Merge branch 'master' of https://github.com/pandas-dev/pandas

Author: phofl

ci/code_checks.sh

@@ -225,7 +225,7 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS02, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03)' ; echo $MSG
+    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS01, SS02, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03)' ; echo $MSG
     $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS02,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 

doc/source/whatsnew/v1.2.0.rst

@@ -623,6 +623,7 @@ I/O
 - Bug in :meth:`DataFrame.to_hdf` was not dropping missing rows with ``dropna=True`` (:issue:`35719`)
 - Bug in :func:`read_html` was raising a ``TypeError`` when supplying a ``pathlib.Path`` argument to the ``io`` parameter (:issue:`37705`)
 - :meth:`to_excel` and :meth:`to_markdown` support writing to fsspec URLs such as S3 and Google Cloud Storage (:issue:`33987`)
+- Bug in :meth:`read_fw` was not skipping blank lines (even with ``skip_blank_lines=True``) (:issue:`37758`)
 
 Plotting
 ^^^^^^^^

pandas/_libs/lib.pyx

@@ -118,6 +118,8 @@ def memory_usage_of_objects(arr: object[:]) -> int64_t:
 
 def is_scalar(val: object) -> bool:
     """
+    Return True if given object is scalar.
+
     Parameters
     ----------
     val : object
@@ -927,6 +929,8 @@ def indices_fast(ndarray index, const int64_t[:] labels, list keys,
 
 def is_float(obj: object) -> bool:
     """
+    Return True if given object is float.
+
     Returns
     -------
     bool
@@ -936,6 +940,8 @@ def is_float(obj: object) -> bool:
 
 def is_integer(obj: object) -> bool:
     """
+    Return True if given object is integer.
+
     Returns
     -------
     bool
@@ -945,6 +951,8 @@ def is_integer(obj: object) -> bool:
 
 def is_bool(obj: object) -> bool:
     """
+    Return True if given object is boolean.
+
     Returns
     -------
     bool
@@ -954,6 +962,8 @@ def is_bool(obj: object) -> bool:
 
 def is_complex(obj: object) -> bool:
     """
+    Return True if given object is complex.
+
     Returns
     -------
     bool
@@ -971,7 +981,7 @@ cpdef bint is_interval(object obj):
 
 def is_period(val: object) -> bool:
     """
-    Return a boolean if this is a Period object.
+    Return True if given object is Period.
 
     Returns
     -------

pandas/io/parsers.py

@@ -3750,6 +3750,19 @@ def _make_reader(self, f):
             self.infer_nrows,
         )
 
+    def _remove_empty_lines(self, lines) -> List:
+        """
+        Returns the list of lines without the empty ones. With fixed-width
+        fields, empty lines become arrays of empty strings.
+
+        See PythonParser._remove_empty_lines.
+        """
+        return [
+            line
+            for line in lines
+            if any(not isinstance(e, str) or e.strip() for e in line)
+        ]
+
 
 def _refine_defaults_read(
     dialect: Union[str, csv.Dialect],

pandas/tests/arithmetic/conftest.py

@@ -2,6 +2,7 @@
 import pytest
 
 import pandas as pd
+from pandas import Float64Index, Int64Index, RangeIndex, UInt64Index
 import pandas._testing as tm
 
 # ------------------------------------------------------------------
@@ -93,10 +94,10 @@ def zero(request):
 
 @pytest.fixture(
     params=[
-        pd.Float64Index(np.arange(5, dtype="float64")),
-        pd.Int64Index(np.arange(5, dtype="int64")),
-        pd.UInt64Index(np.arange(5, dtype="uint64")),
-        pd.RangeIndex(5),
+        Float64Index(np.arange(5, dtype="float64")),
+        Int64Index(np.arange(5, dtype="int64")),
+        UInt64Index(np.arange(5, dtype="uint64")),
+        RangeIndex(5),
     ],
     ids=lambda x: type(x).__name__,
 )

