Merge remote-tracking branch 'upstream/main' into scott/bodo_udf_engine

Author: =

.circleci/config.yml

@@ -61,7 +61,6 @@ pandas/_version.py export-subst
 *.pxi export-ignore
 
 # Ignoring stuff from the top level
-.circleci export-ignore
 .github export-ignore
 asv_bench export-ignore
 ci export-ignore

.gitattributes

@@ -112,7 +112,7 @@ Various tutorials
 
 * `Wes McKinney's (pandas BDFL) blog <https://wesmckinney.com/archives.html>`_
 * `Statistical analysis made easy in Python with SciPy and pandas DataFrames, by Randal Olson <http://www.randalolson.com/2012/08/06/statistical-analysis-made-easy-in-python/>`_
-* `Statistical Data Analysis in Python, tutorial videos, by Christopher Fonnesbeck from SciPy 2013 <https://conference.scipy.org/scipy2013/tutorial_detail.php?id=109>`_
+* `Statistical Data Analysis in Python, tutorial by Christopher Fonnesbeck from SciPy 2013 <https://github.com/fonnesbeck/statistical-analysis-python-tutorial>`_
 * `Financial analysis in Python, by Thomas Wiecki <https://nbviewer.org/github/twiecki/financial-analysis-python-tutorial/blob/master/1.%20Pandas%20Basics.ipynb>`_
 * `Intro to pandas data structures, by Greg Reda <http://www.gregreda.com/2013/10/26/intro-to-pandas-data-structures/>`_
 * `Pandas DataFrames Tutorial, by Karlijn Willems <https://www.datacamp.com/community/tutorials/pandas-tutorial-dataframe-python>`_

ci/deps/circle-311-arm64.yaml

@@ -596,6 +596,8 @@ def sanitize_array(
         # create an extension array from its dtype
         _sanitize_non_ordered(data)
         cls = dtype.construct_array_type()
+        if not hasattr(data, "__array__"):
+            data = list(data)
         subarr = cls._from_sequence(data, dtype=dtype, copy=copy)
 
     # GH#846

doc/source/getting_started/tutorials.rst

@@ -165,7 +165,8 @@ def _finalize_pandas_output(self, frame: DataFrame) -> DataFrame:
                 # The only way self.names is not the same length as number of cols is
                 # if we have int index_col. We should just pad the names(they will get
                 # removed anyways) to expected length then.
-                self.names = list(range(num_cols - len(self.names))) + self.names
+                columns_prefix = [str(x) for x in range(num_cols - len(self.names))]
+                self.names = columns_prefix + self.names
                 multi_index_named = False
             frame.columns = self.names
 

pandas/core/construction.py

@@ -179,3 +179,14 @@ def test_constructor_datetime_nonns(self, constructor):
         arr.flags.writeable = False
         result = constructor(arr)
         tm.assert_equal(result, expected)
+
+    def test_constructor_from_dict_keys(self, constructor, using_infer_string):
+        # https://github.com/pandas-dev/pandas/issues/60343
+        d = {"a": 1, "b": 2}
+        result = constructor(d.keys(), dtype="str")
+        if using_infer_string:
+            assert result.dtype == "str"
+        else:
+            assert result.dtype == "object"
+        expected = constructor(list(d.keys()), dtype="str")
+        tm.assert_equal(result, expected)

pandas/io/parsers/arrow_parser_wrapper.py

@@ -33,7 +33,7 @@ def float_string_frame():
     df = DataFrame(
         np.random.default_rng(2).standard_normal((30, 4)),
         index=Index([f"foo_{i}" for i in range(30)], dtype=object),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
     )
     df["foo"] = "bar"
     return df

pandas/tests/base/test_constructors.py

@@ -108,7 +108,6 @@ def test_constructor_list_of_series(self):
         expected = DataFrame.from_dict(sdict, orient="index")
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="columns inferring logic broken")
     def test_constructor_orient(self, float_string_frame):
         data_dict = float_string_frame.T._series
         recons = DataFrame.from_dict(data_dict, orient="index")

pandas/tests/frame/conftest.py

@@ -7,8 +7,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 from pandas import (
     Categorical,
@@ -162,21 +160,7 @@ def test_constructor_with_convert(self):
         )
         tm.assert_series_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_construction_with_mixed(self, float_string_frame, using_infer_string):
-        # test construction edge cases with mixed types
-
-        # f7u12, this does not work without extensive workaround
-        data = [
-            [datetime(2001, 1, 5), np.nan, datetime(2001, 1, 2)],
-            [datetime(2000, 1, 2), datetime(2000, 1, 3), datetime(2000, 1, 1)],
-        ]
-        df = DataFrame(data)
-
-        # check dtypes
-        result = df.dtypes
-        expected = Series({"datetime64[us]": 3})
-
         # mixed-type frames
         float_string_frame["datetime"] = datetime.now()
         float_string_frame["timedelta"] = timedelta(days=1, seconds=1)
@@ -196,13 +180,11 @@ def test_construction_with_mixed(self, float_string_frame, using_infer_string):
         )
         tm.assert_series_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_construction_with_conversions(self):
         # convert from a numpy array of non-ns timedelta64; as of 2.0 this does
         #  *not* convert
         arr = np.array([1, 2, 3], dtype="timedelta64[s]")
-        df = DataFrame(index=range(3))
-        df["A"] = arr
+        df = DataFrame({"A": arr})
         expected = DataFrame(
             {"A": pd.timedelta_range("00:00:01", periods=3, freq="s")}, index=range(3)
         )
@@ -220,11 +202,11 @@ def test_construction_with_conversions(self):
         assert expected.dtypes["dt1"] == "M8[s]"
         assert expected.dtypes["dt2"] == "M8[s]"
 
-        df = DataFrame(index=range(3))
-        df["dt1"] = np.datetime64("2013-01-01")
-        df["dt2"] = np.array(
+        dt1 = np.datetime64("2013-01-01")
+        dt2 = np.array(
             ["2013-01-01", "2013-01-02", "2013-01-03"], dtype="datetime64[D]"
         )
+        df = DataFrame({"dt1": dt1, "dt2": dt2})
 
         # df['dt3'] = np.array(['2013-01-01 00:00:01','2013-01-01
         # 00:00:02','2013-01-01 00:00:03'],dtype='datetime64[s]')
@@ -401,14 +383,17 @@ def test_update_inplace_sets_valid_block_values():
     assert isinstance(df._mgr.blocks[0].values, Categorical)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_nonconsolidated_item_cache_take():
     # https://github.com/pandas-dev/pandas/issues/35521
 
     # create non-consolidated dataframe with object dtype columns
-    df = DataFrame()
-    df["col1"] = Series(["a"], dtype=object)
+    df = DataFrame(
+        {
+            "col1": Series(["a"], dtype=object),
+        }
+    )
     df["col2"] = Series([0], dtype=object)
+    assert not df._mgr.is_consolidated()
 
     # access column (item cache)
     df["col1"] == "A"