ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
jorisvandenbossche wants to merge 5 commits into from
Closed

ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion #5866

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3535a56
ARROW-7168: [Python] Respect the specified dictionary type when conve…
jorisvandenbossche Nov 19, 2019
bfb8237
additional tests
jorisvandenbossche Nov 20, 2019
003e653
for now use deprecation warnings instead of error
jorisvandenbossche Nov 20, 2019
e4dbb2c
try fix python 2
jorisvandenbossche Nov 20, 2019
39ff8e8
more python 2
jorisvandenbossche Nov 20, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 61 additions & 9 deletions python/pyarrow/array.pxi
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
MemoryPool memory_pool):
"""
Convert the codes of a pandas Categorical to indices for a pyarrow
DictionaryArray, taking into account missing values + mask
"""
if mask is None:
mask = codes == -1
else:
mask = mask | (codes == -1)
return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
if mask is not None or size is not None:
raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
if hasattr(values, '__arrow_array__'):
return _handle_arrow_array_protocol(values, type, mask, size)
elif pandas_api.is_categorical(values):
if type is not None:
if type.id != Type_DICTIONARY:
return _ndarray_to_array(
np.asarray(values), mask, type, c_from_pandas, safe,
pool)
index_type = type.index_type
value_type = type.value_type
if values.ordered != type.ordered:
warnings.warn(
"The 'ordered' flag of the passed categorical values "
"does not match the 'ordered' of the specified type. "
"Using the flag of the values, but in the future this "
"mismatch will raise a ValueError.",
FutureWarning, stacklevel=2)
else:
index_type = None
value_type = None

indices = _codes_to_indices(
values.codes, mask, index_type, memory_pool)
try:
dictionary = array(
values.categories.values, type=value_type,
memory_pool=memory_pool)
except TypeError:
# TODO when removing the deprecation warning, this whole
# try/except can be removed (to bubble the TypeError of
# the first array(..) call)
if value_type is not None:
warnings.warn(
"The dtype of the 'categories' of the passed "
"categorical values ({0}) does not match the "
"specified type ({1}). For now ignoring the specified "
"type, but in the future this mismatch will raise a "
"TypeError".format(
values.categories.dtype, value_type),
FutureWarning, stacklevel=2)
dictionary = array(
values.categories.values, memory_pool=memory_pool)
else:
raise

return DictionaryArray.from_arrays(
values.codes, values.categories.values,
mask=mask, ordered=values.ordered,
from_pandas=True, safe=safe,
memory_pool=memory_pool)
indices, dictionary, ordered=values.ordered, safe=safe)
else:
if pandas_api.have_pandas:
values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
_indices = indices
else:
if from_pandas:
if mask is None:
mask = indices == -1
else:
mask = mask | (indices == -1)
_indices = array(indices, mask=mask, memory_pool=memory_pool)
_indices = _codes_to_indices(indices, mask, None, memory_pool)
else:
_indices = array(indices, mask=mask, memory_pool=memory_pool)

if isinstance(dictionary, Array):
_dictionary = dictionary
Expand Down
74 changes: 74 additions & 0 deletions python/pyarrow/tests/test_pandas.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
cat = pd.Categorical([u'a', u'b', u'a'])
expected_type = pa.dictionary(pa.int8(), pa.string())

result = pa.array(cat)
assert result.to_pylist() == ['a', 'b', 'a']
assert result.type.equals(expected_type)

# with missing values in categorical
cat = pd.Categorical([u'a', u'b', None, u'a'])

result = pa.array(cat)
assert result.to_pylist() == ['a', 'b', None, 'a']
assert result.type.equals(expected_type)

# with additional mask
result = pa.array(cat, mask=np.array([False, False, False, True]))
assert result.to_pylist() == ['a', 'b', None, None]
assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
# ARROW-7168 - ensure specified type is always respected

# the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
cat = pd.Categorical.from_codes(
np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

# different index type -> allow this
# (the type of the 'codes' in pandas is not part of the data type)
typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
result = pa.array(cat, type=typ)
assert result.type.equals(typ)

@pitroupitrouNov 19, 2019

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())

assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?

