Related
I am building a model using customized transformers (KeyError: "None of [Index([('A','B','C')] , dtype='object')] are in the [columns]).
When I run the below code, I get an error because of .fit:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-165-289e1d466eb9> in <module>
10
11 # fit on the complete pipeline
---> 12 training = full_pipeline.fit(X, y)
13
14 # metrics
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
339 """
340 fit_params_steps = self._check_fit_params(**fit_params)
--> 341 Xt = self._fit(X, y, **fit_params_steps)
342 with _print_elapsed_time('Pipeline',
343 self._log_message(len(self.steps) - 1)):
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params_steps)
301 cloned_transformer = clone(transformer)
302 # Fit or load from cache the current transformer
--> 303 X, fitted_transformer = fit_transform_one_cached(
304 cloned_transformer, X, y, None,
305 message_clsname='Pipeline',
~/opt/anaconda3/lib/python3.8/site-packages/joblib/memory.py in __call__(self, *args, **kwargs)
350
351 def __call__(self, *args, **kwargs):
--> 352 return self.func(*args, **kwargs)
353
354 def call_and_shelve(self, *args, **kwargs):
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
752 with _print_elapsed_time(message_clsname, message):
753 if hasattr(transformer, 'fit_transform'):
--> 754 res = transformer.fit_transform(X, y, **fit_params)
755 else:
756 res = transformer.fit(X, y, **fit_params).transform(X)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
385 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
386 if hasattr(last_step, 'fit_transform'):
--> 387 return last_step.fit_transform(Xt, y, **fit_params_last_step)
388 else:
389 return last_step.fit(Xt, y,
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
978 sum of n_components (output dimension) over transformers.
979 """
--> 980 results = self._parallel_func(X, y, fit_params, _fit_transform_one)
981 if not results:
982 # All transformers are None
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _parallel_func(self, X, y, fit_params, func)
1000 transformers = list(self._iter())
1001
-> 1002 return Parallel(n_jobs=self.n_jobs)(delayed(func)(
1003 transformer, X, y, weight,
1004 message_clsname='FeatureUnion',
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__(self, iterable)
1042 self._iterating = self._original_iterator is not None
1043
-> 1044 while self.dispatch_one_batch(iterator):
1045 pass
1046
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
857 return False
858 else:
--> 859 self._dispatch(tasks)
860 return True
861
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in _dispatch(self, batch)
775 with self._lock:
776 job_idx = len(self._jobs)
--> 777 job = self._backend.apply_async(batch, callback=cb)
778 # A job can complete so quickly than its callback is
779 # called before we get here, causing self._jobs to
~/opt/anaconda3/lib/python3.8/site-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)
~/opt/anaconda3/lib/python3.8/site-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):
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__(self)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in <listcomp>(.0)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/fixes.py in __call__(self, *args, **kwargs)
220 def __call__(self, *args, **kwargs):
221 with config_context(**self.config):
--> 222 return self.function(*args, **kwargs)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
752 with _print_elapsed_time(message_clsname, message):
753 if hasattr(transformer, 'fit_transform'):
--> 754 res = transformer.fit_transform(X, y, **fit_params)
755 else:
756 res = transformer.fit(X, y, **fit_params).transform(X)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
385 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
386 if hasattr(last_step, 'fit_transform'):
--> 387 return last_step.fit_transform(Xt, y, **fit_params_last_step)
388 else:
389 return last_step.fit(Xt, y,
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in fit_transform(self, raw_documents, y)
1200 max_features = self.max_features
1201
-> 1202 vocabulary, X = self._count_vocab(raw_documents,
1203 self.fixed_vocabulary_)
1204
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in _count_vocab(self, raw_documents, fixed_vocab)
1112 for doc in raw_documents:
1113 feature_counter = {}
-> 1114 for feature in analyze(doc):
1115 try:
1116 feature_idx = vocabulary[feature]
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in _analyze(doc, analyzer, tokenizer, ngrams, preprocessor, decoder, stop_words)
102 else:
103 if preprocessor is not None:
--> 104 doc = preprocessor(doc)
105 if tokenizer is not None:
106 doc = tokenizer(doc)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in _preprocess(doc, accent_function, lower)
67 """
68 if lower:
---> 69 doc = doc.lower()
70 if accent_function is not None:
71 doc = accent_function(doc)
AttributeError: 'numpy.ndarray' object has no attribute 'lower'
The code is
# MODEL
from sklearn import tree
# Decision Tree
decision_tree = tree.DecisionTreeClassifier()
# define full pipeline --> preprocessing + model
full_pipeline = Pipeline(steps=[
('preprocess_pipeline', preprocess_pipeline),
('model', decision_tree)])
# fit on the complete pipeline
training = full_pipeline.fit(X, y) # <- this step returns the error
# metrics
score_test = \
round(training.score(X, y) * 100, 2)
print(f"\nTraining Accuracy: {score_test}")
I have also tried with .fit_transform but I get the same error.
