trans, weight in self._iter())
740
741 if not result:
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
777 # was dispatched. In particular this covers the edge
778 # case of Parallel used with an exhausted iterator.
--> 779 while self.dispatch_one_batch(iterator):
780 self._iterating = True
781 else:
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in _dispatch(self, batch)
586 dispatch_timestamp = time.time()
587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588 job = self._backend.apply_async(batch, callback=cb)
589 self._jobs.append(job)
590
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in apply_async(self, func, callback)
109 def apply_async(self, func, callback=None):
110 """Schedule a func to be run"""
--> 111 result = ImmediateResult(func)
112 if callback:
113 callback(result)
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\_parallel_backends.py in __init__(self, batch)
330 # Don't delay the application, to avoid keeping the input
331 # arguments in memory
--> 332 self.results = batch()
333
334 def get(self):
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~\Anaconda3\lib\site-packages\sklearn\externals\joblib\parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~\Anaconda3\lib\site-packages\sklearn\pipeline.py in _fit_transform_one(transformer, weight, X, y, **fit_params)
579 **fit_params):
580 if hasattr(transformer, 'fit_transform'):
--> 581 res = transformer.fit_transform(X, y, **fit_params)
582 else:
583 res = transformer.fit(X, y, **fit_params).transform(X)
~\Anaconda3\lib\site-packages\sklearn\pipeline.py in fit_transform(self, X, y, **fit_params)
281 Xt, fit_params = self._fit(X, y, **fit_params)
282 if hasattr(last_step, 'fit_transform'):
--> 283 return last_step.fit_transform(Xt, y, **fit_params)
284 elif last_step is None:
285 return Xt
TypeError: fit_transform() takes 2 positional arguments but 3 were given

Sklearn_pandas in a pipeline returns TypeError: 'builtin_function_or_method' object is not iterable

I have a data set with categorical and numerical features on which I want to apply some transformations followed by XGBClassifier.
Link to data set: https://www.kaggle.com/blastchar/telco-customer-churn
As the transformations are different for the numerical and categorical features, I used sklearn_pandas and its DataFrameMapper.
To perform one-hot encoding on the categorical features, I want to use DictVectorizer. But to use DictVectorizer, I first need to convert the dataframe into a dict, which I try to do with a custom transformer Dictifier.
When I run the Pipeline I get the error 'builtin_function_or_method' object is not iterable. Does anyone know what might be causing this error?
import numpy as np
import pandas as pd
from sklearn_pandas import DataFrameMapper
from sklearn_pandas import CategoricalImputer
from sklearn_pandas import cross_val_score
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import Imputer
from sklearn.preprocessing import StandardScaler
from sklearn.feature_extraction import DictVectorizer
from sklearn.pipeline import Pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.base import BaseEstimator
from sklearn.base import TransformerMixin
import xgboost as xgb
# Importing the data
df = pd.read_csv('../input/WA_Fn-UseC_-Telco-Customer-Churn.csv', na_values=' ')
X, y = df.iloc[:,1:-1], df.iloc[:,-1]
# Label encoding of the target classes
le = LabelEncoder()
y = le.fit_transform(y.values.reshape(y.shape[0], ))
# Defining the num and cat column names
cat_cols = X.columns[X.dtypes == object].tolist()
num_cols = X.columns[X.dtypes != object].tolist()
# DataFrameMappers for num and cat columns
num_transf_mapper = DataFrameMapper([([num_col], [Imputer(strategy="median"), StandardScaler()]) for num_col in num_cols],
input_df=True,
df_out=True)
cat_transf_mapper = DataFrameMapper([(cat_col , [CategoricalImputer()]) for cat_col in cat_cols],
input_df=True,
df_out=True)
# FeatureUnion of num and cat columns
num_cat_union = FeatureUnion([("num_mapper", num_transf_mapper),
("cat_mapper", cat_transf_mapper)])
# Custom transformer to convert Pandas DataFrame into Dict (needed for DictVectorizer)
class Dictifier(BaseEstimator, TransformerMixin):
