Python pandas.factorize方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_mixed(self):

        # doc example reshaping.rst
        x = Series(['A', 'A', np.nan, 'B', 3.14, np.inf])
        labels, uniques = algos.factorize(x)

        exp = np.array([0, 0, -1, 1, 2, 3], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = Index(['A', 'B', 3.14, np.inf])
        tm.assert_index_equal(uniques, exp)

        labels, uniques = algos.factorize(x, sort=True)
        exp = np.array([2, 2, -1, 3, 0, 1], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = Index([3.14, np.inf, 'A', 'B'])
        tm.assert_index_equal(uniques, exp) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def group_sums(x, group):
    '''sum x for each group, simple bincount version, again

    group : array, integer
        assumed to be consecutive integers

    no dtype checking because I want to raise in that case

    uses loop over columns of x

    #TODO: remove this, already copied to tools/grouputils
    '''

    #TODO: transpose return in group_sum, need test coverage first

    # re-label groups or bincount takes too much memory
    if np.max(group) > 2 * x.shape[0]:
        group = pd.factorize(group)[0]

    return np.array([np.bincount(group, weights=x[:, col])
                            for col in range(x.shape[1])]) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_factorize_nan(self):
        # nan should map to na_sentinel, not reverse_indexer[na_sentinel]
        # rizer.factorize should not raise an exception if na_sentinel indexes
        # outside of reverse_indexer
        key = np.array([1, 2, 1, np.nan], dtype='O')
        rizer = ht.Factorizer(len(key))
        for na_sentinel in (-1, 20):
            ids = rizer.factorize(key, sort=True, na_sentinel=na_sentinel)
            expected = np.array([0, 1, 0, na_sentinel], dtype='int32')
            assert len(set(key)) == len(set(expected))
            tm.assert_numpy_array_equal(pd.isna(key),
                                        expected == na_sentinel)

        # nan still maps to na_sentinel when sort=False
        key = np.array([0, np.nan, 1], dtype='O')
        na_sentinel = -1

        # TODO(wesm): unused?
        ids = rizer.factorize(key, sort=False, na_sentinel=na_sentinel)  # noqa

        expected = np.array([2, -1, 0], dtype='int32')
        assert len(set(key)) == len(set(expected))
        tm.assert_numpy_array_equal(pd.isna(key), expected == na_sentinel) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_uint64_factorize(self):
        data = np.array([2**63, 1, 2**63], dtype=np.uint64)
        exp_labels = np.array([0, 1, 0], dtype=np.intp)
        exp_uniques = np.array([2**63, 1], dtype=np.uint64)

        labels, uniques = algos.factorize(data)
        tm.assert_numpy_array_equal(labels, exp_labels)
        tm.assert_numpy_array_equal(uniques, exp_uniques)

        data = np.array([2**63, -1, 2**63], dtype=object)
        exp_labels = np.array([0, 1, 0], dtype=np.intp)
        exp_uniques = np.array([2**63, -1], dtype=object)

        labels, uniques = algos.factorize(data)
        tm.assert_numpy_array_equal(labels, exp_labels)
        tm.assert_numpy_array_equal(uniques, exp_uniques) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def c_discrete(self):
        """Discretized form of c

        If c is discrete then this converts it to
        integers from 0 to `n_c_unique`
        """
        if self._c_discrete is None:
            if isinstance(self._cmap, dict):
                self._labels = np.array(
                    [k for k in self._cmap.keys() if k in self.c_unique]
                )
                self._c_discrete = np.zeros_like(self._c, dtype=int)
                for i, label in enumerate(self._labels):
                    self._c_discrete[self._c == label] = i
            else:
                self._c_discrete = np.zeros_like(self._c, dtype=int)
                self._c_discrete[self._mask], self._labels = pd.factorize(
                    self._c_masked, sort=True
                )
        return self._c_discrete 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def process_embarked():
    global df_titanic_data

    # replacing the missing values with the most commmon value in the variable
    df_titanic_data.Embarked[df_titanic_data.Embarked.isnull()] = df_titanic_data.Embarked.dropna().mode().values

    # converting the values into numbers
    df_titanic_data['Embarked'] = pd.factorize(df_titanic_data['Embarked'])[0]

    # binarizing the constructed features
    if keep_binary:
        df_titanic_data = pd.concat([df_titanic_data, pd.get_dummies(df_titanic_data['Embarked']).rename(
            columns=lambda x: 'Embarked_' + str(x))], axis=1)



# Define a helper function that can use RandomForestClassifier for handling the missing values of the age variable 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def process_cabin():
    # refering to the global variable that contains the titanic examples
    global df_titanic_data

    # repllacing the missing value in cabin variable "U0"
    df_titanic_data['Cabin'][df_titanic_data.Cabin.isnull()] = 'U0'

    # the cabin number is a sequence of of alphanumerical digits, so we are going to create some features
    # from the alphabetical part of it
    df_titanic_data['CabinLetter'] = df_titanic_data['Cabin'].map(lambda l: get_cabin_letter(l))
    df_titanic_data['CabinLetter'] = pd.factorize(df_titanic_data['CabinLetter'])[0]

    # binarizing the cabin letters features
    if keep_binary:
        cletters = pd.get_dummies(df_titanic_data['CabinLetter']).rename(columns=lambda x: 'CabinLetter_' + str(x))
        df_titanic_data = pd.concat([df_titanic_data, cletters], axis=1)

