The following issues were found
pandas/tests/arrays/period/test_arrow_compat.py
48 issues
Line: 1
Column: 1
import pytest
import pandas.util._test_decorators as td
from pandas.core.dtypes.dtypes import PeriodDtype
import pandas as pd
import pandas._testing as tm
from pandas.core.arrays import (
Reported by Pylint.
Line: 41
Column: 5
],
)
def test_arrow_array(data, freq):
import pyarrow as pa
from pandas.core.arrays._arrow_utils import ArrowPeriodType
periods = period_array(data, freq=freq)
result = pa.array(periods)
Reported by Pylint.
Line: 67
Column: 5
@pyarrow_skip
def test_arrow_array_missing():
import pyarrow as pa
from pandas.core.arrays._arrow_utils import ArrowPeriodType
arr = PeriodArray([1, 2, 3], freq="D")
arr[1] = pd.NaT
Reported by Pylint.
Line: 83
Column: 5
@pyarrow_skip
def test_arrow_table_roundtrip():
import pyarrow as pa
from pandas.core.arrays._arrow_utils import ArrowPeriodType
arr = PeriodArray([1, 2, 3], freq="D")
arr[1] = pd.NaT
Reported by Pylint.
Line: 106
Column: 5
@pyarrow_skip
def test_arrow_load_from_zero_chunks():
# GH-41040
import pyarrow as pa
from pandas.core.arrays._arrow_utils import ArrowPeriodType
arr = PeriodArray([], freq="D")
df = pd.DataFrame({"a": arr})
Reported by Pylint.
Line: 125
Column: 5
@pyarrow_skip
def test_arrow_table_roundtrip_without_metadata():
import pyarrow as pa
arr = PeriodArray([1, 2, 3], freq="H")
arr[1] = pd.NaT
df = pd.DataFrame({"a": arr})
Reported by Pylint.
Line: 1
Column: 1
import pytest
import pandas.util._test_decorators as td
from pandas.core.dtypes.dtypes import PeriodDtype
import pandas as pd
import pandas._testing as tm
from pandas.core.arrays import (
Reported by Pylint.
Line: 18
Column: 1
@pyarrow_skip
def test_arrow_extension_type():
from pandas.core.arrays._arrow_utils import ArrowPeriodType
p1 = ArrowPeriodType("D")
p2 = ArrowPeriodType("D")
p3 = ArrowPeriodType("M")
Reported by Pylint.
Line: 19
Column: 5
@pyarrow_skip
def test_arrow_extension_type():
from pandas.core.arrays._arrow_utils import ArrowPeriodType
p1 = ArrowPeriodType("D")
p2 = ArrowPeriodType("D")
p3 = ArrowPeriodType("M")
Reported by Pylint.
Line: 21
Column: 5
def test_arrow_extension_type():
from pandas.core.arrays._arrow_utils import ArrowPeriodType
p1 = ArrowPeriodType("D")
p2 = ArrowPeriodType("D")
p3 = ArrowPeriodType("M")
assert p1.freq == "D"
assert p1 == p2
Reported by Pylint.
pandas/tests/io/parser/common/test_file_buffer_url.py
48 issues
Line: 13
Column: 1
import platform
from urllib.error import URLError
import pytest
from pandas.errors import (
EmptyDataError,
ParserError,
)
Reported by Pylint.
Line: 27
Column: 3
@tm.network
def test_url(all_parsers, csv_dir_path):
# TODO: FTP testing
parser = all_parsers
kwargs = {"sep": "\t"}
url = (
"https://raw.github.com/pandas-dev/pandas/master/"
Reported by Pylint.
Line: 390
Column: 16
path = datapath("io", "data", "csv", "iris.csv")
reader = parser.read_csv(path, chunksize=1)
assert not reader._engine.handles.handle.closed
try:
with reader:
next(reader)
assert False
except AssertionError:
Reported by Pylint.
Line: 396
Column: 16
next(reader)
assert False
except AssertionError:
assert reader._engine.handles.handle.closed
def test_context_manageri_user_provided(all_parsers, datapath):
# make sure that user-provided handles are not closed
parser = all_parsers
Reported by Pylint.
Line: 406
Column: 20
with open(datapath("io", "data", "csv", "iris.csv")) as path:
reader = parser.read_csv(path, chunksize=1)
assert not reader._engine.handles.handle.closed
try:
with reader:
next(reader)
assert False
except AssertionError:
Reported by Pylint.
