From 63f474db81b17978b5b31d591e610946321cb6cd Mon Sep 17 00:00:00 2001
From: liwh <liwh@dongzhengafc.com>
Date: Mon, 13 Sep 2021 15:32:35 +0800
Subject: [PATCH] BUG: Allow pairwise calcuation when comparing the column with
 itself (#25781)

---
 doc/source/whatsnew/v1.4.0.rst              |  1 +
 pandas/core/frame.py                        |  9 ++++++++-
 pandas/tests/frame/methods/test_cov_corr.py | 15 +++++++++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/doc/source/whatsnew/v1.4.0.rst b/doc/source/whatsnew/v1.4.0.rst
index 822c6372ea2a4..7b628e32d21df 100644
--- a/doc/source/whatsnew/v1.4.0.rst
+++ b/doc/source/whatsnew/v1.4.0.rst
@@ -129,6 +129,7 @@ Other enhancements
 - :meth:`DataFrame.__pos__`, :meth:`DataFrame.__neg__` now retain ``ExtensionDtype`` dtypes (:issue:`43883`)
 - The error raised when an optional dependency can't be imported now includes the original exception, for easier investigation (:issue:`43882`)
 - Added :meth:`.ExponentialMovingWindow.sum` (:issue:`13297`)
+- :meth:`DataFrame.corr` now accept the argument ``calculate_diagonal`` to allow results returned from callable to be used as diagonal elements of the correlation matrix instead of setting them to ones (:issue:`25781`)
 
 .. ---------------------------------------------------------------------------
 
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 76a00071c8adc..390d735853090 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -9402,6 +9402,7 @@ def corr(
         self,
         method: str | Callable[[np.ndarray, np.ndarray], float] = "pearson",
         min_periods: int = 1,
+        calculate_diagonal: bool = False,
     ) -> DataFrame:
         """
         Compute pairwise correlation of columns, excluding NA/null values.
@@ -9422,6 +9423,12 @@ def corr(
             Minimum number of observations required per pair of columns
             to have a valid result. Currently only available for Pearson
             and Spearman correlation.
+        calculate_diagonal : bool, optional
+            Whether to calculate pairwise correlation using supplied callable.
+            Ignored when method argument is not callable. If False, pairwise
+            correlation between a column and itself is default to 1.
+
+            .. versionadded:: 1.4.0
 
         Returns
         -------
@@ -9471,7 +9478,7 @@ def corr(
                     valid = mask[i] & mask[j]
                     if valid.sum() < min_periods:
                         c = np.nan
-                    elif i == j:
+                    elif i == j and not calculate_diagonal:
                         c = 1.0
                     elif not valid.all():
                         c = corrf(ac[valid], bc[valid])
diff --git a/pandas/tests/frame/methods/test_cov_corr.py b/pandas/tests/frame/methods/test_cov_corr.py
index 3dbf49df72558..0621c2bf0602e 100644
--- a/pandas/tests/frame/methods/test_cov_corr.py
+++ b/pandas/tests/frame/methods/test_cov_corr.py
@@ -236,6 +236,21 @@ def test_corr_min_periods_greater_than_length(self, method):
         )
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.filterwarnings("ignore: An input array is constant")
+    @td.skip_if_no_scipy
+    @pytest.mark.parametrize("array_creator", [np.ones, np.zeros, np.random.random])
+    def test_corr_diagonal_not_ones(self, array_creator):
+        from scipy.stats import pearsonr
+
+        frame_size = 4
+        df = DataFrame(array_creator((frame_size, frame_size)))
+        cor_mat = df.corr(
+            method=lambda x, y: pearsonr(x, y)[0], calculate_diagonal=True
+        )
+        result_diag = [cor_mat.loc[i, i] for i in range(frame_size)]
+        expected_diag = [pearsonr(df[i], df[i])[0] for i in range(frame_size)]
+        tm.assert_almost_equal(result_diag, expected_diag)
+
 
 class TestDataFrameCorrWith:
     def test_corrwith(self, datetime_frame):