def fit(self, X, y=None):
return self
def transform(self, X):
return X.to_dict('records')
# Pipeline
pipeline = Pipeline([("featureunion", num_cat_union),
("dictifier", Dictifier()),
("vectorizer", DictVectorizer(sort=False)),
("clf", xgb.XGBClassifier(max_depth=3))])
# Perform cross-validation
cross_val_scores = cross_val_score(pipeline, X, y, scoring="roc_auc", cv=3)
Error trace
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py:542: FutureWarning: From version 0.22, errors during fit will result in a cross validation score of NaN by default. Use error_score='raise' if you want an exception raised or error_score=np.nan to adopt the behavior from version 0.22.FutureWarning)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-187-96272018fb87> in <module>()
53
54 # Perform cross-validation
---> 55 cross_val_scores = cross_val_score(pipeline, X, y, scoring="roc_auc", cv=3)
/opt/conda/lib/python3.6/site-packages/sklearn_pandas/cross_validation.py in cross_val_score(model, X, *args, **kwargs)
19 warnings.warn(DEPRECATION_MSG, DeprecationWarning)
20 X = DataWrapper(X)
---> 21 return sk_cross_val_score(model, X, *args, **kwargs)
22
23
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, error_score)
400 fit_params=fit_params,
401 pre_dispatch=pre_dispatch,
--> 402 error_score=error_score)
403 return cv_results['test_score']
404
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)
238 return_times=True, return_estimator=return_estimator,
239 error_score=error_score)
--> 240 for train, test in cv.split(X, y, groups))
241
242 zipped_scores = list(zip(*scores))
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
979 # remaining jobs.
980 self._iterating = False
--> 981 if self.dispatch_one_batch(iterator):
982 self._iterating = self._original_iterator is not None
983
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
821 return False
822 else:
--> 823 self._dispatch(tasks)
824 return True
825
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
778 with self._lock:
779 job_idx = len(self._jobs)
--> 780 job = self._backend.apply_async(batch, callback=cb)
781 # A job can complete so quickly than its callback is
782 # called before we get here, causing self._jobs to
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
181 def apply_async(self, func, callback=None):
182 """Schedule a func to be run"""
--> 183 result = ImmediateResult(func)
184 if callback:
185 callback(result)
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
541 # Don't delay the application, to avoid keeping the input
542 # arguments in memory
--> 543 self.results = batch()
544
545 def get(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, error_score)
526 estimator.fit(X_train, **fit_params)
527 else:
--> 528 estimator.fit(X_train, y_train, **fit_params)
529
530 except Exception as e:
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
263 This estimator
264 """
--> 265 Xt, fit_params = self._fit(X, y, **fit_params)
266 if self._final_estimator is not None:
267 self._final_estimator.fit(Xt, y, **fit_params)
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
228 Xt, fitted_transformer = fit_transform_one_cached(
229 cloned_transformer, Xt, y, None,
--> 230 **fit_params_steps[name])
231 # Replace the transformer of the step with the fitted
232 # transformer. This is necessary when loading the transformer
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/memory.py in __call__(self, *args, **kwargs)
320
321 def __call__(self, *args, **kwargs):
--> 322 return self.func(*args, **kwargs)
323
324 def call_and_shelve(self, *args, **kwargs):
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, **fit_params)
612 def _fit_transform_one(transformer, X, y, weight, **fit_params):
613 if hasattr(transformer, 'fit_transform'):
--> 614 res = transformer.fit_transform(X, y, **fit_params)
615 else:
616 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
790 delayed(_fit_transform_one)(trans, X, y, weight,
791 **fit_params)
--> 792 for name, trans, weight in self._iter())
793
794 if not result:
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
979 # remaining jobs.
