7347756297

Committed 28 Dec 2023 12:48PM UTC coverage: 99.196% (-0.003%) from 99.199%

Build # 7347756297

Build Type

Pull #250

github

Committed by

web-flow

Commit Message

Merge branch 'master' into looseversion

Pull Request Pull Request #250: Remove use of LooseVersion and hide get_renderer warning

Run Details

1727 of 1741 relevant lines covered (99.2%)

1.95 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

97.58

/upsetplot/data.py

from __future__ import print_function, division, absolute_import
from numbers import Number
import warnings

import pandas as pd
import numpy as np


def generate_samples(seed=0, n_samples=10000, n_categories=3):
    """Generate artificial samples assigned to set intersections

    Parameters
    ----------
    seed : int
        A seed for randomisation
    n_samples : int
        Number of samples to generate
    n_categories : int
        Number of categories (named "cat0", "cat1", ...) to generate

    Returns
    -------
    DataFrame
        Field 'value' is a weight or score for each element.
        Field 'index' is a unique id for each element.
        Index includes a boolean indicator mask for each category.

        Note: Further fields may be added in future versions.

    See Also
    --------
    generate_counts : Generates the counts for each subset of categories
        corresponding to these samples.
    """
    rng = np.random.RandomState(seed)
    df = pd.DataFrame({"value": np.zeros(n_samples)})
    for i in range(n_categories):
        r = rng.rand(n_samples)
        df["cat%d" % i] = r > rng.rand()
        df["value"] += r

    df.reset_index(inplace=True)
    df.set_index(["cat%d" % i for i in range(n_categories)], inplace=True)
    return df


def generate_counts(seed=0, n_samples=10000, n_categories=3):
    """Generate artificial counts corresponding to set intersections

    Parameters
    ----------
    seed : int
        A seed for randomisation
    n_samples : int
        Number of samples to generate statistics over
    n_categories : int
        Number of categories (named "cat0", "cat1", ...) to generate

    Returns
    -------
    Series
        Counts indexed by boolean indicator mask for each category.

    See Also
    --------
    generate_samples : Generates a DataFrame of samples that these counts are
        derived from.
    """
    df = generate_samples(seed=seed, n_samples=n_samples, n_categories=n_categories)
    return df.value.groupby(level=list(range(n_categories))).count()


def generate_data(seed=0, n_samples=10000, n_sets=3, aggregated=False):
    warnings.warn(
        "generate_data was replaced by generate_counts in version "
        "0.3 and will be removed in version 0.4.",
        DeprecationWarning,
    )
    if aggregated:
        return generate_counts(seed=seed, n_samples=n_samples, n_categories=n_sets)
    else:
        return generate_samples(seed=seed, n_samples=n_samples, n_categories=n_sets)[
            "value"
        ]


def from_indicators(indicators, data=None):
    """Load category membership indicated by a boolean indicator matrix

    This loader also supports the case where the indicator columns can be
    derived from `data`.

    .. versionadded:: 0.6

    Parameters
    ----------
    indicators : DataFrame-like of booleans, Sequence of str, or callable
        Specifies the category indicators (boolean mask arrays) within
        ``data``, i.e. which records in ``data`` belong to which categories.

        If a list of strings, these should be column names found in ``data``
        whose values are boolean mask arrays.

        If a DataFrame, its columns should correspond to categories, and its
        index should be a subset of those in ``data``, values should be True
        where a data record is in that category, and False or NA otherwise.

        If callable, it will be applied to ``data`` after the latter is
        converted to a Series or DataFrame.

    data : Series-like or DataFrame-like, optional
        If given, the index of category membership is attached to this data.
        It must have the same length as `indicators`.
        If not given, the series will contain the value 1.

    Returns
    -------
    DataFrame or Series
        `data` is returned with its index indicating category membership.
        It will be a Series if `data` is a Series or 1d numeric array or None.

    Notes
    -----
    Categories with indicators that are all False will be removed.

