Implement DataFrame.value_counts

doc/source/whatsnew/v1.0.0.rst

@@ -46,7 +46,7 @@ Other API changes
 ^^^^^^^^^^^^^^^^^
 
 - :meth:`pandas.api.types.infer_dtype` will now return "integer-na" for integer and ``np.nan`` mix (:issue:`27283`)
--
+- Added :meth:`pandas.core.frame.DataFrame.value_counts` (:issue:`5377`).
 -
 
 .. _whatsnew_1000.deprecations:

pandas/core/frame.py

@@ -8394,6 +8394,52 @@ def isin(self, values):
                 self.columns,
             )
 
+    def value_counts(self):
+        """
+        The number of times each unique row appears in the DataFrame.
+
+        Rows that contain any NaN value are omitted from the results.
+
+        Returns
+        -------
+        counts : Series
+
+        See Also
+        --------
+        Series.value_counts: Equivalent method on Series.
+
+        Examples
+        --------
+
+        >>> df = pd.DataFrame({'num_legs': [2, 4, 4], 'num_wings': [2, 0, 0]},
+        ...                   index=['falcon', 'dog', 'cat'])
+        >>> df
+                num_legs  num_wings
+        falcon         2          2
+        dog            4          0
+        cat            4          0
+
+        >>> df.value_counts()
+        num_legs  num_wings
+        2         2            1
+        4         0            2
+        dtype: int64
+
+        >>> df1col = df[['num_legs']]
+        >>> df1col
+                num_legs
+        falcon         2
+        dog            4
+        cat            4
+
+        >>> df1col.value_counts()
+        num_legs
+        2    1
+        4    2
+        dtype: int64
+        """
+        return self.groupby(self.columns.tolist()).size()
+
     # ----------------------------------------------------------------------
     # Add plotting methods to DataFrame
     plot = CachedAccessor("plot", pandas.plotting.PlotAccessor)

pandas/tests/frame/test_analytics.py

@@ -2766,3 +2766,32 @@ def test_multiindex_column_lookup(self):
         result = df.nlargest(3, ("x", "b"))
         expected = df.iloc[[3, 2, 1]]
         tm.assert_frame_equal(result, expected)
+
+    def test_data_frame_value_counts(self):
+        # Multi column data frame.
+        df = pd.DataFrame(
+            {"num_legs": [2, 4, 4], "num_wings": [2, 0, 0]},
+            index=["falcon", "dog", "cat"],
+        )
+        actual = df.value_counts()
+        expected = pd.Series(
+            data=[1, 2],
+            index=pd.MultiIndex.from_arrays(
+                [(2, 4), (2, 0)], names=["num_legs", "num_wings"]
+            ),
+        )
+        tm.assert_series_equal(actual, expected)
+
+        # Single column data frame.
+        df_single_col = df[["num_legs"]]
+        actual = df_single_col.value_counts()
+        expected = pd.Series(
+            data=[1, 2], index=pd.Int64Index(data=[2, 4], name="num_legs")
+        )
+        tm.assert_series_equal(actual, expected)
+
+        # Empty data frame.
+        df_no_cols = pd.DataFrame()
+        actual = df_no_cols.value_counts()
+        expected = pd.Series([], dtype=np.int64)
+        tm.assert_series_equal(actual, expected)