def test_datetime_cut(self):
# GH 14714
# testing for time data to be present as series
data = to_datetime(Series(['2013-01-01', '2013-01-02', '2013-01-03']))
result, bins = cut(data, 3, retbins=True)
expected = Series(['(2012-12-31 23:57:07.200000, 2013-01-01 16:00:00]',
'(2013-01-01 16:00:00, 2013-01-02 08:00:00]',
'(2013-01-02 08:00:00, 2013-01-03 00:00:00]'],
).astype("category", ordered=True)
tm.assert_series_equal(result, expected)
# testing for time data to be present as list
data = [np.datetime64('2013-01-01'), np.datetime64('2013-01-02'),
np.datetime64('2013-01-03')]
result, bins = cut(data, 3, retbins=True)
tm.assert_series_equal(Series(result), expected)
# testing for time data to be present as ndarray
data = np.array([np.datetime64('2013-01-01'),
np.datetime64('2013-01-02'),
np.datetime64('2013-01-03')])
result, bins = cut(data, 3, retbins=True)
tm.assert_series_equal(Series(result), expected)
# testing for time data to be present as datetime index
data = DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03'])
result, bins = cut(data, 3, retbins=True)
tm.assert_series_equal(Series(result), expected)
def test_label_formatting(self):
self.assertEquals(tmod._trim_zeros('1.000'), '1')
# it works
result = cut(np.arange(11.), 2)
result = cut(np.arange(11.) / 1e10, 2)
def test_labels(self):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
result, bins = cut(arr, 4, retbins=True)
ex_levels = ["(-0.001, 0.25]", "(0.25, 0.5]", "(0.5, 0.75]", "(0.75, 1]"]
self.assert_(np.array_equal(result.levels, ex_levels))
result, bins = cut(arr, 4, retbins=True, right=False)
ex_levels = ["[0, 0.25)", "[0.25, 0.5)", "[0.5, 0.75)", "[0.75, 1.001)"]
self.assert_(np.array_equal(result.levels, ex_levels))
def test_cut_pass_labels(self):
arr = [50, 5, 10, 15, 20, 30, 70]
bins = [0, 25, 50, 100]
labels = ['Small', 'Medium', 'Large']
result = cut(arr, bins, labels=labels)
exp = cut(arr, bins)
exp.categories = labels
tm.assert_categorical_equal(result, exp)
def test_cut_pass_labels(self):
arr = [50, 5, 10, 15, 20, 30, 70]
bins = [0, 25, 50, 100]
labels = ["Small", "Medium", "Large"]
result = cut(arr, bins, labels=labels)
exp = cut(arr, bins)
exp.categories = labels
self.assertTrue(result.equals(exp))
def test_single_bin(self):
# issue 14652
expected = Series([0, 0])
s = Series([9., 9.])
result = cut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
s = Series([-9., -9.])
result = cut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
def test_cut_pass_labels(self):
arr = [50, 5, 10, 15, 20, 30, 70]
bins = [0, 25, 50, 100]
labels = ['Small', 'Medium', 'Large']
result = cut(arr, bins, labels=labels)
exp = cut(arr, bins)
exp.levels = labels
self.assert_(result.equals(exp))
def test_cut_pass_labels(self):
arr = [50, 5, 10, 15, 20, 30, 70]
bins = [0, 25, 50, 100]
labels = ['Small', 'Medium', 'Large']
result = cut(arr, bins, labels=labels)
exp = cut(arr, bins)
exp.levels = labels
self.assert_(result.equals(exp))
def test_single_bin(self):
# issue 14652
expected = Series([0, 0])
s = Series([9., 9.])
result = cut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
s = Series([-9., -9.])
result = cut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
def test_na_handling(self):
arr = np.arange(0, 0.75, 0.01)
arr[::3] = np.nan
labels = cut(arr, 4)
ex_labels = np.where(com.isnull(arr), np.nan, labels)
tm.assert_almost_equal(labels, ex_labels)
labels = cut(arr, 4, labels=False)
ex_labels = np.where(com.isnull(arr), np.nan, labels)
tm.assert_almost_equal(labels, ex_labels)
def test_labels(self):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
result, bins = cut(arr, 4, retbins=True)
ex_levels = Index(['(-0.001, 0.25]', '(0.25, 0.5]', '(0.5, 0.75]',
'(0.75, 1]'])
self.assert_index_equal(result.categories, ex_levels)
result, bins = cut(arr, 4, retbins=True, right=False)
ex_levels = Index(['[0, 0.25)', '[0.25, 0.5)', '[0.5, 0.75)',
'[0.75, 1.001)'])
self.assert_index_equal(result.categories, ex_levels)
def test_labels(self):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
result, bins = cut(arr, 4, retbins=True)
ex_levels = Index(
['(-0.001, 0.25]', '(0.25, 0.5]', '(0.5, 0.75]', '(0.75, 1]'])
self.assert_index_equal(result.categories, ex_levels)
result, bins = cut(arr, 4, retbins=True, right=False)
ex_levels = Index(
['[0, 0.25)', '[0.25, 0.5)', '[0.5, 0.75)', '[0.75, 1.001)'])
self.assert_index_equal(result.categories, ex_levels)
def test_labels(self):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
result, bins = cut(arr, 4, retbins=True)
ex_levels = ['(-0.001, 0.25]', '(0.25, 0.5]', '(0.5, 0.75]',
'(0.75, 1]']
self.assert_numpy_array_equal(result.levels, ex_levels)
result, bins = cut(arr, 4, retbins=True, right=False)
ex_levels = ['[0, 0.25)', '[0.25, 0.5)', '[0.5, 0.75)',
'[0.75, 1.001)']
self.assert_numpy_array_equal(result.levels, ex_levels)
def test_label_formatting(self):
self.assertEquals(tmod._trim_zeros("1.000"), "1")
# it works
result = cut(np.arange(11.0), 2)
result = cut(np.arange(11.0) / 1e10, 2)
# #1979, negative numbers
result = tmod._format_label(-117.9998, precision=3)
self.assertEquals(result, "-118")
result = tmod._format_label(117.9998, precision=3)
self.assertEquals(result, "118")
def test_labels(self):
arr = np.tile(np.arange(0, 1.01, 0.1), 4)
labels, bins = cut(arr, 4, retbins=True)
distinct_labels = sorted(unique(labels))
ex_labels = ['(-0.001, 0.25]', '(0.25, 0.5]', '(0.5, 0.75]',
'(0.75, 1]']
self.assertEqual(distinct_labels, ex_labels)
labels, bins = cut(arr, 4, retbins=True, right=False)
distinct_labels = sorted(unique(labels))
ex_labels = ['[0, 0.25)', '[0.25, 0.5)', '[0.5, 0.75)',
'[0.75, 1.001)']
self.assertEqual(distinct_labels, ex_labels)
def test_label_formatting(self):
self.assertEqual(tmod._trim_zeros('1.000'), '1')
# it works
result = cut(np.arange(11.), 2)
result = cut(np.arange(11.) / 1e10, 2)
# #1979, negative numbers
result = tmod._format_label(-117.9998, precision=3)
self.assertEqual(result, '-118')
result = tmod._format_label(117.9998, precision=3)
self.assertEqual(result, '118')
def test_single_bin(self):
# issue 14652
# Explicit dtype since Series produces int64 for ints, while cut
# (due to numpy.searchsorted) would use int32 on i386, so let's assure
# correct default to the architecture int
expected = Series([0, 0], dtype=np.dtype(int))
s = Series([9., 9.])
result = cut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
s = Series([-9., -9.])