980 self._iterating = False
--> 981 if self.dispatch_one_batch(iterator):
982 self._iterating = self._original_iterator is not None
983
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
821 return False
822 else:
--> 823 self._dispatch(tasks)
824 return True
825
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
778 with self._lock:
779 job_idx = len(self._jobs)
--> 780 job = self._backend.apply_async(batch, callback=cb)
781 # A job can complete so quickly than its callback is
782 # called before we get here, causing self._jobs to
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
181 def apply_async(self, func, callback=None):
182 """Schedule a func to be run"""
--> 183 result = ImmediateResult(func)
184 if callback:
185 callback(result)
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
541 # Don't delay the application, to avoid keeping the input
542 # arguments in memory
--> 543 self.results = batch()
544
545 def get(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
259 with parallel_backend(self._backend):
260 return [func(*args, **kwargs)
--> 261 for func, args, kwargs in self.items]
262
263 def __len__(self):
/opt/conda/lib/python3.6/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, **fit_params)
612 def _fit_transform_one(transformer, X, y, weight, **fit_params):
613 if hasattr(transformer, 'fit_transform'):
--> 614 res = transformer.fit_transform(X, y, **fit_params)
615 else:
616 res = transformer.fit(X, y, **fit_params).transform(X)
/opt/conda/lib/python3.6/site-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
460 else:
461 # fit method of arity 2 (supervised transformation)
--> 462 return self.fit(X, y, **fit_params).transform(X)
463
464
/opt/conda/lib/python3.6/site-packages/sklearn_pandas/dataframe_mapper.py in transform(self, X)
342 stacked,
343 columns=self.transformed_names_,
--> 344 index=index)
345 # preserve types
346 for col, dtype in zip(self.transformed_names_, dtypes):
/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
377 else:
378 mgr = self._init_ndarray(data, index, columns, dtype=dtype,
--> 379 copy=copy)
380 elif isinstance(data, (list, types.GeneratorType)):
381 if isinstance(data, types.GeneratorType):
/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in _init_ndarray(self, values, index, columns, dtype, copy)
525 raise_with_traceback(e)
526
--> 527 index, columns = _get_axes(*values.shape)
528 values = values.T
529
/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in _get_axes(N, K, index, columns)
482 index = com._default_index(N)
483 else:
--> 484 index = _ensure_index(index)
485
486 if columns is None:
/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py in _ensure_index(index_like, copy)
4972 index_like = copy(index_like)
4973
-> 4974 return Index(index_like)
4975
4976
/opt/conda/lib/python3.6/site-packages/pandas/core/indexes/base.py in __new__(cls, data, dtype, copy, name, fastpath, tupleize_cols, **kwargs)
449 data, names=name or kwargs.get('names'))
450 # other iterable of some kind
--> 451 subarr = com._asarray_tuplesafe(data, dtype=object)
452 return Index(subarr, dtype=dtype, copy=copy, name=name, **kwargs)
453
/opt/conda/lib/python3.6/site-packages/pandas/core/common.py in _asarray_tuplesafe(values, dtype)
303
304 if not (isinstance(values, (list, tuple)) or hasattr(values, '__array__')):
--> 305 values = list(values)
306 elif isinstance(values, Index):
307 return values.values
TypeError: 'builtin_function_or_method' object is not iterable

This seems like a bug in sklearn_pandas.cross_val_score.
sklearn_pandas wraps the dataframe you supply in a DataWrapper object as seen in source code here:
def cross_val_score(model, X, *args, **kwargs):
warnings.warn(DEPRECATION_MSG, DeprecationWarning)
X = DataWrapper(X)
return sk_cross_val_score(model, X, *args, **kwargs)
which is apparently done to handle older versions of sklearn.cross_validation.cross_val_score which did not handle pandas DataFrames well. DataWrapper returns a list instance when divided into train and test.
But then it is not handled correctly during transform() of DataframeMapper as given in source code here
if self.df_out:
# if no rows were dropped preserve the original index,
# otherwise use a new integer one
no_rows_dropped = len(X) == len(stacked)
if no_rows_dropped:
index = X.index # <== This here is the source of error
else:
index = None
Here, X is not a DataFrame, but a list object, so index is not a list the actual index of pandas as intended, but actually a function of list and hence the error you got.
But since newer sklearn cross_val_score handles DataFrame correctly, you dont have to use the other import.
