def test_astype(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
self.assert_eq(pser.astype(int), psser.astype(int))
self.assert_eq(pser.astype(float), psser.astype(float))
self.assert_eq(pser.astype(np.float32), psser.astype(np.float32))
self.assert_eq(pser.astype(np.int32), psser.astype(np.int32))
self.assert_eq(pser.astype(np.int16), psser.astype(np.int16))
self.assert_eq(pser.astype(np.int8), psser.astype(np.int8))
self.assert_eq(pser.astype(str), psser.astype(str))
self.assert_eq(pser.astype(bool), psser.astype(bool))
self.assert_eq(pser.astype("category"), psser.astype("category"))
cat_type = CategoricalDtype(categories=[2, 1, 3])
self.assert_eq(pser.astype(cat_type), psser.astype(cat_type))
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to integer",
lambda: self.float_withnan_psser.astype(int),
)
self.assertRaisesRegex(
ValueError,
"Cannot convert fractions with missing values to integer",
lambda: self.float_withnan_psser.astype(np.int32),
)
self.assert_eq(self.float_withnan_psser.astype(str), self.float_withnan_psser.astype(str))
self.assert_eq(self.float_withnan_psser.astype(bool), self.float_withnan_psser.astype(bool))
self.assert_eq(
self.float_withnan_psser.astype("category"), self.float_withnan_psser.astype("category")
)
if extension_object_dtypes_available and extension_float_dtypes_available:
pser = pd.Series(pd.Categorical([1.0, 2.0, 3.0]), dtype=pd.Float64Dtype())
psser = ps.from_pandas(pser)
self.assert_eq(pser.astype(pd.BooleanDtype()), psser.astype(pd.BooleanDtype()))
def test_astype(self):
pdf, psdf = self.pdf, self.psdf
for col in self.numeric_df_cols:
pser, psser = pdf[col], psdf[col]
for int_type in [int, np.int32, np.int16, np.int8]:
if not pser.hasnans:
self.assert_eq(pser.astype(int_type),
psser.astype(int_type))
else:
self.assertRaisesRegex(
ValueError,
"Cannot convert %s with missing "
"values to integer" % psser._dtype_op.pretty_name,
lambda: psser.astype(int_type),
)
# TODO(SPARK-37039): the np.nan series.astype(bool) should be True
if not pser.hasnans:
self.assert_eq(pser.astype(bool), psser.astype(bool))
self.assert_eq(pser.astype(float), psser.astype(float))
self.assert_eq(pser.astype(np.float32), psser.astype(np.float32))
self.assert_eq(pser.astype(str), psser.astype(str))
self.assert_eq(pser.astype("category"), psser.astype("category"))
cat_type = CategoricalDtype(categories=[2, 1, 3])
self.assert_eq(pser.astype(cat_type), psser.astype(cat_type))
if extension_object_dtypes_available and extension_float_dtypes_available:
pser = pd.Series(pd.Categorical([1.0, 2.0, 3.0]),
dtype=pd.Float64Dtype())
psser = ps.from_pandas(pser)
self.assert_eq(pser.astype(pd.BooleanDtype()),
psser.astype(pd.BooleanDtype()))
def test_boolean_conversion(s, expected_category, bool_map):
assert _infer_bool_type(s) == expected_category
if pd.isna(s[2]):
expected = pd.Series([True, False, pd.NA], dtype=pd.BooleanDtype())
else:
expected = pd.Series([True, False, True], dtype=pd.BooleanDtype())
actual = convert_to_bool_series(s, True, bool_map=bool_map)
assert_series_equal(expected, actual)
def test_meta():
values = pd.array([True, False, None], dtype="boolean")
ds = dd.from_pandas(pd.Series(values), 2)
assert ds.dtype == pd.BooleanDtype()
dd.utils.assert_eq(ds._meta_nonempty, pd.Series([True, pd.NA], dtype="boolean"))
ddf = dd.from_pandas(pd.DataFrame({"A": values}), 2)
assert ddf.dtypes["A"] == pd.BooleanDtype()
dd.utils.assert_eq(
ddf._meta_nonempty,
pd.DataFrame({"A": pd.array([True, pd.NA], dtype="boolean")}),
)
def test_decide_pandas_dtype(self):
base_arr = np.arange(4)
arr = base_arr.reshape(2, 2)
res = decide_pandas_dtype(arr)
self.assertEqual(res, object)
class NotCoveredType:
pass
mapping = {
object: object,
bool: pd.BooleanDtype(),
str: pd.StringDtype(),
float: float,
int: "Int64",
np.int8: "Int8",
np.uint16: "UInt16",
NotCoveredType: object
}
for tin, tout in mapping.items():
arr = base_arr.astype(tin)
res = decide_pandas_dtype(arr)
self.assertEqual(res, tout)
def pyarrow2pandas_extension( # pylint: disable=too-many-branches,too-many-return-statements
dtype: pa.DataType,
) -> Optional[pd.api.extensions.ExtensionDtype]:
"""Pyarrow to Pandas data types conversion."""
