Initial draft: from_dummies (#41902)

pckSF · web-flow · commit ed55bdf19859 · 2022-06-30T15:25:20.000-04:00
diff --git a/doc/source/reference/general_functions.rst b/doc/source/reference/general_functions.rst
@@ -23,6 +23,7 @@ Data manipulations
    merge_asof
    concat
    get_dummies
+   from_dummies
    factorize
    unique
    wide_to_long
diff --git a/doc/source/user_guide/reshaping.rst b/doc/source/user_guide/reshaping.rst
@@ -706,6 +706,30 @@ To choose another dtype, use the ``dtype`` argument:
 
     pd.get_dummies(df, dtype=bool).dtypes
 
+.. versionadded:: 1.5.0
+
+To convert a "dummy" or "indicator" ``DataFrame``, into a categorical ``DataFrame``,
+for example ``k`` columns of a ``DataFrame`` containing 1s and 0s can derive a
+``DataFrame`` which has ``k`` distinct values using
+:func:`~pandas.from_dummies`:
+
+.. ipython:: python
+
+   df = pd.DataFrame({"prefix_a": [0, 1, 0], "prefix_b": [1, 0, 1]})
+   df
+
+   pd.from_dummies(df, sep="_")
+
+Dummy coded data only requires ``k - 1`` categories to be included, in this case
+the ``k`` th category is the default category, implied by not being assigned any of
+the other ``k - 1`` categories, can be passed via ``default_category``.
+
+.. ipython:: python
+
+   df = pd.DataFrame({"prefix_a": [0, 1, 0]})
+   df
+
+   pd.from_dummies(df, sep="_", default_category="b")
 
 .. _reshaping.factorize:
 
diff --git a/doc/source/whatsnew/v1.5.0.rst b/doc/source/whatsnew/v1.5.0.rst
@@ -100,6 +100,25 @@ as seen in the following example.
                1 2021-01-02 08:00:00  4
                2 2021-01-02 16:00:00  5
 
+.. _whatsnew_150.enhancements.from_dummies:
+
+from_dummies
+^^^^^^^^^^^^
+
+Added new function :func:`~pandas.from_dummies` to convert a dummy coded :class:`DataFrame` into a categorical :class:`DataFrame`.
+
+Example::
+
+.. ipython:: python
+
+    import pandas as pd
+
+    df = pd.DataFrame({"col1_a": [1, 0, 1], "col1_b": [0, 1, 0],
+                       "col2_a": [0, 1, 0], "col2_b": [1, 0, 0],
+                       "col2_c": [0, 0, 1]})
+
+    pd.from_dummies(df, sep="_")
+
 .. _whatsnew_150.enhancements.orc:
 
 Writing to ORC files
diff --git a/pandas/__init__.py b/pandas/__init__.py
@@ -128,6 +128,7 @@
     pivot,
     pivot_table,
     get_dummies,
+    from_dummies,
     cut,
     qcut,
 )
@@ -361,6 +362,7 @@ def __getattr__(name):
     "eval",
     "factorize",
     "get_dummies",
+    "from_dummies",
     "get_option",
     "infer_freq",
     "interval_range",
diff --git a/pandas/core/reshape/api.py b/pandas/core/reshape/api.py
@@ -1,7 +1,10 @@
 # flake8: noqa:F401
 
 from pandas.core.reshape.concat import concat
-from pandas.core.reshape.encoding import get_dummies
+from pandas.core.reshape.encoding import (
+    from_dummies,
+    get_dummies,
+)
 from pandas.core.reshape.melt import (
     lreshape,
     melt,
diff --git a/pandas/core/reshape/encoding.py b/pandas/core/reshape/encoding.py
@@ -1,6 +1,8 @@
 from __future__ import annotations
 
+from collections import defaultdict
 import itertools
+from typing import Hashable
 
 import numpy as np
 
@@ -68,6 +70,7 @@ def get_dummies(
     See Also
     --------
     Series.str.get_dummies : Convert Series to dummy codes.
+    :func:`~pandas.from_dummies` : Convert dummy codes to categorical ``DataFrame``.
 
