Allow passing index_col=False in dd.read_csv (dask#9961)

rjzamora · Oct 4, 2023 · 62dbbff · 62dbbff
1 parent 8ba4475
commit 62dbbff
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/dask/dataframe/io/csv.py b/dask/dataframe/io/csv.py
@@ -486,10 +486,12 @@ def read_pandas(
         lineterminator = "\n"
     if include_path_column and isinstance(include_path_column, bool):
         include_path_column = "path"
-    if "index" in kwargs or "index_col" in kwargs:
+    if "index" in kwargs or (
+        "index_col" in kwargs and kwargs.get("index_col") is not False
+    ):
         raise ValueError(
-            "Keywords 'index' and 'index_col' not supported. "
-            f"Use dd.{reader_name}(...).set_index('my-index') instead"
+            "Keywords 'index' and 'index_col' not supported, except for "
+            "'index_col=False'. Use dd.{reader_name}(...).set_index('my-index') instead"
         )
     for kw in ["iterator", "chunksize"]:
         if kw in kwargs:

diff --git a/dask/dataframe/io/tests/test_csv.py b/dask/dataframe/io/tests/test_csv.py
@@ -1117,6 +1117,10 @@ def test_index_col():
         except ValueError as e:
             assert "set_index" in str(e)
 
+        df = pd.read_csv(fn, index_col=False)
+        ddf = dd.read_csv(fn, blocksize=30, index_col=False)
+        assert_eq(df, ddf, check_index=False)
+
 
 def test_read_csv_with_datetime_index_partitions_one():
     with filetext(timeseries) as fn: