Python Series.value_counts方法代码示例

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def test_series_groupby_value_counts(df, keys, bins, n, m):

    def rebuild_index(df):
        arr = list(map(df.index.get_level_values, range(df.index.nlevels)))
        df.index = MultiIndex.from_arrays(arr, names=df.index.names)
        return df

    for isort, normalize, sort, ascending, dropna \
            in product((False, True), repeat=5):

        kwargs = dict(normalize=normalize, sort=sort,
                      ascending=ascending, dropna=dropna, bins=bins)

        gr = df.groupby(keys, sort=isort)
        left = gr['3rd'].value_counts(**kwargs)

        gr = df.groupby(keys, sort=isort)
        right = gr['3rd'].apply(Series.value_counts, **kwargs)
        right.index.names = right.index.names[:-1] + ['3rd']

        # have to sort on index because of unstable sort on values
        left, right = map(rebuild_index, (left, right))  # xref GH9212
        tm.assert_series_equal(left.sort_index(), right.sort_index()) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def describe(self):
        """
        Describes this Categorical

        Returns
        -------
        description: `DataFrame`
            A dataframe with frequency and counts by category.
        """
        counts = self.value_counts(dropna=False)
        freqs = counts / float(counts.sum())

        from pandas.core.reshape.concat import concat
        result = concat([counts, freqs], axis=1)
        result.columns = ['counts', 'freqs']
        result.index.name = 'categories'

        return result 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def describe(self):
        """ Describes this Categorical

        Returns
        -------
        description: `DataFrame`
            A dataframe with frequency and counts by category.
        """
        counts = self.value_counts(dropna=False)
        freqs = counts / float(counts.sum())

        from pandas.core.reshape.concat import concat
        result = concat([counts, freqs], axis=1)
        result.columns = ['counts', 'freqs']
        result.index.name = 'categories'

        return result 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def value_counts(self, dropna=True):
        """
        Returns a Series containing counts of each category.

        Every category will have an entry, even those with a count of 0.

        Parameters
        ----------
        dropna : boolean, default True
            Don't include counts of NaN.

        Returns
        -------
        counts : Series

        See Also
        --------
        Series.value_counts

        """
        from numpy import bincount
        from pandas import Series, CategoricalIndex

        code, cat = self._codes, self.categories
        ncat, mask = len(cat), 0 <= code
        ix, clean = np.arange(ncat), mask.all()

        if dropna or clean:
            obs = code if clean else code[mask]
            count = bincount(obs, minlength=ncat or None)
        else:
            count = bincount(np.where(mask, code, ncat))
            ix = np.append(ix, -1)

        ix = self._constructor(ix, dtype=self.dtype,
                               fastpath=True)

        return Series(count, index=CategoricalIndex(ix), dtype='int64') 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def value_counts(self, dropna=True):
        """
        Returns a Series containing counts of each category.

        Every category will have an entry, even those with a count of 0.

        Parameters
        ----------
        dropna : boolean, default True
            Don't include counts of NaN, even if NaN is a category.

        Returns
        -------
        counts : Series

        See Also
        --------
        Series.value_counts

        """
        from numpy import bincount
        from pandas import isna, Series, CategoricalIndex

        obj = (self.remove_categories([np.nan]) if dropna and
               isna(self.categories).any() else self)
        code, cat = obj._codes, obj.categories
        ncat, mask = len(cat), 0 <= code
        ix, clean = np.arange(ncat), mask.all()

        if dropna or clean:
            obs = code if clean else code[mask]
            count = bincount(obs, minlength=ncat or None)
        else:
            count = bincount(np.where(mask, code, ncat))
            ix = np.append(ix, -1)

        ix = self._constructor(ix, dtype=self.dtype,
                               fastpath=True)

        return Series(count, index=CategoricalIndex(ix), dtype='int64') 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def value_counts(self, dropna=True):
        """
        Returns a Series containing counts of each category.

        Every category will have an entry, even those with a count of 0.

        Parameters
        ----------
        dropna : boolean, default True
            Don't include counts of NaN.

        Returns
        -------
        counts : Series

        See Also
        --------
        Series.value_counts

        """

        from pandas import Index, Series

        # compute counts on the data with no nans
        data = self._data[~self._mask]
        value_counts = Index(data).value_counts()
        array = value_counts.values

        # TODO(extension)
        # if we have allow Index to hold an ExtensionArray
        # this is easier
        index = value_counts.index.astype(object)

        # if we want nans, count the mask
        if not dropna:

            # TODO(extension)
            # appending to an Index *always* infers
            # w/o passing the dtype
            array = np.append(array, [self._mask.sum()])
            index = Index(np.concatenate(
                [index.values,
                 np.array([np.nan], dtype=object)]), dtype=object)

        return Series(array, index=index) 

# 需要导入模块: from pandas import Series [as 别名]
# 或者: from pandas.Series import value_counts [as 别名]
def test_series_groupby_value_counts(n, m):
    np.random.seed(1234)

    def rebuild_index(df):
        arr = list(map(df.index.get_level_values, range(df.index.nlevels)))
        df.index = MultiIndex.from_arrays(arr, names=df.index.names)
        return df

    def check_value_counts(df, keys, bins):
        for isort, normalize, sort, ascending, dropna \
                in product((False, True), repeat=5):

            kwargs = dict(normalize=normalize, sort=sort,
                          ascending=ascending, dropna=dropna, bins=bins)

            gr = df.groupby(keys, sort=isort)
            left = gr['3rd'].value_counts(**kwargs)

            gr = df.groupby(keys, sort=isort)
            right = gr['3rd'].apply(Series.value_counts, **kwargs)
            right.index.names = right.index.names[:-1] + ['3rd']

            # have to sort on index because of unstable sort on values
            left, right = map(rebuild_index, (left, right))  # xref GH9212
            tm.assert_series_equal(left.sort_index(), right.sort_index())

    def loop(df):
        bins = None, np.arange(0, max(5, df['3rd'].max()) + 1, 2)
        keys = '1st', '2nd', ('1st', '2nd')
        for k, b in product(keys, bins):
            check_value_counts(df, k, b)

    days = date_range('2015-08-24', periods=10)

    frame = DataFrame({
        '1st': np.random.choice(
            list('abcd'), n),
        '2nd': np.random.choice(days, n),
        '3rd': np.random.randint(1, m + 1, n)
    })

    loop(frame)

    frame.loc[1::11, '1st'] = np.nan
    frame.loc[3::17, '2nd'] = np.nan
    frame.loc[7::19, '3rd'] = np.nan
    frame.loc[8::19, '3rd'] = np.nan
    frame.loc[9::19, '3rd'] = np.nan

    loop(frame)