Line: 412
Column: 24
next(reader)
assert False
except AssertionError:
assert not reader._engine.handles.handle.closed
def test_file_descriptor_leak(all_parsers):
# GH 31488
Reported by Pylint.
Line: 26
Column: 1
@tm.network
def test_url(all_parsers, csv_dir_path):
# TODO: FTP testing
parser = all_parsers
kwargs = {"sep": "\t"}
url = (
Reported by Pylint.
Line: 43
Column: 1
@pytest.mark.slow
def test_local_file(all_parsers, csv_dir_path):
parser = all_parsers
kwargs = {"sep": "\t"}
local_path = os.path.join(csv_dir_path, "salaries.csv")
local_result = parser.read_csv(local_path, **kwargs)
Reported by Pylint.
Line: 59
Column: 1
pytest.skip("Failing on: " + " ".join(platform.uname()))
def test_path_path_lib(all_parsers):
parser = all_parsers
df = tm.makeDataFrame()
result = tm.round_trip_pathlib(df.to_csv, lambda p: parser.read_csv(p, index_col=0))
tm.assert_frame_equal(df, result)
Reported by Pylint.
Line: 61
Column: 5
def test_path_path_lib(all_parsers):
parser = all_parsers
df = tm.makeDataFrame()
result = tm.round_trip_pathlib(df.to_csv, lambda p: parser.read_csv(p, index_col=0))
tm.assert_frame_equal(df, result)
def test_path_local_path(all_parsers):
Reported by Pylint.
pandas/tests/indexes/multi/test_names.py
48 issues
Line: 1
Column: 1
import pytest
import pandas as pd
from pandas import MultiIndex
import pandas._testing as tm
def check_level_names(index, names):
assert [level.name for level in index.levels] == list(names)
Reported by Pylint.
Line: 14
Column: 12
def test_slice_keep_name():
x = MultiIndex.from_tuples([("a", "b"), (1, 2), ("c", "d")], names=["x", "y"])
assert x[1:].names == x.names
def test_index_name_retained():
# GH9857
result = pd.DataFrame({"x": [1, 2, 6], "y": [2, 2, 8], "z": [-5, 0, 5]})
Reported by Pylint.
Line: 34
Column: 20
view = idx.view()
copy = idx.copy()
shallow_copy = idx._view()
# changing names should not change level names on object
new_names = [name + "a" for name in idx.names]
idx.names = new_names
check_level_names(idx, ["firsta", "seconda"])
Reported by Pylint.
Line: 128
Column: 9
# GH19029
idx.names = ["foo", "foo"]
with pytest.raises(ValueError, match="name foo occurs multiple times"):
idx._get_level_number("foo")
def test_get_names_from_levels():
idx = MultiIndex.from_product([["a"], [1, 2]], names=["a", "b"])
Reported by Pylint.
Line: 150
Column: 12
with pytest.raises(RuntimeError, match="set_names"):
new.index.name = "bar"
assert pd.Index._no_setting_name is False
assert pd.Int64Index._no_setting_name is False
assert pd.RangeIndex._no_setting_name is False
@pytest.mark.parametrize("func", ["rename", "set_names"])
Reported by Pylint.
Line: 151
Column: 12
new.index.name = "bar"
assert pd.Index._no_setting_name is False
assert pd.Int64Index._no_setting_name is False
assert pd.RangeIndex._no_setting_name is False
@pytest.mark.parametrize("func", ["rename", "set_names"])
@pytest.mark.parametrize(
Reported by Pylint.
Line: 152
Column: 12
assert pd.Index._no_setting_name is False
assert pd.Int64Index._no_setting_name is False
assert pd.RangeIndex._no_setting_name is False
@pytest.mark.parametrize("func", ["rename", "set_names"])
@pytest.mark.parametrize(
"rename_dict, exp_names",
Reported by Pylint.
Line: 1
Column: 1
import pytest
import pandas as pd
from pandas import MultiIndex
import pandas._testing as tm
def check_level_names(index, names):
assert [level.name for level in index.levels] == list(names)
Reported by Pylint.
Line: 8
Column: 1
import pandas._testing as tm
def check_level_names(index, names):
assert [level.name for level in index.levels] == list(names)
def test_slice_keep_name():
x = MultiIndex.from_tuples([("a", "b"), (1, 2), ("c", "d")], names=["x", "y"])
Reported by Pylint.
Line: 9
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
def check_level_names(index, names):
assert [level.name for level in index.levels] == list(names)
def test_slice_keep_name():
x = MultiIndex.from_tuples([("a", "b"), (1, 2), ("c", "d")], names=["x", "y"])
assert x[1:].names == x.names
Reported by Bandit.
pandas/core/computation/ops.py
48 issues
Line: 83
Column: 33
class Term:
def __new__(cls, name, env, side=None, encoding=None):
klass = Constant if not isinstance(name, str) else cls
# error: Argument 2 for "super" not an instance of argument 1
supr_new = super(Term, klass).__new__ # type: ignore[misc]
return supr_new(klass)
Reported by Pylint.
Line: 83
Column: 28
class Term:
def __new__(cls, name, env, side=None, encoding=None):
klass = Constant if not isinstance(name, str) else cls
# error: Argument 2 for "super" not an instance of argument 1
supr_new = super(Term, klass).__new__ # type: ignore[misc]
return supr_new(klass)
Reported by Pylint.
Line: 83
Column: 44
class Term:
def __new__(cls, name, env, side=None, encoding=None):
klass = Constant if not isinstance(name, str) else cls
# error: Argument 2 for "super" not an instance of argument 1
supr_new = super(Term, klass).__new__ # type: ignore[misc]
return supr_new(klass)
Reported by Pylint.
Line: 111
Column: 1
def __call__(self, *args, **kwargs):
return self.value
def evaluate(self, *args, **kwargs):
return self
def _resolve_name(self):
res = self.env.resolve(self.local_name, is_local=self.is_local)
self.update(res)
Reported by Pylint.
Line: 111
Column: 1
def __call__(self, *args, **kwargs):
return self.value
def evaluate(self, *args, **kwargs):
return self
def _resolve_name(self):
res = self.env.resolve(self.local_name, is_local=self.is_local)
self.update(res)
Reported by Pylint.
Line: 457
Column: 17
if self.op in eval_in_python:
res = self.func(left.value, right.value)
else:
from pandas.core.computation.eval import eval
res = eval(self, local_dict=env, engine=engine, parser=parser)
name = env.add_tmp(res)
return term_type(name, env=env)
Reported by Pylint.
Line: 82
Column: 1
super().__init__(msg)
class Term:
def __new__(cls, name, env, side=None, encoding=None):
klass = Constant if not isinstance(name, str) else cls
# error: Argument 2 for "super" not an instance of argument 1
supr_new = super(Term, klass).__new__ # type: ignore[misc]
return supr_new(klass)
Reported by Pylint.
Line: 102
Column: 5
self.encoding = encoding
@property
def local_name(self) -> str:
return self.name.replace(LOCAL_TAG, "")
def __repr__(self) -> str:
return pprint_thing(self.name)
Reported by Pylint.
Line: 111
Column: 5
def __call__(self, *args, **kwargs):
return self.value
def evaluate(self, *args, **kwargs):
return self
def _resolve_name(self):
res = self.env.resolve(self.local_name, is_local=self.is_local)
self.update(res)
Reported by Pylint.
Line: 143
Column: 5
self.value = value
@property
def is_scalar(self) -> bool:
return is_scalar(self._value)
@property
def type(self):
try:
Reported by Pylint.
pandas/core/arrays/string_arrow.py
48 issues
Line: 14
Column: 1
import numpy as np
from pandas._libs import lib
from pandas._typing import (
Dtype,
NpDtype,
PositionalIndexer,
Scalar,
Reported by Pylint.
Line: 64
Column: 5
# file is imported from even if pyarrow is < 1.0.0, before pyarrow.compute
# and its compute functions existed. GH38801
if not pa_version_under1p0:
import pyarrow as pa
import pyarrow.compute as pc
ARROW_CMP_FUNCS = {
"eq": pc.equal,
"ne": pc.not_equal,
Reported by Pylint.
Line: 65
Column: 5
# and its compute functions existed. GH38801
if not pa_version_under1p0:
import pyarrow as pa
import pyarrow.compute as pc
ARROW_CMP_FUNCS = {
"eq": pc.equal,
"ne": pc.not_equal,
"lt": pc.less,
Reported by Pylint.