    Examples
    --------
    >>> import pandas as pd
    >>> from upsetplot import from_indicators
    >>>
    >>> # Just indicators:
    >>> indicators = {"cat1": [True, False, True, False],
    ...               "cat2": [False, True, False, False],
    ...               "cat3": [True, True, False, False]}
    >>> from_indicators(indicators)
    cat1   cat2   cat3
    True   False  True     1.0
    False  True   True     1.0
    True   False  False    1.0
    False  False  False    1.0
    Name: ones, dtype: float64
    >>>
    >>> # Where indicators are included within data, specifying
    >>> # columns by name:
    >>> data = pd.DataFrame({"value": [5, 4, 6, 4], **indicators})
    >>> from_indicators(["cat1", "cat3"], data=data)
                 value   cat1   cat2   cat3
    cat1  cat3
    True  True       5   True  False   True
    False True       4  False   True   True
    True  False      6   True  False  False
    False False      4  False  False  False
    >>>
    >>> # Making indicators out of all boolean columns:
    >>> from_indicators(lambda data: data.select_dtypes(bool), data=data)
                       value   cat1   cat2   cat3
    cat1  cat2  cat3
    True  False True       5   True  False   True
    False True  True       4  False   True   True
    True  False False      6   True  False  False
    False False False      4  False  False  False
    >>>
    >>> # Using a dataset with missing data, we can use missingness as
    >>> # an indicator:
    >>> data = pd.DataFrame({"val1": [pd.NA, .7, pd.NA, .9],
    ...                      "val2": ["male", pd.NA, "female", "female"],
    ...                      "val3": [pd.NA, pd.NA, 23000, 78000]})
    >>> from_indicators(pd.isna, data=data)
                       val1    val2   val3
    val1  val2  val3
    True  False True   <NA>    male   <NA>
    False True  True    0.7    <NA>   <NA>
    True  False False  <NA>  female  23000
    False False False   0.9  female  78000
    """
    if data is not None:
        data = _convert_to_pandas(data)

    if callable(indicators):
        if data is None:
            raise ValueError("data must be provided when indicators is " "callable")
        indicators = indicators(data)

    try:
        indicators[0]
    except Exception:
        pass
    else:
        if isinstance(indicators[0], (str, int)):
            if data is None:
                raise ValueError(
                    "data must be provided when indicators are "
                    "specified as a list of columns"
                )
            if isinstance(indicators, tuple):
                raise ValueError("indicators as tuple is not supported")
            # column array
            indicators = data[indicators]

    indicators = pd.DataFrame(indicators).fillna(False).infer_objects()
    # drop all-False (should we be dropping all-True also? making an option?)
    indicators = indicators.loc[:, indicators.any(axis=0)]

    if not all(dtype.kind == "b" for dtype in indicators.dtypes):
        raise ValueError("The indicators must all be boolean")

    if data is not None:
        if not (
            isinstance(indicators.index, pd.RangeIndex)
            and indicators.index[0] == 0
            and indicators.index[-1] == len(data) - 1
        ):
            # index is specified on indicators. Need to align it to data
            if not indicators.index.isin(data.index).all():
                raise ValueError(
                    "If indicators.index is not the default, "
                    "all its values must be present in "
                    "data.index"
                )
            indicators = indicators.reindex(index=data.index, fill_value=False)
    else:
        data = pd.Series(np.ones(len(indicators)), name="ones")

    indicators.set_index(list(indicators.columns), inplace=True)
    data.index = indicators.index

    return data


def _convert_to_pandas(data, copy=True):
    is_series = False
    if hasattr(data, "loc"):
        if copy:
            data = data.copy(deep=False)
        is_series = data.ndim == 1
    elif len(data):
        try:
            is_series = isinstance(data[0], Number)
        except KeyError:
            is_series = False
    if is_series:
        data = pd.Series(data)
    else:
        data = pd.DataFrame(data)
    return data


def from_memberships(memberships, data=None):
    """Load data where each sample has a collection of category names

    The output should be suitable for passing to `UpSet` or `plot`.