     Notes
     -----
@@ -316,3 +319,202 @@ def get_empty_frame(data) -> DataFrame:
             dummy_mat = dummy_mat[:, 1:]
             dummy_cols = dummy_cols[1:]
         return DataFrame(dummy_mat, index=index, columns=dummy_cols)
+
+
+def from_dummies(
+    data: DataFrame,
+    sep: None | str = None,
+    default_category: None | Hashable | dict[str, Hashable] = None,
+) -> DataFrame:
+    """
+    Create a categorical ``DataFrame`` from a ``DataFrame`` of dummy variables.
+
+    Inverts the operation performed by :func:`~pandas.get_dummies`.
+
+    .. versionadded:: 1.5.0
+
+    Parameters
+    ----------
+    data : DataFrame
+        Data which contains dummy-coded variables in form of integer columns of
+        1's and 0's.
+    sep : str, default None
+        Separator used in the column names of the dummy categories they are
+        character indicating the separation of the categorical names from the prefixes.
+        For example, if your column names are 'prefix_A' and 'prefix_B',
+        you can strip the underscore by specifying sep='_'.
+    default_category : None, Hashable or dict of Hashables, default None
+        The default category is the implied category when a value has none of the
+        listed categories specified with a one, i.e. if all dummies in a row are
+        zero. Can be a single value for all variables or a dict directly mapping
+        the default categories to a prefix of a variable.
+
+    Returns
+    -------
+    DataFrame
+        Categorical data decoded from the dummy input-data.
+
+    Raises
+    ------
+    ValueError
+        * When the input ``DataFrame`` ``data`` contains NA values.
+        * When the input ``DataFrame`` ``data`` contains column names with separators
+          that do not match the separator specified with ``sep``.
+        * When a ``dict`` passed to ``default_category`` does not include an implied
+          category for each prefix.
+        * When a value in ``data`` has more than one category assigned to it.
+        * When ``default_category=None`` and a value in ``data`` has no category
+          assigned to it.
+    TypeError
+        * When the input ``data`` is not of type ``DataFrame``.
+        * When the input ``DataFrame`` ``data`` contains non-dummy data.
+        * When the passed ``sep`` is of a wrong data type.
+        * When the passed ``default_category`` is of a wrong data type.
+
+    See Also
+    --------
+    :func:`~pandas.get_dummies` : Convert ``Series`` or ``DataFrame`` to dummy codes.
+    :class:`~pandas.Categorical` : Represent a categorical variable in classic.
+
+    Notes
+    -----
+    The columns of the passed dummy data should only include 1's and 0's,
+    or boolean values.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"a": [1, 0, 0, 1], "b": [0, 1, 0, 0],
+    ...                    "c": [0, 0, 1, 0]})
+
+    >>> df
+       a  b  c
+    0  1  0  0
+    1  0  1  0
+    2  0  0  1
+    3  1  0  0
+
+    >>> pd.from_dummies(df)
+    0     a
+    1     b
+    2     c
+    3     a
+
+    >>> df = pd.DataFrame({"col1_a": [1, 0, 1], "col1_b": [0, 1, 0],
+    ...                    "col2_a": [0, 1, 0], "col2_b": [1, 0, 0],
+    ...                    "col2_c": [0, 0, 1]})
+
+    >>> df
+          col1_a  col1_b  col2_a  col2_b  col2_c
+    0       1       0       0       1       0
+    1       0       1       1       0       0
+    2       1       0       0       0       1
+
+    >>> pd.from_dummies(df, sep="_")
+        col1    col2
+    0    a       b
+    1    b       a
+    2    a       c
+
+    >>> df = pd.DataFrame({"col1_a": [1, 0, 0], "col1_b": [0, 1, 0],
+    ...                    "col2_a": [0, 1, 0], "col2_b": [1, 0, 0],
+    ...                    "col2_c": [0, 0, 0]})
+
+    >>> df
+          col1_a  col1_b  col2_a  col2_b  col2_c
+    0       1       0       0       1       0
+    1       0       1       1       0       0
+    2       0       0       0       0       0
+
