Fixed pandas-dev#34859: Added support for '0' and '1' in BooleanArray._from_sequence_of_strings method (pandas-dev#35061)

Author: SanthoshBala18

doc/source/whatsnew/v1.1.0.rst

@@ -328,6 +328,7 @@ Other enhancements
 - :meth:`DataFrame.to_html` and :meth:`DataFrame.to_string`'s ``col_space`` parameter now accepts a list or dict to change only some specific columns' width (:issue:`28917`).
 - :meth:`DataFrame.to_excel` can now also write OpenOffice spreadsheet (.ods) files (:issue:`27222`)
 - :meth:`~Series.explode` now accepts ``ignore_index`` to reset the index, similarly to :meth:`pd.concat` or :meth:`DataFrame.sort_values` (:issue:`34932`).
+- :meth:`read_csv` now accepts string values like "0", "0.0", "1", "1.0" as convertible to the nullable boolean dtype (:issue:`34859`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/arrays/boolean.py

@@ -286,9 +286,9 @@ def _from_sequence_of_strings(
         def map_string(s):
             if isna(s):
                 return s
-            elif s in ["True", "TRUE", "true"]:
+            elif s in ["True", "TRUE", "true", "1", "1.0"]:
                 return True
-            elif s in ["False", "FALSE", "false"]:
+            elif s in ["False", "FALSE", "false", "0", "0.0"]:
                 return False
             else:
                 raise ValueError(f"{s} cannot be cast to bool")

pandas/tests/arrays/boolean/test_construction.py

@@ -247,10 +247,11 @@ def test_coerce_to_numpy_array():
 
 def test_to_boolean_array_from_strings():
     result = BooleanArray._from_sequence_of_strings(
-        np.array(["True", "False", np.nan], dtype=object)
+        np.array(["True", "False", "1", "1.0", "0", "0.0", np.nan], dtype=object)
     )
     expected = BooleanArray(
-        np.array([True, False, False]), np.array([False, False, True])
+        np.array([True, False, True, True, False, False, False]),
+        np.array([False, False, False, False, False, False, True]),
     )
 
     tm.assert_extension_array_equal(result, expected)

pandas/tests/io/parser/test_dtypes.py

@@ -561,9 +561,13 @@ def test_boolean_dtype(all_parsers):
             "True",
             "TRUE",
             "true",
+            "1",
+            "1.0",
             "False",
             "FALSE",
             "false",
+            "0",
+            "0.0",
             "NaN",
             "nan",
             "NA",
@@ -576,7 +580,23 @@ def test_boolean_dtype(all_parsers):
     expected = pd.DataFrame(
         {
             "a": pd.array(
-                [True, True, True, False, False, False, None, None, None, None, None],
+                [
+                    True,
+                    True,
+                    True,
+                    True,
+                    True,
+                    False,
+                    False,
+                    False,
+                    False,
+                    False,
+                    None,
+                    None,
+                    None,
+                    None,
+                    None,
+                ],
                 dtype="boolean",
             )
         }