result = cut(s, 1, labels=False)
tm.assert_series_equal(result, expected)
def test_label_formatting(self):
self.assertEqual(tmod._trim_zeros('1.000'), '1')
# it works
result = cut(np.arange(11.), 2)
result = cut(np.arange(11.) / 1e10, 2)
# #1979, negative numbers
result = tmod._format_label(-117.9998, precision=3)
self.assertEqual(result, '-118')
result = tmod._format_label(117.9998, precision=3)
self.assertEqual(result, '118')
def test_inf_handling(self):
data = np.arange(6)
data_ser = Series(data, dtype='int64')
result = cut(data, [-np.inf, 2, 4, np.inf])
result_ser = cut(data_ser, [-np.inf, 2, 4, np.inf])
ex_categories = Index(['(-inf, 2]', '(2, 4]', '(4, inf]'])
tm.assert_index_equal(result.categories, ex_categories)
tm.assert_index_equal(result_ser.cat.categories, ex_categories)
self.assertEqual(result[5], '(4, inf]')
self.assertEqual(result[0], '(-inf, 2]')
self.assertEqual(result_ser[5], '(4, inf]')
self.assertEqual(result_ser[0], '(-inf, 2]')
def test_na_handling(self):
arr = np.arange(0, 0.75, 0.01)
arr[::3] = np.nan
result = cut(arr, 4)
result_arr = np.asarray(result)
ex_arr = np.where(com.isnull(arr), np.nan, result_arr)
tm.assert_almost_equal(result_arr, ex_arr)
result = cut(arr, 4, labels=False)
ex_result = np.where(com.isnull(arr), np.nan, result)
tm.assert_almost_equal(result, ex_result)
def test_inf_handling(self):
data = np.arange(6)
data_ser = Series(data, dtype='int64')
result = cut(data, [-np.inf, 2, 4, np.inf])
result_ser = cut(data_ser, [-np.inf, 2, 4, np.inf])
ex_categories = Index(['(-inf, 2]', '(2, 4]', '(4, inf]'])
tm.assert_index_equal(result.categories, ex_categories)
tm.assert_index_equal(result_ser.cat.categories, ex_categories)
self.assertEqual(result[5], '(4, inf]')
self.assertEqual(result[0], '(-inf, 2]')
self.assertEqual(result_ser[5], '(4, inf]')
self.assertEqual(result_ser[0], '(-inf, 2]')
def test_inf_handling(self):
data = np.arange(6)
data_ser = Series(data,dtype='int64')
result = cut(data, [-np.inf, 2, 4, np.inf])
result_ser = cut(data_ser, [-np.inf, 2, 4, np.inf])
ex_levels = ['(-inf, 2]', '(2, 4]', '(4, inf]']
np.testing.assert_array_equal(result.levels, ex_levels)
np.testing.assert_array_equal(result_ser.levels, ex_levels)
self.assertEquals(result[5], '(4, inf]')
self.assertEquals(result[0], '(-inf, 2]')
self.assertEquals(result_ser[5], '(4, inf]')
self.assertEquals(result_ser[0], '(-inf, 2]')
def test_na_handling(self):
arr = np.arange(0, 0.75, 0.01)
arr[::3] = np.nan
result = cut(arr, 4)
result_arr = np.asarray(result)
ex_arr = np.where(com.isnull(arr), np.nan, result_arr)
tm.assert_almost_equal(result_arr, ex_arr)
result = cut(arr, 4, labels=False)
ex_result = np.where(com.isnull(arr), np.nan, result)
tm.assert_almost_equal(result, ex_result)
def test_inf_handling(self):
data = np.arange(6)
data_ser = Series(data, dtype="int64")
result = cut(data, [-np.inf, 2, 4, np.inf])
result_ser = cut(data_ser, [-np.inf, 2, 4, np.inf])
ex_categories = ["(-inf, 2]", "(2, 4]", "(4, inf]"]
np.testing.assert_array_equal(result.categories, ex_categories)
np.testing.assert_array_equal(result_ser.cat.categories, ex_categories)
self.assertEqual(result[5], "(4, inf]")
self.assertEqual(result[0], "(-inf, 2]")
self.assertEqual(result_ser[5], "(4, inf]")
self.assertEqual(result_ser[0], "(-inf, 2]")
def test_inf_handling(self):
data = np.arange(6)
data_ser = Series(data,dtype='int64')
result = cut(data, [-np.inf, 2, 4, np.inf])
result_ser = cut(data_ser, [-np.inf, 2, 4, np.inf])
