Skip to content

ARROW-1039: Python: Remove duplicate column #773

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
xhochy wants to merge 1 commit into from
Closed

ARROW-1039: Python: Remove duplicate column #773

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
29 changes: 29 additions & 0 deletions python/pyarrow/array.pxi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,6 +432,7 @@ cdef set PRIMITIVE_TYPES = set([
_Type_UINT32, _Type_INT32,
_Type_UINT64, _Type_INT64,
_Type_TIMESTAMP, _Type_DATE32,
_Type_TIME32, _Type_TIME64,
_Type_DATE64,
_Type_HALF_FLOAT,
_Type_FLOAT,
Expand Down Expand Up @@ -816,6 +817,32 @@ cdef class Date64Value(ArrayValue):
ap.Value(self.index) / 1000).date()


cdef class Time32Value(ArrayValue):

def as_py(self):
cdef:
CTime32Array* ap = <CTime32Array*> self.sp_array.get()
CTime32Type* dtype = <CTime32Type*> ap.type().get()

if dtype.unit() == TimeUnit_SECOND:
return (datetime.datetime(1970, 1, 1) + datetime.timedelta(seconds=ap.Value(self.index))).time()
else:
return (datetime.datetime(1970, 1, 1) + datetime.timedelta(milliseconds=ap.Value(self.index))).time()


cdef class Time64Value(ArrayValue):

def as_py(self):
cdef:
CTime64Array* ap = <CTime64Array*> self.sp_array.get()
CTime64Type* dtype = <CTime64Type*> ap.type().get()

if dtype.unit() == TimeUnit_MICRO:
return (datetime.datetime(1970, 1, 1) + datetime.timedelta(microseconds=ap.Value(self.index))).time()
else:
return (datetime.datetime(1970, 1, 1) + datetime.timedelta(microseconds=ap.Value(self.index) / 1000)).time()


cdef dict DATETIME_CONVERSION_FUNCTIONS

try:
Expand Down Expand Up @@ -975,6 +1002,8 @@ cdef dict _scalar_classes = {
_Type_INT64: Int64Value,
_Type_DATE32: Date32Value,
_Type_DATE64: Date64Value,
_Type_TIME32: Time32Value,
_Type_TIME64: Time64Value,
_Type_TIMESTAMP: TimestampValue,
_Type_FLOAT: FloatValue,
_Type_DOUBLE: DoubleValue,
Expand Down
6 changes: 6 additions & 0 deletions python/pyarrow/includes/libarrow.pxd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -249,6 +249,12 @@ cdef extern from "arrow/api.h" namespace "arrow" nogil:
cdef cppclass CDate64Array" arrow::Date64Array"(CArray):
int64_t Value(int i)

cdef cppclass CTime32Array" arrow::Time32Array"(CArray):
int32_t Value(int i)

cdef cppclass CTime64Array" arrow::Time64Array"(CArray):
int64_t Value(int i)

cdef cppclass CTimestampArray" arrow::TimestampArray"(CArray):
int64_t Value(int i)

Expand Down
4 changes: 2 additions & 2 deletions python/pyarrow/tests/test_parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -449,13 +449,13 @@ def test_date_time_types():

table = pa.Table.from_arrays([a1, a2, a3, a4, a5, a6],
['date32', 'date64', 'timestamp[us]',
'time32[s]', 'time64[us]', 'time32[s]'])
'time32[s]', 'time64[us]', 'time32_from64[s]'])

# date64 as date32
# time32[s] to time32[ms]
expected = pa.Table.from_arrays([a1, a1, a3, a4, a5, ex_a6],
['date32', 'date64', 'timestamp[us]',
'time32[s]', 'time64[us]', 'time32[s]'])
'time32[s]', 'time64[us]', 'time32_from64[s]'])

_check_roundtrip(table, expected=expected, version='2.0')

Expand Down