Skip to content

CLN: Cleanup tests for .rank() #15658

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
+592 −554
Closed

CLN: Cleanup tests for .rank() #15658

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
9580af0
CLN: Cleanup tests for .rank()
rouzazari Mar 11, 2017
d0a2abc
Fixed linting error with datetime.datetime import
rouzazari Mar 12, 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
169 changes: 1 addition & 168 deletions pandas/tests/frame/test_analytics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

from __future__ import print_function

from datetime import timedelta, datetime
from datetime import timedelta
from distutils.version import LooseVersion
import sys
import pytest
Expand Down Expand Up @@ -642,173 +642,6 @@ def test_cumprod(self):
df.cumprod(0)
df.cumprod(1)

def test_rank(self):
tm._skip_if_no_scipy()
from scipy.stats import rankdata

self.frame['A'][::2] = np.nan
self.frame['B'][::3] = np.nan
self.frame['C'][::4] = np.nan
self.frame['D'][::5] = np.nan

ranks0 = self.frame.rank()
ranks1 = self.frame.rank(1)
mask = np.isnan(self.frame.values)

fvals = self.frame.fillna(np.inf).values

exp0 = np.apply_along_axis(rankdata, 0, fvals)
exp0[mask] = np.nan

exp1 = np.apply_along_axis(rankdata, 1, fvals)
exp1[mask] = np.nan

tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)

# integers
df = DataFrame(np.random.randint(0, 5, size=40).reshape((10, 4)))

result = df.rank()
exp = df.astype(float).rank()
tm.assert_frame_equal(result, exp)

result = df.rank(1)
exp = df.astype(float).rank(1)
tm.assert_frame_equal(result, exp)

def test_rank2(self):
df = DataFrame([[1, 3, 2], [1, 2, 3]])
expected = DataFrame([[1.0, 3.0, 2.0], [1, 2, 3]]) / 3.0
result = df.rank(1, pct=True)
tm.assert_frame_equal(result, expected)

df = DataFrame([[1, 3, 2], [1, 2, 3]])
expected = df.rank(0) / 2.0
result = df.rank(0, pct=True)
tm.assert_frame_equal(result, expected)

df = DataFrame([['b', 'c', 'a'], ['a', 'c', 'b']])
expected = DataFrame([[2.0, 3.0, 1.0], [1, 3, 2]])
result = df.rank(1, numeric_only=False)
tm.assert_frame_equal(result, expected)

expected = DataFrame([[2.0, 1.5, 1.0], [1, 1.5, 2]])
result = df.rank(0, numeric_only=False)
tm.assert_frame_equal(result, expected)

df = DataFrame([['b', np.nan, 'a'], ['a', 'c', 'b']])
expected = DataFrame([[2.0, nan, 1.0], [1.0, 3.0, 2.0]])
result = df.rank(1, numeric_only=False)
tm.assert_frame_equal(result, expected)

expected = DataFrame([[2.0, nan, 1.0], [1.0, 1.0, 2.0]])
result = df.rank(0, numeric_only=False)
tm.assert_frame_equal(result, expected)

# f7u12, this does not work without extensive workaround
data = [[datetime(2001, 1, 5), nan, datetime(2001, 1, 2)],
[datetime(2000, 1, 2), datetime(2000, 1, 3),
datetime(2000, 1, 1)]]
df = DataFrame(data)

# check the rank
expected = DataFrame([[2., nan, 1.],
[2., 3., 1.]])
result = df.rank(1, numeric_only=False, ascending=True)
tm.assert_frame_equal(result, expected)

expected = DataFrame([[1., nan, 2.],
[2., 1., 3.]])
result = df.rank(1, numeric_only=False, ascending=False)
tm.assert_frame_equal(result, expected)

# mixed-type frames
self.mixed_frame['datetime'] = datetime.now()
self.mixed_frame['timedelta'] = timedelta(days=1, seconds=1)

result = self.mixed_frame.rank(1)
expected = self.mixed_frame.rank(1, numeric_only=True)
tm.assert_frame_equal(result, expected)

df = DataFrame({"a": [1e-20, -5, 1e-20 + 1e-40, 10,
1e60, 1e80, 1e-30]})
exp = DataFrame({"a": [3.5, 1., 3.5, 5., 6., 7., 2.]})
tm.assert_frame_equal(df.rank(), exp)

def test_rank_na_option(self):
tm._skip_if_no_scipy()
from scipy.stats import rankdata

self.frame['A'][::2] = np.nan
self.frame['B'][::3] = np.nan
self.frame['C'][::4] = np.nan
self.frame['D'][::5] = np.nan

# bottom
ranks0 = self.frame.rank(na_option='bottom')
ranks1 = self.frame.rank(1, na_option='bottom')

fvals = self.frame.fillna(np.inf).values

exp0 = np.apply_along_axis(rankdata, 0, fvals)
exp1 = np.apply_along_axis(rankdata, 1, fvals)

tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)

# top
ranks0 = self.frame.rank(na_option='top')
ranks1 = self.frame.rank(1, na_option='top')

fval0 = self.frame.fillna((self.frame.min() - 1).to_dict()).values
fval1 = self.frame.T
fval1 = fval1.fillna((fval1.min() - 1).to_dict()).T
fval1 = fval1.fillna(np.inf).values

exp0 = np.apply_along_axis(rankdata, 0, fval0)
exp1 = np.apply_along_axis(rankdata, 1, fval1)

tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)

# descending

# bottom
ranks0 = self.frame.rank(na_option='top', ascending=False)
ranks1 = self.frame.rank(1, na_option='top', ascending=False)

fvals = self.frame.fillna(np.inf).values

exp0 = np.apply_along_axis(rankdata, 0, -fvals)
exp1 = np.apply_along_axis(rankdata, 1, -fvals)

tm.assert_almost_equal(ranks0.values, exp0)
tm.assert_almost_equal(ranks1.values, exp1)

# descending

# top
ranks0 = self.frame.rank(na_option='bottom', ascending=False)
ranks1 = self.frame.rank(1, na_option='bottom', ascending=False)

fval0 = self.frame.fillna((self.frame.min() - 1).to_dict()).values
fval1 = self.frame.T
fval1 = fval1.fillna((fval1.min() - 1).to_dict()).T
fval1 = fval1.fillna(np.inf).values

exp0 = np.apply_along_axis(rankdata, 0, -fval0)
exp1 = np.apply_along_axis(rankdata, 1, -fval1)

tm.assert_numpy_array_equal(ranks0.values, exp0)
tm.assert_numpy_array_equal(ranks1.values, exp1)

def test_rank_axis(self):
# check if using axes' names gives the same result
df = pd.DataFrame([[2, 1], [4, 3]])
tm.assert_frame_equal(df.rank(axis=0), df.rank(axis='index'))
tm.assert_frame_equal(df.rank(axis=1), df.rank(axis='columns'))

def test_sem(self):
alt = lambda x: np.std(x, ddof=1) / np.sqrt(len(x))
self._check_stat_op('sem', alt)
Expand Down
Loading