if pa.types.is_int8(dtype):
return pd.Int8Dtype()
if pa.types.is_int16(dtype):
return pd.Int16Dtype()
if pa.types.is_int32(dtype):
return pd.Int32Dtype()
if pa.types.is_int64(dtype):
return pd.Int64Dtype()
if pa.types.is_uint8(dtype):
return pd.UInt8Dtype()
if pa.types.is_uint16(dtype):
return pd.UInt16Dtype()
if pa.types.is_uint32(dtype):
return pd.UInt32Dtype()
if pa.types.is_uint64(dtype):
return pd.UInt64Dtype()
if pa.types.is_boolean(dtype):
return pd.BooleanDtype()
if pa.types.is_string(dtype):
return pd.StringDtype()
return None
def test_pandas_extension_types():
"""Test pandas extension data type happy path."""
# pylint: disable=no-member
test_params = [
(pd.CategoricalDtype(),
pd.Series(["a", "a", "b", "b", "c", "c"], dtype="category"), None),
(pd.DatetimeTZDtype(tz='UTC'),
pd.Series(pd.date_range(start="20200101", end="20200301"),
dtype="datetime64[ns, utc]"), None),
(pd.Int64Dtype(), pd.Series(range(10), dtype="Int64"), None),
(pd.StringDtype(), pd.Series(["foo", "bar", "baz"],
dtype="string"), None),
(pd.PeriodDtype(freq='D'),
pd.Series(pd.period_range('1/1/2019', '1/1/2020', freq='D')), None),
(
pd.SparseDtype("float"),
pd.Series(range(100)).where(lambda s: s < 5,
other=np.nan).astype("Sparse[float]"),
{
"nullable": True
},
),
(pd.BooleanDtype(), pd.Series([1, 0, 0, 1, 1], dtype="boolean"), None),
(
pd.IntervalDtype(subtype="int64"),
pd.Series(pd.IntervalIndex.from_breaks([0, 1, 2, 3, 4])),
None,
)
]
for dtype, data, series_kwargs in test_params:
series_kwargs = {} if series_kwargs is None else series_kwargs
series_schema = SeriesSchema(pandas_dtype=dtype, **series_kwargs)
assert isinstance(series_schema.validate(data), pd.Series)
def test_null_values(self):
data = np.array([["dadf", 10.9, -2, False], ["c", 100.9, 1, True],
[None, None, None, None]])
df = pd.DataFrame({
"col1": data[:, 0],
"col2": data[:, 1],
"col3": data[:, 2],
"col4": data[:, 3]
})
inOp = dataframeToOperator(
df,
schemaStr='col1 string, col2 double, col3 long, col4 boolean',
op_type='batch')
res = inOp.collectToDataframe()
print(res.dtypes)
print(res)
self.assertEqual(res.dtypes[0], pd.StringDtype())
self.assertEqual(res.dtypes[1], np.float64)
self.assertEqual(res.dtypes[2], pd.Int64Dtype())
self.assertEqual(res.dtypes[3], pd.BooleanDtype())
self.assertTrue(pd.isna(res["col1"][2]))
self.assertTrue(pd.isna(res["col2"][2]))
self.assertTrue(pd.isna(res["col3"][2]))
self.assertTrue(pd.isna(res["col4"][2]))
def test_memory(self):
from pyalink.alink.config import g_config
g_config["collect_storage_type"] = "memory"
schema = "f_string string,f_long long,f_int int,f_double double,f_boolean boolean"
op = dataframeToOperator(self.df, schemaStr=schema, op_type="batch")
col_names = op.getColNames()
col_types = op.getColTypes()
self.assertEqual(col_names[0], "f_string")
self.assertEqual(col_names[1], "f_long")
self.assertEqual(col_names[2], "f_int")
self.assertEqual(col_names[3], "f_double")
self.assertEqual(col_names[4], "f_boolean")
self.assertEqual(col_types[0], "VARCHAR")
self.assertEqual(col_types[1], "BIGINT")
self.assertEqual(col_types[2], "INT")
self.assertEqual(col_types[3], "DOUBLE")
self.assertEqual(col_types[4], "BOOLEAN")
df2 = op.collectToDataframe()
print(df2)
print(df2.dtypes)
self.assertEqual(df2['f_string'].dtype, pd.StringDtype())
