Python forest.RandomForestClassifier方法代码示例

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def __init__(self, n_estimators=10, criterion='gini', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight='balanced'):
        self._hyperparams = {
            'n_estimators': n_estimators,
            'criterion': criterion,
            'max_depth': max_depth,
            'min_samples_split': min_samples_split,
            'min_samples_leaf': min_samples_leaf,
            'min_weight_fraction_leaf': min_weight_fraction_leaf,
            'max_features': max_features,
            'max_leaf_nodes': max_leaf_nodes,
            'min_impurity_decrease': min_impurity_decrease,
            'min_impurity_split': min_impurity_split,
            'bootstrap': bootstrap,
            'oob_score': oob_score,
            'n_jobs': n_jobs,
            'random_state': random_state,
            'verbose': verbose,
            'warm_start': warm_start,
            'class_weight': class_weight}
        self._wrapped_model = Op(**self._hyperparams) 

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def test_nlp_not_padded_invalid(self):
        num_words = 1024
        (x_train, y_train), (_, _) = TestUtil.get_random_variable_length_dataset(max_value=num_words)

        explained_model = RandomForestClassifier(n_estimators=64, max_depth=5, random_state=1)

        counter = CountVectoriser(num_words)
        tfidf_transformer = TfidfTransformer()

        explained_model = Pipeline([('counts', counter),
                                    ('tfidf', tfidf_transformer),
                                    ('model', explained_model)])
        explained_model.fit(x_train, y_train)

        model_builder = RNNModelBuilder(embedding_size=num_words, with_embedding=True,
                                        num_layers=2, num_units=32, activation="relu", p_dropout=0.2, verbose=0,
                                        batch_size=32, learning_rate=0.001, num_epochs=2, early_stopping_patience=128)
        masking_operation = WordDropMasking()
        loss = binary_crossentropy
        explainer = CXPlain(explained_model, model_builder, masking_operation, loss)

        with self.assertRaises(ValueError):
            explainer.fit(x_train, y_train) 

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def multi_scorer_gridsearch(estimator, x, y):
    """
    Helper for sklearn, required to be able to score by more than one metric.
    :param estimator:
    :param x:
    :param y:
    :return:
    """
    with __lock:
        if isinstance(estimator, SVC):
            if estimator.kernel == 'rbf':
                params = {'C': estimator.C, 'gamma': estimator.gamma, 'kernel': estimator.kernel}
            else:
                params = {'C': estimator.C, 'kernel': estimator.kernel}
        if isinstance(estimator, RandomForestClassifier):
            log.info('RandomForestClassifier')
            params = {'max_features': estimator.max_features, 'n_estimators': estimator.n_estimators,
                      'criterion': estimator.criterion}

        try:
            with open(settings.GRID_SEARCH_FOLDER_TMP + ''.join(__rand_id), 'rb') as f:
                all_scores = pickle.load(f)
        except FileNotFoundError:
            all_scores = dict()

        accuracy, precision, recall, roc, f1 = _get_scores(estimator, x, y)

        scores = {'accuracy': accuracy, 'precision': precision, 'recall': recall, 'roc': roc, 'f1': f1}

        params = frozenset(params.items())
        if params not in all_scores.keys():
            all_scores[params] = []

        all_scores[params].append(scores)
        with open(settings.GRID_SEARCH_FOLDER_TMP + ''.join(__rand_id), 'wb+') as f:
            pickle.dump(all_scores, f)

    return roc 

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def rf_grid_search(data_set: DataSet, n_est_values=16, n_jobs=8):
    num_of_estimators = numpy.random.random_integers(10, 1000, n_est_values)
    max_feat = range(2, 44)
    param_grid = dict(max_features=max_feat, n_estimators=num_of_estimators, criterion=['gini', 'entropy'])
    return grid_search(RandomForestClassifier(), param_grid, data_set, n_jobs=n_jobs) 