pandas/tests/arithmetic/test_datetime64.py

@@ -17,6 +17,7 @@
 
 import pandas as pd
 from pandas import (
+    DateOffset,
     DatetimeIndex,
     NaT,
     Period,
@@ -166,8 +167,8 @@ class TestDatetime64SeriesComparison:
                 [NaT, NaT, Timedelta("3 days")],
             ),
             (
-                [pd.Period("2011-01", freq="M"), NaT, pd.Period("2011-03", freq="M")],
-                [NaT, NaT, pd.Period("2011-03", freq="M")],
+                [Period("2011-01", freq="M"), NaT, Period("2011-03", freq="M")],
+                [NaT, NaT, Period("2011-03", freq="M")],
             ),
         ],
     )
@@ -1078,7 +1079,7 @@ def test_dt64arr_add_timestamp_raises(self, box_with_array):
             3.14,
             np.array([2.0, 3.0]),
             # GH#13078 datetime +/- Period is invalid
-            pd.Period("2011-01-01", freq="D"),
+            Period("2011-01-01", freq="D"),
             # https://github.com/pandas-dev/pandas/issues/10329
             time(1, 2, 3),
         ],
@@ -1288,7 +1289,7 @@ def test_dt64arr_add_sub_relativedelta_offsets(self, box_with_array):
             ("microseconds", 5),
         ]
         for i, kwd in enumerate(relative_kwargs):
-            off = pd.DateOffset(**dict([kwd]))
+            off = DateOffset(**dict([kwd]))
 
             expected = DatetimeIndex([x + off for x in vec_items])
             expected = tm.box_expected(expected, box_with_array)
@@ -1298,7 +1299,7 @@ def test_dt64arr_add_sub_relativedelta_offsets(self, box_with_array):
             expected = tm.box_expected(expected, box_with_array)
             tm.assert_equal(expected, vec - off)
 
-            off = pd.DateOffset(**dict(relative_kwargs[: i + 1]))
+            off = DateOffset(**dict(relative_kwargs[: i + 1]))
 
             expected = DatetimeIndex([x + off for x in vec_items])
             expected = tm.box_expected(expected, box_with_array)
@@ -1431,14 +1432,14 @@ def test_dt64arr_add_sub_DateOffset(self, box_with_array):
         # GH#10699
         s = date_range("2000-01-01", "2000-01-31", name="a")
         s = tm.box_expected(s, box_with_array)
-        result = s + pd.DateOffset(years=1)
-        result2 = pd.DateOffset(years=1) + s
+        result = s + DateOffset(years=1)
+        result2 = DateOffset(years=1) + s
         exp = date_range("2001-01-01", "2001-01-31", name="a")._with_freq(None)
         exp = tm.box_expected(exp, box_with_array)
         tm.assert_equal(result, exp)
         tm.assert_equal(result2, exp)
 
-        result = s - pd.DateOffset(years=1)
+        result = s - DateOffset(years=1)
         exp = date_range("1999-01-01", "1999-01-31", name="a")._with_freq(None)
         exp = tm.box_expected(exp, box_with_array)
         tm.assert_equal(result, exp)
@@ -1527,7 +1528,7 @@ def test_dt64arr_add_sub_offset_array(
         [
             (
                 "__add__",
-                pd.DateOffset(months=3, days=10),
+                DateOffset(months=3, days=10),
                 [
                     Timestamp("2014-04-11"),
                     Timestamp("2015-04-11"),
@@ -1538,7 +1539,7 @@ def test_dt64arr_add_sub_offset_array(
             ),
             (
                 "__add__",
-                pd.DateOffset(months=3),
+                DateOffset(months=3),
                 [
                     Timestamp("2014-04-01"),
                     Timestamp("2015-04-01"),
@@ -1549,7 +1550,7 @@ def test_dt64arr_add_sub_offset_array(
             ),
             (
                 "__sub__",
-                pd.DateOffset(months=3, days=10),
+                DateOffset(months=3, days=10),
                 [
                     Timestamp("2013-09-21"),
                     Timestamp("2014-09-21"),
@@ -1560,7 +1561,7 @@ def test_dt64arr_add_sub_offset_array(
             ),
             (
                 "__sub__",
-                pd.DateOffset(months=3),
+                DateOffset(months=3),
                 [
                     Timestamp("2013-10-01"),
                     Timestamp("2014-10-01"),

pandas/tests/arithmetic/test_interval.py

@@ -290,6 +290,6 @@ def test_index_series_compat(self, op, constructor, expected_type, assert_func):
     def test_comparison_operations(self, scalars):
         # GH #28981
         expected = Series([False, False])
-        s = Series([pd.Interval(0, 1), pd.Interval(1, 2)], dtype="interval")
+        s = Series([Interval(0, 1), Interval(1, 2)], dtype="interval")
         result = s == scalars
         tm.assert_series_equal(result, expected)