Meezo ML

كيف نقوم بتطبيق خوارزمية ExtraTreesClassifier باستخدام مكتبة Sklearn؟

كيف نقوم بتطبيق خوارزمية BaggingClassifier باستخدام مكتبة Sklearn؟

قمت ببناء مودل LogisticRegression لكن عند محاولة قياس الكفاءة يظهر لي الخطأالتالي: import numpy as np from tensorflow.keras.datasets import mnist from sklearn.linear_model import LogisticRegression from sklearn.pipeline import Pipeline from tensorflow.keras.utils import to_categorical from sklearn.metrics import f1_score,precision_score,recall_score,accuracy_score,log_loss (x_train, y_train),(x_test, y_test) = mnist.load_data() x_train.shape image_size = x_train.shape[1] input_size = image_size * image_size x_train = np.reshape(x_train, [-1, input_size])/ 255 x_test = np.reshape(x_test, [-1, input_size]) / 255 #y_train = to_categorical(y_train) #y_test = to_categorical(y_test) t =LogisticRegression() t.fit(x_train, y_train) f1_score(y_test,t.predict(x_test)) --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-1-bbb2bd2287ff> in <module> 15 t =LogisticRegression() 16 t.fit(x_train, y_train) ---> 17 f1_score(y_test,t.predict(x_test)) 18 19 #ValueError: Target is multiclass but average='binary'. Please choose another average setting, one of [None, 'micro', 'macro', 'weighted']. ~\anaconda3\lib\site-packages\sklearn\metrics\_classification.py in f1_score(y_true, y_pred, labels, pos_label, average, sample_weight, zero_division) 1097 pos_label=pos_label, average=average, 1098 sample_weight=sample_weight, -> 1099 zero_division=zero_division) 1100 1101 ~\anaconda3\lib\site-packages\sklearn\metrics\_classification.py in fbeta_score(y_true, y_pred, beta, labels, pos_label, average, sample_weight, zero_division) 1224 warn_for=('f-score',), 1225 sample_weight=sample_weight, -> 1226 zero_division=zero_division) 1227 return f 1228 ~\anaconda3\lib\site-packages\sklearn\metrics\_classification.py in precision_recall_fscore_support(y_true, y_pred, beta, labels, pos_label, average, warn_for, sample_weight, zero_division) 1482 raise ValueError("beta should be >=0 in the F-beta score") 1483 labels = _check_set_wise_labels(y_true, y_pred, average, labels, -> 1484 pos_label) 1485 1486 # Calculate tp_sum, pred_sum, true_sum ### ~\anaconda3\lib\site-packages\sklearn\metrics\_classification.py in _check_set_wise_labels(y_true, y_pred, average, labels, pos_label) 1314 raise ValueError("Target is %s but average='binary'. Please " 1315 "choose another average setting, one of %r." -> 1316 % (y_type, average_options)) 1317 elif pos_label not in (None, 1): 1318 warnings.warn("Note that pos_label (set to %r) is ignored when " ValueError: Target is multiclass but average='binary'. Please choose another average setting, one of [None, 'micro', 'macro', 'weighted']. ما الحل؟

ظهور الخطأ التالي ValueError: bad input shape عند محاولة تدريب نموذج باستخدام خوارزمية MultinomialNB. الكود مع الخطأ: import numpy as np from sklearn.naive_bayes import MultinomialNB from tensorflow.keras.utils import to_categorical from tensorflow.keras.datasets import mnist from sklearn.metrics import accuracy_score (X, Y),(Xtest, Ytest) = mnist.load_data() Y = to_categorical(Y) Ytest = to_categorical(Ytest) X = np.reshape(X, [-1, X.shape[1]*X.shape[1]]) Xtest = np.reshape(Xtest, [-1, input_size]) M =MultinomialNB() M.fit(X, Y) --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-19-161d6ac448e8> in <module> 10 Xtest = np.reshape(Xtest, [-1, input_size]) 11 t =MultinomialNB() ---> 12 t.fit(X, Y) 13 accuracy_score(Ytest,t.predict(Xtest)) # 0.8357 ~\anaconda3\lib\site-packages\sklearn\naive_bayes.py in fit(self, X, y, sample_weight) 607 self : object 608 """ --> 609 X, y = self._check_X_y(X, y) 610 _, n_features = X.shape 611 self.n_features_ = n_features ~\anaconda3\lib\site-packages\sklearn\naive_bayes.py in _check_X_y(self, X, y) 473 474 def _check_X_y(self, X, y): --> 475 return check_X_y(X, y, accept_sparse='csr') 476 477 def _update_class_log_prior(self, class_prior=None): ~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator) 758 dtype=None) 759 else: --> 760 y = column_or_1d(y, warn=True) 761 _assert_all_finite(y) 762 if y_numeric and y.dtype.kind == 'O': ~\anaconda3\lib\site-packages\sklearn\utils\validation.py in column_or_1d(y, warn) 795 return np.ravel(y) 796 --> 797 raise ValueError("bad input shape {0}".format(shape)) 798 799 ValueError: bad input shape (60000, 10)