ex_levels = ['(-inf, 2]', '(2, 4]', '(4, inf]']
np.testing.assert_array_equal(result.levels, ex_levels)
np.testing.assert_array_equal(result_ser.levels, ex_levels)
self.assertEquals(result[5], '(4, inf]')
self.assertEquals(result[0], '(-inf, 2]')
self.assertEquals(result_ser[5], '(4, inf]')
self.assertEquals(result_ser[0], '(-inf, 2]')
def test_noright(self):
data = np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1, 2.575])
result, bins = cut(data, 4, right=False, retbins=True)
exp_codes = np.array([0, 0, 0, 2, 3, 0, 1], dtype=np.int8)
tm.assert_numpy_array_equal(result.codes, exp_codes)
exp = np.array([0.2, 2.575, 4.95, 7.325, 9.7095])
tm.assert_almost_equal(bins, exp)
def test_label_precision(self):
arr = np.arange(0, 0.73, 0.01)
result = cut(arr, 4, precision=2)
ex_levels = ['(-0.00072, 0.18]', '(0.18, 0.36]', '(0.36, 0.54]',
'(0.54, 0.72]']
self.assert_(np.array_equal(result.levels, ex_levels))
def test_label_precision(self):
arr = np.arange(0, 0.73, 0.01)
result = cut(arr, 4, precision=2)
ex_levels = ['(-0.00072, 0.18]', '(0.18, 0.36]', '(0.36, 0.54]',
'(0.54, 0.72]']
self.assert_(np.array_equal(result.levels, ex_levels))
def test_arraylike(self):
data = [.2, 1.4, 2.5, 6.2, 9.7, 2.1]
result, bins = cut(data, 3, retbins=True)
exp_codes = np.array([0, 0, 0, 1, 2, 0], dtype=np.int8)
tm.assert_numpy_array_equal(result.codes, exp_codes)
exp = np.array([0.1905, 3.36666667, 6.53333333, 9.7])
tm.assert_almost_equal(bins, exp)
def test_label_precision(self):
arr = np.arange(0, 0.73, 0.01)
result = cut(arr, 4, precision=2)
ex_levels = Index(['(-0.00072, 0.18]', '(0.18, 0.36]',
'(0.36, 0.54]', '(0.54, 0.72]'])
self.assert_index_equal(result.categories, ex_levels)
def test_arraylike(self):
data = [.2, 1.4, 2.5, 6.2, 9.7, 2.1]
result, bins = cut(data, 3, retbins=True)
exp_codes = np.array([0, 0, 0, 1, 2, 0], dtype=np.int8)
tm.assert_numpy_array_equal(result.codes, exp_codes)
exp = np.array([0.1905, 3.36666667, 6.53333333, 9.7])
tm.assert_almost_equal(bins, exp)
def test_noright(self):
data = np.array([.2, 1.4, 2.5, 6.2, 9.7, 2.1, 2.575])
result, bins = cut(data, 4, right=False, retbins=True)
exp_codes = np.array([0, 0, 0, 2, 3, 0, 1], dtype=np.int8)
tm.assert_numpy_array_equal(result.codes, exp_codes)
exp = np.array([0.2, 2.575, 4.95, 7.325, 9.7095])
tm.assert_almost_equal(bins, exp)
def test_cut_out_of_bounds(self):
arr = np.random.randn(100)
result = cut(arr, [-1, 0, 1])
mask = result.codes == -1
ex_mask = (arr < -1) | (arr > 1)
self.assert_numpy_array_equal(mask, ex_mask)
def test_label_precision(self):
arr = np.arange(0, 0.75, 0.01)
labels = cut(arr, 4, precision=2)
distinct_labels = sorted(unique(labels))
ex_labels = ['(-0.00074, 0.18]', '(0.18, 0.37]', '(0.37, 0.55]',
'(0.55, 0.74]']
self.assertEqual(distinct_labels, ex_labels)
def test_cut_out_of_bounds(self):
arr = np.random.randn(100)
result = cut(arr, [-1, 0, 1])
mask = result.labels == -1
ex_mask = (arr < -1) | (arr > 1)
self.assertTrue(np.array_equal(mask, ex_mask))
def test_cut_return_categorical(self):
s = Series([0, 1, 2, 3, 4, 5, 6, 7, 8])
res = cut(s, 3)
exp = Series(Categorical.from_codes([0, 0, 0, 1, 1, 1, 2, 2, 2],
["(-0.008, 2.667]",
"(2.667, 5.333]", "(5.333, 8]"],
ordered=True))
tm.assert_series_equal(res, exp)
def test_cut_out_of_bounds(self):
arr = np.random.randn(100)
result = cut(arr, [-1, 0, 1])
mask = result.codes == -1
ex_mask = (arr < -1) | (arr > 1)
self.assert_numpy_array_equal(mask, ex_mask)
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, 0.25, 0.5, 0.75, 1.0])
assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins, include_lowest=True)
self.assert_(np.array_equal(labels, ex_levels))
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
tm.assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins, include_lowest=True)
self.assert_categorical_equal(labels, ex_levels)
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
tm.assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins, include_lowest=True)
self.assert_categorical_equal(labels, ex_levels)
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
ex_bins[0] -= (arr.max() - arr.min()) * 0.001
assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins)
self.assert_(np.array_equal(labels, ex_levels))
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
assert_equal(result.cat.codes.values, [0, 0, 1, 1])
assert_almost_equal(bins, [-0.003, 1.5, 3])
result, bins = qcut(s, 2, retbins=True)
assert_equal(result.cat.codes.values, [0, 0, 1, 1])
assert_almost_equal(bins, [0, 1.5, 3])
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values, [0, 0, 1, 1])
tm.assert_almost_equal(bins, [-0.003, 1.5, 3])
result, bins = qcut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values, [0, 0, 1, 1])
tm.assert_almost_equal(bins, [0, 1.5, 3])
def test_qcut(self):
arr = np.random.randn(1000)
labels, bins = qcut(arr, 4, retbins=True)
ex_bins = quantile(arr, [0, .25, .5, .75, 1.])
ex_bins[0] -= (arr.max() - arr.min()) * 0.001
assert_almost_equal(bins, ex_bins)
ex_levels = cut(arr, ex_bins)
self.assert_(np.array_equal(labels, ex_levels))
def test_cut_out_of_bounds(self):
np.random.seed(12345)
arr = np.random.randn(100)
result = cut(arr, [-1, 0, 1])
mask = result.labels == -1
ex_mask = (arr < -1) | (arr > 1)
self.assert_(np.array_equal(mask, ex_mask))
def test_datetime_bin(self):
data = [np.datetime64('2012-12-13'), np.datetime64('2012-12-15')]
bin_data = ['2012-12-12', '2012-12-14', '2012-12-16']
expected = Series(['(2012-12-12 00:00:00, 2012-12-14 00:00:00]',
'(2012-12-14 00:00:00, 2012-12-16 00:00:00]'],
).astype("category", ordered=True)
for conv in [Timestamp, Timestamp, np.datetime64]:
bins = [conv(v) for v in bin_data]
result = cut(data, bins=bins)
tm.assert_series_equal(Series(result), expected)
bin_pydatetime = [Timestamp(v).to_pydatetime() for v in bin_data]
result = cut(data, bins=bin_pydatetime)
tm.assert_series_equal(Series(result), expected)
bins = to_datetime(bin_data)
result = cut(data, bins=bin_pydatetime)
tm.assert_series_equal(Series(result), expected)
def test_value_counts(self):
from pandas.tools.tile import cut
arr = np.random.randn(4)
factor = cut(arr, 4)
tm.assert_isinstance(factor, Categorical)
result = algos.value_counts(factor)
expected = algos.value_counts(np.asarray(factor))
tm.assert_series_equal(result, expected)
def test_series_retbins(self):
# GH 8589
s = Series(np.arange(4))
result, bins = cut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values,
np.array([0, 0, 1, 1], dtype=np.int8))
tm.assert_numpy_array_equal(bins, np.array([-0.003, 1.5, 3]))
result, bins = qcut(s, 2, retbins=True)
tm.assert_numpy_array_equal(result.cat.codes.values,
np.array([0, 0, 1, 1], dtype=np.int8))
tm.assert_numpy_array_equal(bins, np.array([0, 1.5, 3]))
def test_value_counts(self):
np.random.seed(1234)
from pandas.tools.tile import cut
arr = np.random.randn(4)
factor = cut(arr, 4)
tm.assertIsInstance(factor, Categorical)
result = algos.value_counts(factor)