Change it from:
from sklearn_pandas import cross_val_score
to this:
from sklearn.model_selection import cross_val_score
So now you wont get that error anymore.
But, still further down the code, you will get another error about:
AttributeError: 'numpy.ndarray' object has no attribute 'to_dict'
This is because you wrap both your DataFrameMapper objects into a FeatureUnion by doing this:
num_cat_union = FeatureUnion([("num_mapper", num_transf_mapper),
("cat_mapper", cat_transf_mapper)])
and then do this:
pipeline = Pipeline([("featureunion", num_cat_union),
("dictifier", Dictifier()),
("vectorizer", DictVectorizer(sort=False)),
("clf", xgb.XGBClassifier(max_depth=3))])
Your Dictifier expects a DataFrame to be passed to it, so that it can call to_dict() on it, but the previous step in pipeline FeatureUnion will not preserve the DataFrame, it will convert that into a numpy array.
Generally, DataFrameMapper and FeatureUnion don't work well together. I would advise you to remove the FeatureUnion altogether and instead combine your both DataFrameMapper objects into a single object. This will effectively work as you wanted FeatureUnion to work.
Something like this:
transformers = []
# Combine both your operations here only
transformers.extend([([num_col], [Imputer(strategy="median"),
StandardScaler()]) for num_col in num_cols])
transformers.extend([(cat_col , [CategoricalImputer()]) for cat_col in cat_cols])
num_cat_union = DataFrameMapper(transformers,
input_df=True,
df_out=True)
# Your other code
...
...

Let show just part of the code as I do
class MultiColumn(BaseEstimator, TransformerMixin):
def __init__(self,columns = None):
self.columns = columns # array of column names to encode
def fit(self,X,y=None):
return self
def transform(self, X):
return X[self.columns]
NUMERIC = df[['var1', 'var2']]
CATEGORICAL = df[['var3', 'var4']]
class Imputation(BaseEstimator, TransformerMixin):
def transform(self, X, y=None, **fit_params):
return X.fillna(NUMERIC.median())
def fit_transform(self, X, y=None, **fit_params):
self.fit(X, y, **fit_params)
return self.transform(X)
def fit(self, X, y=None, **fit_params):
return self
class Cat(BaseEstimator, TransformerMixin):
def transform(self, X, y=None, **fit_params):
enc = DictVectorizer(sparse = False)
encc = enc.fit(CATEGORICAL.T.to_dict().values())
enc_data = encc.transform(X.T.to_dict().values())
enc_data[np.isnan(enc_data)] = 1
return enc_data
def fit_transform(self, X, y=None, **fit_params):
self.fit(X, y, **fit_params)
return self.transform(X)
def fit(self, X, y=None, **fit_params):
return self
And Pipeline
pipeline = Pipeline([
# Use FeatureUnion to combine the features
('union', FeatureUnion(
transformer_list=[
# numeric
('numeric', Pipeline([
('selector', MultiColumn(columns=['var1', 'var2'])),
('imp', Imputation()),
('scaling', preprocessing.StandardScaler(with_mean = 0.))
])),
# categorical
('categorical', Pipeline([
('selector', MultiColumn(columns=['var3', 'var4'])),
('one_hot', Cat()),
(CategoricalImputer())
])),
])),
('model_fitting', xgb.XGBClassifier(max_depth=3)),
])

All together in a pipeline. I hope this might help.
