Merge remote-tracking branch 'upstream/master' into 32bit-ci

Author: fangchenli

doc/source/user_guide/io.rst

@@ -5686,7 +5686,7 @@ ignored.
    dtypes: float64(1), int64(1)
    memory usage: 15.3 MB
 
-Given the next test set:
+The following test functions will be used below to compare the performance of several IO methods:
 
 .. code-block:: python
 
@@ -5791,7 +5791,7 @@ Given the next test set:
    def test_parquet_read():
        pd.read_parquet("test.parquet")
 
-When writing, the top-three functions in terms of speed are ``test_feather_write``, ``test_hdf_fixed_write`` and ``test_hdf_fixed_write_compress``.
+When writing, the top three functions in terms of speed are ``test_feather_write``, ``test_hdf_fixed_write`` and ``test_hdf_fixed_write_compress``.
 
 .. code-block:: ipython
 
@@ -5825,7 +5825,7 @@ When writing, the top-three functions in terms of speed are ``test_feather_write
    In [13]: %timeit test_parquet_write(df)
    67.6 ms ± 706 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
 
-When reading, the top three are ``test_feather_read``, ``test_pickle_read`` and
+When reading, the top three functions in terms of speed are ``test_feather_read``, ``test_pickle_read`` and
 ``test_hdf_fixed_read``.
 
 
@@ -5862,8 +5862,7 @@ When reading, the top three are ``test_feather_read``, ``test_pickle_read`` and
    24.4 ms ± 146 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)
 
 
-For this test case ``test.pkl.compress``, ``test.parquet`` and ``test.feather`` took the least space on disk.
-Space on disk (in bytes)
+The files ``test.pkl.compress``, ``test.parquet`` and ``test.feather`` took the least space on disk (in bytes).
 
 .. code-block:: none
 

pandas/core/base.py

@@ -1201,6 +1201,16 @@ def factorize(self, sort: bool = False, na_sentinel: Optional[int] = -1):
         >>> ser.searchsorted([1, 3], side='right')
         array([1, 3])
 
+        >>> ser = pd.Series(pd.to_datetime(['3/11/2000', '3/12/2000', '3/13/2000']))
+        >>> ser
+        0   2000-03-11
+        1   2000-03-12
+        2   2000-03-13
+        dtype: datetime64[ns]
+
+        >>> ser.searchsorted('3/14/2000')
+        3
+
         >>> ser = pd.Categorical(
         ...     ['apple', 'bread', 'bread', 'cheese', 'milk'], ordered=True
         ... )

pandas/tests/series/test_constructors.py

@@ -689,6 +689,13 @@ def test_constructor_coerce_float_valid(self, float_dtype):
         expected = Series([1, 2, 3.5]).astype(float_dtype)
         tm.assert_series_equal(s, expected)
 
+    def test_constructor_invalid_coerce_ints_with_float_nan(self, any_int_dtype):
+        # GH 22585
+
+        msg = "cannot convert float NaN to integer"
+        with pytest.raises(ValueError, match=msg):
+            Series([1, 2, np.nan], dtype=any_int_dtype)
+
     def test_constructor_dtype_no_cast(self):
         # see gh-1572
         s = Series([1, 2, 3])