self.assertEqual(df2['f_long'].dtype, pd.Int64Dtype())
self.assertEqual(df2['f_int'].dtype, pd.Int32Dtype())
self.assertEqual(df2['f_double'].dtype, np.float64)
self.assertEqual(df2['f_boolean'].dtype, pd.BooleanDtype())
def _dtypes(self, categories=None):
""" Implied types of the columns in the schema """
import pandas as pd
if self.has_pandas_metadata:
md = self.pandas_metadata['columns']
tz = {
c['name']: c['metadata']['timezone']
for c in md
if (c.get('metadata', {}) or {}).get('timezone', None)
}
else:
tz = None
self.tz = tz
categories = self.check_categories(categories)
dtype = OrderedDict(
(name, (converted_types.typemap(f) if f.num_children in
[None, 0] else np.dtype("O")))
for name, f in self.schema.root.children.items()
if getattr(f, 'isflat', False) is False)
for i, (col, dt) in enumerate(dtype.copy().items()):
if dt.kind in ['i', 'b']:
# int/bool columns that may have nulls become float columns
num_nulls = 0
for rg in self.row_groups:
chunk = rg.columns[i]
if chunk.meta_data.statistics is None:
num_nulls = True
break
if chunk.meta_data.statistics.null_count is None:
num_nulls = True
break
if chunk.meta_data.statistics.null_count:
num_nulls = True
break
if num_nulls:
if dt.kind == "b":
dtype[col] = pd.BooleanDtype()
elif dtype[col].itemsize == 1:
dtype[col] = pd.Int8Dtype()
elif dtype[col].itemsize == 2:
dtype[col] = pd.Int16Dtype()
elif dtype[col].itemsize == 4:
dtype[col] = pd.Int32Dtype()
else:
dtype[col] = pd.Int64Dtype()
elif dt.kind == "M":
if tz is not None and tz.get(col, False):
dtype[col] = pd.Series([], dtype='M8[ns]').dt.tz_localize(
tz[col]).dtype
elif dt == 'S12':
dtype[col] = 'M8[ns]'
for field in categories:
dtype[field] = 'category'
for cat in self.cats:
dtype[cat] = "category"
self.dtypes = dtype
return dtype
def test_bucketing_parquet_dataset(path, glue_database, glue_table,
bucketing_data, dtype):
# Skip invalid combinations of data and data types
if type(bucketing_data[0]) == int and "int" not in dtype.lower():
pytest.skip()
if type(bucketing_data[0]) == bool and "bool" not in dtype.lower():
pytest.skip()
if type(bucketing_data[0]) == str and (dtype != "string"
or dtype != "object"):
pytest.skip()
nb_of_buckets = 2
df = pd.DataFrame({"c0": bucketing_data, "c1": ["foo", "bar", "baz"]})
r = wr.s3.to_parquet(
df=df,
path=path,
database=glue_database,
table=glue_table,
dataset=True,
mode="overwrite",
bucketing_info=(["c0"], nb_of_buckets),
)
assert len(r["paths"]) == 2
assert r["paths"][0].endswith("bucket-00000.snappy.parquet")
assert r["paths"][1].endswith("bucket-00001.snappy.parquet")
dtype = None
if isinstance(bucketing_data[0], int):
dtype = pd.Int64Dtype()
if isinstance(bucketing_data[0], bool):
dtype = pd.BooleanDtype()
if isinstance(bucketing_data[0], str):
dtype = pd.StringDtype()
first_bucket_df = wr.s3.read_parquet(path=[r["paths"][0]])
assert len(first_bucket_df) == 2
assert pd.Series([bucketing_data[0], bucketing_data[2]],
dtype=dtype).equals(first_bucket_df["c0"])
assert pd.Series(["foo", "baz"],
dtype=pd.StringDtype()).equals(first_bucket_df["c1"])
second_bucket_df = wr.s3.read_parquet(path=[r["paths"][1]])
assert len(second_bucket_df) == 1
assert pd.Series([bucketing_data[1]],
dtype=dtype).equals(second_bucket_df["c0"])
assert pd.Series(["bar"],