I read this: AttributeError: 'numpy.ndarray' object has no attribute 'lower' fitting logistic model data but it seems that I am not passing X or y in the Decision tree like in that example, but maybe I am wrong.
Adding
# Defining the steps in the text pipeline
text_pipeline = Pipeline(steps=[
('text_transformer', TextTransformer()),
('cv', CountVectorizer(analyzer='word', ngram_range=(2, 2), lowercase=False))])
I get this new error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-159-289e1d466eb9> in <module>
10
11 # fit on the complete pipeline
---> 12 training = full_pipeline.fit(X, y)
13
14 # metrics
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
339 """
340 fit_params_steps = self._check_fit_params(**fit_params)
--> 341 Xt = self._fit(X, y, **fit_params_steps)
342 with _print_elapsed_time('Pipeline',
343 self._log_message(len(self.steps) - 1)):
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params_steps)
301 cloned_transformer = clone(transformer)
302 # Fit or load from cache the current transformer
--> 303 X, fitted_transformer = fit_transform_one_cached(
304 cloned_transformer, X, y, None,
305 message_clsname='Pipeline',
~/opt/anaconda3/lib/python3.8/site-packages/joblib/memory.py in __call__(self, *args, **kwargs)
350
351 def __call__(self, *args, **kwargs):
--> 352 return self.func(*args, **kwargs)
353
354 def call_and_shelve(self, *args, **kwargs):
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
752 with _print_elapsed_time(message_clsname, message):
753 if hasattr(transformer, 'fit_transform'):
--> 754 res = transformer.fit_transform(X, y, **fit_params)
755 else:
756 res = transformer.fit(X, y, **fit_params).transform(X)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
385 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
386 if hasattr(last_step, 'fit_transform'):
--> 387 return last_step.fit_transform(Xt, y, **fit_params_last_step)
388 else:
389 return last_step.fit(Xt, y,
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
978 sum of n_components (output dimension) over transformers.
