ENH: Add axis argument to Dataframe.corr

doc/source/whatsnew/v1.2.0.rst

@@ -54,7 +54,7 @@ For example:
 Other enhancements
 ^^^^^^^^^^^^^^^^^^
 - :class:`Index` with object dtype supports division and multiplication (:issue:`34160`)
--
+- :meth:`DataFrame.corr` now allows an ``axis`` argument, set to 0 by default (correlation among columns) (:issue:`35002`)
 -
 
 .. _whatsnew_120.api_breaking.python:

pandas/core/frame.py

@@ -20,6 +20,7 @@
  TYPE_CHECKING,
  Any,
  AnyStr,
+ Callable,
  Dict,
  FrozenSet,
  Hashable,
@@ -5787,7 +5788,7 @@ def nsmallest(self, n, columns, keep="first") -> "DataFrame":
  population GDP alpha-2
  Tuvalu 11300 38 TV
  Anguilla 11300 311 AI
- Iceland 337000 17036 IS
+ Iceland 337000 17036  IS
 
  When using ``keep='last'``, ties are resolved in reverse order:
 
@@ -8116,9 +8117,14 @@ def _series_round(s, decimals):
  # ----------------------------------------------------------------------
  # Statistical methods, etc.
 
- def corr(self, method="pearson", min_periods=1) -> "DataFrame":
+ def corr(
+ self,
+ method: Union[str, Callable[[np.ndarray, np.ndarray], np.float64]] = "pearson",
+ min_periods: Optional[int] = 1,
+ axis: Union[str, int] = 0,
+ ) -> "DataFrame":
  """
- Compute pairwise correlation of columns, excluding NA/null values.
+ Compute pairwise correlation of rows or columns, excluding NA/null values.
 
  Parameters
  ----------
@@ -8140,6 +8146,12 @@ def corr(self, method="pearson", min_periods=1) -> "DataFrame":
  to have a valid result. Currently only available for Pearson
  and Spearman correlation.
 
+ axis : {0 or 'index', 1 or 'columns'}, default 0
+ The axis to use. 0 or 'index' to compute column-wise, 1 or 'columns' for
+ row-wise.
+
+ .. versionadded:: 1.2.0
+
  Returns
  -------
  DataFrame
@@ -8162,12 +8174,22 @@ def corr(self, method="pearson", min_periods=1) -> "DataFrame":
  dogs cats
  dogs 1.0 0.3
  cats 0.3 1.0
+ >>> df.corr(method=histogram_intersection, axis=1)
+ 0 1 2 3
+ 0 1.0 0.3 0.2 0.3
+ 1 0.3 1.0 0.0 0.1
+ 2 0.2 0.0 1.0 0.2
+ 3 0.3 0.1 0.2 1.0
  """
  numeric_df = self._get_numeric_data()
- cols = numeric_df.columns
+ axis = numeric_df._get_axis_number(axis)
+ cols = numeric_df._get_agg_axis(axis)
  idx = cols.copy()
  mat = numeric_df.to_numpy(dtype=float, na_value=np.nan, copy=False)
 
+ if axis == 1:
+ mat = mat.transpose()
+
  if method == "pearson":
  correl = libalgos.nancorr(mat, minp=min_periods)
  elif method == "spearman":

pandas/tests/frame/methods/test_cov_corr.py

@@ -175,6 +175,15 @@ def test_corr_int(self):
  df3.cov()
  df3.corr()
 
+ @td.skip_if_no_scipy
+ @pytest.mark.parametrize("meth", ["pearson", "spearman", "kendall"])
+ def test_corr_axes(self, meth):
+ # https://github.com/pandas-dev/pandas/issues/35002
+ df = pd.DataFrame(np.random.normal(size=(10, 4)))
+ expected = df.T.corr(meth, axis=0)
+ result = df.corr(meth, axis=1)
+ tm.assert_frame_equal(result, expected)
+
  @td.skip_if_no_scipy
  @pytest.mark.parametrize(
  "nullable_column", [pd.array([1, 2, 3]), pd.array([1, 2, None])]