8th day of python challenges 111-117
This commit is contained in:
abd.shallal
@@ -0,0 +1,3 @@
|
||||
from .array import JSONArray, JSONDtype, make_data
|
||||
|
||||
__all__ = ["JSONArray", "JSONDtype", "make_data"]
|
||||
@@ -0,0 +1,198 @@
|
||||
"""Test extension array for storing nested data in a pandas container.
|
||||
|
||||
The JSONArray stores lists of dictionaries. The storage mechanism is a list,
|
||||
not an ndarray.
|
||||
|
||||
Note:
|
||||
|
||||
We currently store lists of UserDicts. Pandas has a few places
|
||||
internally that specifically check for dicts, and does non-scalar things
|
||||
in that case. We *want* the dictionaries to be treated as scalars, so we
|
||||
hack around pandas by using UserDicts.
|
||||
"""
|
||||
from collections import UserDict, abc
|
||||
import itertools
|
||||
import numbers
|
||||
import random
|
||||
import string
|
||||
import sys
|
||||
|
||||
import numpy as np
|
||||
|
||||
from pandas.core.dtypes.base import ExtensionDtype
|
||||
|
||||
from pandas.core.arrays import ExtensionArray
|
||||
|
||||
|
||||
class JSONDtype(ExtensionDtype):
|
||||
type = abc.Mapping
|
||||
name = "json"
|
||||
na_value = UserDict()
|
||||
|
||||
@classmethod
|
||||
def construct_array_type(cls):
|
||||
"""Return the array type associated with this dtype
|
||||
|
||||
Returns
|
||||
-------
|
||||
type
|
||||
"""
|
||||
return JSONArray
|
||||
|
||||
@classmethod
|
||||
def construct_from_string(cls, string):
|
||||
if string == cls.name:
|
||||
return cls()
|
||||
else:
|
||||
raise TypeError("Cannot construct a '{}' from '{}'".format(cls, string))
|
||||
|
||||
|
||||
class JSONArray(ExtensionArray):
|
||||
dtype = JSONDtype()
|
||||
__array_priority__ = 1000
|
||||
|
||||
def __init__(self, values, dtype=None, copy=False):
|
||||
for val in values:
|
||||
if not isinstance(val, self.dtype.type):
|
||||
raise TypeError("All values must be of type " + str(self.dtype.type))
|
||||
self.data = values
|
||||
|
||||
# Some aliases for common attribute names to ensure pandas supports
|
||||
# these
|
||||
self._items = self._data = self.data
|
||||
# those aliases are currently not working due to assumptions
|
||||
# in internal code (GH-20735)
|
||||
# self._values = self.values = self.data
|
||||
|
||||
@classmethod
|
||||
def _from_sequence(cls, scalars, dtype=None, copy=False):
|
||||
return cls(scalars)
|
||||
|
||||
@classmethod
|
||||
def _from_factorized(cls, values, original):
|
||||
return cls([UserDict(x) for x in values if x != ()])
|
||||
|
||||
def __getitem__(self, item):
|
||||
if isinstance(item, numbers.Integral):
|
||||
return self.data[item]
|
||||
elif isinstance(item, np.ndarray) and item.dtype == "bool":
|
||||
return self._from_sequence([x for x, m in zip(self, item) if m])
|
||||
elif isinstance(item, abc.Iterable):
|
||||
# fancy indexing
|
||||
return type(self)([self.data[i] for i in item])
|
||||
else:
|
||||
# slice
|
||||
return type(self)(self.data[item])
|
||||
|
||||
def __setitem__(self, key, value):
|
||||
if isinstance(key, numbers.Integral):
|
||||
self.data[key] = value
|
||||
else:
|
||||
if not isinstance(value, (type(self), abc.Sequence)):
|
||||
# broadcast value
|
||||
value = itertools.cycle([value])
|
||||
|
||||
if isinstance(key, np.ndarray) and key.dtype == "bool":
|
||||
# masking
|
||||
for i, (k, v) in enumerate(zip(key, value)):
|
||||
if k:
|
||||
assert isinstance(v, self.dtype.type)
|
||||
self.data[i] = v
|
||||
else:
|
||||
for k, v in zip(key, value):
|
||||
assert isinstance(v, self.dtype.type)
|
||||
self.data[k] = v
|
||||
|
||||
def __len__(self):
|
||||
return len(self.data)
|
||||
|
||||
@property
|
||||
def nbytes(self):
|
||||
return sys.getsizeof(self.data)
|
||||
|
||||
def isna(self):
|
||||
return np.array([x == self.dtype.na_value for x in self.data], dtype=bool)
|
||||
|
||||
def take(self, indexer, allow_fill=False, fill_value=None):
