From 56cb6881a559442432d89c6650281dd96322f941 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <33491632+MarcoGorelli@users.noreply.github.com>
Date: Mon, 3 Jul 2023 12:13:46 +0100
Subject: [PATCH 1/2] add DataFrame.unique_indices

---
 .../dataframe_api/dataframe_object.py         | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/spec/API_specification/dataframe_api/dataframe_object.py b/spec/API_specification/dataframe_api/dataframe_object.py
index ee8855bc..d893671c 100644
--- a/spec/API_specification/dataframe_api/dataframe_object.py
+++ b/spec/API_specification/dataframe_api/dataframe_object.py
@@ -740,6 +740,27 @@ def is_nan(self) -> DataFrame:
         """
         ...
 
+    def unique_indices(self, keys: Sequence[str], *, skip_nulls: bool = True) -> Column[int]:
+        """
+        Return indices corresponding to unique values across in selected columns.
+
+        Returns
+        -------
+        Column[int]
+            Indices corresponding to unique values.
+
+        Notes
+        -----
+        There are no ordering guarantees. In particular, if there are multiple
+        indices corresponding to the same unique value(s), there is no guarantee
+        about which one will appear in the result.
+        If the original column(s) contain multiple `'NaN'` values, then
+        only a single index corresponding to those values should be returned.
+        Likewise for null values (if ``skip_nulls=False``).
+        To get the unique values, you can do ``df.get_rows(df.unique_indices(keys))``.
+        """
+        ...
+
     def fill_nan(self, value: float | 'null', /) -> DataFrame:
         """
         Fill ``nan`` values with the given fill value.

From 7fc2e1b9a9781181c122d5c8f8906f8a0615ec2d Mon Sep 17 00:00:00 2001
From: MarcoGorelli <33491632+MarcoGorelli@users.noreply.github.com>
Date: Fri, 7 Jul 2023 17:04:34 +0100
Subject: [PATCH 2/2] typo + minor reword

---
 spec/API_specification/dataframe_api/column_object.py    | 2 +-
 spec/API_specification/dataframe_api/dataframe_object.py | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/spec/API_specification/dataframe_api/column_object.py b/spec/API_specification/dataframe_api/column_object.py
index 10ba9a35..d45a543f 100644
--- a/spec/API_specification/dataframe_api/column_object.py
+++ b/spec/API_specification/dataframe_api/column_object.py
@@ -622,7 +622,7 @@ def unique_indices(self, *, skip_nulls: bool = True) -> Column[int]:
         indices corresponding to the same unique value, there is no guarantee
         about which one will appear in the result.
         If the original Column contains multiple `'NaN'` values, then
-        only a single index corresponding to those values should be returned.
+        only a single index corresponding to those values will be returned.
         Likewise for null values (if ``skip_nulls=False``).
         To get the unique values, you can do ``col.get_rows(col.unique_indices())``.
         """
diff --git a/spec/API_specification/dataframe_api/dataframe_object.py b/spec/API_specification/dataframe_api/dataframe_object.py
index fab8c622..fb0948e8 100644
--- a/spec/API_specification/dataframe_api/dataframe_object.py
+++ b/spec/API_specification/dataframe_api/dataframe_object.py
@@ -760,7 +760,7 @@ def is_nan(self) -> DataFrame:
 
     def unique_indices(self, keys: Sequence[str], *, skip_nulls: bool = True) -> Column[int]:
         """
-        Return indices corresponding to unique values across in selected columns.
+        Return indices corresponding to unique values across selected columns.
 
         Returns
         -------
@@ -773,7 +773,7 @@ def unique_indices(self, keys: Sequence[str], *, skip_nulls: bool = True) -> Col
         indices corresponding to the same unique value(s), there is no guarantee
         about which one will appear in the result.
         If the original column(s) contain multiple `'NaN'` values, then
-        only a single index corresponding to those values should be returned.
+        only a single index corresponding to those values will be returned.
         Likewise for null values (if ``skip_nulls=False``).
         To get the unique values, you can do ``df.get_rows(df.unique_indices(keys))``.
         """