كيف نقوم بتطبيق خوارزمية VotingRegressor لمهمة توقع باستخدام مكتبة Sklearn ؟

أريد بناء مجموعة بيانات عشوائية باستخدام مكتبة Sklearn كيف نقوم بذلك؟

كيف نفوم بتطبيق خوارزمية AdaBoostClassifier باستخدام مكتبة Sklearn؟

أحاول أن أقوم بترميز النص باستخدام ال TF-IDF لكن يظهر لي الخطأ ValueError: np.nan is an invalid document, expected byte or unicode string. في هذا المقطع البرمجي التالي: from sklearn.feature_extraction.text import TfidfVectorizer import pandas as pd data = pd.read_csv("train.csv") tfidf = TfidfVectorizer(encoding='utf-8',decode_error='replace') enc = tfidf.fit_transform(data['tweets']) ما السبب؟ ظهور الخطأ ValueError: np.nan is an invalid document, expected byte or unicode string عند محاولة ترميز النص باستخدام TfidfVectorizer

كيف نقوم بتطبيق الترميز CountVectorizer باستخدام مكتبة Sklearn؟

ماهي ال AffinityPropagation و كيف يتم تطبيقها في Sklearn؟

ماهو ال DBScan وكيف نقوم بتطبيقه باستخدام مكتبة Sklearn؟

ظهور الخطأ التالي ValueError: Found array with dim 3. Estimator expected <= 2 عند محاولة تدريب نموذج باستخدام خوارزمية MultinomialNB؟ import numpy as np from tensorflow.keras.datasets import mnist from sklearn.naive_bayes import MultinomialNB from sklearn.pipeline import Pipeline from tensorflow.keras.utils import to_categorical from sklearn.metrics import f1_score,precision_score,recall_score,accuracy_score,log_loss (x_train, y_train),(x_test, y_test) = mnist.load_data() x_train.shape t = Pipeline([('clf',MultinomialNB())]) t = text_clf.fit(x_train, y_train) accuracy_score(y_test,t.predict(x_test)) --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-25-434bf8f46433> in <module> 10 # تعريف pipline 11 t = Pipeline([('clf',MultinomialNB())]) ---> 12 t = text_clf.fit(x_train, y_train) 13 accuracy_score(y_test,t.predict(x_test)) ~\anaconda3\lib\site-packages\sklearn\pipeline.py in fit(self, X, y, **fit_params) 352 self._log_message(len(self.steps) - 1)): 353 if self._final_estimator != 'passthrough': --> 354 self._final_estimator.fit(Xt, y, **fit_params) 355 return self 356 ~\anaconda3\lib\site-packages\sklearn\naive_bayes.py in fit(self, X, y, sample_weight) 607 self : object 608 """ --> 609 X, y = self._check_X_y(X, y) 610 _, n_features = X.shape 611 self.n_features_ = n_features ~\anaconda3\lib\site-packages\sklearn\naive_bayes.py in _check_X_y(self, X, y) 473 474 def _check_X_y(self, X, y): --> 475 return check_X_y(X, y, accept_sparse='csr') 476 477 def _update_class_log_prior(self, class_prior=None): ~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator) 753 ensure_min_features=ensure_min_features, 754 warn_on_dtype=warn_on_dtype, --> 755 estimator=estimator) 756 if multi_output: 757 y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False, ~\anaconda3\lib\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) 572 if not allow_nd and array.ndim >= 3: 573 raise ValueError("Found array with dim %d. %s expected <= 2." --> 574 % (array.ndim, estimator_name)) 575 576 if force_all_finite: ValueError: Found array with dim 3. Estimator expected <= 2.