# mismatching values type -> raise error (for now a deprecation warning)
typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
with pytest.warns(FutureWarning):
result = pa.array(cat, type=typ)
assert result.to_pylist() == ['a', 'b']

# mismatching order -> raise error (for now a deprecation warning)
typ = pa.dictionary(
index_type=pa.int8(), value_type=pa.string(), ordered=True)
with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
result = pa.array(cat, type=typ)
assert result.to_pylist() == ['a', 'b']

# with mask
typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
result = pa.array(cat, type=typ, mask=np.array([False, True]))
assert result.type.equals(typ)
assert result.to_pylist() == ['a', None]

# empty categorical -> be flexible in values type to allow
cat = pd.Categorical([])

typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
result = pa.array(cat, type=typ)
assert result.type.equals(typ)
assert result.to_pylist() == []
typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
result = pa.array(cat, type=typ)
assert result.type.equals(typ)
assert result.to_pylist() == []

# passing non-dictionary type
cat = pd.Categorical(['a', 'b'])
result = pa.array(cat, type=pa.string())
expected = pa.array(['a', 'b'], type=pa.string())
assert result.equals(expected)
assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion#5866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

jorisvandenbossche
wants to merge
5
commits into

from

 Closed


ARROW-7168: [Python] Respect the specified dictionary type for pd.Categorical conversion
#5866
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


5 commits


Select commit
Hold shift + click to select a range
3535a56

ARROW-7168: [Python] Respect the specified dictionary type when conve…


jorisvandenbossche Nov 19, 2019
bfb8237

additional tests


jorisvandenbossche Nov 20, 2019
003e653

for now use deprecation warnings instead of error


jorisvandenbossche Nov 20, 2019
e4dbb2c

try fix python 2


jorisvandenbossche Nov 20, 2019
39ff8e8

more python 2


jorisvandenbossche Nov 20, 2019

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


70 changes: 61 additions & 9 deletions
python/pyarrow/array.pxi

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -15,6 +15,8 @@
# specific language governing permissions and limitations
# under the License.

import warnings


cdef _sequence_to_array(object sequence, object mask, object size,
 DataType type, CMemoryPool* pool, c_bool from_pandas):
Expand DownExpand Up@@ -84,6 +86,19 @@ cdef _ndarray_to_array(object values, object mask, DataType type,
 return pyarrow_wrap_array(chunked_out.get().chunk(0))


cdef _codes_to_indices(object codes, object mask, DataType type,
 MemoryPool memory_pool):
 """
 Convert the codes of a pandas Categorical to indices for a pyarrow
 DictionaryArray, taking into account missing values + mask
 """
 if mask is None:
 mask = codes == -1
 else:
 mask = mask | (codes == -1)
 return array(codes, mask=mask, type=type, memory_pool=memory_pool)


def _handle_arrow_array_protocol(obj, type, mask, size):
 if mask is not None or size is not None:
 raise ValueError(
Expand DownExpand Up@@ -199,11 +214,50 @@ def array(object obj, type=None, mask=None, size=None, from_pandas=None,
 if hasattr(values, '__arrow_array__'):
 return _handle_arrow_array_protocol(values, type, mask, size)
 elif pandas_api.is_categorical(values):
 if type is not None:
 if type.id != Type_DICTIONARY:
 return _ndarray_to_array(
 np.asarray(values), mask, type, c_from_pandas, safe,
 pool)
 index_type = type.index_type
 value_type = type.value_type
 if values.ordered != type.ordered:
 warnings.warn(
 "The 'ordered' flag of the passed categorical values "
 "does not match the 'ordered' of the specified type. "
 "Using the flag of the values, but in the future this "
 "mismatch will raise a ValueError.",
 FutureWarning, stacklevel=2)
 else:
 index_type = None
 value_type = None

 indices = _codes_to_indices(
 values.codes, mask, index_type, memory_pool)
 try:
 dictionary = array(
 values.categories.values, type=value_type,
 memory_pool=memory_pool)
 except TypeError:
 # TODO when removing the deprecation warning, this whole
 # try/except can be removed (to bubble the TypeError of
 # the first array(..) call)
 if value_type is not None:
 warnings.warn(
 "The dtype of the 'categories' of the passed "
 "categorical values ({0}) does not match the "
 "specified type ({1}). For now ignoring the specified "
 "type, but in the future this mismatch will raise a "
 "TypeError".format(
 values.categories.dtype, value_type),
 FutureWarning, stacklevel=2)
 dictionary = array(
 values.categories.values, memory_pool=memory_pool)
 else:
 raise

