def test_integer_with_nulls(self):
# pandas requires upcast to float dtype
int_dtypes = ['i1', 'i2', 'i4', 'i8', 'u1', 'u2', 'u4', 'u8']
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
expected_cols = []
arrays = []
for name in int_dtypes:
values = np.random.randint(0, 100, size=num_values)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
expected = values.astype('f8')
expected[null_mask] = np.nan
expected_cols.append(expected)
ex_frame = pd.DataFrame(dict(zip(int_dtypes, expected_cols)),
columns=int_dtypes)
table = A.Table.from_arrays(int_dtypes, arrays)
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_integer_with_nulls(self):
# pandas requires upcast to float dtype
int_dtypes = ['i1', 'i2', 'i4', 'i8', 'u1', 'u2', 'u4', 'u8']
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
expected_cols = []
arrays = []
for name in int_dtypes:
values = np.random.randint(0, 100, size=num_values)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
expected = values.astype('f8')
expected[null_mask] = np.nan
expected_cols.append(expected)
ex_frame = pd.DataFrame(dict(zip(int_dtypes, expected_cols)),
columns=int_dtypes)
table = A.Table.from_arrays(arrays, int_dtypes)
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_float_nulls(self):
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
dtypes = [('f4', A.float_()), ('f8', A.double())]
names = ['f4', 'f8']
expected_cols = []
arrays = []
fields = []
for name, arrow_dtype in dtypes:
values = np.random.randn(num_values).astype(name)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
fields.append(A.Field.from_py(name, arrow_dtype))
values[null_mask] = np.nan
expected_cols.append(values)
ex_frame = pd.DataFrame(dict(zip(names, expected_cols)),
columns=names)
table = A.Table.from_arrays(arrays, names)
assert table.schema.equals(A.Schema.from_fields(fields))
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_float_nulls(self):
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
dtypes = [('f4', A.float_()), ('f8', A.double())]
names = ['f4', 'f8']
expected_cols = []
arrays = []
fields = []
for name, arrow_dtype in dtypes:
values = np.random.randn(num_values).astype(name)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
fields.append(A.Field.from_py(name, arrow_dtype))
values[null_mask] = np.nan
expected_cols.append(values)
ex_frame = pd.DataFrame(dict(zip(names, expected_cols)),
columns=names)
table = A.Table.from_arrays(names, arrays)
assert table.schema.equals(A.Schema.from_fields(fields))
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_boolean_nulls(self):
# pandas requires upcast to object dtype
num_values = 100
np.random.seed(0)
mask = np.random.randint(0, 10, size=num_values) < 3
values = np.random.randint(0, 10, size=num_values) < 5
arr = A.from_pandas_series(values, mask)
expected = values.astype(object)
expected[mask] = None
ex_frame = pd.DataFrame({'bools': expected})
table = A.Table.from_arrays(['bools'], [arr])
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_boolean_nulls(self):
# pandas requires upcast to object dtype
num_values = 100
np.random.seed(0)
mask = np.random.randint(0, 10, size=num_values) < 3
values = np.random.randint(0, 10, size=num_values) < 5
arr = A.from_pandas_series(values, mask)
expected = values.astype(object)
expected[mask] = None
ex_frame = pd.DataFrame({'bools': expected})
table = A.Table.from_arrays(['bools'], [arr])
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_boolean_nulls(self):
# pandas requires upcast to object dtype
num_values = 100
np.random.seed(0)
mask = np.random.randint(0, 10, size=num_values) < 3
values = np.random.randint(0, 10, size=num_values) < 5
arr = A.from_pandas_series(values, mask)
expected = values.astype(object)
expected[mask] = None
field = A.Field.from_py('bools', A.bool_())
schema = A.Schema.from_fields([field])
ex_frame = pd.DataFrame({'bools': expected})
table = A.Table.from_arrays([arr], ['bools'])
assert table.schema.equals(schema)
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_boolean_nulls(self):
# pandas requires upcast to object dtype
num_values = 100
np.random.seed(0)
mask = np.random.randint(0, 10, size=num_values) < 3
values = np.random.randint(0, 10, size=num_values) < 5
arr = A.from_pandas_series(values, mask)
expected = values.astype(object)
expected[mask] = None
field = A.Field.from_py('bools', A.bool_())
schema = A.Schema.from_fields([field])
ex_frame = pd.DataFrame({'bools': expected})
table = A.Table.from_arrays([arr], ['bools'])
assert table.schema.equals(schema)
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_float_nulls(self):
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
dtypes = ['f4', 'f8']
expected_cols = []
arrays = []
for name in dtypes:
values = np.random.randn(num_values).astype(name)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
values[null_mask] = np.nan
expected_cols.append(values)
ex_frame = pd.DataFrame(dict(zip(dtypes, expected_cols)),
columns=dtypes)
table = A.Table.from_arrays(dtypes, arrays)
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_float_nulls(self):
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
dtypes = ['f4', 'f8']
expected_cols = []
arrays = []
for name in dtypes:
values = np.random.randn(num_values).astype(name)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
values[null_mask] = np.nan
expected_cols.append(values)
ex_frame = pd.DataFrame(dict(zip(dtypes, expected_cols)),
columns=dtypes)
table = A.Table.from_arrays(dtypes, arrays)
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
