Python preprocessing.LabelEncoder方法代码示例

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def test_explain_model_local_with_predicted_label(self):
        """
        Test for explain_local of classical explainer
        :return:
        """
        X_train, X_test, y_train, y_test = setup_mnli_test_train_split()

        label_encoder = LabelEncoder()
        y_train = label_encoder.fit_transform(y_train)
        explainer = ClassicalTextExplainer()
        classifier, best_params = explainer.fit(X_train, y_train)
        explainer.preprocessor.labelEncoder = label_encoder
        y = classifier.predict(DOCUMENT)
        predicted_label = label_encoder.inverse_transform(y)
        local_explanation = explainer.explain_local(DOCUMENT, predicted_label)
        assert len(local_explanation.local_importance_values) == len(local_explanation.features) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def __init__(self, estimator, dtype=float, sparse=True):
        """
        :param estimator: scikit-learn classifier object.

        :param dtype: data type used when building feature array.
            scikit-learn estimators work exclusively on numeric data. The
            default value should be fine for almost all situations.

        :param sparse: Whether to use sparse matrices internally.
            The estimator must support these; not all scikit-learn classifiers
            do (see their respective documentation and look for "sparse
            matrix"). The default value is True, since most NLP problems
            involve sparse feature sets. Setting this to False may take a
            great amount of memory.
        :type sparse: boolean.
        """
        self._clf = estimator
        self._encoder = LabelEncoder()
        self._vectorizer = DictVectorizer(dtype=dtype, sparse=sparse) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def __init__(self,
                 corpus,
                 sherlock_features: List[str] = None,
                 topic_feature: str = None,
                 label_enc: LabelEncoder = None,
                 id_filter: List[str] = None,
                 max_col_count:int = None,
                 shuffle_group:str=None):

        super().__init__(corpus,
                                    sherlock_features,
                                    topic_feature,
                                    label_enc,
                                    id_filter,
                                    max_col_count)

        l = len(self.df_header)
        self.tempcorpus = corpus

        self.shuffle_group = shuffle_group
        self.prng = np.random.RandomState(SEED)
        self.shuffle_order = self.prng.permutation(l) 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def cat_onehot_encoder(df,y,col,selection=True):
    feat_x = df.values.reshape(-1,1)

    from sklearn.preprocessing import LabelEncoder

    le = LabelEncoder()
    le.fit(feat_x)
    feat_x = le.transform(feat_x)

    mlbs = OneHotEncoder(sparse=True).fit(feat_x.reshape(-1,1))
    from scipy.sparse import csr_matrix
    features_tmp = mlbs.transform(feat_x.reshape(-1,1))
    features_tmp = csr_matrix(features_tmp,dtype=float).tocsr()
    models = None
    auc_score = None
    if selection is True:
        auc_score, models = train_lightgbm_for_feature_selection(features_tmp, y)
        print(col, "auc", auc_score)
    #new_feature = pd.DataFrame(features_tmp,columns=["mul_feature_"+col])
    new_feature = features_tmp




    return new_feature,mlbs,models,auc_score,le 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def preprocessData(dataset):

    le = preprocessing.LabelEncoder()

    # in case divid-by-zero
    dataset.Open[dataset.Open == 0] = 1

    # add prediction target: next day Up/Down
    threshold = 0.000
    dataset['UpDown'] = (dataset['Close'] - dataset['Open']) / dataset['Open']
    dataset.UpDown[dataset.UpDown >= threshold] = 'Up'
    dataset.UpDown[dataset.UpDown < threshold] = 'Down'
    dataset.UpDown = le.fit(dataset.UpDown).transform(dataset.UpDown)
    dataset.UpDown = dataset.UpDown.shift(-1) # shift 1, so the y is actually next day's up/down
    dataset = dataset.drop(dataset.index[-1]) # drop last one because it has no up/down value
    return dataset 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def get_query_y(self, Qy, Qyc, class_label):
        """
        Returns labeled representation of classes of Query set and a list of labels.
        """
        labels = []
        m = len(Qy)
        for i in range(m):
            labels += [Qy[i]] * Qyc[i]
        labels = np.array(labels).reshape(len(labels), 1)
        label_encoder = LabelEncoder()
        Query_y = torch.Tensor(
            label_encoder.fit_transform(labels).astype(int)).long()
        if self.gpu:
            Query_y = Query_y.cuda()
        Query_y_labels = np.unique(labels)
        return Query_y, Query_y_labels 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def get_cars_data():
    """
    Load the cars dataset, split it into X and y, and then call the label encoder to get an integer y column.

    :return:
    """

    df = pd.read_csv('source_data/cars/car.data.txt')
    X = df.reindex(columns=[x for x in df.columns.values if x != 'class'])
    y = df.reindex(columns=['class'])
    y = preprocessing.LabelEncoder().fit_transform(y.values.reshape(-1, ))

    mapping = [
        {'col': 'buying', 'mapping': [('vhigh', 0), ('high', 1), ('med', 2), ('low', 3)]},
        {'col': 'maint', 'mapping': [('vhigh', 0), ('high', 1), ('med', 2), ('low', 3)]},
        {'col': 'doors', 'mapping': [('2', 0), ('3', 1), ('4', 2), ('5more', 3)]},
        {'col': 'persons', 'mapping': [('2', 0), ('4', 1), ('more', 2)]},
        {'col': 'lug_boot', 'mapping': [('small', 0), ('med', 1), ('big', 2)]},
        {'col': 'safety', 'mapping': [('high', 0), ('med', 1), ('low', 2)]},
    ]

    return X, y, mapping 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def get_mushroom_data():
    """
    Load the mushroom dataset, split it into X and y, and then call the label encoder to get an integer y column.