    Parameters
    ----------
    memberships : sequence of collections of strings
        Each element corresponds to a data point, indicating the sets it is a
        member of.  Each category is named by a string.
    data : Series-like or DataFrame-like, optional
        If given, the index of category memberships is attached to this data.
        It must have the same length as `memberships`.
        If not given, the series will contain the value 1.

    Returns
    -------
    DataFrame or Series
        `data` is returned with its index indicating category membership.
        It will be a Series if `data` is a Series or 1d numeric array.
        The index will have levels ordered by category names.

    Examples
    --------
    >>> from upsetplot import from_memberships
    >>> from_memberships([
    ...     ['cat1', 'cat3'],
    ...     ['cat2', 'cat3'],
    ...     ['cat1'],
    ...     []
    ... ])
    cat1   cat2   cat3
    True   False  True     1
    False  True   True     1
    True   False  False    1
    False  False  False    1
    Name: ones, dtype: ...
    >>> # now with data:
    >>> import numpy as np
    >>> from_memberships([
    ...     ['cat1', 'cat3'],
    ...     ['cat2', 'cat3'],
    ...     ['cat1'],
    ...     []
    ... ], data=np.arange(12).reshape(4, 3))
                       0   1   2
    cat1  cat2  cat3
    True  False True   0   1   2
    False True  True   3   4   5
    True  False False  6   7   8
    False False False  9  10  11
    """
    df = pd.DataFrame([{name: True for name in names} for names in memberships])
    for set_name in df.columns:
        if not hasattr(set_name, "lower"):
            raise ValueError("Category names should be strings")
    if df.shape[1] == 0:
        raise ValueError("Require at least one category. None were found.")
    df.sort_index(axis=1, inplace=True)
    df.fillna(False, inplace=True)
    df = df.astype(bool)
    df.set_index(list(df.columns), inplace=True)
    if data is None:
        return df.assign(ones=1)["ones"]

    data = _convert_to_pandas(data)
    if len(data) != len(df):
        raise ValueError(
            "memberships and data must have the same length. "
            "Got len(memberships) == %d, len(data) == %d"
            % (len(memberships), len(data))
        )
    data.index = df.index
    return data


def from_contents(contents, data=None, id_column="id"):
    """Build data from category listings

    Parameters
    ----------
    contents : Mapping (or iterable over pairs) of strings to sets
        Keys are category names, values are sets of identifiers (int or
        string).
    data : DataFrame, optional
        If provided, this should be indexed by the identifiers used in
        `contents`.
    id_column : str, default='id'
        The column name to use for the identifiers in the output.

    Returns
    -------
    DataFrame
        `data` is returned with its index indicating category membership,
        including a column named according to id_column.
        If data is not given, the order of rows is not assured.

    Notes
    -----
    The order of categories in the output DataFrame is determined from
    `contents`, which may have non-deterministic iteration order.

    Examples
    --------
    >>> from upsetplot import from_contents
    >>> contents = {'cat1': ['a', 'b', 'c'],
    ...             'cat2': ['b', 'd'],
    ...             'cat3': ['e']}
    >>> from_contents(contents)
                      id
    cat1  cat2  cat3
    True  False False  a
          True  False  b
          False False  c
    False True  False  d
          False True   e
    >>> import pandas as pd
    >>> contents = {'cat1': [0, 1, 2],
    ...             'cat2': [1, 3],
    ...             'cat3': [4]}
    >>> data = pd.DataFrame({'favourite': ['green', 'red', 'red',
    ...                                    'yellow', 'blue']})
    >>> from_contents(contents, data=data)
                       id favourite
    cat1  cat2  cat3
    True  False False   0     green
          True  False   1       red
          False False   2       red
    False True  False   3    yellow
          False True    4      blue
    """
    cat_series = [
        pd.Series(True, index=list(elements), name=name)
        for name, elements in contents.items()
    ]
    if not all(s.index.is_unique for s in cat_series):
        raise ValueError("Got duplicate ids in a category")