 return DictionaryArray.from_arrays(
 values.codes, values.categories.values,
 mask=mask, ordered=values.ordered,
 from_pandas=True, safe=safe,
 memory_pool=memory_pool)
 indices, dictionary, ordered=values.ordered, safe=safe)
 else:
 if pandas_api.have_pandas:
 values, type = pandas_api.compat.get_datetimetz_type(
Expand DownExpand Up@@ -1543,11 +1597,9 @@ cdef class DictionaryArray(Array):
 _indices = indices
 else:
 if from_pandas:
 if mask is None:
 mask = indices == -1
 else:
 mask = mask | (indices == -1)
 _indices = array(indices, mask=mask, memory_pool=memory_pool)
 _indices = _codes_to_indices(indices, mask, None, memory_pool)
 else:
 _indices = array(indices, mask=mask, memory_pool=memory_pool)

 if isinstance(dictionary, Array):
 _dictionary = dictionary
Expand Down

74 changes: 74 additions & 0 deletions
python/pyarrow/tests/test_pandas.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3212,6 +3212,80 @@ def test_variable_dictionary_to_pandas():
 tm.assert_series_equal(result_dense, expected_dense)


def test_dictionary_from_pandas():
 cat = pd.Categorical([u'a', u'b', u'a'])
 expected_type = pa.dictionary(pa.int8(), pa.string())

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', 'a']
 assert result.type.equals(expected_type)

 # with missing values in categorical
 cat = pd.Categorical([u'a', u'b', None, u'a'])

 result = pa.array(cat)
 assert result.to_pylist() == ['a', 'b', None, 'a']
 assert result.type.equals(expected_type)

 # with additional mask
 result = pa.array(cat, mask=np.array([False, False, False, True]))
 assert result.to_pylist() == ['a', 'b', None, None]
 assert result.type.equals(expected_type)


def test_dictionary_from_pandas_specified_type():
 # ARROW-7168 - ensure specified type is always respected

 # the same as cat = pd.Categorical(['a', 'b']) but explicit about dtypes
 cat = pd.Categorical.from_codes(
 np.array([0, 1], dtype='int8'), np.array(['a', 'b'], dtype=object))

 # different index type -> allow this
 # (the type of the 'codes' in pandas is not part of the data type)
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't you check also the array value? (for example using result.to_pylist())
 assert result.to_pylist() == ['a', 'b']

@pitroupitrouNov 19, 2019

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, should you perhaps check passing a mask argument to pa.array()?
 # mismatching values type -> raise error (for now a deprecation warning)
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 with pytest.warns(FutureWarning):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # mismatching order -> raise error (for now a deprecation warning)
 typ = pa.dictionary(
 index_type=pa.int8(), value_type=pa.string(), ordered=True)
 with pytest.warns(FutureWarning, match="The 'ordered' flag of the passed"):
 result = pa.array(cat, type=typ)
 assert result.to_pylist() == ['a', 'b']

 # with mask
 typ = pa.dictionary(index_type=pa.int16(), value_type=pa.string())
 result = pa.array(cat, type=typ, mask=np.array([False, True]))
 assert result.type.equals(typ)
 assert result.to_pylist() == ['a', None]

 # empty categorical -> be flexible in values type to allow
 cat = pd.Categorical([])

 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.string())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []
 typ = pa.dictionary(index_type=pa.int8(), value_type=pa.int64())
 result = pa.array(cat, type=typ)
 assert result.type.equals(typ)
 assert result.to_pylist() == []

 # passing non-dictionary type
 cat = pd.Categorical(['a', 'b'])
 result = pa.array(cat, type=pa.string())
 expected = pa.array(['a', 'b'], type=pa.string())
 assert result.equals(expected)
 assert result.to_pylist() == ['a', 'b']


# ----------------------------------------------------------------------
# Array protocol in pandas conversions tests

Expand Down