979 """
--> 980 results = self._parallel_func(X, y, fit_params, _fit_transform_one)
981 if not results:
982 # All transformers are None
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _parallel_func(self, X, y, fit_params, func)
1000 transformers = list(self._iter())
1001
-> 1002 return Parallel(n_jobs=self.n_jobs)(delayed(func)(
1003 transformer, X, y, weight,
1004 message_clsname='FeatureUnion',
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__(self, iterable)
1042 self._iterating = self._original_iterator is not None
1043
-> 1044 while self.dispatch_one_batch(iterator):
1045 pass
1046
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
857 return False
858 else:
--> 859 self._dispatch(tasks)
860 return True
861
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in _dispatch(self, batch)
775 with self._lock:
776 job_idx = len(self._jobs)
--> 777 job = self._backend.apply_async(batch, callback=cb)
778 # A job can complete so quickly than its callback is
779 # called before we get here, causing self._jobs to
~/opt/anaconda3/lib/python3.8/site-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)
~/opt/anaconda3/lib/python3.8/site-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):
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in __call__(self)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/opt/anaconda3/lib/python3.8/site-packages/joblib/parallel.py in <listcomp>(.0)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/fixes.py in __call__(self, *args, **kwargs)
220 def __call__(self, *args, **kwargs):
221 with config_context(**self.config):
--> 222 return self.function(*args, **kwargs)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
752 with _print_elapsed_time(message_clsname, message):
753 if hasattr(transformer, 'fit_transform'):
--> 754 res = transformer.fit_transform(X, y, **fit_params)
755 else:
756 res = transformer.fit(X, y, **fit_params).transform(X)
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
385 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
386 if hasattr(last_step, 'fit_transform'):
--> 387 return last_step.fit_transform(Xt, y, **fit_params_last_step)
388 else:
389 return last_step.fit(Xt, y,
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in fit_transform(self, raw_documents, y)
1200 max_features = self.max_features
1201
-> 1202 vocabulary, X = self._count_vocab(raw_documents,
1203 self.fixed_vocabulary_)
1204
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in _count_vocab(self, raw_documents, fixed_vocab)
1112 for doc in raw_documents:
1113 feature_counter = {}
-> 1114 for feature in analyze(doc):
1115 try:
1116 feature_idx = vocabulary[feature]
~/opt/anaconda3/lib/python3.8/site-packages/sklearn/feature_extraction/text.py in _analyze(doc, analyzer, tokenizer, ngrams, preprocessor, decoder, stop_words)
104 doc = preprocessor(doc)
105 if tokenizer is not None:
--> 106 doc = tokenizer(doc)
107 if ngrams is not None:
108 if stop_words is not None:
TypeError: cannot use a string pattern on a bytes-like object
If I remove text_pipeline, the error does not occur, so it seems that something is going wrong because of the way to use countVectorizer.
An example of text is
an example
example number 1
this is another small example
I have other columns that are numerical and categorical.
Have you experienced a similar issue? If yes, how did you handle it?
A common error in text transformers of sklearn involves the shape of the data: unlike most other sklearn preprocessors, text transformers generally expect a one-dimensional input, and python's duck-typing causes weird errors from both arrays and strings being iterables.
Your TextTransformer.transform returns X[['Tweet']], which is 2-dimensional, and will cause problems with the subsequent CountVectorizer. (Converting to a numpy array with .values doesn't change the dimensionality problem, but there's also no compelling reason to do that conversion.) Returning X['Tweet'] instead should cure that problem.
I am using Python 3.7 in a Jupyter Notebook. I am creating classification models based on Jason Brownlee's ebook Machine Learning Mastery with Python. The code is essentially cut and pasted from the ebook into the Jupyter Notebook. The models work fine when I split the data but when I use k-fold cross validation it generates a Future warning message I'll cut and paste the code and message below. I entered error_score =np.nan and it didn't fix the problem but I don't know where the code should be entered. I would appreciate any advice but keep in mind that I am a novice. Thanks
# Logistic Regression Classification
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
df = pd.read_csv('Diabetes_Classification.csv')
array = df.values
X = array[:,0:8]
Y = array[:,8]
kfold = KFold(n_splits=10, random_state=7)
model = LogisticRegression(solver='liblinear')
error_score = np.nan
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
# Logistic Regression Classification
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
df = pd.read_csv('Diabetes_Classification.csv')
array = df.values
X = array[:,0:8]
Y = array[:,8]
kfold = KFold(n_splits=10, random_state=7)
model = LogisticRegression(solver='liblinear')
error_score = np.nan
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
/Users/roberthoyt/opt/anaconda3/lib/python3.7/site-
packages/sklearn/model_selection/_validation.py:530: 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)
ValueError Traceback (most recent call last)
<ipython-input-105-010e5612fd63> in <module>
11 model = LogisticRegression(solver='liblinear')
12 error_score = np.nan
---> 13 results = cross_val_score(model, X, Y, cv=kfold)
14 print(results.mean())
~/opt/anaconda3/lib/python3.7/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)
389 fit_params=fit_params,
390 pre_dispatch=pre_dispatch,
--> 391 error_score=error_score)
392 return cv_results['test_score']
393
~/opt/anaconda3/lib/python3.7/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)
230 return_times=True, return_estimator=return_estimator,
231 error_score=error_score)
--> 232 for train, test in cv.split(X, y, groups))
233
234 zipped_scores = list(zip(*scores))
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in __call__(self, iterable)
919 # remaining jobs.