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def test_nlp_padded_valid(self):
        num_words = 1024
        (x_train, y_train), (x_test, y_test) = TestUtil.get_random_variable_length_dataset(max_value=num_words)

        explained_model = RandomForestClassifier(n_estimators=64, max_depth=5, random_state=1)

        counter = CountVectoriser(num_words)
        tfidf_transformer = TfidfTransformer()

        explained_model = Pipeline([('counts', counter),
                                    ('tfidf', tfidf_transformer),
                                    ('model', explained_model)])
        explained_model.fit(x_train, y_train)

        model_builder = RNNModelBuilder(embedding_size=num_words, with_embedding=True,
                                        num_layers=2, num_units=32, activation="relu", p_dropout=0.2, verbose=0,
                                        batch_size=32, learning_rate=0.001, num_epochs=2, early_stopping_patience=128)
        masking_operation = WordDropMasking()
        loss = binary_crossentropy
        explainer = CXPlain(explained_model, model_builder, masking_operation, loss)

        x_train = pad_sequences(x_train, padding="post", truncating="post", dtype=int)
        x_test = pad_sequences(x_test, padding="post", truncating="post", dtype=int, maxlen=x_train.shape[1])

        explainer.fit(x_train, y_train)
        eval_score = explainer.score(x_test, y_test)
        train_score = explainer.get_last_fit_score()
        median = explainer.predict(x_test)
        self.assertTrue(median.shape == x_test.shape) 

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def test_imdb_padded_valid(self):
        num_samples = 32
        num_words = 1024
        (x_train, y_train), (x_test, y_test) = TestUtil.get_imdb(word_dictionary_size=num_words,
                                                                 num_subsamples=num_samples)

        explained_model = RandomForestClassifier(n_estimators=64, max_depth=5, random_state=1)

        counter = CountVectoriser(num_words)
        tfidf_transformer = TfidfTransformer()

        explained_model = Pipeline([('counts', counter),
                                    ('tfidf', tfidf_transformer),
                                    ('model', explained_model)])
        explained_model.fit(x_train, y_train)

        model_builder = RNNModelBuilder(embedding_size=num_words, with_embedding=True,
                                        num_layers=2, num_units=32, activation="relu", p_dropout=0.2, verbose=0,
                                        batch_size=32, learning_rate=0.001, num_epochs=2, early_stopping_patience=128)
        masking_operation = WordDropMasking()
        loss = binary_crossentropy
        explainer = CXPlain(explained_model, model_builder, masking_operation, loss)

        x_train = pad_sequences(x_train, padding="post", truncating="post", dtype=int)
        x_test = pad_sequences(x_test, padding="post", truncating="post", dtype=int, maxlen=x_train.shape[1])

        explainer.fit(x_train, y_train)
        eval_score = explainer.score(x_test, y_test)
        train_score = explainer.get_last_fit_score()
        median = explainer.predict(x_test)
        self.assertTrue(median.shape == x_test.shape) 

# 需要导入模块: from sklearn.ensemble import forest [as 别名]
# 或者: from sklearn.ensemble.forest import RandomForestClassifier [as 别名]
def test_nlp_erroneous_rnn_args_invalid(self):
        num_words = 1024
        (x_train, y_train), (x_test, y_test) = TestUtil.get_random_variable_length_dataset(max_value=num_words)

        explained_model = RandomForestClassifier(n_estimators=64, max_depth=5, random_state=1)

        counter = CountVectoriser(num_words)
        tfidf_transformer = TfidfTransformer()

        explained_model = Pipeline([('counts', counter),
                                    ('tfidf', tfidf_transformer),
                                    ('model', explained_model)])
        explained_model.fit(x_train, y_train)

        with self.assertRaises(ValueError):
            _ = RNNModelBuilder(with_embedding=True, verbose=0)  # Must also specify the embedding_size argument.

        model_builder = RNNModelBuilder(embedding_size=num_words, with_embedding=True, verbose=0)

        input_layer = Input(shape=(10, 2))
        with self.assertRaises(ValueError):
            model_builder.build(input_layer)

        input_layer = Input(shape=(10, 3))
        with self.assertRaises(ValueError):
            model_builder.build(input_layer)