|
||||
# re-implement here, since NumPy has trouble setting
|
||||
# sized objects like UserDicts into scalar slots of
|
||||
# an ndarary.
|
||||
indexer = np.asarray(indexer)
|
||||
msg = (
|
||||
"Index is out of bounds or cannot do a "
|
||||
"non-empty take from an empty array."
|
||||
)
|
||||
|
||||
if allow_fill:
|
||||
if fill_value is None:
|
||||
fill_value = self.dtype.na_value
|
||||
# bounds check
|
||||
if (indexer < -1).any():
|
||||
raise ValueError
|
||||
try:
|
||||
output = [
|
||||
self.data[loc] if loc != -1 else fill_value for loc in indexer
|
||||
]
|
||||
except IndexError:
|
||||
raise IndexError(msg)
|
||||
else:
|
||||
try:
|
||||
output = [self.data[loc] for loc in indexer]
|
||||
except IndexError:
|
||||
raise IndexError(msg)
|
||||
|
||||
return self._from_sequence(output)
|
||||
|
||||
def copy(self):
|
||||
return type(self)(self.data[:])
|
||||
|
||||
def astype(self, dtype, copy=True):
|
||||
# NumPy has issues when all the dicts are the same length.
|
||||
# np.array([UserDict(...), UserDict(...)]) fails,
|
||||
# but np.array([{...}, {...}]) works, so cast.
|
||||
|
||||
# needed to add this check for the Series constructor
|
||||
if isinstance(dtype, type(self.dtype)) and dtype == self.dtype:
|
||||
if copy:
|
||||
return self.copy()
|
||||
return self
|
||||
return np.array([dict(x) for x in self], dtype=dtype, copy=copy)
|
||||
|
||||
def unique(self):
|
||||
# Parent method doesn't work since np.array will try to infer
|
||||
# a 2-dim object.
|
||||
return type(self)(
|
||||
[dict(x) for x in list({tuple(d.items()) for d in self.data})]
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def _concat_same_type(cls, to_concat):
|
||||
data = list(itertools.chain.from_iterable([x.data for x in to_concat]))
|
||||
return cls(data)
|
||||
|
||||
def _values_for_factorize(self):
|
||||
frozen = self._values_for_argsort()
|
||||
if len(frozen) == 0:
|
||||
# _factorize_array expects 1-d array, this is a len-0 2-d array.
|
||||
frozen = frozen.ravel()
|
||||
return frozen, ()
|
||||
|
||||
def _values_for_argsort(self):
|
||||
# Disable NumPy's shape inference by including an empty tuple...
|
||||
# If all the elemnts of self are the same size P, NumPy will
|
||||
# cast them to an (N, P) array, instead of an (N,) array of tuples.
|
||||
frozen = [()] + [tuple(x.items()) for x in self]
|
||||
return np.array(frozen, dtype=object)[1:]
|
||||
|
||||
|
||||
def make_data():
|
||||
# TODO: Use a regular dict. See _NDFrameIndexer._setitem_with_indexer
|
||||
return [
|
||||
UserDict(
|
||||
[
|
||||
(random.choice(string.ascii_letters), random.randint(0, 100))
|
||||
for _ in range(random.randint(0, 10))
|
||||
]
|
||||
)
|
||||
for _ in range(100)
|
||||
]
|
||||
@@ -0,0 +1,312 @@
|
||||
import collections
|
||||
import operator
|
||||
|
||||
import pytest
|
||||
|
||||
from pandas.compat import PY36
|
||||
|
||||
import pandas as pd
|
||||
from pandas.tests.extension import base
|
||||
import pandas.util.testing as tm
|
||||
|
||||
from .array import JSONArray, JSONDtype, make_data
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def dtype():
|
||||
return JSONDtype()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def data():
|
||||
"""Length-100 PeriodArray for semantics test."""