    df = pd.concat(cat_series, axis=1, sort=False)
    if id_column in df.columns:
        raise ValueError("A category cannot be named %r" % id_column)
    df.fillna(False, inplace=True)
    cat_names = list(df.columns)

    if data is not None:
        if set(df.columns).intersection(data.columns):
            raise ValueError("Data columns overlap with category names")
        if id_column in data.columns:
            raise ValueError("data cannot contain a column named %r" % id_column)
        not_in_data = df.drop(data.index, axis=0, errors="ignore")
        if len(not_in_data):
            raise ValueError(
                "Found identifiers in contents that are not in "
                "data: %r" % not_in_data.index.values
            )
        df = df.reindex(index=data.index).fillna(False)
        df = pd.concat([data, df], axis=1, sort=False)
    df.index.name = id_column
    return df.reset_index().set_index(cat_names)

1	from __future__ import print_function, division, absolute_import	2✔
2	from numbers import Number	2✔
3	import warnings	2✔
4		2✔
5	import pandas as pd	2✔
6	import numpy as np	2✔
7
8
9	def generate_samples(seed=0, n_samples=10000, n_categories=3):	2✔
10	"""Generate artificial samples assigned to set intersections
11
12	Parameters
13	----------
14	seed : int
15	A seed for randomisation
16	n_samples : int
17	Number of samples to generate
18	n_categories : int
19	Number of categories (named "cat0", "cat1", ...) to generate
20
21	Returns
22	-------
23	DataFrame
24	Field 'value' is a weight or score for each element.
25	Field 'index' is a unique id for each element.
26	Index includes a boolean indicator mask for each category.
27
28	Note: Further fields may be added in future versions.
29
30	See Also
31	--------
32	generate_counts : Generates the counts for each subset of categories
33	corresponding to these samples.
34	"""
35	rng = np.random.RandomState(seed)	2✔
36	df = pd.DataFrame({"value": np.zeros(n_samples)})	2✔
37	for i in range(n_categories):	2✔
38	r = rng.rand(n_samples)	2✔
39	df["cat%d" % i] = r > rng.rand()	2✔
40	df["value"] += r	2✔
41
42	df.reset_index(inplace=True)	2✔
43	df.set_index(["cat%d" % i for i in range(n_categories)], inplace=True)	2✔
44	return df	2✔
45
46
47	def generate_counts(seed=0, n_samples=10000, n_categories=3):	2✔
48	"""Generate artificial counts corresponding to set intersections
49
50	Parameters
51	----------
52	seed : int
53	A seed for randomisation
54	n_samples : int
55	Number of samples to generate statistics over
56	n_categories : int
57	Number of categories (named "cat0", "cat1", ...) to generate
58
59	Returns
60	-------
61	Series
62	Counts indexed by boolean indicator mask for each category.
63
64	See Also
65	--------
66	generate_samples : Generates a DataFrame of samples that these counts are
67	derived from.
68	"""
69	df = generate_samples(seed=seed, n_samples=n_samples, n_categories=n_categories)	2✔
70	return df.value.groupby(level=list(range(n_categories))).count()	2✔
71
72
73	def generate_data(seed=0, n_samples=10000, n_sets=3, aggregated=False):	2✔
74	warnings.warn(	2✔
75	"generate_data was replaced by generate_counts in version "	2✔
76	"0.3 and will be removed in version 0.4.",
77	DeprecationWarning,	2✔
78	)
79	if aggregated:	2✔
80	return generate_counts(seed=seed, n_samples=n_samples, n_categories=n_sets)	×
81	else:	×
82	return generate_samples(seed=seed, n_samples=n_samples, n_categories=n_sets)[	2✔
83	"value"	2✔
84	]
85
86
87	def from_indicators(indicators, data=None):	2✔