Line: 87
Column: 3
raise ImportError(msg)
# TODO: Inherit directly from BaseStringArrayMethods. Currently we inherit from
# ObjectStringArrayMixin because we want to have the object-dtype based methods as
# fallback for the ones that pyarrow doesn't yet support
class ArrowStringArray(OpsMixin, BaseStringArray, ObjectStringArrayMixin):
Reported by Pylint.
Line: 151
Column: 5
)
@classmethod
def _from_sequence(cls, scalars, dtype: Dtype | None = None, copy: bool = False):
from pandas.core.arrays.masked import BaseMaskedArray
_chk_pyarrow_available()
if dtype and not (isinstance(dtype, str) and dtype == "string"):
Reported by Pylint.
Line: 163
Column: 25
if isinstance(scalars, BaseMaskedArray):
# avoid costly conversion to object dtype in ensure_string_array and
# numerical issues with Float32Dtype
na_values = scalars._mask
result = scalars._data
result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
return cls(pa.array(result, mask=na_values, type=pa.string()))
# convert non-na-likes to str
Reported by Pylint.
Line: 164
Column: 22
# avoid costly conversion to object dtype in ensure_string_array and
# numerical issues with Float32Dtype
na_values = scalars._mask
result = scalars._data
result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
return cls(pa.array(result, mask=na_values, type=pa.string()))
# convert non-na-likes to str
result = lib.ensure_string_array(scalars, copy=copy)
Reported by Pylint.
Line: 173
Column: 5
return cls(pa.array(result, type=pa.string(), from_pandas=True))
@classmethod
def _from_sequence_of_strings(
cls, strings, dtype: Dtype | None = None, copy: bool = False
):
return cls._from_sequence(strings, dtype=dtype, copy=copy)
@property
Reported by Pylint.
Line: 189
Column: 31
"""Correctly construct numpy arrays when passed to `np.asarray()`."""
return self.to_numpy(dtype=dtype)
def __arrow_array__(self, type=None):
"""Convert myself to a pyarrow Array or ChunkedArray."""
return self._data
# error: Argument 1 of "to_numpy" is incompatible with supertype "ExtensionArray";
# supertype defines the argument type as "Union[ExtensionDtype, str, dtype[Any],
Reported by Pylint.
Line: 189
Column: 31
"""Correctly construct numpy arrays when passed to `np.asarray()`."""
return self.to_numpy(dtype=dtype)
def __arrow_array__(self, type=None):
"""Convert myself to a pyarrow Array or ChunkedArray."""
return self._data
# error: Argument 1 of "to_numpy" is incompatible with supertype "ExtensionArray";
# supertype defines the argument type as "Union[ExtensionDtype, str, dtype[Any],
Reported by Pylint.
pandas/tests/series/methods/test_rename.py
47 issues
Line: 65
Column: 3
s = Series(range(5))
s.rename({}, axis=0)
s.rename({}, axis="index")
# FIXME: dont leave commenred-out
# TODO: clean up shared index validation
# with pytest.raises(ValueError, match="No axis named 5"):
# s.rename({}, axis=5)
def test_rename_inplace(self, datetime_series):
Reported by Pylint.
Line: 66
Column: 3
s.rename({}, axis=0)
s.rename({}, axis="index")
# FIXME: dont leave commenred-out
# TODO: clean up shared index validation
# with pytest.raises(ValueError, match="No axis named 5"):
# s.rename({}, axis=5)
def test_rename_inplace(self, datetime_series):
renamer = lambda x: x.strftime("%Y%m%d")
Reported by Pylint.
Line: 100
Column: 29
# GH 17407
s = Series(range(1, 6), index=Index(range(2, 7), name="IntIndex"))
result = s.rename(str)
expected = s.rename(lambda i: str(i))
tm.assert_series_equal(result, expected)
assert result.name == expected.name
Reported by Pylint.
Line: 1
Column: 1
from datetime import datetime
import numpy as np
from pandas import (
Index,
Series,
)
import pandas._testing as tm
Reported by Pylint.
Line: 12
Column: 1
import pandas._testing as tm
class TestRename:
def test_rename(self, datetime_series):
ts = datetime_series
renamer = lambda x: x.strftime("%Y%m%d")
renamed = ts.rename(renamer)
assert renamed.index[0] == renamer(ts.index[0])
Reported by Pylint.
Line: 13
Column: 5
class TestRename:
def test_rename(self, datetime_series):
ts = datetime_series
renamer = lambda x: x.strftime("%Y%m%d")
renamed = ts.rename(renamer)
assert renamed.index[0] == renamer(ts.index[0])
Reported by Pylint.