|
||||
data = make_data()
|
||||
|
||||
# Why the while loop? NumPy is unable to construct an ndarray from
|
||||
# equal-length ndarrays. Many of our operations involve coercing the
|
||||
# EA to an ndarray of objects. To avoid random test failures, we ensure
|
||||
# that our data is coercible to an ndarray. Several tests deal with only
|
||||
# the first two elements, so that's what we'll check.
|
||||
|
||||
while len(data[0]) == len(data[1]):
|
||||
data = make_data()
|
||||
|
||||
return JSONArray(data)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def data_missing():
|
||||
"""Length 2 array with [NA, Valid]"""
|
||||
return JSONArray([{}, {"a": 10}])
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def data_for_sorting():
|
||||
return JSONArray([{"b": 1}, {"c": 4}, {"a": 2, "c": 3}])
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def data_missing_for_sorting():
|
||||
return JSONArray([{"b": 1}, {}, {"a": 4}])
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def na_value(dtype):
|
||||
return dtype.na_value
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def na_cmp():
|
||||
return operator.eq
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def data_for_grouping():
|
||||
return JSONArray(
|
||||
[
|
||||
{"b": 1},
|
||||
{"b": 1},
|
||||
{},
|
||||
{},
|
||||
{"a": 0, "c": 2},
|
||||
{"a": 0, "c": 2},
|
||||
{"b": 1},
|
||||
{"c": 2},
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
class BaseJSON:
|
||||
# NumPy doesn't handle an array of equal-length UserDicts.
|
||||
# The default assert_series_equal eventually does a
|
||||
# Series.values, which raises. We work around it by
|
||||
# converting the UserDicts to dicts.
|
||||
def assert_series_equal(self, left, right, **kwargs):
|
||||
if left.dtype.name == "json":
|
||||
assert left.dtype == right.dtype
|
||||
left = pd.Series(
|
||||
JSONArray(left.values.astype(object)), index=left.index, name=left.name
|
||||
)
|
||||
right = pd.Series(
|
||||
JSONArray(right.values.astype(object)),
|
||||
index=right.index,
|
||||
name=right.name,
|
||||
)
|
||||
tm.assert_series_equal(left, right, **kwargs)
|
||||
|
||||
def assert_frame_equal(self, left, right, *args, **kwargs):
|
||||
tm.assert_index_equal(
|
||||
left.columns,
|
||||
right.columns,
|
||||
exact=kwargs.get("check_column_type", "equiv"),
|
||||
check_names=kwargs.get("check_names", True),
|
||||
check_exact=kwargs.get("check_exact", False),
|
||||
check_categorical=kwargs.get("check_categorical", True),
|
||||
obj="{obj}.columns".format(obj=kwargs.get("obj", "DataFrame")),
|
||||
)
|
||||
|
||||
jsons = (left.dtypes == "json").index
|
||||
|
||||
for col in jsons:
|
||||
self.assert_series_equal(left[col], right[col], *args, **kwargs)
|
||||
|
||||
left = left.drop(columns=jsons)
|
||||
right = right.drop(columns=jsons)
|
||||
tm.assert_frame_equal(left, right, *args, **kwargs)
|
||||
|
||||
|
||||
class TestDtype(BaseJSON, base.BaseDtypeTests):
|
||||
pass
|
||||
|
||||
|
||||
class TestInterface(BaseJSON, base.BaseInterfaceTests):
|
||||
def test_custom_asserts(self):
