Skip to content

TST: move pandas/tests/io/test_date_converters.py to pandas/tests/io/parsers/parse_dates.py #15707

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 6 commits into from
Closed

TST: move pandas/tests/io/test_date_converters.py to pandas/tests/io/parsers/parse_dates.py #15707

Changes from 5 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b977615
Merge remote-tracking branch 'pandas-dev/master'
jaehoonhwang Mar 8, 2017
9b20caa
Merge remote-tracking branch 'pandas-dev/master'
jaehoonhwang Mar 16, 2017
3eb63c5
TST15519 Moving Unit tests to appropriate file
jaehoonhwang Mar 16, 2017
e019e95
Imported read_table and using self.readcsv
jaehoonhwang Mar 17, 2017
ef6e8fa
Fixing up few lines and imports
jaehoonhwang Mar 17, 2017
0b309d3
Fixed frame email and PEP8
jaehoonhwang Mar 18, 2017
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
152 changes: 150 additions & 2 deletions pandas/tests/io/parser/parse_dates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
"""

from distutils.version import LooseVersion
from datetime import datetime
from datetime import datetime, date

import pytest
import numpy as np
Expand All @@ -19,12 +19,15 @@
import pandas.util.testing as tm

import pandas.io.date_converters as conv
from pandas import DataFrame, Series, Index, DatetimeIndex
from pandas import DataFrame, Series, Index, DatetimeIndex, MultiIndex
from pandas import compat
from pandas.compat import parse_date, StringIO, lrange
from pandas.compat.numpy import np_array_datetime64_compat
from pandas.io.parsers import read_table
Copy link
Contributor

Choose a reason for hiding this comment

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

don't use read_table

instead these should use self.read_csv

from pandas.tseries.index import date_range



class ParseDatesTests(object):

def test_separator_date_conflict(self):
Expand Down Expand Up @@ -510,3 +513,148 @@ def test_parse_date_time_multi_level_column_name(self):
expected = DataFrame(expected_data,
columns=['date_time', ('A', 'a'), ('B', 'b')])
tm.assert_frame_equal(result, expected)

def test_parse_date_time(self):
Copy link
Contributor

Choose a reason for hiding this comment

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

things that are strictly related the the actual parsing (e.g. just involve conv) can be put in a separate class; name it TestConverters (otherwise it won't be run)

Copy link
Contributor

Choose a reason for hiding this comment

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

actually nvm about this comment

# From test_date_coverter
Copy link
Contributor

Choose a reason for hiding this comment

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

this comment not needed

dates = np.array(['2007/1/3', '2008/2/4'], dtype=object)
times = np.array(['05:07:09', '06:08:00'], dtype=object)
expected = np.array([datetime(2007, 1, 3, 5, 7, 9),
datetime(2008, 2, 4, 6, 8, 0)])

result = conv.parse_date_time(dates, times)
self.assertTrue((result == expected).all())

data = """\
date, time, a, b
2001-01-05, 10:00:00, 0.0, 10.
2001-01-05, 00:00:00, 1., 11.
"""
datecols = {'date_time': [0, 1]}
df = read_table(StringIO(data), sep=',', header=0,
parse_dates=datecols, date_parser=conv.parse_date_time)
self.assertIn('date_time', df)
self.assertEqual(df.date_time.loc[0], datetime(2001, 1, 5, 10, 0, 0))

data = ("KORD,19990127, 19:00:00, 18:56:00, 0.8100\n"
"KORD,19990127, 20:00:00, 19:56:00, 0.0100\n"
"KORD,19990127, 21:00:00, 20:56:00, -0.5900\n"
"KORD,19990127, 21:00:00, 21:18:00, -0.9900\n"
"KORD,19990127, 22:00:00, 21:56:00, -0.5900\n"
"KORD,19990127, 23:00:00, 22:56:00, -0.5900")

date_spec = {'nominal': [1, 2], 'actual': [1, 3]}
df = self.read_csv(StringIO(data), header=None, parse_dates=date_spec,
date_parser=conv.parse_date_time)

def test_parse_date_fields(self):
years = np.array([2007, 2008])
months = np.array([1, 2])
days = np.array([3, 4])
result = conv.parse_date_fields(years, months, days)
expected = np.array([datetime(2007, 1, 3), datetime(2008, 2, 4)])
self.assertTrue((result == expected).all())