920 self._iterating = False
--> 921 if self.dispatch_one_batch(iterator):
922 self._iterating = self._original_iterator is not None
923
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in dispatch_one_batch(self,
iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
~/opt/anaconda3/lib/python3.7/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
~/opt/anaconda3/lib/python3.7/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)
~/opt/anaconda3/lib/python3.7/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):
~/opt/anaconda3/lib/python3.7/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):
~/opt/anaconda3/lib/python3.7/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):
~/opt/anaconda3/lib/python3.7/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)
514 estimator.fit(X_train, **fit_params)
515 else:
--> 516 estimator.fit(X_train, y_train, **fit_params)
517
518 except Exception as e:
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/linear_model/logistic.py in fit(self, X, y,
sample_weight)
1531 X, y = check_X_y(X, y, accept_sparse='csr', dtype=_dtype, order="C",
1532 accept_large_sparse=solver != 'liblinear')
-> 1533 check_classification_targets(y)
1534 self.classes_ = np.unique(y)
1535 n_samples, n_features = X.shape
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/multiclass.py in
check_classification_targets(y)
167 if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
168 'multilabel-indicator', 'multilabel-sequences']:
--> 169 raise ValueError("Unknown label type: %r" % y_type)
170
171
ValueError: Unknown label type: 'continuous'
The problem is that your targets are continuous and you're doing a classification task. Make sure The column you're using a target is categorical. You may have to convert it to integer. All of this is reported in the traceback:
check_classification_targets(y)
167 if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
168 'multilabel-indicator', 'multilabel-sequences']:
--> 169 raise ValueError("Unknown label type: %r" % y_type)
Your target is not in the accepted targets. your target is continuous:
ValueError: Unknown label type: 'continuous'
Check if your target is an integer with df.dtypes and change it to integer if it isn't.
Y = array[:,8].astype(int)
That is assuming that you haven't made the mistake of making a classification task on continuous values. You can also check if all values represent 0s and 1s:
np.unique(array[:, 8])
I'm trying to run a Classification Tree on data about Visa applications (includes categories such as workplace, average pay, etc.) but I'm pulling the following error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-114-33e98dd52d68> in <module>
3 from sklearn.model_selection import cross_val_predict
4 clf = tree.DecisionTreeClassifier()
----> 5 y_pred = cross_val_predict(clf, x, y, cv=10)
6 cm = ConfusionMatrix(y, y_pred)
7 print(cm)
/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in cross_val_predict(estimator, X, y, groups, cv, n_jobs, verbose, fit_params, pre_dispatch, method)
775 prediction_blocks = parallel(delayed(_fit_and_predict)(
776 clone(estimator), X, y, train, test, verbose, fit_params, method)
--> 777 for train, test in cv.split(X, y, groups))
778
779 # Concatenate the predictions
/anaconda3/lib/python3.7/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
915 # remaining jobs.