|
||||
# This would always trigger the KeyError from trying to put
|
||||
# an array of equal-length UserDicts inside an ndarray.
|
||||
data = JSONArray(
|
||||
[
|
||||
collections.UserDict({"a": 1}),
|
||||
collections.UserDict({"b": 2}),
|
||||
collections.UserDict({"c": 3}),
|
||||
]
|
||||
)
|
||||
a = pd.Series(data)
|
||||
self.assert_series_equal(a, a)
|
||||
self.assert_frame_equal(a.to_frame(), a.to_frame())
|
||||
|
||||
b = pd.Series(data.take([0, 0, 1]))
|
||||
with pytest.raises(AssertionError):
|
||||
self.assert_series_equal(a, b)
|
||||
|
||||
with pytest.raises(AssertionError):
|
||||
self.assert_frame_equal(a.to_frame(), b.to_frame())
|
||||
|
||||
|
||||
class TestConstructors(BaseJSON, base.BaseConstructorsTests):
|
||||
@pytest.mark.skip(reason="not implemented constructor from dtype")
|
||||
def test_from_dtype(self, data):
|
||||
# construct from our dtype & string dtype
|
||||
pass
|
||||
|
||||
|
||||
class TestReshaping(BaseJSON, base.BaseReshapingTests):
|
||||
@pytest.mark.skip(reason="Different definitions of NA")
|
||||
def test_stack(self):
|
||||
"""
|
||||
The test does .astype(object).stack(). If we happen to have
|
||||
any missing values in `data`, then we'll end up with different
|
||||
rows since we consider `{}` NA, but `.astype(object)` doesn't.
|
||||
"""
|
||||
|
||||
@pytest.mark.xfail(reason="dict for NA")
|
||||
def test_unstack(self, data, index):
|
||||
# The base test has NaN for the expected NA value.
|
||||
# this matches otherwise
|
||||
return super().test_unstack(data, index)
|
||||
|
||||
|
||||
class TestGetitem(BaseJSON, base.BaseGetitemTests):
|
||||
pass
|
||||
|
||||
|
||||
class TestMissing(BaseJSON, base.BaseMissingTests):
|
||||
@pytest.mark.skip(reason="Setting a dict as a scalar")
|
||||
def test_fillna_series(self):
|
||||
"""We treat dictionaries as a mapping in fillna, not a scalar."""
|
||||
|
||||
@pytest.mark.skip(reason="Setting a dict as a scalar")
|
||||
def test_fillna_frame(self):
|
||||
"""We treat dictionaries as a mapping in fillna, not a scalar."""
|
||||
|
||||
|
||||
unhashable = pytest.mark.skip(reason="Unhashable")
|
||||
unstable = pytest.mark.skipif(
|
||||
not PY36, reason="Dictionary order unstable" # 3.6 or higher
|
||||
)
|
||||
|
||||
|
||||
class TestReduce(base.BaseNoReduceTests):
|
||||
pass
|
||||
|
||||
|
||||
class TestMethods(BaseJSON, base.BaseMethodsTests):
|
||||
@unhashable
|
||||
def test_value_counts(self, all_data, dropna):
|
||||
pass
|
||||
|
||||
@unhashable
|
||||
def test_sort_values_frame(self):
