File size: 10,210 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 |
""" test feather-format compat """
import numpy as np
import pytest
from pandas.compat.pyarrow import (
pa_version_under18p0,
pa_version_under19p0,
)
import pandas as pd
import pandas._testing as tm
from pandas.io.feather_format import read_feather, to_feather # isort:skip
pytestmark = pytest.mark.filterwarnings(
"ignore:Passing a BlockManager to DataFrame:DeprecationWarning"
)
pa = pytest.importorskip("pyarrow")
@pytest.mark.single_cpu
class TestFeather:
def check_error_on_write(self, df, exc, err_msg):
# check that we are raising the exception
# on writing
with pytest.raises(exc, match=err_msg):
with tm.ensure_clean() as path:
to_feather(df, path)
def check_external_error_on_write(self, df):
# check that we are raising the exception
# on writing
with tm.external_error_raised(Exception):
with tm.ensure_clean() as path:
to_feather(df, path)
def check_round_trip(self, df, expected=None, write_kwargs={}, **read_kwargs):
if expected is None:
expected = df.copy()
with tm.ensure_clean() as path:
to_feather(df, path, **write_kwargs)
result = read_feather(path, **read_kwargs)
tm.assert_frame_equal(result, expected)
def test_error(self):
msg = "feather only support IO with DataFrames"
for obj in [
pd.Series([1, 2, 3]),
1,
"foo",
pd.Timestamp("20130101"),
np.array([1, 2, 3]),
]:
self.check_error_on_write(obj, ValueError, msg)
def test_basic(self):
df = pd.DataFrame(
{
"string": list("abc"),
"int": list(range(1, 4)),
"uint": np.arange(3, 6).astype("u1"),
"float": np.arange(4.0, 7.0, dtype="float64"),
"float_with_null": [1.0, np.nan, 3],
"bool": [True, False, True],
"bool_with_null": [True, np.nan, False],
"cat": pd.Categorical(list("abc")),
"dt": pd.DatetimeIndex(
list(pd.date_range("20130101", periods=3)), freq=None
),
"dttz": pd.DatetimeIndex(
list(pd.date_range("20130101", periods=3, tz="US/Eastern")),
freq=None,
),
"dt_with_null": [
pd.Timestamp("20130101"),
pd.NaT,
pd.Timestamp("20130103"),
],
"dtns": pd.DatetimeIndex(
list(pd.date_range("20130101", periods=3, freq="ns")), freq=None
),
}
)
df["periods"] = pd.period_range("2013", freq="M", periods=3)
df["timedeltas"] = pd.timedelta_range("1 day", periods=3)
df["intervals"] = pd.interval_range(0, 3, 3)
assert df.dttz.dtype.tz.zone == "US/Eastern"
expected = df.copy()
expected.loc[1, "bool_with_null"] = None
self.check_round_trip(df, expected=expected)
def test_duplicate_columns(self):
# https://github.com/wesm/feather/issues/53
# not currently able to handle duplicate columns
df = pd.DataFrame(np.arange(12).reshape(4, 3), columns=list("aaa")).copy()
self.check_external_error_on_write(df)
def test_read_columns(self):
# GH 24025
df = pd.DataFrame(
{
"col1": list("abc"),
"col2": list(range(1, 4)),
"col3": list("xyz"),
"col4": list(range(4, 7)),
}
)
columns = ["col1", "col3"]
self.check_round_trip(df, expected=df[columns], columns=columns)
def test_read_columns_different_order(self):
# GH 33878
df = pd.DataFrame({"A": [1, 2], "B": ["x", "y"], "C": [True, False]})
expected = df[["B", "A"]]
self.check_round_trip(df, expected, columns=["B", "A"])
def test_unsupported_other(self):
# mixed python objects
df = pd.DataFrame({"a": ["a", 1, 2.0]})
self.check_external_error_on_write(df)
def test_rw_use_threads(self):
df = pd.DataFrame({"A": np.arange(100000)})
self.check_round_trip(df, use_threads=True)
self.check_round_trip(df, use_threads=False)
def test_path_pathlib(self):
df = pd.DataFrame(
1.1 * np.arange(120).reshape((30, 4)),
columns=pd.Index(list("ABCD")),
index=pd.Index([f"i-{i}" for i in range(30)]),
).reset_index()
result = tm.round_trip_pathlib(df.to_feather, read_feather)
tm.assert_frame_equal(df, result)
def test_path_localpath(self):
df = pd.DataFrame(
1.1 * np.arange(120).reshape((30, 4)),
columns=pd.Index(list("ABCD")),
index=pd.Index([f"i-{i}" for i in range(30)]),
).reset_index()