# Import necessary modules
from sklearn_pandas import DataFrameMapper
from sklearn_pandas import CategoricalImputer
# Check number of nulls in each feature column
nulls_per_column = X.isnull().sum()
print(nulls_per_column)
# Create a boolean mask for categorical columns
categorical_feature_mask = X.dtypes == object
# Get list of categorical column names
categorical_columns = X.columns[categorical_feature_mask].tolist()
# Get list of non-categorical column names
non_categorical_columns = X.columns[~categorical_feature_mask].tolist()
# Apply numeric imputer
numeric_imputation_mapper = DataFrameMapper(
[([numeric_feature], Imputer(strategy="median")) for numeric_feature in non_categorical_columns],
input_df=True,
df_out=True
)
# Apply categorical imputer
categorical_imputation_mapper = DataFrameMapper(
[(category_feature, CategoricalImputer()) for category_feature in categorical_columns],
input_df=True,
df_out=True
)
# Import FeatureUnion
from sklearn.pipeline import FeatureUnion
# Combine the numeric and categorical transformations
numeric_categorical_union = FeatureUnion([
("num_mapper", numeric_imputation_mapper),
("cat_mapper", categorical_imputation_mapper)
])
# Create full pipeline
pipeline = Pipeline([
("featureunion", numeric_categorical_union),
("dictifier", Dictifier()),
("vectorizer", DictVectorizer(sort=False)),
("clf", xgb.XGBClassifier())
])
# Perform cross-validation
cross_val_scores = cross_val_score(pipeline, kidney_data, y, scoring="roc_auc", cv=3)
# Print avg. AUC
print("3-fold AUC: ", np.mean(cross_val_scores))

ValueError in pipeline - featureHasher not working?

I think I'm having issues getting my vectorizer working within a gridsearch pipeline:
data as panda df x_train:
bathrooms bedrooms price building_id manager_id
10 1.5 3 3000 53a5b119ba8f7b61d4e010512e0dfc85 5ba989232d0489da1b5f2c45f6688adc
10000 1.0 2 5465 c5c8a357cba207596b04d1afd1e4f130 7533621a882f71e25173b27e3139d83d
100004 1.0 1 2850 c3ba40552e2120b0acfc3cb5730bb2aa d9039c43983f6e564b1482b273bd7b01
100007 1.0 1 3275 28d9ad350afeaab8027513a3e52ac8d5 1067e078446a7897d2da493d2f741316
100013 1.0 4 3350 0 98e13ad4b495b9613cef886d79a6291f
numeric_predictors = ['bathrooms', 'bedrooms', 'price']
categorical_predictors = ['building_id', 'manager_id']
minMaxScaler fit & transform:
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import MinMaxScaler
class MyScaler(BaseEstimator, TransformerMixin):
def __init__(self, cols):
self.cols = cols
def fit(self, X, y=None):
self.scaler = MinMaxScaler()
self.scaler.fit(X[self.cols])
return self
def transform(self, X):
return self.scaler.transform(X[self.cols])
My categorical feature hashing vectorizer:
from sklearn.feature_extraction import FeatureHasher
from sklearn.feature_extraction.text import HashingVectorizer
class MyVectorizer(BaseEstimator, TransformerMixin):
"""
Vectorize a set of categorical variables
"""
def __init__(self, cols, hashing=None):
"""
args:
cols: a list of column names of the categorical variables
hashing:
If None, then vectorization is a simple one-hot-encoding.
If an integer, then hashing is the number of features in the output.
"""
self.cols = cols
self.hashing = hashing
def fit(self, X, y=None):
data = X[self.cols]
# Choose a vectorizer
if self.hashing is None:
self.myvec = HashingVectorizer()
else:
self.myvec = FeatureHasher(n_features = self.hashing)
self.myvec.fit(X[self.cols].to_dict(orient='records'))
return self
def transform(self, X):
# Vectorize Input
if self.hashing is None:
return pd.DataFrame(
self.myvec.transform(X[self.cols].to_dict(orient='records')),
columns = self.myvec.feature_names_
)
else:
return pd.DataFrame(
self.myvec.transform(X[self.cols].to_dict(orient='records')).toarray()
)
GridSearch hyperparameters:
search_params = {
'preprocess__vectorize__hashing': [20, 40, 80],
'predict__alpha': [.01, .1, 1, 2, 10]
}
pipeline:
from sklearn.pipeline import Pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.linear_model import LinearRegression
pipeline = Pipeline([
('preprocess', FeatureUnion([
('scale', MyScaler(cols=numeric_predictors)),
('vectorize', MyVectorizer(cols=categorical_predictors, hashing=5))
])),
('predict', MultinomialNB())
])
And last, calling this with the gridsearchCV classifier:
grid_search = GridSearchCV(pipeline, search_params)
grid_search.fit(x_train, y_train)
I get a ValueError: Input X must be non-negative. I checked and my numeric_predictor columns' data all non-negative, so I am narrowing it down to an issue with the hashing of the categorical predictors.