data = ("year, month, day, a\n 2001 , 01 , 10 , 10.\n"
"2001 , 02 , 1 , 11.")
datecols = {'ymd': [0, 1, 2]}
df = read_table(StringIO(data), sep=',', header=0,
parse_dates=datecols,
date_parser=conv.parse_date_fields)
self.assertIn('ymd', df)
self.assertEqual(df.ymd.loc[0], datetime(2001, 1, 10))

def test_datetime_six_col(self):
years = np.array([2007, 2008])
months = np.array([1, 2])
days = np.array([3, 4])
hours = np.array([5, 6])
minutes = np.array([7, 8])
seconds = np.array([9, 0])
expected = np.array([datetime(2007, 1, 3, 5, 7, 9),
datetime(2008, 2, 4, 6, 8, 0)])

result = conv.parse_all_fields(years, months, days,
hours, minutes, seconds)


self.assertTrue((result == expected).all())

data = """\
year, month, day, hour, minute, second, a, b
2001, 01, 05, 10, 00, 0, 0.0, 10.
2001, 01, 5, 10, 0, 00, 1., 11.
"""
datecols = {'ymdHMS': [0, 1, 2, 3, 4, 5]}
df = read_table(StringIO(data), sep=',', header=0,
parse_dates=datecols,
date_parser=conv.parse_all_fields)
self.assertIn('ymdHMS', df)
self.assertEqual(df.ymdHMS.loc[0], datetime(2001, 1, 5, 10, 0, 0))

def test_datetime_fractional_seconds(self):
data = """\
year, month, day, hour, minute, second, a, b
2001, 01, 05, 10, 00, 0.123456, 0.0, 10.
2001, 01, 5, 10, 0, 0.500000, 1., 11.
"""
datecols = {'ymdHMS': [0, 1, 2, 3, 4, 5]}
df = read_table(StringIO(data), sep=',', header=0,
parse_dates=datecols,
date_parser=conv.parse_all_fields)
self.assertIn('ymdHMS', df)
self.assertEqual(df.ymdHMS.loc[0], datetime(2001, 1, 5, 10, 0, 0,
microsecond=123456))
self.assertEqual(df.ymdHMS.loc[1], datetime(2001, 1, 5, 10, 0, 0,
microsecond=500000))

def test_generic(self):
data = "year, month, day, a\n 2001, 01, 10, 10.\n 2001, 02, 1, 11."
datecols = {'ym': [0, 1]}
dateconverter = lambda y, m: date(year=int(y), month=int(m), day=1)
df = read_table(StringIO(data), sep=',', header=0,
parse_dates=datecols,
date_parser=dateconverter)
self.assertIn('ym', df)
self.assertEqual(df.ym.loc[0], date(2001, 1, 1))

def test_dateparser_resolution_if_not_ns(self):
# GH 10245
data = """\
date,time,prn,rxstatus
2013-11-03,19:00:00,126,00E80000
2013-11-03,19:00:00,23,00E80000
2013-11-03,19:00:00,13,00E80000
"""

def date_parser(date, time):
datetime = np_array_datetime64_compat(
date + 'T' + time + 'Z', dtype='datetime64[s]')
return datetime


df = self.read_csv(StringIO(data), date_parser=date_parser,
parse_dates={'datetime': ['date', 'time']},
index_col=['datetime', 'prn'])

datetimes = np_array_datetime64_compat(['2013-11-03T19:00:00Z'] * 3,
dtype='datetime64[s]')
df_correct = DataFrame(data={'rxstatus': ['00E80000'] * 3},
index=MultiIndex.from_tuples(
[(datetimes[0], 126),
(datetimes[1], 23),
(datetimes[2], 13)],
names=['datetime', 'prn']))
assert_frame_equal(df, df_correct)

def test_parse_date_column_with_empty_string(self):
# GH 6428
data = """case,opdate
7,10/18/2006
7,10/18/2008
621, """
result = self.read_csv(StringIO(data), parse_dates=['opdate'])
expected_data = [[7, '10/18/2006'],
[7, '10/18/2008'],
[621, ' ']]
expected = DataFrame(expected_data, columns=['case', 'opdate'])
tm.assert_frame_equal(result, expected)