result = tm.round_trip_localpath(df.to_feather, read_feather)
tm.assert_frame_equal(df, result)
def test_passthrough_keywords(self):
df = pd.DataFrame(
1.1 * np.arange(120).reshape((30, 4)),
columns=pd.Index(list("ABCD")),
index=pd.Index([f"i-{i}" for i in range(30)]),
).reset_index()
self.check_round_trip(df, write_kwargs={"version": 1})
@pytest.mark.network
@pytest.mark.single_cpu
def test_http_path(self, feather_file, httpserver):
# GH 29055
expected = read_feather(feather_file)
with open(feather_file, "rb") as f:
httpserver.serve_content(content=f.read())
res = read_feather(httpserver.url)
tm.assert_frame_equal(expected, res)
def test_read_feather_dtype_backend(
self, string_storage, dtype_backend, using_infer_string
):
# GH#50765
df = pd.DataFrame(
{
"a": pd.Series([1, np.nan, 3], dtype="Int64"),
"b": pd.Series([1, 2, 3], dtype="Int64"),
"c": pd.Series([1.5, np.nan, 2.5], dtype="Float64"),
"d": pd.Series([1.5, 2.0, 2.5], dtype="Float64"),
"e": [True, False, None],
"f": [True, False, True],
"g": ["a", "b", "c"],
"h": ["a", "b", None],
}
)
with tm.ensure_clean() as path:
to_feather(df, path)
with pd.option_context("mode.string_storage", string_storage):
result = read_feather(path, dtype_backend=dtype_backend)
if dtype_backend == "pyarrow":
pa = pytest.importorskip("pyarrow")
if using_infer_string:
string_dtype = pd.ArrowDtype(pa.large_string())
else:
string_dtype = pd.ArrowDtype(pa.string())
else:
string_dtype = pd.StringDtype(string_storage)
expected = pd.DataFrame(
{
"a": pd.Series([1, np.nan, 3], dtype="Int64"),
"b": pd.Series([1, 2, 3], dtype="Int64"),
"c": pd.Series([1.5, np.nan, 2.5], dtype="Float64"),
"d": pd.Series([1.5, 2.0, 2.5], dtype="Float64"),
"e": pd.Series([True, False, pd.NA], dtype="boolean"),
"f": pd.Series([True, False, True], dtype="boolean"),
"g": pd.Series(["a", "b", "c"], dtype=string_dtype),
"h": pd.Series(["a", "b", None], dtype=string_dtype),
}
)
if dtype_backend == "pyarrow":
from pandas.arrays import ArrowExtensionArray
expected = pd.DataFrame(
{
col: ArrowExtensionArray(pa.array(expected[col], from_pandas=True))
for col in expected.columns
}
)
if using_infer_string:
expected.columns = expected.columns.astype(
pd.StringDtype(string_storage, na_value=np.nan)
)
tm.assert_frame_equal(result, expected)
def test_int_columns_and_index(self):
df = pd.DataFrame({"a": [1, 2, 3]}, index=pd.Index([3, 4, 5], name="test"))
self.check_round_trip(df)
def test_invalid_dtype_backend(self):
msg = (
"dtype_backend numpy is invalid, only 'numpy_nullable' and "
"'pyarrow' are allowed."
)
df = pd.DataFrame({"int": list(range(1, 4))})
with tm.ensure_clean("tmp.feather") as path:
df.to_feather(path)
with pytest.raises(ValueError, match=msg):
read_feather(path, dtype_backend="numpy")
def test_string_inference(self, tmp_path, using_infer_string):
# GH#54431
path = tmp_path / "test_string_inference.p"
df = pd.DataFrame(data={"a": ["x", "y"]})
df.to_feather(path)
with pd.option_context("future.infer_string", True):
result = read_feather(path)
dtype = pd.StringDtype(na_value=np.nan)
expected = pd.DataFrame(
data={"a": ["x", "y"]}, dtype=pd.StringDtype(na_value=np.nan)
)
expected = pd.DataFrame(
data={"a": ["x", "y"]},
dtype=dtype,
columns=pd.Index(
["a"],
dtype=object
if pa_version_under19p0 and not using_infer_string
else dtype,
),
)
tm.assert_frame_equal(result, expected)
@pytest.mark.skipif(pa_version_under18p0, reason="not supported before 18.0")
def test_string_inference_string_view_type(self, tmp_path):
# GH#54798
import pyarrow as pa
from pyarrow import feather
path = tmp_path / "string_view.parquet"
table = pa.table({"a": pa.array([None, "b", "c"], pa.string_view())})
feather.write_feather(table, path)
with pd.option_context("future.infer_string", True):
result = read_feather(path)
expected = pd.DataFrame(
data={"a": [None, "b", "c"]}, dtype=pd.StringDtype(na_value=np.nan)
)
tm.assert_frame_equal(result, expected)
|