    :return:
    """

    df = pd.read_csv('source_data/mushrooms/agaricus-lepiota.csv')
    X = df.reindex(columns=[x for x in df.columns.values if x != 'class'])
    y = df.reindex(columns=['class'])
    y = preprocessing.LabelEncoder().fit_transform(y.values.reshape(-1, ))

    # this data is truly categorical, with no known concept of ordering
    mapping = None

    return X, y, mapping 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def get_splice_data():
    """
    Load the mushroom dataset, split it into X and y, and then call the label encoder to get an integer y column.

    :return:
    """

    df = pd.read_csv('source_data/splice/splice.csv')
    X = df.reindex(columns=[x for x in df.columns.values if x != 'class'])
    X['dna'] = X['dna'].map(lambda x: list(str(x).strip()))
    for idx in range(60):
        X['dna_%d' % (idx, )] = X['dna'].map(lambda x: x[idx])
    del X['dna']

    y = df.reindex(columns=['class'])
    y = preprocessing.LabelEncoder().fit_transform(y.values.reshape(-1, ))

    # this data is truly categorical, with no known concept of ordering
    mapping = None

    return X, y, mapping 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def get_X_y(**kwargs):
    """simple wrapper around pd.read_csv that extracts features and labels

    Some systematic preprocessing is also carried out to avoid doing this
    transformation repeatedly in the code.
    """
    global label_encoder
    df = pd.read_csv(info['path'], sep='\t', **kwargs)
    return preprocess(df, label_encoder)

###############################################################################
# Classifier objects in |sklearn| often require :code:`y` to be integer labels.
# Additionally, |APS| requires a binary version of the labels.  For these two
# purposes, we create:
#
# * a |LabelEncoder|, that we pre-fitted on the known :code:`y` classes
# * a |OneHotEncoder|, pre-fitted on the resulting integer labels.
#
# Their |transform| methods can the be called at appopriate times. 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def fit(self, X, y):
        from sklearn.preprocessing import LabelEncoder
        from sklearn.utils import compute_class_weight

        label_encoder = LabelEncoder().fit(y)
        classes = label_encoder.classes_
        class_weight = compute_class_weight(self.class_weight, classes, y)

        # Intentionally modify the balanced class_weight
        # to simulate a bug and raise an exception
        if self.class_weight == "balanced":
            class_weight += 1.

        # Simply assigning coef_ to the class_weight
        self.coef_ = class_weight
        return self 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def score(self,
              actual: np.array,
              predicted: np.array,
              sample_weight: typing.Optional[np.array] = None,
              labels: typing.Optional[np.array] = None,
              **kwargs) -> float:
        lb = LabelEncoder()
        labels = lb.fit_transform(labels)
        actual = lb.transform(actual)
        method = "binary"
        if len(labels) > 2:
            predicted = np.argmax(predicted, axis=1)
            method = "micro"
        else:
            predicted = (predicted > self._threshold)
        f4_score = fbeta_score(actual, predicted, labels=labels, average=method, sample_weight=sample_weight, beta=4)
        return f4_score 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def score(self,
              actual: np.array,
              predicted: np.array,
              sample_weight: typing.Optional[np.array] = None,
              labels: typing.Optional[np.array] = None,
              **kwargs) -> float:
        # label actuals as 1 or 0
        lb = LabelEncoder()
        labels = lb.fit_transform(labels)
        actual = lb.transform(actual)

        # label predictions as 1 or 0
        predicted = predicted >= self._threshold

        # use sklearn to get fp and fn
        cm = confusion_matrix(actual, predicted, sample_weight=sample_weight, labels=labels)
        tn, fp, fn, tp = cm.ravel()

        # calculate`$1*FP + $2*FN`
        return ((fp * self.__class__._fp_cost) + (fn * self.__class__._fn_cost)) / (
                    tn + fp + fn + tp)  # divide by total weighted count to make loss invariant to data size 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def score(self,
              actual: np.array,
              predicted: np.array,
              sample_weight: typing.Optional[np.array] = None,
              labels: typing.Optional[np.array] = None,
              **kwargs) -> float:
        lb = LabelEncoder()
        labels = lb.fit_transform(labels)
        actual = lb.transform(actual)
        method = "binary"
        if len(labels) > 2:
            predicted = np.argmax(predicted, axis=1)
            method = "micro"
        else:
            predicted = (predicted > self._threshold)
        f3_score = fbeta_score(actual, predicted, labels=labels, average=method, sample_weight=sample_weight, beta=3)
        return f3_score 

# 需要导入模块: from sklearn import preprocessing [as 别名]
# 或者: from sklearn.preprocessing import LabelEncoder [as 别名]
def fit(self, X, y, sample_weight=None, eval_set=None, sample_weight_eval_set=None, **kwargs):
        lb = LabelEncoder()
        lb.fit(self.labels)
        y = lb.transform(y)
        orig_cols = list(X.names)
        XX = X.to_pandas()
        params = {
            'train_dir': user_dir(),
            'allow_writing_files': False,
            'thread_count': 10,
            # 'loss_function': 'Logloss'
        }
        from catboost import CatBoostClassifier
        model = CatBoostClassifier(**params)
        model.fit(XX, y=y, sample_weight=sample_weight, verbose=False,
                  cat_features=list(X[:, [str, int]].names))  # Amazon specific, also no early stopping

        # must always set best_iterations
        self.set_model_properties(model=model,
                                  features=orig_cols,
                                  importances=model.feature_importances_,
                                  iterations=0)