dtype=pd.StringDtype()).equals(second_bucket_df["c1"])
loaded_dfs = [
wr.s3.read_parquet(path=path),
wr.athena.read_sql_table(table=glue_table,
database=glue_database,
ctas_approach=False),
]
for loaded_df in loaded_dfs:
assert len(loaded_df) == 3
assert all(x in bucketing_data for x in loaded_df["c0"].to_list())
def test_nullable_types(self):
df = pd.DataFrame({"tag1": [10, None], "tag2": [True, None]})
df1 = df.astype({"tag1": "Int64", "tag2": pd.BooleanDtype()})
push("test/pandas/nullable_types",
df1,
encoder=DataFrameEncoder(index=False))
df2 = pull("test/pandas/nullable_types")
map(lambda x, y: self.assertEqual(x, y), zip(df2.dtypes, df1.dtypes))
def test_astype_to_boolean_array():
# astype to BooleanArray
arr = pd.array([True, False, None], dtype="boolean")
result = arr.astype("boolean")
tm.assert_extension_array_equal(result, arr)
result = arr.astype(pd.BooleanDtype())
tm.assert_extension_array_equal(result, arr)
def test_astype_to_boolean_array():
# astype to BooleanArray
arr = pd.array([0.0, 1.0, None], dtype="Float64")
result = arr.astype("boolean")
expected = pd.array([False, True, None], dtype="boolean")
tm.assert_extension_array_equal(result, expected)
result = arr.astype(pd.BooleanDtype())
tm.assert_extension_array_equal(result, expected)
def __init__(self, pandas_obj):
# validate and assign object
self._validate(pandas_obj)
self._obj = pandas_obj
# define incorporated modules - columns consisting of others will not have the dtype changed
self._INCORPORATED_MODULES = ['builtins', 'numpy', 'pandas']
# define a possible list of null values
self._NULL_VALS = [
None, np.nan, 'np.nan', 'nan', np.inf, 'np.inf', 'inf', -np.inf,
'-np.inf', '', 'n/a', 'na', 'N/A', 'NA', 'unknown', 'unk',
'UNKNOWN', 'UNK'
]
# assign dtypes and limits
# boolean
BOOL_STRINGS_TRUE = ['t', 'true', 'yes', 'on']
BOOL_STRINGS_FALSE = ['f', 'false', 'no', 'off']
self._BOOL_MAP_DICT = {i: True
for i in BOOL_STRINGS_TRUE
}.update({i: False
for i in BOOL_STRINGS_FALSE})
self._DTYPE_BOOL_BASE = np.bool
self._DTYPE_BOOL_NULLABLE = pd.BooleanDtype()
# unsigned integers - base and nullable
self._DTYPES_UINT_BASE = [np.uint8, np.uint16, np.uint32, np.uint64]
self._DTYPES_UINT_NULLABLE = [
pd.UInt8Dtype(),
pd.UInt16Dtype(),
pd.UInt32Dtype(),
pd.UInt64Dtype()
]
self._LIMIT_LOW_UINT = [
np.iinfo(i).min for i in self._DTYPES_UINT_BASE
]
self._LIMIT_HIGH_UINT = [
np.iinfo(i).max for i in self._DTYPES_UINT_BASE
]
# signed integers - base and nullable
self._DTYPES_INT_BASE = [np.int8, np.int16, np.int32, np.int64]
self._DTYPES_INT_NULLABLE = [
pd.Int8Dtype(),
pd.Int16Dtype(),
pd.Int32Dtype(),
pd.Int64Dtype()
]
self._LIMIT_LOW_INT = [np.iinfo(i).min for i in self._DTYPES_INT_BASE]
self._LIMIT_HIGH_INT = [np.iinfo(i).max for i in self._DTYPES_INT_BASE]
# floats - nullable by default
self._DTYPES_FLOAT = [np.float16, np.float32, np.float64]
# datetime - nullable by default
self._DTYPE_DATETIME = np.datetime64
# string
self._DTYPE_STRING = pd.StringDtype()
# categorical - nullable by default
self._DTYPE_CATEGORICAL = pd.CategoricalDtype()
def load_audit(name):
df = load_csv(name)
df = df.where((pandas.notnull(df)), None)
df["Adjusted"] = df["Adjusted"].astype(int)
df["Age"] = df["Age"].astype(pandas.Int64Dtype() if name.endswith("NA") else int)