Line: 13
Column: 5
class TestRename:
def test_rename(self, datetime_series):
ts = datetime_series
renamer = lambda x: x.strftime("%Y%m%d")
renamed = ts.rename(renamer)
assert renamed.index[0] == renamer(ts.index[0])
Reported by Pylint.
Line: 14
Column: 9
class TestRename:
def test_rename(self, datetime_series):
ts = datetime_series
renamer = lambda x: x.strftime("%Y%m%d")
renamed = ts.rename(renamer)
assert renamed.index[0] == renamer(ts.index[0])
# dict
Reported by Pylint.
Line: 17
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
ts = datetime_series
renamer = lambda x: x.strftime("%Y%m%d")
renamed = ts.rename(renamer)
assert renamed.index[0] == renamer(ts.index[0])
# dict
rename_dict = dict(zip(ts.index, renamed.index))
renamed2 = ts.rename(rename_dict)
tm.assert_series_equal(renamed, renamed2)
Reported by Bandit.
Line: 25
Column: 9
tm.assert_series_equal(renamed, renamed2)
# partial dict
s = Series(np.arange(4), index=["a", "b", "c", "d"], dtype="int64")
renamed = s.rename({"b": "foo", "d": "bar"})
tm.assert_index_equal(renamed.index, Index(["a", "foo", "c", "bar"]))
# index with name
renamer = Series(
Reported by Pylint.
pandas/tests/extension/test_integer.py
47 issues
Line: 17
Column: 1
"""
import numpy as np
import pytest
import pandas as pd
import pandas._testing as tm
from pandas.api.types import (
is_extension_array_dtype,
Reported by Pylint.
Line: 59
Column: 10
@pytest.fixture
def data(dtype):
return pd.array(make_data(), dtype=dtype)
@pytest.fixture
def data_for_twos(dtype):
Reported by Pylint.
Line: 64
Column: 19
@pytest.fixture
def data_for_twos(dtype):
return pd.array(np.ones(100) * 2, dtype=dtype)
@pytest.fixture
def data_missing(dtype):
Reported by Pylint.
Line: 69
Column: 18
@pytest.fixture
def data_missing(dtype):
return pd.array([pd.NA, 1], dtype=dtype)
@pytest.fixture
def data_for_sorting(dtype):
Reported by Pylint.
Line: 74
Column: 22
@pytest.fixture
def data_for_sorting(dtype):
return pd.array([1, 2, 0], dtype=dtype)
@pytest.fixture
def data_missing_for_sorting(dtype):
Reported by Pylint.
Line: 79
Column: 30
@pytest.fixture
def data_missing_for_sorting(dtype):
return pd.array([1, pd.NA, 0], dtype=dtype)
@pytest.fixture
def na_cmp():
Reported by Pylint.
Line: 95
Column: 23
@pytest.fixture
def data_for_grouping(dtype):
b = 1
a = 0
c = 2
na = pd.NA
return pd.array([b, b, na, na, a, a, b, c], dtype=dtype)
Reported by Pylint.
Line: 105
Column: 5
class TestDtype(base.BaseDtypeTests):
@pytest.mark.skip(reason="using multiple dtypes")
def test_is_dtype_unboxes_dtype(self):
# we have multiple dtypes, so skip
pass
class TestArithmeticOps(base.BaseArithmeticOpsTests):
Reported by Pylint.
Line: 119
Column: 3
if exc is None:
sdtype = tm.get_dtype(s)
if sdtype.is_unsigned_integer and (op_name == "__rsub__"):
# TODO see https://github.com/pandas-dev/pandas/issues/22023
pytest.skip("unsigned subtraction gives negative values")
if (
hasattr(other, "dtype")
and not is_extension_array_dtype(other.dtype)
Reported by Pylint.
Line: 137
Column: 3
if op_name in ("__rtruediv__", "__truediv__", "__div__"):
expected = expected.fillna(np.nan).astype("Float64")
elif op_name.startswith("__r"):
# TODO reverse operators result in object dtype
# see https://github.com/pandas-dev/pandas/issues/22024
expected = expected.astype(sdtype)
result = result.astype(sdtype)
else:
# combine method result in 'biggest' (int64) dtype
Reported by Pylint.
pandas/tests/io/pytables/test_put.py
47 issues
Line: 9
Column: 1
)
import numpy as np
import pytest
from pandas._libs.tslibs import Timestamp
import pandas as pd
from pandas import (
Reported by Pylint.