916 self._iterating = False
--> 917 if self.dispatch_one_batch(iterator):
918 self._iterating = self._original_iterator is not None
919
/anaconda3/lib/python3.7/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
/anaconda3/lib/python3.7/site-packages/sklearn/externals/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
/anaconda3/lib/python3.7/site-packages/sklearn/externals/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)
/anaconda3/lib/python3.7/site-packages/sklearn/externals/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):
/anaconda3/lib/python3.7/site-packages/sklearn/externals/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):
/anaconda3/lib/python3.7/site-packages/sklearn/externals/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):
/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in _fit_and_predict(estimator, X, y, train, test, verbose, fit_params, method)
848 estimator.fit(X_train, **fit_params)
849 else:
--> 850 estimator.fit(X_train, y_train, **fit_params)
851 func = getattr(estimator, method)
852 predictions = func(X_test)
/anaconda3/lib/python3.7/site-packages/sklearn/tree/tree.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
799 sample_weight=sample_weight,
800 check_input=check_input,
--> 801 X_idx_sorted=X_idx_sorted)
802 return self
803
/anaconda3/lib/python3.7/site-packages/sklearn/tree/tree.py in fit(self, X, y, sample_weight, check_input, X_idx_sorted)
114 random_state = check_random_state(self.random_state)
115 if check_input:
--> 116 X = check_array(X, dtype=DTYPE, accept_sparse="csc")
117 y = check_array(y, ensure_2d=False, dtype=None)
118 if issparse(X):
/anaconda3/lib/python3.7/site-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
525 try:
526 warnings.simplefilter('error', ComplexWarning)
--> 527 array = np.asarray(array, dtype=dtype, order=order)
528 except ComplexWarning:
529 raise ValueError("Complex data not supported\n"
/anaconda3/lib/python3.7/site-packages/numpy/core/numeric.py in asarray(a, dtype, order)
499
500 """
--> 501 return array(a, dtype, copy=False, order=order)
502
503
TypeError: float() argument must be a string or a number, not 'Timestamp'
I've tried resetting the Kernel but I'm confused on what the error is telling me
The code I am trying to run is this:
from sklearn import tree
from pandas_ml import ConfusionMatrix
from sklearn.model_selection import cross_val_predict
clf = tree.DecisionTreeClassifier()
y_pred = cross_val_predict(clf, x, y, cv=10)
cm = ConfusionMatrix(y, y_pred)
print(cm)
cm.print_stats()
It should be producing the stats when ran correctly
I am newbie in programming and machine learning. I am doing an assignment on KNN and amazon fine food reviews but getting this error.
My code:
from sklearn.model_selection import train_test_split
Y = data['Score'].values
X_with_stop= data['Text_with_stop'].values
X_no_stop = data['New_Text'].values
X_with_stop_train, X_with_stop_test, y_train, y_test = train_test_split(X_with_stop, Y, test_size=0.33, shuffle=False)
print(X_with_stop_train.shape, y_train.shape,y_test.shape)
from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer()
bow_X_train_brute = vectorizer.fit_transform(X_with_stop_train)
bow_X_test_brute = vectorizer.transform(X_with_stop_test)
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import cross_val_score
from sklearn.metrics import accuracy_score
neighbors = list(range(3,99,2))
cv_scores = []
for k in neighbors:
knn = KNeighborsClassifier(n_neighbors=k,algorithm='brute')
scores = cross_val_score(knn, bow_X_train_brute, y_train, cv=10, scoring='accuracy')
cv_scores.append(scores.mean())
MSE = [1 - x for x in cv_scores]
# determining best k
optimal_k = neighbors[MSE.index(min(MSE))]
print ("The optimal number of neighbors is %d" % optimal_k)
# plot misclassification error vs k
plt.plot(neighbors, MSE)
plt.xlabel('Number of Neighbors K')
plt.ylabel('Misclassification Error')
plt.title("Plot for K vs Error for Brute force algorithm")
plt.show()
The output:
(413629,) (413629,) (203729,)
The error i am getting is as below:
MemoryError Traceback (most recent call last)
<ipython-input-17-f1ce8e46a2a3> in <module>()
43 for k in neighbors:
44 knn = KNeighborsClassifier(n_neighbors=k,algorithm='brute')
---> 45 scores = cross_val_score(knn, bow_X_train_brute, y_train, cv=10, scoring='accuracy')
46 cv_scores.append(scores.mean())
47
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch)