|
||||
# TODO (EA.factorize): see if _values_for_factorize allows this.
|
||||
pass
|
||||
|
||||
@unstable
|
||||
def test_argsort(self, data_for_sorting):
|
||||
super().test_argsort(data_for_sorting)
|
||||
|
||||
@unstable
|
||||
def test_argsort_missing(self, data_missing_for_sorting):
|
||||
super().test_argsort_missing(data_missing_for_sorting)
|
||||
|
||||
@unstable
|
||||
@pytest.mark.parametrize("ascending", [True, False])
|
||||
def test_sort_values(self, data_for_sorting, ascending):
|
||||
super().test_sort_values(data_for_sorting, ascending)
|
||||
|
||||
@unstable
|
||||
@pytest.mark.parametrize("ascending", [True, False])
|
||||
def test_sort_values_missing(self, data_missing_for_sorting, ascending):
|
||||
super().test_sort_values_missing(data_missing_for_sorting, ascending)
|
||||
|
||||
@pytest.mark.skip(reason="combine for JSONArray not supported")
|
||||
def test_combine_le(self, data_repeated):
|
||||
pass
|
||||
|
||||
@pytest.mark.skip(reason="combine for JSONArray not supported")
|
||||
def test_combine_add(self, data_repeated):
|
||||
pass
|
||||
|
||||
@pytest.mark.skip(reason="combine for JSONArray not supported")
|
||||
def test_combine_first(self, data):
|
||||
pass
|
||||
|
||||
@unhashable
|
||||
def test_hash_pandas_object_works(self, data, kind):
|
||||
super().test_hash_pandas_object_works(data, kind)
|
||||
|
||||
@pytest.mark.skip(reason="broadcasting error")
|
||||
def test_where_series(self, data, na_value):
|
||||
# Fails with
|
||||
# *** ValueError: operands could not be broadcast together
|
||||
# with shapes (4,) (4,) (0,)
|
||||
super().test_where_series(data, na_value)
|
||||
|
||||
@pytest.mark.skip(reason="Can't compare dicts.")
|
||||
def test_searchsorted(self, data_for_sorting):
|
||||
super().test_searchsorted(data_for_sorting)
|
||||
|
||||
|
||||
class TestCasting(BaseJSON, base.BaseCastingTests):
|
||||
@pytest.mark.skip(reason="failing on np.array(self, dtype=str)")
|
||||
def test_astype_str(self):
|
||||
"""This currently fails in NumPy on np.array(self, dtype=str) with
|
||||
|
||||
*** ValueError: setting an array element with a sequence
|
||||
"""
|
||||
|
||||
|
||||
# We intentionally don't run base.BaseSetitemTests because pandas'
|
||||
# internals has trouble setting sequences of values into scalar positions.
|
||||
|
||||
|
||||
class TestGroupby(BaseJSON, base.BaseGroupbyTests):
|
||||
@unhashable
|
||||
def test_groupby_extension_transform(self):
|
||||
"""
|
||||
This currently fails in Series.name.setter, since the
|
||||
name must be hashable, but the value is a dictionary.
|
||||
I think this is what we want, i.e. `.name` should be the original
|
||||
values, and not the values for factorization.
|
||||
"""
|
||||
|
||||
@unhashable
|
||||
def test_groupby_extension_apply(self):
|
||||
"""
|
||||
This fails in Index._do_unique_check with
|
||||
|
||||
> hash(val)
|
||||
E TypeError: unhashable type: 'UserDict' with
|
||||
|
||||
I suspect that once we support Index[ExtensionArray],
|
||||
we'll be able to dispatch unique.
|
||||
"""
|
||||
|
||||
@unstable
|
||||
@pytest.mark.parametrize("as_index", [True, False])
|
||||
def test_groupby_extension_agg(self, as_index, data_for_grouping):
|
||||
super().test_groupby_extension_agg(as_index, data_for_grouping)
|
||||
|
||||
|
||||
class TestArithmeticOps(BaseJSON, base.BaseArithmeticOpsTests):
|
||||
def test_error(self, data, all_arithmetic_operators):
|
||||
pass
|
||||
|
||||
def test_add_series_with_extension_array(self, data):
|
||||
ser = pd.Series(data)
|
||||
with pytest.raises(TypeError, match="unsupported"):
|
||||
ser + data
|
||||
|
||||
def test_divmod_series_array(self):
|
||||
# GH 23287
|
||||
# skipping because it is not implemented
|
||||
pass
|
||||
|
||||
def _check_divmod_op(self, s, op, other, exc=NotImplementedError):
|
||||
return super()._check_divmod_op(s, op, other, exc=TypeError)
|
||||
|
||||
|
||||
class TestComparisonOps(BaseJSON, base.BaseComparisonOpsTests):
|
||||
pass
|
||||
|
||||
|
||||
class TestPrinting(BaseJSON, base.BasePrintingTests):
|
||||
pass
|
||||
Reference in New Issue
Block a user