كيف نقوم بتطبيق الترميز TF-IDF باستخدام مكتبة Sklearn؟

كيفية تطبيق معيار f1-score في مكتبة Sklearn لقياس كفاءة نموذج؟

كيف نقوم بتطبيق خوارزمية Categorical Naive Bayes لمهمة تصنيف في مكتبة Sklearn؟

كيف نقوم بتطبيق خوارزمية Complement Naive Bayes لمهمة تصنيف في Sklearn؟

كيفية تطبيق One-Hot Encoding باستخدام مكتبة Sklearn؟

عند محاولة تدريب model ( نموذج ) يظهر لي الخطأ التالي Expected 2D array, got 1D array instead الكود: from sklearn.preprocessing import LabelEncoder import pandas as pd from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression # إنشاءداتا data = {'size': [100, 30, 50, 200, 2], 'class': ['big', 'small', 'medium', 'verybig', 'verysmall']} df = pd.DataFrame(data) le = LabelEncoder() le.fit(df['class']) df['class'] = le.transform(df['class']) X_train, X_test, y_train, y_test = train_test_split(df['size'], df['class'], random_state = 42, test_size = 0.33) linreg = LinearRegression() linreg.fit(X_train, y_train) linreg.score(x_test,y_test) --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-9-f740a0daa981> in <module> 12 X_train, X_test, y_train, y_test = train_test_split(df['size'], df['class'], random_state = 42, test_size = 0.33) 13 linreg = LinearRegression() ---> 14 linreg.fit(X_train, y_train) 15 linreg.score(x_test,y_test) ~\anaconda3\lib\site-packages\sklearn\linear_model\_base.py in fit(self, X, y, sample_weight) 490 n_jobs_ = self.n_jobs 491 X, y = check_X_y(X, y, accept_sparse=['csr', 'csc', 'coo'], --> 492 y_numeric=True, multi_output=True) 493 494 if sample_weight is not None: ~\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator) 753 ensure_min_features=ensure_min_features, 754 warn_on_dtype=warn_on_dtype, --> 755 estimator=estimator) 756 if multi_output: 757 y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False, ~\anaconda3\lib\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) 554 "Reshape your data either using array.reshape(-1, 1) if " 555 "your data has a single feature or array.reshape(1, -1) " --> 556 "if it contains a single sample.".format(array)) 557 558 # in the future np.flexible dtypes will be handled like object dtypes ValueError: Expected 2D array, got 1D array instead: array=[ 50 100 200].

كيفية تطبيق خوارزمية BernoulliNB لمهمة تصنيف في Sklearn؟

لدي الكود التالي: from sklearn.model_selection import cross_val_score from sklearn.datasets import load_iris from sklearn.preprocessing import OneHotEncoder from sklearn.tree import DecisionTreeClassifier dataset = load_iris() Xdata = pd.DataFrame(data=dataset.data, columns=dataset.feature_names) encoder = OneHotEncoder() ydata = encoder.fit_transform(pd.DataFrame(dataset.target)).toarray() model = DecisionTreeClassifier(max_depth=1) cross_val_score(model, Xdata, ydata, cv=4, scoring="roc_auc") --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-20-6be5be8289ab> in <module> 11 model = DecisionTreeClassifier(max_depth=1) 12 ---> 13 cross_val_score(model, Xdata, ydata, cv=4, scoring="roc_auc") ~\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, error_score) 388 fit_params=fit_params, 389 pre_dispatch=pre_dispatch, --> 390 error_score=error_score) 391 return cv_results['test_score'] 392 ~\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, return_estimator, error_score) 234 return_times=True, return_estimator=return_estimator, 235 error_score=error_score) --> 236 for train, test in cv.split(X, y, groups)) 237 238 zipped_scores = list(zip(*scores)) ~\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable) 1002 # remaining jobs. 1003 self._iterating = False -> 1004 if self.dispatch_one_batch(iterator): 1005 self._iterating = self._original_iterator is not None 1006 ~\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator) 833 return False 834 else: --> 835 self._dispatch(tasks) 836 return True 837 ~\anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch) 752 with self._lock: 753 job_idx = len(self._jobs) --> 754 job = self._backend.apply_async(batch, callback=cb) 755 # A job can complete so quickly than its callback is 756 # called before we get here, causing self._jobs to ~\anaconda3\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback) 207 def apply_async(self, func, callback=None): 208 """Schedule a func to be run""" --> 209 result = ImmediateResult(func) 210 if callback: 211 callback(result) ~\anaconda3\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch) 588 # Don't delay the application, to avoid keeping the input 589 # arguments in memory --> 590 self.results = batch() 591 592 def get(self): ~\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self) 254 with parallel_backend(self._backend, n_jobs=self._n_jobs): 255 return [func(*args, **kwargs) --> 256 for func, args, kwargs in self.items] 257 258 def __len__(self): ~\anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0) 254 with parallel_backend(self._backend, n_jobs=self._n_jobs): 255 return [func(*args, **kwargs) --> 256 for func, args, kwargs in self.items] 257 258 def __len__(self): ~\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) 542 else: 543 fit_time = time.time() - start_time --> 544 test_scores = _score(estimator, X_test, y_test, scorer) 545 score_time = time.time() - start_time - fit_time 546 if return_train_score: ~\anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _score(estimator, X_test, y_test, scorer) 589 scores = scorer(estimator, X_test) 590 else: --> 591 scores = scorer(estimator, X_test, y_test) 592 593 error_msg = ("scoring must return a number, got %s (%s) " ~\anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in __call__(self, estimator, *args, **kwargs) 85 if isinstance(scorer, _BaseScorer): 86 score = scorer._score(cached_call, estimator, ---> 87 *args, **kwargs) 88 else: 89 score = scorer(estimator, *args, **kwargs) ~\anaconda3\lib\site-packages\sklearn\metrics\_scorer.py in _score(self, method_caller, clf, X, y, sample_weight) 330 **self._kwargs) 331 else: --> 332 return self._sign * self._score_func(y, y_pred, **self._kwargs) 333 334 def _factory_args(self): ~\anaconda3\lib\site-packages\sklearn\metrics\_ranking.py in roc_auc_score(y_true, y_score, average, sample_weight, max_fpr, multi_class, labels) 393 max_fpr=max_fpr), 394 y_true, y_score, average, --> 395 sample_weight=sample_weight) 396 397 ~\anaconda3\lib\site-packages\sklearn\metrics\_base.py in _average_binary_score(binary_metric, y_true, y_score, average, sample_weight) 118 y_score_c = y_score.take([c], axis=not_average_axis).ravel() 119 score[c] = binary_metric(y_true_c, y_score_c, --> 120 sample_weight=score_weight) 121 122 # Average the results ~\anaconda3\lib\site-packages\sklearn\metrics\_ranking.py in _binary_roc_auc_score(y_true, y_score, sample_weight, max_fpr) 219 """Binary roc auc score""" 220 if len(np.unique(y_true)) != 2: --> 221 raise ValueError("Only one class present in y_true. ROC AUC score " 222 "is not defined in that case.") 223 ValueError: Only one class present in y_true. ROC AUC score is not defined in that case.