340 n_jobs=n_jobs, verbose=verbose,
341 fit_params=fit_params,
--> 342 pre_dispatch=pre_dispatch)
343 return cv_results['test_score']
344
C:\ProgramData\Anaconda3\lib\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)
204 fit_params, return_train_score=return_train_score,
205 return_times=True)
--> 206 for train, test in cv.split(X, y, groups))
207
208 if return_train_score:
C:\ProgramData\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:
C:\ProgramData\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
C:\ProgramData\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
C:\ProgramData\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)
C:\ProgramData\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):
C:\ProgramData\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):
C:\ProgramData\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):
C:\ProgramData\Anaconda3\lib\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, error_score)
486 fit_time = time.time() - start_time
487 # _score will return dict if is_multimetric is True
--> 488 test_scores = _score(estimator, X_test, y_test, scorer, is_multimetric)
489 score_time = time.time() - start_time - fit_time
490 if return_train_score:
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _score(estimator, X_test, y_test, scorer, is_multimetric)
521 """
522 if is_multimetric:
--> 523 return _multimetric_score(estimator, X_test, y_test, scorer)
524 else:
525 if y_test is None:
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _multimetric_score(estimator, X_test, y_test, scorers)
551 score = scorer(estimator, X_test)
552 else:
--> 553 score = scorer(estimator, X_test, y_test)
554
555 if hasattr(score, 'item'):
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\metrics\scorer.py in __call__(self, estimator, X, y_true, sample_weight)
99 super(_PredictScorer, self).__call__(estimator, X, y_true,
100 sample_weight=sample_weight)
--> 101 y_pred = estimator.predict(X)
102 if sample_weight is not None:
103 return self._sign * self._score_func(y_true, y_pred,
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\neighbors\classification.py in predict(self, X)
143 X = check_array(X, accept_sparse='csr')
144
--> 145 neigh_dist, neigh_ind = self.kneighbors(X)
146
147 classes_ = self.classes_
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\neighbors\base.py in kneighbors(self, X, n_neighbors, return_distance)
355 if self.effective_metric_ == 'euclidean':
356 dist = pairwise_distances(X, self._fit_X, 'euclidean',
--> 357 n_jobs=n_jobs, squared=True)
358 else:
359 dist = pairwise_distances(
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\metrics\pairwise.py in pairwise_distances(X, Y, metric, n_jobs, **kwds)
1245 func = partial(distance.cdist, metric=metric, **kwds)
1246
-> 1247 return _parallel_pairwise(X, Y, func, n_jobs, **kwds)
1248
1249
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\metrics\pairwise.py in _parallel_pairwise(X, Y, func, n_jobs, **kwds)
1088 if n_jobs == 1:
1089 # Special case to avoid picklability checks in delayed
-> 1090 return func(X, Y, **kwds)
1091
1092 # TODO: in some cases, backend='threading' may be appropriate
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\metrics\pairwise.py in euclidean_distances(X, Y, Y_norm_squared, squared, X_norm_squared)
244 YY = row_norms(Y, squared=True)[np.newaxis, :]
245
--> 246 distances = safe_sparse_dot(X, Y.T, dense_output=True)
247 distances *= -2
248 distances += XX
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\extmath.py in safe_sparse_dot(a, b, dense_output)
133 """
134 if issparse(a) or issparse(b):
--> 135 ret = a * b
136 if dense_output and hasattr(ret, "toarray"):
137 ret = ret.toarray()
C:\ProgramData\Anaconda3\lib\site-packages\scipy\sparse\base.py in __mul__(self, other)
477 if self.shape[1] != other.shape[0]:
478 raise ValueError('dimension mismatch')
--> 479 return self._mul_sparse_matrix(other)
480
481 # If it's a list or whatever, treat it like a matrix
C:\ProgramData\Anaconda3\lib\site-packages\scipy\sparse\compressed.py in _mul_sparse_matrix(self, other)
500 maxval=nnz)
501 indptr = np.asarray(indptr, dtype=idx_dtype)
--> 502 indices = np.empty(nnz, dtype=idx_dtype)
503 data = np.empty(nnz, dtype=upcast(self.dtype, other.dtype))
504
A MemoryError usually means that you ran out of RAM. And seeing the size of your dataset, I think it might be a plausible explanation.