Line: 208
Column: 10
df["datetime1"] = datetime.datetime(2001, 1, 2, 0, 0)
df["datetime2"] = datetime.datetime(2001, 1, 3, 0, 0)
df.loc[df.index[3:6], ["obj1"]] = np.nan
df = df._consolidate()._convert(datetime=True)
with ensure_clean_store(setup_path) as store:
_maybe_remove(store, "df")
# PerformanceWarning
Reported by Pylint.
Line: 208
Column: 10
df["datetime1"] = datetime.datetime(2001, 1, 2, 0, 0)
df["datetime2"] = datetime.datetime(2001, 1, 3, 0, 0)
df.loc[df.index[3:6], ["obj1"]] = np.nan
df = df._consolidate()._convert(datetime=True)
with ensure_clean_store(setup_path) as store:
_maybe_remove(store, "df")
# PerformanceWarning
Reported by Pylint.
Line: 228
Column: 19
with ensure_clean_store(setup_path) as store:
def check(format, index):
df = DataFrame(np.random.randn(10, 2), columns=list("AB"))
df.index = index(len(df))
_maybe_remove(store, "df")
store.put("df", df, format=format)
Reported by Pylint.
Line: 1
Column: 1
import datetime
import re
from warnings import (
catch_warnings,
simplefilter,
)
import numpy as np
import pytest
Reported by Pylint.
Line: 35
Column: 1
pytestmark = pytest.mark.single
def test_format_type(setup_path):
df = DataFrame({"A": [1, 2]})
with ensure_clean_path(setup_path) as path:
with HDFStore(path) as store:
store.put("a", df, format="fixed")
store.put("b", df, format="table")
Reported by Pylint.
Line: 36
Column: 5
def test_format_type(setup_path):
df = DataFrame({"A": [1, 2]})
with ensure_clean_path(setup_path) as path:
with HDFStore(path) as store:
store.put("a", df, format="fixed")
store.put("b", df, format="table")
Reported by Pylint.
Line: 42
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
store.put("a", df, format="fixed")
store.put("b", df, format="table")
assert store.get_storer("a").format_type == "fixed"
assert store.get_storer("b").format_type == "table"
def test_format_kwarg_in_constructor(setup_path):
# GH 13291
Reported by Bandit.
Line: 43
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
store.put("b", df, format="table")
assert store.get_storer("a").format_type == "fixed"
assert store.get_storer("b").format_type == "table"
def test_format_kwarg_in_constructor(setup_path):
# GH 13291
Reported by Bandit.
Line: 46
Column: 1
assert store.get_storer("b").format_type == "table"
def test_format_kwarg_in_constructor(setup_path):
# GH 13291
msg = "format is not a defined argument for HDFStore"
with tm.ensure_clean(setup_path) as path:
Reported by Pylint.
pandas/tests/io/json/test_readlines.py
47 issues
Line: 4
Column: 1
from io import StringIO
from pathlib import Path
import pytest
import pandas as pd
from pandas import (
DataFrame,
read_json,
Reported by Pylint.
Line: 92
Column: 26
@pytest.mark.parametrize("chunksize", [1, 1.0])
def test_readjson_chunks(lines_json_df, chunksize):
# Basic test that read_json(chunks=True) gives the same result as
# read_json(chunks=False)
# GH17048: memory usage when lines=True
unchunked = read_json(StringIO(lines_json_df), lines=True)
Reported by Pylint.
Line: 104
Column: 44
tm.assert_frame_equal(chunked, unchunked)
def test_readjson_chunksize_requires_lines(lines_json_df):
msg = "chunksize can only be passed if lines=True"
with pytest.raises(ValueError, match=msg):
with read_json(StringIO(lines_json_df), lines=False, chunksize=2) as _:
pass
Reported by Pylint.
Line: 125
Column: 30
tm.assert_series_equal(chunked, unchunked)
def test_readjson_each_chunk(lines_json_df):
# Other tests check that the final result of read_json(chunksize=True)
# is correct. This checks the intermediate chunks.
with read_json(StringIO(lines_json_df), lines=True, chunksize=2) as reader:
chunks = list(reader)
assert chunks[0].shape == (2, 2)
Reported by Pylint.