88	"""Load category membership indicated by a boolean indicator matrix
89
90	This loader also supports the case where the indicator columns can be
91	derived from `data`.
92
93	.. versionadded:: 0.6
94
95	Parameters
96	----------
97	indicators : DataFrame-like of booleans, Sequence of str, or callable
98	Specifies the category indicators (boolean mask arrays) within
99	``data``, i.e. which records in ``data`` belong to which categories.
100
101	If a list of strings, these should be column names found in ``data``
102	whose values are boolean mask arrays.
103
104	If a DataFrame, its columns should correspond to categories, and its
105	index should be a subset of those in ``data``, values should be True
106	where a data record is in that category, and False or NA otherwise.
107
108	If callable, it will be applied to ``data`` after the latter is
109	converted to a Series or DataFrame.
110
111	data : Series-like or DataFrame-like, optional
112	If given, the index of category membership is attached to this data.
113	It must have the same length as `indicators`.
114	If not given, the series will contain the value 1.
115
116	Returns
117	-------
118	DataFrame or Series
119	`data` is returned with its index indicating category membership.
120	It will be a Series if `data` is a Series or 1d numeric array or None.
121
122	Notes
123	-----
124	Categories with indicators that are all False will be removed.
125
126	Examples
127	--------
128	>>> import pandas as pd
129	>>> from upsetplot import from_indicators
130	>>>
131	>>> # Just indicators:
132	>>> indicators = {"cat1": [True, False, True, False],
133	... "cat2": [False, True, False, False],
134	... "cat3": [True, True, False, False]}
135	>>> from_indicators(indicators)
136	cat1 cat2 cat3
137	True False True 1.0
138	False True True 1.0
139	True False False 1.0
140	False False False 1.0
141	Name: ones, dtype: float64
142	>>>
143	>>> # Where indicators are included within data, specifying
144	>>> # columns by name:
145	>>> data = pd.DataFrame({"value": [5, 4, 6, 4], **indicators})
146	>>> from_indicators(["cat1", "cat3"], data=data)
147	value cat1 cat2 cat3
148	cat1 cat3
149	True True 5 True False True
150	False True 4 False True True
151	True False 6 True False False
152	False False 4 False False False
153	>>>
154	>>> # Making indicators out of all boolean columns:
155	>>> from_indicators(lambda data: data.select_dtypes(bool), data=data)
156	value cat1 cat2 cat3
157	cat1 cat2 cat3
158	True False True 5 True False True
159	False True True 4 False True True
160	True False False 6 True False False
161	False False False 4 False False False
162	>>>
163	>>> # Using a dataset with missing data, we can use missingness as
164	>>> # an indicator:
165	>>> data = pd.DataFrame({"val1": [pd.NA, .7, pd.NA, .9],
166	... "val2": ["male", pd.NA, "female", "female"],
167	... "val3": [pd.NA, pd.NA, 23000, 78000]})
168	>>> from_indicators(pd.isna, data=data)
169	val1 val2 val3
170	val1 val2 val3
171	True False True <NA> male <NA>
172	False True True 0.7 <NA> <NA>
173	True False False <NA> female 23000
174	False False False 0.9 female 78000
175	"""
176	if data is not None:	2✔
177	data = _convert_to_pandas(data)	2✔
178
179	if callable(indicators):	2✔
180	if data is None:	2✔
181	raise ValueError("data must be provided when indicators is " "callable")	2✔
182	indicators = indicators(data)	2✔
183
184	try:	2✔
185	indicators[0]	2✔
186	except Exception:	2✔
187	pass	2✔
188	else:	×
189	if isinstance(indicators[0], (str, int)):	2✔
190	if data is None:	2✔
191	raise ValueError(	2✔
192	"data must be provided when indicators are "	2✔
