BUG(string dtype): Resolve pytables xfail when reading with condition (…

…#60943)
pandas-dev · Feb 18, 2025 · a615c54 · a615c54
1 parent 7de155f
commit a615c54
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 15 deletions.
diff --git a/pandas/io/pytables.py b/pandas/io/pytables.py
@@ -4159,6 +4159,8 @@ def _create_axes(
                 ordered = data_converted.ordered
                 meta = "category"
                 metadata = np.asarray(data_converted.categories).ravel()
+            elif isinstance(blk.dtype, StringDtype):
+                meta = str(blk.dtype)
 
             data, dtype_name = _get_data_and_dtype_name(data_converted)
 
@@ -4419,7 +4421,8 @@ def read_column(
                     errors=self.errors,
                 )
                 cvs = col_values[1]
-                return Series(cvs, name=column, copy=False)
+                dtype = getattr(self.table.attrs, f"{column}_meta", None)
+                return Series(cvs, name=column, copy=False, dtype=dtype)
 
         raise KeyError(f"column [{column}] not found in the table")
 
@@ -4769,8 +4772,18 @@ def read(
                 df = DataFrame._from_arrays([values], columns=cols_, index=index_)
             if not (using_string_dtype() and values.dtype.kind == "O"):
                 assert (df.dtypes == values.dtype).all(), (df.dtypes, values.dtype)
+
+            # If str / string dtype is stored in meta, use that.
+            converted = False
+            for column in cols_:
+                dtype = getattr(self.table.attrs, f"{column}_meta", None)
+                if dtype in ["str", "string"]:
+                    df[column] = df[column].astype(dtype)
+                    converted = True
+            # Otherwise try inference.
             if (
-                using_string_dtype()
+                not converted
+                and using_string_dtype()
                 and isinstance(values, np.ndarray)
                 and is_string_array(
                     values,

diff --git a/pandas/tests/io/pytables/test_append.py b/pandas/tests/io/pytables/test_append.py
@@ -5,8 +5,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs.tslibs import Timestamp
 from pandas.compat import PY312
 
@@ -516,7 +514,6 @@ def test_append_with_empty_string(setup_path):
         tm.assert_frame_equal(store.select("df"), df)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_append_with_data_columns(setup_path):
     with ensure_clean_store(setup_path) as store:
         df = DataFrame(

diff --git a/pandas/tests/io/pytables/test_categorical.py b/pandas/tests/io/pytables/test_categorical.py
@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas import (
     Categorical,
     DataFrame,
@@ -140,7 +138,6 @@ def test_categorical(setup_path):
             store.select("df3/meta/s/meta")
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_categorical_conversion(tmp_path, setup_path):
     # GH13322
     # Check that read_hdf with categorical columns doesn't return rows if

diff --git a/pandas/tests/io/pytables/test_read.py b/pandas/tests/io/pytables/test_read.py
@@ -5,8 +5,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.compat import is_platform_windows
 
 import pandas as pd
@@ -72,7 +70,6 @@ def test_read_missing_key_opened_store(tmp_path, setup_path):
         read_hdf(store, "k1")
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_read_column(setup_path):
     df = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),

diff --git a/pandas/tests/io/pytables/test_select.py b/pandas/tests/io/pytables/test_select.py
@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs.tslibs import Timestamp
 from pandas.compat import PY312
 
@@ -666,7 +664,6 @@ def test_frame_select(setup_path, request):
         #     store.select('frame', [crit1, crit2])
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_frame_select_complex(setup_path):
     # select via complex criteria
 
@@ -980,7 +977,6 @@ def test_query_long_float_literal(setup_path):
         tm.assert_frame_equal(expected, result)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_query_compare_column_type(setup_path):
     # GH 15492
     df = DataFrame(