As part of my thesis work, I am working on an anomaly detection workflow. It utilizes SGDOneClassSVM of Scikit-Learn due to the high amount of data (~ 265k records and 45 features). I am successful with implementing the model and finetuning the hyperparamaters.
Using a number of libraries, data treated by StandardScaler() is utilized first to find principal components with IncrementalPCA(). Then SGDOneClassSVM() model was built and good result was gained:
model = SGDOneClassSVM(nu=0.1810486, shuffle=True, fit_intercept=True, random_state=42, tol=1e-3)
model.fit(X_train_pca, y_train)
y_pred = model.predict(X_valid_pca)
cm = confusion_matrix(y_valid, y_pred, labels=[-1, 1])
print(cm)
print(f1_score(y_valid, y_pred))
[[ 497 13]
[ 15 35035]]
0.9996005592170961
The validation curve of the above model
Having ploted the calibration curve I realized there is a room for further improvement:
Calibration curve of the above model
I tried to calibrate the model in different ways, but none worked.
1,
final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv='prefit')
prob_iso = final_model_isotonic.decision_function(X_calib)
X_plot, y_iso = calibration_curve(y_calib, prob_iso, n_bins = 10, normalize = True)
plt.figure(figsize=(12, 9))
plt.plot([0, 1], [0, 1], color='blue', linestyle = '--', label = 'Reference')
plt.plot(y_iso, X_plot, color='green', marker = '.', label = 'Final Model - Isotonic Calibration')
leg = plt.legend(loc = 'upper left')
plt.xlabel('Average Predicted Probability in each bin')
plt.ylabel('Ratio of positives')
plt.show()
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_29952/1350381664.py in <module>
1 final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv='prefit')
----> 2 prob_iso = final_model_isotonic.decision_function(X_calib)
3
4 X_plot, y_iso = calibration_curve(y_calib, prob_iso, n_bins = 10, normalize = True)
5
AttributeError: 'CalibratedClassifierCV' object has no attribute 'decision_function'
2, Here - what I can see - is that is says fit has not happened. Based on the first code block it actually has happened.
final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv='prefit')
final_model_isotonic.fit(X_valid_pca, y_valid)
prob = final_model_isotonic.decision_function(X_calib_pca)
# Creating Calibration Curve
x, y = calibration_curve(y_calib, prob, n_bins = 10, normalize = True)
# Plot calibration curve
plt.figure(figsize=(13, 7))
# Plot perfectly calibrated
plt.plot([0, 1], [0, 1], color='blue', linestyle = '--', label = 'Reference')
# Plot model's calibration curve
plt.plot(y, x, color='green', marker = '.', label = 'Final Model')
leg = plt.legend(loc = 'upper left')
plt.xlabel('Average Predicted Probability in each bin')
plt.ylabel('Ratio of positives')
plt.show()
---------------------------------------------------------------------------
NotFittedError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_29952/4100438610.py in <module>
1 final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv='prefit')
----> 2 final_model_isotonic.fit(X_valid_pca, y_valid)
3 prob = final_model_isotonic.decision_function(X_calib_pca)
4
5 # Creating Calibration Curve
~\Anaconda3\lib\site-packages\sklearn\calibration.py in fit(self, X, y, sample_weight)
281 if self.cv == "prefit":
282 # `classes_` should be consistent with that of base_estimator
--> 283 check_is_fitted(self.base_estimator, attributes=["classes_"])
284 self.classes_ = self.base_estimator.classes_
285
~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_is_fitted(estimator, attributes, msg, all_or_any)
1220
1221 if not fitted:
-> 1222 raise NotFittedError(msg % {"name": type(estimator).__name__})
1223
1224
NotFittedError: This SGDOneClassSVM instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator.