193	"specified as a list of columns"
194	)
195	if isinstance(indicators, tuple):	2✔
196	raise ValueError("indicators as tuple is not supported")	2✔
197	# column array
198	indicators = data[indicators]	2✔
199
200	indicators = pd.DataFrame(indicators).fillna(False).infer_objects()	2✔
201	# drop all-False (should we be dropping all-True also? making an option?)
202	indicators = indicators.loc[:, indicators.any(axis=0)]	2✔
203
204	if not all(dtype.kind == "b" for dtype in indicators.dtypes):	2✔
205	raise ValueError("The indicators must all be boolean")	2✔
206
207	if data is not None:	2✔
208	if not (	2✔
209	isinstance(indicators.index, pd.RangeIndex)	2✔
210	and indicators.index[0] == 0	2✔
211	and indicators.index[-1] == len(data) - 1	2✔
212	):
213	# index is specified on indicators. Need to align it to data
214	if not indicators.index.isin(data.index).all():	2✔
215	raise ValueError(	2✔
216	"If indicators.index is not the default, "	2✔
217	"all its values must be present in "
218	"data.index"
219	)
220	indicators = indicators.reindex(index=data.index, fill_value=False)	2✔
221	else:
222	data = pd.Series(np.ones(len(indicators)), name="ones")	2✔
223
224	indicators.set_index(list(indicators.columns), inplace=True)	2✔
225	data.index = indicators.index	2✔
226
227	return data	2✔
228
229
230	def _convert_to_pandas(data, copy=True):	2✔
231	is_series = False	2✔
232	if hasattr(data, "loc"):	2✔
233	if copy:	2✔
234	data = data.copy(deep=False)	2✔
235	is_series = data.ndim == 1	2✔
236	elif len(data):	2✔
237	try:	2✔
238	is_series = isinstance(data[0], Number)	2✔
239	except KeyError:	2✔
240	is_series = False	2✔
241	if is_series:	2✔
242	data = pd.Series(data)	2✔
243	else:
244	data = pd.DataFrame(data)	2✔
245	return data	2✔
246
247
248	def from_memberships(memberships, data=None):	2✔
249	"""Load data where each sample has a collection of category names
250
251	The output should be suitable for passing to `UpSet` or `plot`.
252
253	Parameters
254	----------
255	memberships : sequence of collections of strings
256	Each element corresponds to a data point, indicating the sets it is a
257	member of. Each category is named by a string.
258	data : Series-like or DataFrame-like, optional
259	If given, the index of category memberships is attached to this data.
260	It must have the same length as `memberships`.
261	If not given, the series will contain the value 1.
262
263	Returns
264	-------
265	DataFrame or Series
266	`data` is returned with its index indicating category membership.
267	It will be a Series if `data` is a Series or 1d numeric array.
268	The index will have levels ordered by category names.
269
270	Examples
271	--------
272	>>> from upsetplot import from_memberships
273	>>> from_memberships([
274	... ['cat1', 'cat3'],
275	... ['cat2', 'cat3'],
276	... ['cat1'],
277	... []
278	... ])
279	cat1 cat2 cat3
280	True False True 1
281	False True True 1
282	True False False 1
283	False False False 1
284	Name: ones, dtype: ...
285	>>> # now with data:
286	>>> import numpy as np
287	>>> from_memberships([
288	... ['cat1', 'cat3'],
289	... ['cat2', 'cat3'],
290	... ['cat1'],
291	... []
292	... ], data=np.arange(12).reshape(4, 3))
293	0 1 2
294	cat1 cat2 cat3
295	True False True 0 1 2
296	False True True 3 4 5
297	True False False 6 7 8
298	False False False 9 10 11
299	"""
300	df = pd.DataFrame([{name: True for name in names} for names in memberships])	2✔
301	for set_name in df.columns:	2✔
302	if not hasattr(set_name, "lower"):	2✔
303	raise ValueError("Category names should be strings")	2✔