ValueError Traceback (most recent call last)
<ipython-input-62-50522376d1e5> in <module>()
1 grid_search = GridSearchCV(pipeline, search_params)
----> 2 grid_search.fit(x_train, y_train)
3 grid_search.best_params_
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/model_selection/_search.pyc in fit(self, X, y, groups, **fit_params)
636 error_score=self.error_score)
637 for parameters, (train, test) in product(candidate_params,
--> 638 cv.split(X, y, groups)))
639
640 # if one choose to see train score, "out" will contain train score info
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
777 # was dispatched. In particular this covers the edge
778 # case of Parallel used with an exhausted iterator.
--> 779 while self.dispatch_one_batch(iterator):
780 self._iterating = True
781 else:
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
623 return False
624 else:
--> 625 self._dispatch(tasks)
626 return True
627
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
586 dispatch_timestamp = time.time()
587 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 588 job = self._backend.apply_async(batch, callback=cb)
589 self._jobs.append(job)
590
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in apply_async(self, func, callback)
109 def apply_async(self, func, callback=None):
110 """Schedule a func to be run"""
--> 111 result = ImmediateResult(func)
112 if callback:
113 callback(result)
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/_parallel_backends.pyc in __init__(self, batch)
330 # Don't delay the application, to avoid keeping the input
331 # arguments in memory
--> 332 self.results = batch()
333
334 def get(self):
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/model_selection/_validation.pyc in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
435 estimator.fit(X_train, **fit_params)
436 else:
--> 437 estimator.fit(X_train, y_train, **fit_params)
438
439 except Exception as e:
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/pipeline.pyc in fit(self, X, y, **fit_params)
257 Xt, fit_params = self._fit(X, y, **fit_params)
258 if self._final_estimator is not None:
--> 259 self._final_estimator.fit(Xt, y, **fit_params)
260 return self
261
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/naive_bayes.pyc in fit(self, X, y, sample_weight)
602 self.feature_count_ = np.zeros((n_effective_classes, n_features),
603 dtype=np.float64)
--> 604 self._count(X, Y)
605 alpha = self._check_alpha()
606 self._update_feature_log_prob(alpha)
/home/fred/anaconda2/lib/python2.7/site-packages/sklearn/naive_bayes.pyc in _count(self, X, Y)
706 """Count and smooth feature occurrences."""
707 if np.any((X.data if issparse(X) else X) < 0):
--> 708 raise ValueError("Input X must be non-negative")
709 self.feature_count_ += safe_sparse_dot(Y.T, X)
710 self.class_count_ += Y.sum(axis=0)
ValueError: Input X must be non-negative
> /home/fred/anaconda2/lib/python2.7/site-packages/sklearn/naive_bayes.py(708)_count()
706 """Count and smooth feature occurrences."""
707 if np.any((X.data if issparse(X) else X) < 0):
--> 708 raise ValueError("Input X must be non-negative")
709 self.feature_count_ += safe_sparse_dot(Y.T, X)
710 self.class_count_ += Y.sum(axis=0)

Yes, when hashing is not None, FeatureHasher() is chosen, which can output negative values.
But you can remove convert those negative values to positive by using the non_negative parameter of FeatureHashser as given in documentation:
non_negative : boolean, optional, default False
When True, an absolute value is applied to the features matrix prior
to returning it. When used in conjunction with
alternate_sign=True, this significantly reduces the inner product
preservation property.
So change this line in MyVectorizer:
self.myvec = FeatureHasher(n_features = self.hashing)
to this:
self.myvec = FeatureHasher(n_features = self.hashing, non_negative=True)
Note:
This parameter has been deprecated since version 0.19 and will be removed in 0.21.
You need to study how this parameter will affect your classification problem.