Line: 174
Column: 37
@pytest.mark.parametrize("chunksize", [0, -1, 2.2, "foo"])
def test_readjson_invalid_chunksize(lines_json_df, chunksize):
msg = r"'chunksize' must be an integer >=1"
with pytest.raises(ValueError, match=msg):
with read_json(StringIO(lines_json_df), lines=True, chunksize=chunksize) as _:
pass
Reported by Pylint.
Line: 1
Column: 1
from io import StringIO
from pathlib import Path
import pytest
import pandas as pd
from pandas import (
DataFrame,
read_json,
Reported by Pylint.
Line: 17
Column: 1
@pytest.fixture
def lines_json_df():
df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
return df.to_json(lines=True, orient="records")
def test_read_jsonl():
Reported by Pylint.
Line: 18
Column: 5
@pytest.fixture
def lines_json_df():
df = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
return df.to_json(lines=True, orient="records")
def test_read_jsonl():
# GH9180
Reported by Pylint.
Line: 22
Column: 1
return df.to_json(lines=True, orient="records")
def test_read_jsonl():
# GH9180
result = read_json('{"a": 1, "b": 2}\n{"b":2, "a" :1}\n', lines=True)
expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"])
tm.assert_frame_equal(result, expected)
Reported by Pylint.
Line: 29
Column: 1
tm.assert_frame_equal(result, expected)
def test_read_datetime():
# GH33787
df = DataFrame(
[([1, 2], ["2020-03-05", "2020-04-08T09:58:49+00:00"], "hector")],
columns=["accounts", "date", "name"],
)
Reported by Pylint.
pandas/tests/arrays/sparse/test_dtype.py
47 issues
Line: 4
Column: 1
import re
import numpy as np
import pytest
import pandas as pd
from pandas.core.arrays.sparse import SparseDtype
Reported by Pylint.
Line: 102
Column: 12
],
)
def test_is_numeric(dtype, expected):
assert dtype._is_numeric is expected
def test_str_uses_object():
result = SparseDtype(str).subtype
assert result == np.dtype("object")
Reported by Pylint.
Line: 155
Column: 18
],
)
def test_parse_subtype(string, expected):
subtype, _ = SparseDtype._parse_subtype(string)
assert subtype == expected
@pytest.mark.parametrize(
"string", ["Sparse[int, 1]", "Sparse[float, 0.0]", "Sparse[bool, True]"]
Reported by Pylint.
Line: 1
Column: 1
import re
import numpy as np
import pytest
import pandas as pd
from pandas.core.arrays.sparse import SparseDtype
Reported by Pylint.
Line: 19
Column: 1
("object", np.nan),
("datetime64[ns]", np.datetime64("NaT", "ns")),
("timedelta64[ns]", np.timedelta64("NaT", "ns")),
],
)
def test_inferred_dtype(dtype, fill_value):
sparse_dtype = SparseDtype(dtype)
result = sparse_dtype.fill_value
if pd.isna(fill_value):
Reported by Pylint.
Line: 25
Column: 36
sparse_dtype = SparseDtype(dtype)
result = sparse_dtype.fill_value
if pd.isna(fill_value):
assert pd.isna(result) and type(result) == type(fill_value)
else:
assert result == fill_value
def test_from_sparse_dtype():
Reported by Pylint.
Line: 25
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
sparse_dtype = SparseDtype(dtype)
result = sparse_dtype.fill_value
if pd.isna(fill_value):
assert pd.isna(result) and type(result) == type(fill_value)
else:
assert result == fill_value
def test_from_sparse_dtype():
Reported by Bandit.
Line: 27
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
if pd.isna(fill_value):
assert pd.isna(result) and type(result) == type(fill_value)
else:
assert result == fill_value
def test_from_sparse_dtype():
dtype = SparseDtype("float", 0)
result = SparseDtype(dtype)
Reported by Bandit.
Line: 30
Column: 1
assert result == fill_value
def test_from_sparse_dtype():
dtype = SparseDtype("float", 0)
result = SparseDtype(dtype)
assert result.fill_value == 0
Reported by Pylint.
Line: 33
Suggestion:
https://bandit.readthedocs.io/en/latest/plugins/b101_assert_used.html
def test_from_sparse_dtype():
dtype = SparseDtype("float", 0)
result = SparseDtype(dtype)
assert result.fill_value == 0
def test_from_sparse_dtype_fill_value():
dtype = SparseDtype("int", 1)
result = SparseDtype(dtype, fill_value=2)
Reported by Bandit.