Skip to content

Commit

Permalink
CLN: Cleanup tests for .rank()
Browse files Browse the repository at this point in the history 
Work in Progress

1. Created new `pandas/tests/series/test_rank` and `pandas/tests/frame/test_rank`
2. Moved tests from `pandas/tests/test_stats` to `series` or `frame`
version of `test_rank`
3. move `rank` tests from `frame/test_analytics` to `frame/test_rank`
4. move `rank` tests from `series/test_analytics` to
`series/test_analytics`

See pandas-dev#15640
  • Loading branch information
@rouzazari
rouzazari committed Mar 12, 2017
1 parent 5eac08a commit 9580af0
Show file tree
Hide file tree
Showing 5 changed files with 591 additions and 553 deletions.
167 changes: 0 additions & 167 deletions pandas/tests/frame/test_analytics.py
View file
Original file line number Diff line number Diff line change
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

0 comments on commit 9580af0

Please sign in to comment.