304	if df.shape[1] == 0:	2✔
305	raise ValueError("Require at least one category. None were found.")	2✔
306	df.sort_index(axis=1, inplace=True)	2✔
307	df.fillna(False, inplace=True)	2✔
308	df = df.astype(bool)	2✔
309	df.set_index(list(df.columns), inplace=True)	2✔
310	if data is None:	2✔
311	return df.assign(ones=1)["ones"]	2✔
312
313	data = _convert_to_pandas(data)	2✔
314	if len(data) != len(df):	2✔
315	raise ValueError(	2✔
316	"memberships and data must have the same length. "	2✔
317	"Got len(memberships) == %d, len(data) == %d"
318	% (len(memberships), len(data))	2✔
319	)
320	data.index = df.index	2✔
321	return data	2✔
322
323
324	def from_contents(contents, data=None, id_column="id"):	2✔
325	"""Build data from category listings
326
327	Parameters
328	----------
329	contents : Mapping (or iterable over pairs) of strings to sets
330	Keys are category names, values are sets of identifiers (int or
331	string).
332	data : DataFrame, optional
333	If provided, this should be indexed by the identifiers used in
334	`contents`.
335	id_column : str, default='id'
336	The column name to use for the identifiers in the output.
337
338	Returns
339	-------
340	DataFrame
341	`data` is returned with its index indicating category membership,
342	including a column named according to id_column.
343	If data is not given, the order of rows is not assured.
344
345	Notes
346	-----
347	The order of categories in the output DataFrame is determined from
348	`contents`, which may have non-deterministic iteration order.
349
350	Examples
351	--------
352	>>> from upsetplot import from_contents
353	>>> contents = {'cat1': ['a', 'b', 'c'],
354	... 'cat2': ['b', 'd'],
355	... 'cat3': ['e']}
356	>>> from_contents(contents)
357	id
358	cat1 cat2 cat3
359	True False False a
360	True False b
361	False False c
362	False True False d
363	False True e
364	>>> import pandas as pd
365	>>> contents = {'cat1': [0, 1, 2],
366	... 'cat2': [1, 3],
367	... 'cat3': [4]}
368	>>> data = pd.DataFrame({'favourite': ['green', 'red', 'red',
369	... 'yellow', 'blue']})
370	>>> from_contents(contents, data=data)
371	id favourite
372	cat1 cat2 cat3
373	True False False 0 green
374	True False 1 red
375	False False 2 red
376	False True False 3 yellow
377	False True 4 blue
378	"""
379	cat_series = [	2✔
380	pd.Series(True, index=list(elements), name=name)	2✔
381	for name, elements in contents.items()	2✔
382	]
383	if not all(s.index.is_unique for s in cat_series):	2✔
384	raise ValueError("Got duplicate ids in a category")	2✔
385
386	df = pd.concat(cat_series, axis=1, sort=False)	2✔
387	if id_column in df.columns:	2✔
388	raise ValueError("A category cannot be named %r" % id_column)	2✔
389	df.fillna(False, inplace=True)	2✔
390	cat_names = list(df.columns)	2✔
391
392	if data is not None:	2✔
393	if set(df.columns).intersection(data.columns):	2✔
394	raise ValueError("Data columns overlap with category names")	2✔
395	if id_column in data.columns:	2✔
396	raise ValueError("data cannot contain a column named %r" % id_column)	2✔
397	not_in_data = df.drop(data.index, axis=0, errors="ignore")	2✔
398	if len(not_in_data):	2✔
399	raise ValueError(	2✔
400	"Found identifiers in contents that are not in "	2✔
401	"data: %r" % not_in_data.index.values	2✔
402	)
403	df = df.reindex(index=data.index).fillna(False)	2✔
404	df = pd.concat([data, df], axis=1, sort=False)	2✔
405	df.index.name = id_column	2✔
406	return df.reset_index().set_index(cat_names)	2✔

jnothman / UpSetPlot / 7347756297

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous