Skip to content

sas7bdat date/datetime formats #13089

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
wants to merge 2 commits into from
Closed

sas7bdat date/datetime formats #13089

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a8d9287
handle date/datetime formats
Winand May 4, 2016
4c90494
Use origin kw of to_datetime
Winand May 5, 2016
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
12 changes: 9 additions & 3 deletions pandas/io/sas/sas7bdat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -629,9 +629,15 @@ def _chunk_to_dataframe(self):
rslt[name] = self._byte_chunk[jb, :].view(
dtype=self.byte_order + 'd')
rslt[name] = np.asarray(rslt[name], dtype=np.float64)
if self.convert_dates and (self.column_formats[j] == "MMDDYY"):
epoch = pd.datetime(1960, 1, 1)
rslt[name] = epoch + pd.to_timedelta(rslt[name], unit='d')
if self.convert_dates:
unit = None
if self.column_formats[j] in const.sas_date_formats:
unit = 'd'
elif self.column_formats[j] in const.sas_datetime_formats:
unit = 's'
if unit:
rslt[name] = pd.to_datetime(rslt[name], unit=unit,
origin="1960-01-01")
jb += 1
elif self.column_types[j] == b's':
rslt[name] = self._string_chunk[js, :]
Expand Down
14 changes: 14 additions & 0 deletions pandas/io/sas/sas_constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,3 +145,17 @@ class index:
b"\xFF\xFF\xFF\xFE": index.columnListIndex,
b"\xFE\xFF\xFF\xFF\xFF\xFF\xFF\xFF": index.columnListIndex,
b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFE": index.columnListIndex}


# List of frequently used SAS date and datetime formats
# http://support.sas.com/documentation/cdl/en/etsug/60372/HTML/default/viewer.htm#etsug_intervals_sect009.htm
sas_date_formats = ("DATE", "DAY", "DDMMYY", "DOWNAME", "JULDAY", "JULIAN",
"MMDDYY", "MMYY", "MMYYC", "MMYYD", "MMYYP", "MMYYS",
"MMYYN", "MONNAME", "MONTH", "MONYY", "QTR", "QTRR",
"NENGO", "WEEKDATE", "WEEKDATX", "WEEKDAY", "WEEKV",
"WORDDATE", "WORDDATX", "YEAR", "YYMM", "YYMMC", "YYMMD",
"YYMMP", "YYMMS", "YYMMN", "YYMON", "YYMMDD", "YYQ",
"YYQC", "YYQD", "YYQP", "YYQS", "YYQN", "YYQR", "YYQRC",
"YYQRD", "YYQRP", "YYQRS", "YYQRN")

sas_datetime_formats = "DATETIME", "DTWKDATX"
Binary file added pandas/io/tests/sas/data/dt.sas7bdat
View file
Open in desktop
Binary file not shown.
10 changes: 10 additions & 0 deletions pandas/io/tests/sas/test_sas7bdat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,3 +112,13 @@ def test_airline():
df0 = pd.read_csv(fname)
df0 = df0.astype(np.float64)
tm.assert_frame_equal(df, df0, check_exact=False)


def test_date_time():
dirpath = tm.get_data_path()
fname = os.path.join(dirpath, "dt.sas7bdat")
df = pd.read_sas(fname)
di = pd.to_datetime(["1960-05-03", "1993-10-19", "2014-10-04",
"1960-01-02 10:17:36"])
df0 = pd.DataFrame(di, index=("D1", "D2", "D3", "DT")).T
tm.assert_frame_equal(df, df0)