+    >>> pd.from_dummies(df, sep="_", default_category={"col1": "d", "col2": "e"})
+        col1    col2
+    0    a       b
+    1    b       a
+    2    d       e
+    """
+    from pandas.core.reshape.concat import concat
+
+    if not isinstance(data, DataFrame):
+        raise TypeError(
+            "Expected 'data' to be a 'DataFrame'; "
+            f"Received 'data' of type: {type(data).__name__}"
+        )
+
+    if data.isna().any().any():
+        raise ValueError(
+            "Dummy DataFrame contains NA value in column: "
+            f"'{data.isna().any().idxmax()}'"
+        )
+
+    # index data with a list of all columns that are dummies
+    try:
+        data_to_decode = data.astype("boolean", copy=False)
+    except TypeError:
+        raise TypeError("Passed DataFrame contains non-dummy data")
+
+    # collect prefixes and get lists to slice data for each prefix
+    variables_slice = defaultdict(list)
+    if sep is None:
+        variables_slice[""] = list(data.columns)
+    elif isinstance(sep, str):
+        for col in data_to_decode.columns:
+            prefix = col.split(sep)[0]
+            if len(prefix) == len(col):
+                raise ValueError(f"Separator not specified for column: {col}")
+            variables_slice[prefix].append(col)
+    else:
+        raise TypeError(
+            "Expected 'sep' to be of type 'str' or 'None'; "
+            f"Received 'sep' of type: {type(sep).__name__}"
+        )
+
+    if default_category is not None:
+        if isinstance(default_category, dict):
+            if not len(default_category) == len(variables_slice):
+                len_msg = (
+                    f"Length of 'default_category' ({len(default_category)}) "
+                    f"did not match the length of the columns being encoded "
+                    f"({len(variables_slice)})"
+                )
+                raise ValueError(len_msg)
+        elif isinstance(default_category, Hashable):
+            default_category = dict(
+                zip(variables_slice, [default_category] * len(variables_slice))
+            )
+        else:
+            raise TypeError(
+                "Expected 'default_category' to be of type "
+                "'None', 'Hashable', or 'dict'; "
+                "Received 'default_category' of type: "
+                f"{type(default_category).__name__}"
+            )
+
+    cat_data = {}
+    for prefix, prefix_slice in variables_slice.items():
+        if sep is None:
+            cats = prefix_slice.copy()
+        else:
+            cats = [col[len(prefix + sep) :] for col in prefix_slice]
+        assigned = data_to_decode.loc[:, prefix_slice].sum(axis=1)
+        if any(assigned > 1):
+            raise ValueError(
+                "Dummy DataFrame contains multi-assignment(s); "
+                f"First instance in row: {assigned.idxmax()}"
+            )
+        elif any(assigned == 0):
+            if isinstance(default_category, dict):
+                cats.append(default_category[prefix])
+            else:
+                raise ValueError(
+                    "Dummy DataFrame contains unassigned value(s); "
+                    f"First instance in row: {assigned.idxmin()}"
+                )
+            data_slice = concat(
+                (data_to_decode.loc[:, prefix_slice], assigned == 0), axis=1
+            )
+        else:
+            data_slice = data_to_decode.loc[:, prefix_slice]
+        cats_array = np.array(cats, dtype="object")
+        # get indices of True entries along axis=1
+        cat_data[prefix] = cats_array[data_slice.to_numpy().nonzero()[1]]
+
+    return DataFrame(cat_data)
diff --git a/pandas/tests/api/test_api.py b/pandas/tests/api/test_api.py
@@ -116,6 +116,7 @@ class TestPDApi(Base):
         "eval",
         "factorize",
         "get_dummies",
+        "from_dummies",
         "infer_freq",
         "isna",
         "isnull",
diff --git a/pandas/tests/reshape/test_from_dummies.py b/pandas/tests/reshape/test_from_dummies.py