3,
final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv=3)
final_model_isotonic.fit(X_valid_pca)
y_hat_calib = final_model_isotonic.predict(X_calib_pca)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_29952/3807651700.py in <module>
1 final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv=3)
----> 2 final_model_isotonic.fit(X_valid_pca)
3 y_hat_calib = final_model_isotonic.predict(X_calib_pca)
4
5
TypeError: fit() missing 1 required positional argument: 'y'
4,
final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv=3)
final_model_isotonic.fit(X_valid_pca, y_valid)
y_hat_calib = final_model_isotonic.predict(X_calib_pca)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_29952/2453888579.py in <module>
1 final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv=3)
----> 2 final_model_isotonic.fit(X_valid_pca, y_valid)
3 y_hat_calib = final_model_isotonic.predict(X_calib_pca)
4
5
~\Anaconda3\lib\site-packages\sklearn\calibration.py in fit(self, X, y, sample_weight)
339 parallel = Parallel(n_jobs=self.n_jobs)
340
--> 341 self.calibrated_classifiers_ = parallel(
342 delayed(_fit_classifier_calibrator_pair)(
343 clone(base_estimator),
~\Anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
1041 # remaining jobs.
1042 self._iterating = False
-> 1043 if self.dispatch_one_batch(iterator):
1044 self._iterating = self._original_iterator is not None
1045
~\Anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
859 return False
860 else:
--> 861 self._dispatch(tasks)
862 return True
863
~\Anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
777 with self._lock:
778 job_idx = len(self._jobs)
--> 779 job = self._backend.apply_async(batch, callback=cb)
780 # A job can complete so quickly than its callback is
781 # called before we get here, causing self._jobs to
~\Anaconda3\lib\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)
~\Anaconda3\lib\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):
~\Anaconda3\lib\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
~\Anaconda3\lib\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
~\Anaconda3\lib\site-packages\sklearn\utils\fixes.py in __call__(self, *args, **kwargs)
214 def __call__(self, *args, **kwargs):
215 with config_context(**self.config):
--> 216 return self.function(*args, **kwargs)
217
218
~\Anaconda3\lib\site-packages\sklearn\calibration.py in _fit_classifier_calibrator_pair(estimator, X, y, train, test, supports_sw, method, classes, sample_weight)
515 predictions = _compute_predictions(pred_method, method_name, X_test, n_classes)
516
--> 517 calibrated_classifier = _fit_calibrator(
518 estimator, predictions, y_test, classes, method, sample_weight=sw_test
519 )
~\Anaconda3\lib\site-packages\sklearn\calibration.py in _fit_calibrator(clf, predictions, y, classes, method, sample_weight)
623 Y = label_binarize(y, classes=classes)
624 label_encoder = LabelEncoder().fit(classes)
--> 625 pos_class_indices = label_encoder.transform(clf.classes_)
626 calibrators = []
627 for class_idx, this_pred in zip(pos_class_indices, predictions.T):
AttributeError: 'SGDOneClassSVM' object has no attribute 'classes_'
5,
X = np.concatenate([X_train_pca, X_valid_pca])
y = np.concatenate([y_train, y_valid])
valid_fold = [-1 for _ in range(X_train.shape[0])] + [0 for _ in range(X_valid.shape[0])]
ps = PredefinedSplit(valid_fold)
final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv=ps)
final_model_isotonic.fit(X, y)
y_hat_calib = final_model_isotonic.predict(X_calib_pca)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_29952/2567788326.py in <module>
5
6 final_model_isotonic = CalibratedClassifierCV(model, method="isotonic", cv=ps)
----> 7 final_model_isotonic.fit(X, y)
8 y_hat_calib = final_model_isotonic.predict(X_calib_pca)
9
~\Anaconda3\lib\site-packages\sklearn\calibration.py in fit(self, X, y, sample_weight)
339 parallel = Parallel(n_jobs=self.n_jobs)
340
--> 341 self.calibrated_classifiers_ = parallel(
342 delayed(_fit_classifier_calibrator_pair)(
343 clone(base_estimator),
~\Anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
1041 # remaining jobs.
1042 self._iterating = False
-> 1043 if self.dispatch_one_batch(iterator):
1044 self._iterating = self._original_iterator is not None
1045
~\Anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
859 return False
860 else:
--> 861 self._dispatch(tasks)
862 return True
863
~\Anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch)
777 with self._lock:
778 job_idx = len(self._jobs)
--> 779 job = self._backend.apply_async(batch, callback=cb)
780 # A job can complete so quickly than its callback is
781 # called before we get here, causing self._jobs to
~\Anaconda3\lib\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)
~\Anaconda3\lib\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):
~\Anaconda3\lib\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
~\Anaconda3\lib\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
~\Anaconda3\lib\site-packages\sklearn\utils\fixes.py in __call__(self, *args, **kwargs)
214 def __call__(self, *args, **kwargs):
215 with config_context(**self.config):
--> 216 return self.function(*args, **kwargs)
217
218
~\Anaconda3\lib\site-packages\sklearn\calibration.py in _fit_classifier_calibrator_pair(estimator, X, y, train, test, supports_sw, method, classes, sample_weight)
515 predictions = _compute_predictions(pred_method, method_name, X_test, n_classes)
516
--> 517 calibrated_classifier = _fit_calibrator(
518 estimator, predictions, y_test, classes, method, sample_weight=sw_test
519 )
~\Anaconda3\lib\site-packages\sklearn\calibration.py in _fit_calibrator(clf, predictions, y, classes, method, sample_weight)
623 Y = label_binarize(y, classes=classes)
624 label_encoder = LabelEncoder().fit(classes)
--> 625 pos_class_indices = label_encoder.transform(clf.classes_)
626 calibrators = []
627 for class_idx, this_pred in zip(pos_class_indices, predictions.T):
AttributeError: 'SGDOneClassSVM' object has no attribute 'classes_'
It would be kind if you could advise me. I planned to share the whole workflow and the data, too, but the data is large e.g. to make available on GitHub. I am sorry.
Related
I am trying to train a StackingClassifier in Sklearn, but I keep running into this error where the fit method seems to be complaining about me having passed it numpy arrays. To my knowledge, this is how all the fit methods in sklearn are supposed to work. I read and followed the example from the documentation and expanded on it to include a more complex and comprehensive pipeline that would process categorical, ordinal, scalar, and text data.
Sorry in advance for the lengthy code sample, but I felt it was necessary to provide a complete reproducible example. Simply breaking down the pipeline into its constituent estimators and test those individually did not raise any exceptions, so I figure that the error somehow comes from the gestalt estimator.
Select Features
categorical_data = [
"race",
"gender",
"admission_type_id",
"discharge_disposition_id",
"admission_source_id",
"insulin",
"diabetesMed",
"change",
"payer_code",
"A1Cresult",
"metformin",
"repaglinide",
"nateglinide",
"chlorpropamide",
"glimepiride",
"glipizide",
"glyburide",
"tolbutamide",
"pioglitazone",
"rosiglitazone",
"acarbose",
"miglitol",
"tolazamide",
"glyburide.metformin",
"glipizide.metformin",
]
ordinal_data = [
"age"
]
scalar_data = [
"num_medications",
"time_in_hospital",
"num_lab_procedures",
"num_procedures",
"number_outpatient",
"number_emergency",
"number_inpatient",
"number_diagnoses",
]
text_data = [
"diag_1_desc",
"diag_2_desc",
"diag_3_desc"
]
Create Column Transformers
impute_trans = compose.make_column_transformer(
(
impute.SimpleImputer(
strategy="constant",
fill_value="missing"
),
categorical_data
)
)
encode_trans = compose.make_column_transformer(
(
preprocessing.OneHotEncoder(
sparse=False,
handle_unknown="ignore"
),
categorical_data
),
(
preprocessing.OrdinalEncoder(),
ordinal_data
)
)
scalar_trans = compose.make_column_transformer(
(preprocessing.StandardScaler(), scalar_data),
)
text_trans = compose.make_column_transformer(
(TfidfVectorizer(ngram_range=(1,2)), "diag_1_desc"),
(TfidfVectorizer(ngram_range=(1,2)), "diag_2_desc"),
(TfidfVectorizer(ngram_range=(1,2)), "diag_3_desc"),
)
Create Estimators
cat_pre_pipe = make_pipeline(impute_trans, encode_trans)
logreg = LogisticRegression(
solver = "saga",
penalty="elasticnet",
l1_ratio=0.5,
max_iter=1000
)
text_pipe = make_pipeline(text_trans, logreg)
scalar_pipe = make_pipeline(scalar_trans, logreg)
cat_pipe = make_pipeline(cat_pre_pipe, logreg)
estimators = [
("cat", cat_pipe),
("text", text_pipe),
("scalar", scalar_pipe)
]
Create Stacking Classifier
stack_clf = StackingClassifier(
estimators=estimators,
final_estimator=logreg
)
diabetes_data = pd.read_csv("8k_diabetes.csv", delimiter=',')
x_train, x_test, y_train, y_test = train_test_split(
pd.concat([
preprocess_dataframe(diabetes_data[text_data]),
diabetes_data[categorical_data + scalar_data]
], axis=1),
diabetes_data["readmitted"].astype(int)
)
stack_clf.fit(x_train, y_train)
Complete Stack Trace
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/utils/__init__.py:409, in _get_column_indices(X, key)
408 try:
--> 409 all_columns = X.columns
410 except AttributeError:
AttributeError: 'numpy.ndarray' object has no attribute 'columns'
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
Input In [19], in <cell line: 1>()
----> 1 stack_clf.fit(x_train, y_train)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/ensemble/_stacking.py:488, in StackingClassifier.fit(self, X, y, sample_weight)
486 self._le = LabelEncoder().fit(y)
487 self.classes_ = self._le.classes_
--> 488 return super().fit(X, self._le.transform(y), sample_weight)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/ensemble/_stacking.py:158, in _BaseStacking.fit(self, X, y, sample_weight)
153 stack_method = [self.stack_method] * len(all_estimators)
155 # Fit the base estimators on the whole training data. Those
156 # base estimators will be used in transform, predict, and
157 # predict_proba. They are exposed publicly.
--> 158 self.estimators_ = Parallel(n_jobs=self.n_jobs)(
159 delayed(_fit_single_estimator)(clone(est), X, y, sample_weight)
160 for est in all_estimators
161 if est != "drop"
162 )
164 self.named_estimators_ = Bunch()
165 est_fitted_idx = 0
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/parallel.py:1043, in Parallel.__call__(self, iterable)
1034 try:
1035 # Only set self._iterating to True if at least a batch
1036 # was dispatched. In particular this covers the edge
(...)
1040 # was very quick and its callback already dispatched all the
1041 # remaining jobs.
1042 self._iterating = False
-> 1043 if self.dispatch_one_batch(iterator):
1044 self._iterating = self._original_iterator is not None
1046 while self.dispatch_one_batch(iterator):
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/parallel.py:861, in Parallel.dispatch_one_batch(self, iterator)
859 return False
860 else:
--> 861 self._dispatch(tasks)
862 return True
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/parallel.py:779, in Parallel._dispatch(self, batch)
777 with self._lock:
778 job_idx = len(self._jobs)
--> 779 job = self._backend.apply_async(batch, callback=cb)
780 # A job can complete so quickly than its callback is
781 # called before we get here, causing self._jobs to
782 # grow. To ensure correct results ordering, .insert is
783 # used (rather than .append) in the following line
784 self._jobs.insert(job_idx, job)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/_parallel_backends.py:208, in SequentialBackend.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)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/_parallel_backends.py:572, in ImmediateResult.__init__(self, batch)
569 def __init__(self, batch):
570 # Don't delay the application, to avoid keeping the input
571 # arguments in memory
--> 572 self.results = batch()
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/parallel.py:262, in BatchedCalls.__call__(self)
258 def __call__(self):
259 # Set the default nested backend to self._backend but do not set the
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]
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/joblib/parallel.py:262, in <listcomp>(.0)
258 def __call__(self):
259 # Set the default nested backend to self._backend but do not set the
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]
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/utils/fixes.py:216, in _FuncWrapper.__call__(self, *args, **kwargs)
214 def __call__(self, *args, **kwargs):
215 with config_context(**self.config):
--> 216 return self.function(*args, **kwargs)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/ensemble/_base.py:42, in _fit_single_estimator(estimator, X, y, sample_weight, message_clsname, message)
40 else:
41 with _print_elapsed_time(message_clsname, message):
---> 42 estimator.fit(X, y)
43 return estimator
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/pipeline.py:390, in Pipeline.fit(self, X, y, **fit_params)
364 """Fit the model.
365
366 Fit all the transformers one after the other and transform the
(...)
387 Pipeline with fitted steps.
388 """
389 fit_params_steps = self._check_fit_params(**fit_params)
--> 390 Xt = self._fit(X, y, **fit_params_steps)
391 with _print_elapsed_time("Pipeline", self._log_message(len(self.steps) - 1)):
392 if self._final_estimator != "passthrough":
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/pipeline.py:348, in Pipeline._fit(self, X, y, **fit_params_steps)
346 cloned_transformer = clone(transformer)
347 # Fit or load from cache the current transformer
--> 348 X, fitted_transformer = fit_transform_one_cached(
349 cloned_transformer,
350 X,
351 y,
352 None,
353 message_clsname="Pipeline",
354 message=self._log_message(step_idx),
355 **fit_params_steps[name],
356 )
357 # Replace the transformer of the step with the fitted
358 # transformer. This is necessary when loading the transformer
359 # from the cache.
360 self.steps[step_idx] = (name, fitted_transformer)
File ~/anaconda3/envs/assignment2/lib/python3.8/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/assignment2/lib/python3.8/site-packages/sklearn/pipeline.py:893, in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
891 with _print_elapsed_time(message_clsname, message):
892 if hasattr(transformer, "fit_transform"):
--> 893 res = transformer.fit_transform(X, y, **fit_params)
894 else:
895 res = transformer.fit(X, y, **fit_params).transform(X)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/pipeline.py:434, in Pipeline.fit_transform(self, X, y, **fit_params)
432 fit_params_last_step = fit_params_steps[self.steps[-1][0]]
433 if hasattr(last_step, "fit_transform"):
--> 434 return last_step.fit_transform(Xt, y, **fit_params_last_step)
435 else:
436 return last_step.fit(Xt, y, **fit_params_last_step).transform(Xt)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py:672, in ColumnTransformer.fit_transform(self, X, y)
670 self._check_n_features(X, reset=True)
671 self._validate_transformers()
--> 672 self._validate_column_callables(X)
673 self._validate_remainder(X)
675 result = self._fit_transform(X, y, _fit_transform_one)
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py:352, in ColumnTransformer._validate_column_callables(self, X)
350 columns = columns(X)
351 all_columns.append(columns)
--> 352 transformer_to_input_indices[name] = _get_column_indices(X, columns)
354 self._columns = all_columns
355 self._transformer_to_input_indices = transformer_to_input_indices
File ~/anaconda3/envs/assignment2/lib/python3.8/site-packages/sklearn/utils/__init__.py:411, in _get_column_indices(X, key)
409 all_columns = X.columns
410 except AttributeError:
--> 411 raise ValueError(
412 "Specifying the columns using strings is only "
413 "supported for pandas DataFrames"
414 )
415 if isinstance(key, str):
416 columns = [key]
ValueError: Specifying the columns using strings is only supported for pandas DataFrames
Full Pipeline Diagram
Your categorical pipeline chains two column transformers together. After the first one, the output is a numpy array, but then the second one cannot select transformers by column name as you've requested. Notice the final error message is more informative here, ValueError: Specifying the columns using strings is only supported for pandas DataFrames.
I'd suggest using one column transformer with separate pipelines instead of one pipeline with multiple columntransformers for this reason.
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'm trying to use gridsearchCV to search over specified parameters scoring with neg log loss:
grid = GridSearchCV(spec_pipeline, param_grid = spec_params, scoring = 'neg_log_loss', cv = logo, verbose = 10)
grid.fit(X, y_true, groups = names)
ValueError: y_true contains only one label (1.0). Please provide the true labels explicitly through the labels argument.
The same code but scoring with accuracy works fine. I found that for log loss we need to specify the labels, which works fine when using sklearn.metrics:
y_labels = np.unique(y_true)
y_labels
array([0., 1., 2.])
metrics.log_loss(y_true, y_pred, labels = y_labels )
So I tried:
grid.fit(order_inner_x, y_inner, groups = names_inner, labels = y_labels)
ValueError: not enough values to unpack (expected 2, got 1)
I've tried quite a few variations of the above and also creating my own scorer with:
LogLoss = make_scorer(log_loss, greater_is_better=False, needs_proba=True)
But everything I try comes down to one of the two above errors. Obviously I'm missing something, so any help much appreciated.
Update:
Made a small mistake in the above - this is a three class problem, not a binary problem as I first implied.
I've tried Ben's suggestion (thanks!):
LogLoss = metrics.make_scorer(metrics.log_loss, greater_is_better=False, needs_proba=True, labels=[0, 1, 2])
grid = GridSearchCV(spec_pipeline, param_grid = spec_params, scoring = LogLoss, cv = logo, verbose = 10)
grid.fit(order_inner_x, y_inner, groups=names_inner)
I'm getting a different error, so hopefully one step closer, here's the full traceback:
ValueError Traceback (most recent call last)
<ipython-input-164-43d9f1633dc9> in <module>
2
3 grid = GridSearchCV(spec_pipeline, param_grid = spec_params, scoring = LogLoss, cv = logo, verbose = 10)
----> 4 grid.fit(order_inner_x, y_inner, groups=names_inner)
~/anaconda3/lib/python3.7/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]
~/anaconda3/lib/python3.7/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
~/anaconda3/lib/python3.7/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)
~/anaconda3/lib/python3.7/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
918 self._iterating = self._original_iterator is not None
919
--> 920 while self.dispatch_one_batch(iterator):
921 pass
922
~/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_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)
566 fit_time = time.time() - start_time
567 # _score will return dict if is_multimetric is True
--> 568 test_scores = _score(estimator, X_test, y_test, scorer, is_multimetric)
569 score_time = time.time() - start_time - fit_time
570 if return_train_score:
~/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in _score(estimator, X_test, y_test, scorer, is_multimetric)
603 """
604 if is_multimetric:
--> 605 return _multimetric_score(estimator, X_test, y_test, scorer)
606 else:
607 if y_test is None:
~/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in _multimetric_score(estimator, X_test, y_test, scorers)
633 score = scorer(estimator, X_test)
634 else:
--> 635 score = scorer(estimator, X_test, y_test)
636
637 if hasattr(score, 'item'):
~/anaconda3/lib/python3.7/site-packages/sklearn/metrics/scorer.py in __call__(self, clf, X, y, sample_weight)
133 ' but need classifier with two'
134 ' classes for {} scoring'.format(
--> 135 y_pred.shape, self._score_func.__name__))
136 if sample_weight is not None:
137 return self._sign * self._score_func(y, y_pred,
ValueError: got predict_proba of shape (200, 3), but need classifier with two classes for log_loss scoring
You're most of the way there: you need to provide the labels to your metric. In this attempt:
grid.fit(order_inner_x, y_inner, groups = names_inner, labels = y_labels)
you pass the labels, but to the grid search's fit method rather than the scoring parameter itself.
make_scorer allows other keyword arguments to be passed to the metric function, so this should work:
LogLoss = make_scorer(log_loss, greater_is_better=False, needs_proba=True, labels=[0, 1])
grid = GridSearchCV(spec_pipeline, param_grid = spec_params, scoring = LogLoss, cv = logo, verbose = 10)
grid.fit(X, y_true, groups = names)
I am learning RandomizedSearchCV with a toy example. Suppose that I want to build a linear model y = ax + b. I wrote a custom sklearn estimator that looks like the following:
import numpy as np
# import the base estimator
from sklearn.base import BaseEstimator, RegressorMixin
class testEstimator(BaseEstimator,RegressorMixin):
def __init__(self, alpha=1, beta=0):
self.alpha = alpha
self.beta = beta
def fit(self, X, y=None):
mu = np.ones((len(X)))
for ii in range(len(X)):
mu[ii] = self.alpha*X[ii] + self.beta
self.mu_ = mu
return self
def predict(self, X):
try:
getattr(self,"mu_")
except:
raise RuntimeError("You must train classifer before predicting data!")
return self.mu_
def score(self, X, y):
print("y: ", y)
print("mu: ", self.mu_)
return np.dot(y - self.predict(X), y - self.predict(X))/len(X)
Then, I need to test this.
# temp estimator
tempEs = testEstimator()
# temp params grid
params_grid_temp = {'alpha': [0,1,2,3,4,5,6], 'beta': [0,1,2,3,4]}
# test randomizedSearchCV
temp = RandomizedSearchCV(tempEs, params_grid_temp)
# define X,y
X = range(10)
y = np.dot(2, range(10)) + 4
# fit model
temp.fit(X,y)
However, I got the error
ValueError Traceback (most recent call last)
<ipython-input-8-72a46fdf9098> in <module>
9 y = np.dot(2, range(10)) + 4
10 # fit model
---> 11 temp.fit(X,y)
~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
71 FutureWarning)
72 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 73 return f(**kwargs)
74 return inner_f
75
~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
734 return results
735
--> 736 self._run_search(evaluate_candidates)
737
738 # For multi-metric evaluation, store the best_index_, best_params_ and
~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
1527 def _run_search(self, evaluate_candidates):
1528 """Search n_iter candidates from param_distributions"""
-> 1529 evaluate_candidates(ParameterSampler(
1530 self.param_distributions, self.n_iter,
1531 random_state=self.random_state))
~\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params)
706 n_splits, n_candidates, n_candidates * n_splits))
707
--> 708 out = parallel(delayed(_fit_and_score)(clone(base_estimator),
709 X, y,
710 train=train, test=test,
~\Anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
1027 # remaining jobs.
1028 self._iterating = False
-> 1029 if self.dispatch_one_batch(iterator):
1030 self._iterating = self._original_iterator is not None
1031
~\Anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
845 return False
846 else:
--> 847 self._dispatch(tasks)
848 return True
849
~\Anaconda3\lib\site-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
~\Anaconda3\lib\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)
~\Anaconda3\lib\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):
~\Anaconda3\lib\site-packages\joblib\parallel.py in __call__(self)
250 # change the default number of processes to -1
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
~\Anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0)
250 # change the default number of processes to -1
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
~\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, return_estimator, error_score)
558 else:
559 fit_time = time.time() - start_time
--> 560 test_scores = _score(estimator, X_test, y_test, scorer)
561 score_time = time.time() - start_time - fit_time
562 if return_train_score:
~\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _score(estimator, X_test, y_test, scorer)
605 scores = scorer(estimator, X_test)
606 else:
--> 607 scores = scorer(estimator, X_test, y_test)
608
609 error_msg = ("scoring must return a number, got %s (%s) "
~\Anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in __call__(self, estimator, *args, **kwargs)
88 *args, **kwargs)
89 else:
---> 90 score = scorer(estimator, *args, **kwargs)
91 scores[name] = score
92 return scores
~\Anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in _passthrough_scorer(estimator, *args, **kwargs)
370 def _passthrough_scorer(estimator, *args, **kwargs):
371 """Function that wraps estimator.score"""
--> 372 return estimator.score(*args, **kwargs)
373
374
<ipython-input-7-0c2138d9bf96> in score(self, X, y)
20 print("y: ", y)
21 print("mu: ", self.mu_)
---> 22 return np.dot(y - self.predict(X), y - self.predict(X))/len(X)
ValueError: operands could not be broadcast together with shapes (2,) (8,)
I figured out (2,) means the size of y and (8,) means the size of self.mu_. How does this happen? They are supposed to be 10.
Okay, I found the problem. Your predict method is totally wrong. It must return predicted value instead of returning mu_.
def predict(self, X):
return self.alpha*X + self.beta
That's it. You can also optimize code in your fit method
Python sci-kit learn KNN Grid Search Cross Validation error
I am trying to recreated KNN model for prediction of car destination.
https://github.com/carlosbkm/car-destination-prediction
The code is not working at Grid search cross validation here:
https://github.com/carlosbkm/car-destination-prediction/blob/master/k-nearest-model.ipynb
At first geodash was not working so I switched it to geodash2 and there was no problem.
When I try to fit the model I get.
TypeError: unsupported operand type(s) for /: 'str' and 'int'
When I try to fit X and y for Grid Search Cross Validation I get an error.
The problem is coming from
def cv_optimize(clf, parameters, X, y, n_jobs=1, n_folds=5, score_func=None):
if score_func:
gs = GridSearchCV(clf, param_grid=parameters, cv=n_folds, n_jobs=n_jobs, scoring=score_func)
else:
gs = GridSearchCV(clf, param_grid=parameters, n_jobs=n_jobs, cv=n_folds)
gs.fit(X, y)
print ("BEST", gs.best_params_, gs.best_score_, gs.cv_results_)
best = gs.best_estimator_
return best
I can not fit the model to X and y:
gs.fit(X, y)
I tried to make X and y into floats but nothing changed
When I execute this:
# Create a k-Nearest Neighbors Regression estimator
knn_estimator = KNeighborsRegressor()
#knn_parameters = {"n_neighbors": [1,2,5,10,20,50,100]}
knn_parameters = {"n_neighbors": [1,2,5]}
knn_best = cv_optimize(knn_estimator, knn_parameters, X_train, y_train, score_func='neg_mean_squared_error')
I get:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-124-34b56429c6b5> in <module>()
4 #knn_parameters = {"n_neighbors": [1,2,5,10,20,50,100]}
5 knn_parameters = {"n_neighbors": [1,2,5]}
----> 6 knn_best = cv_optimize(knn_estimator, knn_parameters, X_train, y_train, score_func='neg_mean_squared_error')
<ipython-input-116-1a00f84f1047> in cv_optimize(clf, parameters, X, y, n_jobs, n_folds, score_func)
6 else:
7 gs = GridSearchCV(clf, param_grid=parameters, n_jobs=n_jobs, cv=n_folds)
----> 8 gs.fit(X, y)
9 print ("BEST", gs.best_params_, gs.best_score_, gs.cv_results_)
10 best = gs.best_estimator_
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups)
943 train/test set.
944 """
--> 945 return self._fit(X, y, groups, ParameterGrid(self.param_grid))
946
947
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _fit(self, X, y, groups, parameter_iterable)
562 return_times=True, return_parameters=True,
563 error_score=self.error_score)
--> 564 for parameters in parameter_iterable
565 for train, test in cv_iter)
566
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
756 # was dispatched. In particular this covers the edge
757 # case of Parallel used with an exhausted iterator.
--> 758 while self.dispatch_one_batch(iterator):
759 self._iterating = True
760 else:
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
606 return False
607 else:
--> 608 self._dispatch(tasks)
609 return True
610
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
569 dispatch_timestamp = time.time()
570 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571 job = self._backend.apply_async(batch, callback=cb)
572 self._jobs.append(job)
573
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
107 def apply_async(self, func, callback=None):
108 """Schedule a func to be run"""
--> 109 result = ImmediateResult(func)
110 if callback:
111 callback(result)
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
324 # Don't delay the application, to avoid keeping the input
325 # arguments in memory
--> 326 self.results = batch()
327
328 def get(self):
~/anaconda3/envs/datascience/lib/python3.6/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/envs/datascience/lib/python3.6/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/envs/datascience/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, error_score)
258 else:
259 fit_time = time.time() - start_time
--> 260 test_score = _score(estimator, X_test, y_test, scorer)
261 score_time = time.time() - start_time - fit_time
262 if return_train_score:
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _score(estimator, X_test, y_test, scorer)
286 score = scorer(estimator, X_test)
287 else:
--> 288 score = scorer(estimator, X_test, y_test)
289 if hasattr(score, 'item'):
290 try:
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/metrics/scorer.py in __call__(self, estimator, X, y_true, sample_weight)
89 super(_PredictScorer, self).__call__(estimator, X, y_true,
90 sample_weight=sample_weight)
---> 91 y_pred = estimator.predict(X)
92 if sample_weight is not None:
93 return self._sign * self._score_func(y_true, y_pred,
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/neighbors/regression.py in predict(self, X)
151
152 if weights is None:
--> 153 y_pred = np.mean(_y[neigh_ind], axis=1)
154 else:
155 y_pred = np.empty((X.shape[0], _y.shape[1]), dtype=np.float64)
~/anaconda3/envs/datascience/lib/python3.6/site-packages/numpy/core/fromnumeric.py in mean(a, axis, dtype, out, keepdims)
2907
2908 return _methods._mean(a, axis=axis, dtype=dtype,
-> 2909 out=out, **kwargs)
2910
2911
~/anaconda3/envs/datascience/lib/python3.6/site-packages/numpy/core/_methods.py in _mean(a, axis, dtype, out, keepdims)
71 if isinstance(ret, mu.ndarray):
72 ret = um.true_divide(
---> 73 ret, rcount, out=ret, casting='unsafe', subok=False)
74 if is_float16_result and out is None:
75 ret = arr.dtype.type(ret)
TypeError: unsupported operand type(s) for /: 'str' and 'int'