كيفية ترميز البيانات الفئوية ( بيانات نصية ) باستخدام الكلاس OrdinalEncoder في مكتبة Sklearn؟

كيف نقوم بترميز فئات البيانات (Classes) النصية عندما نتعامل مع مشكلة NLP ؟

كيفية تطبيق خوارزمية Multinomial Naive Bayes لمهمة تصنيف في Sklearn؟

كيفية تطبيق خوارزمية Gaussian Naive Bayesلمهمة تصنيف في Sklearn؟

قمت ببناء نموذج، لكن يظهر لي دوماً الخطأ التالي: #استيراد المكتبات import numpy as np from sklearn.linear_model import LogisticRegression from sklearn.naive_bayes import GaussianNB from sklearn.ensemble import RandomForestClassifier, VotingClassifier from sklearn.datasets import load_breast_cancer from sklearn.model_selection import train_test_split #تحميل البيانات data = load_breast_cancer().data labels = load_breast_cancer().target # تقسيم البيانات X_train, y_train,X_test, y_test = train_test_split(data, labels, test_size=0.2, random_state=2021, shuffle =True) c1 = LogisticRegression(multi_class='multinomial', random_state=1) c2 = RandomForestClassifier(n_estimators=50, random_state=1) c3 = GaussianNB() ec1 = VotingClassifier(estimators=[ ('lr', c1), ('rf', c2), ('gnb', c3)], voting='hard') ec1 = ec1.fit(X_train, y_train) print(ec1.score(X_test,y_test)) --------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-16-46caf1469fab> in <module> 17 18 ec1 = VotingClassifier(estimators=[ ('lr', c1), ('rf', c2), ('gnb', c3)], voting='hard') ---> 19 ec1 = ec1.fit(X_train, y_train) 20 print(ec1.score(X_test,y_test))#0.9385964912280702 ~\anaconda3\lib\site-packages\sklearn\ensemble\_voting.py in fit(self, X, y, sample_weight) 207 208 """ --> 209 check_classification_targets(y) 210 if isinstance(y, np.ndarray) and len(y.shape) > 1 and y.shape[1] > 1: 211 raise NotImplementedError('Multilabel and multi-output' ~\anaconda3\lib\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-multioutput'