df["Deductions"] = df["Deductions"].astype(pandas.BooleanDtype() if name.endswith("NA") else bool)
df["Income"] = df["Income"].astype(float)
df["Hours"] = df["Hours"].astype(float)
return split_csv(df)
def test_dtypes_are_correct_after_groupby_last(self, data):
# GH46409
df = DataFrame({
"id": [1, 2, 3, 4],
"test": [True, pd.NA, data, False]
}).convert_dtypes()
result = df.groupby("id").last().test
expected = df.set_index("id").test
assert result.dtype == pd.BooleanDtype()
tm.assert_series_equal(expected, result)
def get_sparse_series() -> Dict[str, pd.Series]:
test_series = {
"int_sparse":
pd.Series([-1, 0, 1, 2, 3], dtype=pd.SparseDtype(np.int32, 0)),
"float_sparse":
pd.Series(
[np.nan, 0, 1, 2, 3],
dtype=pd.SparseDtype(np.float64, np.nan),
),
"complex_sparse":
pd.Series(
[
np.nan,
complex(0, 1),
complex(1, -1),
complex(2, 4),
complex(3, -12)
],
dtype=pd.SparseDtype(np.complex128, np.nan),
),
"bool_sparse":
pd.Series(
[True, False, False],
dtype=pd.SparseDtype(np.bool, False),
),
"str_obj_sparse":
pd.Series(
pd.arrays.SparseArray([None, None, "gold", "black", "silver"]), ),
# Pending https://github.com/pandas-dev/pandas/issues/35762
# pd.Series([NoneT, 0, 1, 2, 3, 4], name="datetime_sparse", dtype=pd.SparseDtype(np.datetime64)),
# Pandas dtypes
"pd_int64_sparse":
pd.Series(
[0, 1, 2, 3, None],
dtype=pd.SparseDtype(pd.Int64Dtype()),
),
# Pending https://github.com/pandas-dev/pandas/issues/35793
# pd.Series(
# ["a", "b", "c", None],
# name="pd_categorical_sparse",
# dtype=pd.SparseDtype(pd.CategoricalDtype(['a', 'b', 'c', 'd']))
# )
}
if pandas_version[0] >= 1 and not_pandas_1_0_5:
test_series["pd_string_sparse"] = pd.Series(
["Patty", "Valentine", "Upper", "", "", ""],
dtype=pd.SparseDtype(pd.StringDtype(), ""),
)
test_series["pd_bool_sparse"] = pd.Series(
[True, False, False, None],
dtype=pd.SparseDtype(pd.BooleanDtype(), None),
)
return test_series
def read(
self,
path,
columns=None,
use_nullable_dtypes=False,
storage_options: StorageOptions = None,
**kwargs,
):
kwargs["use_pandas_metadata"] = True
to_pandas_kwargs = {}
if use_nullable_dtypes:
if LooseVersion(self.api.__version__) >= "0.16":
import pandas as pd
mapping = {
self.api.int8(): pd.Int8Dtype(),
self.api.int16(): pd.Int16Dtype(),
self.api.int32(): pd.Int32Dtype(),
self.api.int64(): pd.Int64Dtype(),
self.api.uint8(): pd.UInt8Dtype(),
self.api.uint16(): pd.UInt16Dtype(),
self.api.uint32(): pd.UInt32Dtype(),
self.api.uint64(): pd.UInt64Dtype(),
self.api.bool_(): pd.BooleanDtype(),
self.api.string(): pd.StringDtype(),
}
to_pandas_kwargs["types_mapper"] = mapping.get
else:
raise ValueError(
"'use_nullable_dtypes=True' is only supported for pyarrow >= 0.16 "
f"({self.api.__version__} is installed"
)
manager = get_option("mode.data_manager")
if manager == "array":
to_pandas_kwargs["split_blocks"] = True # type: ignore[assignment]
path_or_handle, handles, kwargs["filesystem"] = _get_path_or_handle(
path,
kwargs.pop("filesystem", None),
storage_options=storage_options,
mode="rb",
)
try:
result = self.api.parquet.read_table(
path_or_handle, columns=columns, **kwargs
).to_pandas(**to_pandas_kwargs)
if manager == "array":
result = result._as_manager("array", copy=False)
return result
finally:
if handles is not None:
handles.close()