    # creating features from the numerical side of the cabin
    df_titanic_data['CabinNumber'] = df_titanic_data['Cabin'].map(lambda x: get_cabin_num(x)).astype(int) + 1

    # scaling the feature
    if keep_scaled:
        scaler_processing = preprocessing.StandardScaler()
    df_titanic_data['CabinNumber_scaled'] = scaler_processing.fit_transform(df_titanic_data.CabinNumber.reshape(-1, 1)) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_factorize(self, data_for_grouping, na_sentinel):
        labels, uniques = pd.factorize(data_for_grouping,
                                       na_sentinel=na_sentinel)
        expected_labels = np.array([0, 0, na_sentinel,
                                   na_sentinel, 1, 1, 0, 2],
                                   dtype=np.intp)
        expected_uniques = data_for_grouping.take([0, 4, 7])

        tm.assert_numpy_array_equal(labels, expected_labels)
        self.assert_extension_array_equal(uniques, expected_uniques) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_factorize_equivalence(self, data_for_grouping, na_sentinel):
        l1, u1 = pd.factorize(data_for_grouping, na_sentinel=na_sentinel)
        l2, u2 = data_for_grouping.factorize(na_sentinel=na_sentinel)

        tm.assert_numpy_array_equal(l1, l2)
        self.assert_extension_array_equal(u1, u2) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_factorize_empty(self, data):
        labels, uniques = pd.factorize(data[:0])
        expected_labels = np.array([], dtype=np.intp)
        expected_uniques = type(data)._from_sequence([], dtype=data[:0].dtype)

        tm.assert_numpy_array_equal(labels, expected_labels)
        self.assert_extension_array_equal(uniques, expected_uniques) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_groupby_extension_agg(self, as_index, data_for_grouping):
        df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4],
                           "B": data_for_grouping})
        result = df.groupby("B", as_index=as_index).A.mean()
        _, index = pd.factorize(data_for_grouping, sort=True)

        index = pd.Index(index, name="B")
        expected = pd.Series([3, 1, 4], index=index, name="A")
        if as_index:
            self.assert_series_equal(result, expected)
        else:
            expected = expected.reset_index()
            self.assert_frame_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_groupby_extension_no_sort(self, data_for_grouping):
        df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4],
                           "B": data_for_grouping})
        result = df.groupby("B", sort=False).A.mean()
        _, index = pd.factorize(data_for_grouping, sort=False)

        index = pd.Index(index, name="B")
        expected = pd.Series([1, 3, 4], index=index, name="A")
        self.assert_series_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_factorized_sort():
    cat = pd.Categorical(['b', 'b', None, 'a'])
    labels, uniques = pd.factorize(cat, sort=True)
    expected_labels = np.array([1, 1, -1, 0], dtype=np.intp)
    expected_uniques = pd.Categorical(['a', 'b'])

    tm.assert_numpy_array_equal(labels, expected_labels)
    tm.assert_categorical_equal(uniques, expected_uniques) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_factorized_sort_ordered():
    cat = pd.Categorical(['b', 'b', None, 'a'],
                         categories=['c', 'b', 'a'],
                         ordered=True)

    labels, uniques = pd.factorize(cat, sort=True)
    expected_labels = np.array([0, 0, -1, 1], dtype=np.intp)
    expected_uniques = pd.Categorical(['b', 'a'],
                                      categories=['c', 'b', 'a'],
                                      ordered=True)

    tm.assert_numpy_array_equal(labels, expected_labels)
    tm.assert_categorical_equal(uniques, expected_uniques) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import factorize [as 别名]
def test_basic(self):

        labels, uniques = algos.factorize(['a', 'b', 'b', 'a', 'a', 'c', 'c',
                                           'c'])
        tm.assert_numpy_array_equal(
            uniques, np.array(['a', 'b', 'c'], dtype=object))

        labels, uniques = algos.factorize(['a', 'b', 'b', 'a',
                                           'a', 'c', 'c', 'c'], sort=True)
        exp = np.array([0, 1, 1, 0, 0, 2, 2, 2], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = np.array(['a', 'b', 'c'], dtype=object)
        tm.assert_numpy_array_equal(uniques, exp)

        labels, uniques = algos.factorize(list(reversed(range(5))))
        exp = np.array([0, 1, 2, 3, 4], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = np.array([4, 3, 2, 1, 0], dtype=np.int64)
        tm.assert_numpy_array_equal(uniques, exp)

        labels, uniques = algos.factorize(list(reversed(range(5))), sort=True)

        exp = np.array([4, 3, 2, 1, 0], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = np.array([0, 1, 2, 3, 4], dtype=np.int64)
        tm.assert_numpy_array_equal(uniques, exp)

        labels, uniques = algos.factorize(list(reversed(np.arange(5.))))
        exp = np.array([0, 1, 2, 3, 4], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = np.array([4., 3., 2., 1., 0.], dtype=np.float64)
        tm.assert_numpy_array_equal(uniques, exp)

        labels, uniques = algos.factorize(list(reversed(np.arange(5.))),
                                          sort=True)
        exp = np.array([4, 3, 2, 1, 0], dtype=np.intp)
        tm.assert_numpy_array_equal(labels, exp)
        exp = np.array([0., 1., 2., 3., 4.], dtype=np.float64)
        tm.assert_numpy_array_equal(uniques, exp)