To be sure, just look at your RAM usage while executing your code.
I am trying to find the best hyperparameters for my SVM using Grid Search. When doing it the following way:
from sklearn.model_selection import GridSearchCV
param_grid = {'coef0': [10, 5, 0.5, 0.001], 'C': [100, 50, 1, 0.001]}
poly_svm_search = SVC(kernel="poly", degree="2")
grid_search = GridSearchCV(poly_svm_search, param_grid, cv=5, scoring='f1')
grid_search.fit(train_data, train_labels)
I get this error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-72-dadf5782618c> in <module>
8
----> 9 grid_search.fit(train_data, train_labels)
~/.local/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
720 return results_container[0]
721
--> 722 self._run_search(evaluate_candidates)
723
724 results = results_container[0]
~/.local/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
1189 def _run_search(self, evaluate_candidates):
1190 """Search all candidates in param_grid"""
-> 1191 evaluate_candidates(ParameterGrid(self.param_grid))
1192
1193
~/.local/lib/python3.6/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params)
709 for parameters, (train, test)
710 in product(candidate_params,
--> 711 cv.split(X, y, groups)))
712
713 all_candidate_params.extend(candidate_params)
~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
981 # remaining jobs.
982 self._iterating = False
--> 983 if self.dispatch_one_batch(iterator):
984 self._iterating = self._original_iterator is not None
985
~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
823 return False
824 else:
--> 825 self._dispatch(tasks)
826 return True
827
~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
780 with self._lock:
781 job_idx = len(self._jobs)
--> 782 job = self._backend.apply_async(batch, callback=cb)
783 # A job can complete so quickly than its callback is
784 # called before we get here, causing self._jobs to
~/.local/lib/python3.6/site-packages/sklearn/externals/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)
~/.local/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
543 # Don't delay the application, to avoid keeping the input
544 # arguments in memory
--> 545 self.results = batch()
546
547 def get(self):
~/.local/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):
~/.local/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):
~/.local/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:
~/.local/lib/python3.6/site-packages/sklearn/svm/base.py in fit(self, X, y, sample_weight)
210
211 seed = rnd.randint(np.iinfo('i').max)
--> 212 fit(X, y, sample_weight, solver_type, kernel, random_seed=seed)
213 # see comment on the other call to np.iinfo in this file
214
~/.local/lib/python3.6/site-packages/sklearn/svm/base.py in _sparse_fit(self, X, y, sample_weight, solver_type, kernel, random_seed)
291 sample_weight, self.nu, self.cache_size, self.epsilon,
292 int(self.shrinking), int(self.probability), self.max_iter,
--> 293 random_seed)
294
295 self._warn_from_fit_status()
sklearn/svm/libsvm_sparse.pyx in sklearn.svm.libsvm_sparse.libsvm_sparse_train()
TypeError: an integer is required
My train_labels variable contains a list of booleans, so I have a binary classification problem. train_data is a <class'scipy.sparse.csr.csr_matrix'>, basically containing all scaled and One-Hot encoded features.
What did I do wrong? It's hard for me to track down what the issue is here. I thank you for any help in advance ;).
When you initialize the SVC using this line:
poly_svm_search = SVC(kernel="poly", degree="2")
You are supplying degree param with a string, due to inverted commas around it. But according to the documentation, degree takes an integer as value.
degree : int, optional (default=3) Degree of the polynomial kernel
function (‘poly’). Ignored by all other kernels.
So you need to do this:
poly_svm_search = SVC(kernel="poly", degree=2)
Notice how I did not use inverted commas here.