def test_is_bool_dtype():
assert not com.is_bool_dtype(int)
assert not com.is_bool_dtype(str)
assert not com.is_bool_dtype(pd.Series([1, 2]))
assert not com.is_bool_dtype(np.array(["a", "b"]))
assert not com.is_bool_dtype(pd.Index(["a", "b"]))
assert com.is_bool_dtype(bool)
assert com.is_bool_dtype(np.bool)
assert com.is_bool_dtype(np.array([True, False]))
assert com.is_bool_dtype(pd.Index([True, False]))
assert com.is_bool_dtype(pd.BooleanDtype())
assert com.is_bool_dtype(pd.array([True, False, None], dtype="boolean"))
def read(
self,
path,
columns=None,
use_nullable_dtypes=False,
storage_options: StorageOptions = None,
**kwargs,
) -> DataFrame:
kwargs["use_pandas_metadata"] = True
to_pandas_kwargs = {}
if use_nullable_dtypes:
import pandas as pd
mapping = {
self.api.int8(): pd.Int8Dtype(),
self.api.int16(): pd.Int16Dtype(),
self.api.int32(): pd.Int32Dtype(),
self.api.int64(): pd.Int64Dtype(),
self.api.uint8(): pd.UInt8Dtype(),
self.api.uint16(): pd.UInt16Dtype(),
self.api.uint32(): pd.UInt32Dtype(),
self.api.uint64(): pd.UInt64Dtype(),
self.api.bool_(): pd.BooleanDtype(),
self.api.string(): pd.StringDtype(),
self.api.float32(): pd.Float32Dtype(),
self.api.float64(): pd.Float64Dtype(),
}
to_pandas_kwargs["types_mapper"] = mapping.get
manager = get_option("mode.data_manager")
if manager == "array":
to_pandas_kwargs["split_blocks"] = True # type: ignore[assignment]
path_or_handle, handles, kwargs["filesystem"] = _get_path_or_handle(
path,
kwargs.pop("filesystem", None),
storage_options=storage_options,
mode="rb",
)
try:
result = self.api.parquet.read_table(
path_or_handle, columns=columns,
**kwargs).to_pandas(**to_pandas_kwargs)
if manager == "array":
result = result._as_manager("array", copy=False)
return result
finally:
if handles is not None:
handles.close()
def test_numeric_nullable_dtypes(self):
dtypes = [
pd.StringDtype(),
pd.BooleanDtype(),
pd.Float64Dtype(),
pd.Float32Dtype(),
pd.Int64Dtype(),
pd.UInt64Dtype(),
pd.Int32Dtype(),
pd.UInt32Dtype(),
pd.Int16Dtype(),
pd.UInt16Dtype(),
pd.Int8Dtype(),
pd.UInt8Dtype(),
pd.StringDtype(),
]
# TODO: Re-add (".xml", "xml"),
# TODO: See https://github.com/dmyersturnbull/typed-dfs/issues/46
for suffix, fn in [
(".snappy", "parquet"),
(".feather", "feather"),
(".csv", "csv"),
(".tsv", "tsv"),
(".json", "json"),
(".xlsx", "xlsx"),
(".xls", "xls"),
(".xlsb", "xlsb"),
(".ods", "ods"),
(".pickle", "pickle"),
]:
# TODO: include xml
for dtype in dtypes:
with tmpfile(suffix) as path:
try:
df = Ind2Col2.convert(
Ind2Col2(
sample_data_ind2_col2_pd_na())).astype(dtype)
assert list(df.index.names) == ["qqq", "rrr"]
assert list(df.columns) == ["abc", "xyz"]
getattr(df, "to_" + fn)(path)
df2 = getattr(Ind2Col2, "read_" + fn)(path)
assert list(df2.index.names) == ["qqq", "rrr"]
assert list(df2.columns) == ["abc", "xyz"]
except Exception:
logger.error(f"Failed on path {path}, dtype {dtype}")
raise
def test_build_series_from_nullable_pandas_dtype(pd_dtype, expect_dtype):
if pd_dtype == pd.StringDtype():
data = ["a", pd.NA, "c", pd.NA, "e"]
elif pd_dtype == pd.BooleanDtype():
data = [True, pd.NA, False, pd.NA, True]
else:
data = [1, pd.NA, 3, pd.NA, 5]
pd_data = pd.Series(data, dtype=pd_dtype)
gd_data = cudf.Series.from_pandas(pd_data)
assert gd_data.dtype == expect_dtype
