Skip to content

BUG/DOC: restrict possibilities for assembly of dates using a DataFrame #12996

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 1 commit into from
Closed

BUG/DOC: restrict possibilities for assembly of dates using a DataFrame #12996

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
38 changes: 16 additions & 22 deletions pandas/tseries/tests/test_timeseries.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2318,24 +2318,18 @@ def test_dataframe(self):
assert_series_equal(result, expected2)

# unit mappings
units = [{'year': 'year',
units = [{'year': 'years',
'month': 'months',
'day': 'days',
'hour': 'hours',
'minute': 'minutes',
'second': 'seconds'},
{'year': 'year',
'month': 'month',
'day': 'day',
'hour': 'HH',
'minute': 'MM',
'second': 'SS'},
{'year': '%Y',
'month': '%m',
'day': '%d',
'hour': '%H',
'minute': '%M',
'second': '%S'},
{'year': 'y',
'month': 'month',
'day': 'd',
'hour': 'h',
'minute': 'm',
'second': 's'},
'hour': 'hour',
'minute': 'min',
'second': 'sec'},
]

for d in units:
Expand All @@ -2344,12 +2338,12 @@ def test_dataframe(self):
Timestamp('20160305 07:59:11')])
assert_series_equal(result, expected)

d = {'year': 'y',
d = {'year': 'year',
'month': 'month',
'day': 'd',
'hour': 'h',
'minute': 'm',
'second': 's',
'day': 'day',
'hour': 'hour',
'minute': 'minute',
'second': 'second',
'ms': 'ms',
'us': 'us',
'ns': 'ns'}
Expand All @@ -2360,7 +2354,7 @@ def test_dataframe(self):
assert_series_equal(result, expected)

# coerce back to int
result = to_datetime(df.astype(str), unit=d)
result = to_datetime(df.astype(str))
assert_series_equal(result, expected)

# passing coerce
Expand Down
81 changes: 17 additions & 64 deletions pandas/tseries/tools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,53 +244,10 @@ def to_datetime(arg, errors='raise', dayfirst=False, yearfirst=False,

Examples
--------
Take separate series and convert to datetime

>>> import pandas as pd
>>> i = pd.date_range('20000101',periods=100)
>>> df = pd.DataFrame(dict(year = i.year, month = i.month, day = i.day))
>>> pd.to_datetime(df.year*10000 + df.month*100 + df.day, format='%Y%m%d')
0 2000-01-01
1 2000-01-02
...
98 2000-04-08
99 2000-04-09
Length: 100, dtype: datetime64[ns]

Or from strings

>>> dfs = df.astype(str)
>>> pd.to_datetime(dfs.day + dfs.month + dfs.year, format="%d%m%Y")
0 2000-01-01
1 2000-01-02
...
98 2000-04-08
99 2000-04-09
Length: 100, dtype: datetime64[ns]

Infer the format from the first entry

>>> pd.to_datetime(dfs.month + '/' + dfs.day + '/' + dfs.year,
infer_datetime_format=True)
0 2000-01-01
1 2000-01-02
...
98 2000-04-08
99 2000-04-09

This gives the same results as omitting the `infer_datetime_format=True`,
but is much faster.

Date that does not meet timestamp limitations:

>>> pd.to_datetime('13000101', format='%Y%m%d')
datetime.datetime(1300, 1, 1, 0, 0)
>>> pd.to_datetime('13000101', format='%Y%m%d', errors='coerce')
NaT


Assembling a datetime from multiple columns of a DataFrame. The keys can be
strptime-like (%Y, %m) or common abbreviations like ('year', 'month')
common abbreviations like ['year', 'month', 'day', 'minute', 'second',
'ms', 'us', 'ns']) or plurals of the same

>>> df = pd.DataFrame({'year': [2015, 2016],
'month': [2, 3],
Expand All @@ -300,6 +257,12 @@ def to_datetime(arg, errors='raise', dayfirst=False, yearfirst=False,
1 2016-03-05
dtype: datetime64[ns]

Date that does not meet timestamp limitations:

>>> pd.to_datetime('13000101', format='%Y%m%d')
datetime.datetime(1300, 1, 1, 0, 0)
>>> pd.to_datetime('13000101', format='%Y%m%d', errors='coerce')
NaT
"""
return _to_datetime(arg, errors=errors, dayfirst=dayfirst,
yearfirst=yearfirst,
Expand Down Expand Up @@ -439,31 +402,21 @@ def _convert_listlike(arg, box, format, name=None):

# mappings for assembling units
_unit_map = {'year': 'year',
'y': 'year',
'%Y': 'year',
'years': 'year',
'month': 'month',
'M': 'month',
'%m': 'month',
'months': 'month',
'day': 'day',
'days': 'day',
'd': 'day',
'%d': 'day',
'h': 'h',
'hour': 'h',
'hh': 'h',
'%H': 'h',
'hours': 'h',
'minute': 'm',
't': 'm',
'minutes': 'm',
'min': 'm',
'%M': 'm',
'mm': 'm',
'MM': 'm',
'%M': 'm',
's': 's',
'seconds': 's',
'mins': 'm',
'second': 's',
'%S': 's',
'ss': 's',
'seconds': 's',
'sec': 's',
'secs': 's',
'ms': 'ms',
'millisecond': 'ms',
'milliseconds': 'ms',
Expand Down Expand Up @@ -505,7 +458,7 @@ def f(value):
return _unit_map[value]

# m is case significant
if value.lower() in _unit_map and not value.startswith('m'):
if value.lower() in _unit_map:
return _unit_map[value.lower()]

return value
Expand Down