# check mask
expect_mask = [True if x is not pd.NA else False for x in pd_data]
got_mask = mask_to_bools(gd_data._column.base_mask, 0,
len(gd_data)).to_array()
np.testing.assert_array_equal(expect_mask, got_mask)
def test_build_df_from_nullable_pandas_dtype(pd_dtype, expect_dtype):
if pd_dtype == pd.StringDtype():
data = ["a", pd.NA, "c", pd.NA, "e"]
elif pd_dtype == pd.BooleanDtype():
data = [True, pd.NA, False, pd.NA, True]
else:
data = [1, pd.NA, 3, pd.NA, 5]
pd_data = pd.DataFrame.from_dict({"a": data}, dtype=pd_dtype)
gd_data = cudf.DataFrame.from_pandas(pd_data)
assert gd_data["a"].dtype == expect_dtype
# check mask
expect_mask = [True if x is not pd.NA else False for x in pd_data["a"]]
got_mask = mask_to_bools(
gd_data["a"]._column.base_mask, 0, len(gd_data)
).values_host
np.testing.assert_array_equal(expect_mask, got_mask)
def test_orc_read_skiprows(tmpdir):
buff = BytesIO()
df = pd.DataFrame(
{"a": [1, 0, 1, 0, None, 1, 1, 1, 0, None, 0, 0, 1, 1, 1, 1]},
dtype=pd.BooleanDtype(),
)
writer = pyorc.Writer(buff, pyorc.Struct(a=pyorc.Boolean()))
tuples = list(
map(
lambda x: (None, ) if x[0] is pd.NA else x,
list(df.itertuples(index=False, name=None)),
))
writer.writerows(tuples)
writer.close()
skiprows = 10
expected = cudf.read_orc(buff)[skiprows::].reset_index(drop=True)
got = cudf.read_orc(buff, skiprows=skiprows)
assert_eq(expected, got)
def get_dummy_deltas(employees_path):
employees = pd.read_csv(employees_path, nrows=10)
# Create deleted flag
employees["record_deleted"] = False
employees["record_deleted"] = employees["record_deleted"].astype(
pd.BooleanDtype())
# Cast to new int cols
for col in ["employee_id", "department_id", "manager_id"]:
employees[col] = employees[col].astype(pd.Int64Dtype())
# Cast to new str cols
for col in ["sex", "forename", "surname"]:
employees[col] = employees[col].astype(pd.StringDtype())
# Let's split up the data and make some changes
day1 = employees[employees.employee_id.isin([1, 2, 3, 4,
5])].reset_index(drop=True)
day2 = employees[employees.employee_id.isin([5, 6,
7])].reset_index(drop=True)
day2.loc[0, "department_id"] = 2
day2.loc[0, "manager_id"] = 18
day3 = employees[employees.employee_id.isin([1, 7, 9, 10,
11])].reset_index(drop=True)
day3.department_id = 2
day3.manager_id = 5
# Reset this persons values for clarity
day3.loc[0, "record_deleted"] = True
day3.loc[0, "department_id"] = 1
day3.loc[0, "manager_id"] = 17
deltas = {"day1": day1, "day2": day2, "day3": day3}
return deltas
def test_df_pdv1_types():
pdv1_test_mapping = {
'int8col': {
'vals': [1, 2, 3],
'pd_type': pd.Int8Dtype()
},
'int16col': {
'vals': [1, 2, 3],
'pd_type': pd.Int16Dtype()
},
'int32col': {
'vals': [1, 2, 3],
'pd_type': pd.Int32Dtype()
},
'int64col': {
'vals': [1, 2, 3],
'pd_type': pd.Int64Dtype()
},
'stringcol': {
'vals': ['one', 'two', 'three'],
'pd_type': pd.StringDtype()
},
'boolcol': {
'vals': [True, False, True],
'pd_type': pd.BooleanDtype()
}
}
pdv1_df = pd.DataFrame({
col_name: col_meta['vals']
for col_name, col_meta in pdv1_test_mapping.items()
})
pdv1_df = pdv1_df.astype({
col_name: col_meta['pd_type']
for col_name, col_meta in pdv1_test_mapping.items()
})
return pdv1_df
def test_to_table_nullable(self):
boolean_array = pd.array([True, False, None], dtype=pd.BooleanDtype())
int8_array = pd.array([1, 2, None], dtype=pd.Int8Dtype())
int16_array = pd.array([1, 2, None], dtype=pd.Int16Dtype())
int32_array = pd.array([1, 2, None], dtype=pd.Int32Dtype())
int64_array = pd.array([1, 2, None], dtype=pd.Int64Dtype())
float_array = pd.array([1.1, 2.2, None], dtype=pd.Float32Dtype())
double_array = pd.array([1.1, 2.2, None], dtype=pd.Float64Dtype())
string_array = pd.array(["s11", "s22", None], dtype=pd.StringDtype())
object_array = pd.array([pd.NA, "s22", None], dtype=object)
df = pd.DataFrame({
"NullableBoolean": boolean_array,
"NullableInt8": int8_array,
"NullableInt16": int16_array,
"NullableInt32": int32_array,
"NullableInt64": int64_array,
"NullableFloat": float_array,
"NullableDouble": double_array,
"NullableString": string_array,
"NullableObject": object_array,
})
table = to_table(df)
self.assertIs(table.columns[0].data_type, dtypes.bool_)
self.assertIs(table.columns[1].data_type, dtypes.int8)
self.assertIs(table.columns[2].data_type, dtypes.int16)
self.assertIs(table.columns[3].data_type, dtypes.int32)
self.assertIs(table.columns[4].data_type, dtypes.int64)
self.assertIs(table.columns[5].data_type, dtypes.float32)
self.assertIs(table.columns[6].data_type, dtypes.double)
self.assertIs(table.columns[7].data_type, dtypes.string)
self.assertIs(table.columns[8].data_type, dtypes.PyObject)
self.assertEqual(table.size, 3)
table_string = table.to_string()
self.assertEqual(9, table_string.count("null"))
def j_type_to_py_type(t):
typeclass = t.getTypeClass()
typeclass_name = typeclass.getName()
if typeclass_name in [
'java.lang.Double', 'java.lang.Float', 'double', 'float'
]:
return np.float64
elif typeclass_name in [
'java.lang.Long', 'java.lang.Integer', 'int', 'long'
]:
return pd.Int64Dtype()
elif typeclass_name == 'java.lang.String':
return pd.StringDtype()
elif typeclass_name == 'java.sql.Timestamp':
return np.datetime64
elif typeclass_name == "com.alibaba.alink.common.linalg.Vector" or typeclass_name == "com.alibaba.alink.common.linalg.DenseVector" or typeclass_name == "com.alibaba.alink.common.linalg.SparseVector":
return pd.StringDtype()
elif typeclass_name in ["java.lang.Boolean", 'boolean']:
return pd.BooleanDtype()
else:
print(
"Java type is not supported in Python for automatic conversion of values: %s"
% typeclass_name)
return t
import cudf
from cudf.testing._utils import assert_eq
from cudf.utils.dtypes import (
pandas_dtypes_to_cudf_dtypes,
pyarrow_dtypes_to_pandas_dtypes,
)
ALL_POSSIBLE_VALUES = "ALL_POSSIBLE_VALUES"
_PANDAS_TO_AVRO_SCHEMA_MAP = {
cudf.dtype("int8"): "int",
pd.Int8Dtype(): ["int", "null"],
pd.Int16Dtype(): ["int", "null"],
pd.Int32Dtype(): ["int", "null"],
pd.Int64Dtype(): ["long", "null"],
pd.BooleanDtype(): ["boolean", "null"],
pd.StringDtype(): ["string", "null"],
cudf.dtype("bool_"): "boolean",
cudf.dtype("int16"): "int",
cudf.dtype("int32"): "int",
cudf.dtype("int64"): "long",
cudf.dtype("O"): "string",
cudf.dtype("str"): "string",
cudf.dtype("float32"): "float",
cudf.dtype("float64"): "double",
cudf.dtype("<M8[ns]"): {"type": "long", "logicalType": "timestamp-millis"},
cudf.dtype("<M8[ms]"): {"type": "long", "logicalType": "timestamp-millis"},
cudf.dtype("<M8[us]"): {"type": "long", "logicalType": "timestamp-micros"},
}
PANDAS_TO_ORC_TYPES = {