cats = ['(-1.194, -0.535]', '(-0.535, 0.121]', '(0.121, 0.777]',
'(0.777, 1.433]']
expected_index = CategoricalIndex(cats, cats, ordered=True)
expected = Series([1, 1, 1, 1], index=expected_index)
tm.assert_series_equal(result.sort_index(), expected.sort_index())
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas import Index, PeriodIndex, DatetimeIndex
name = getattr(values, 'name', None)
values = Series(values).values
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
if com.is_categorical_dtype(values.dtype):
result = values.value_counts(dropna)
else:
dtype = values.dtype
is_period = com.is_period_arraylike(values)
is_datetimetz = com.is_datetimetz(values)
if com.is_datetime_or_timedelta_dtype(
dtype) or is_period or is_datetimetz:
if is_period:
values = PeriodIndex(values)
elif is_datetimetz:
tz = getattr(values, 'tz', None)
values = DatetimeIndex(values).tz_localize(None)
values = values.view(np.int64)
keys, counts = htable.value_count_scalar64(values, dropna)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# localize to the original tz if necessary
if is_datetimetz:
keys = DatetimeIndex(keys).tz_localize(tz)
# convert the keys back to the dtype we came in
else:
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna and mask.any():
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
if not isinstance(keys, Index):
keys = Index(keys)
result = Series(counts, index=keys, name=name)
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)),
fill_value=0)
result.index = bins[:-1]
if sort:
result = result.sort_values(ascending=ascending)
if normalize:
result = result / float(values.size)
return result
def test_cut_pass_series_name_to_factor(self):
s = Series(np.random.randn(100), name='foo')
factor = cut(s, 4)
self.assertEqual(factor.name, 'foo')
def test_cut_out_of_range_more(self):
# #1511
s = Series([0, -1, 0, 1, -3], name='x')
ind = cut(s, [0, 1], labels=False)
exp = Series([np.nan, np.nan, np.nan, 0, np.nan], name='x')
tm.assert_series_equal(ind, exp)
def test_simple(self):
data = np.ones(5)
result = cut(data, 4, labels=False)
desired = np.array([1, 1, 1, 1, 1])
tm.assert_numpy_array_equal(result, desired, check_dtype=False)
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
name = getattr(values, 'name', None)
if bins is not None:
try:
from pandas.tools.tile import cut
values = Series(values).values
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
if is_extension_type(values) and not is_datetimetz(values):
# handle Categorical and sparse,
# datetime tz can be handeled in ndarray path
result = Series(values).values.value_counts(dropna=dropna)
result.name = name
counts = result.values
else:
# ndarray path. pass original to handle DatetimeTzBlock
keys, counts = _value_counts_arraylike(values, dropna=dropna)
from pandas import Index, Series
if not isinstance(keys, Index):
keys = Index(keys)
result = Series(counts, index=keys, name=name)
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)), fill_value=0)
result.index = bins[:-1]
if sort:
result = result.sort_values(ascending=ascending)
if normalize:
result = result / float(counts.sum())
return result
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas.tseries.period import PeriodIndex
is_period = com.is_period_arraylike(values)
values = Series(values).values
is_category = com.is_categorical_dtype(values.dtype)
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
elif is_category:
bins = values.categories
cat = values
values = cat.codes
dtype = values.dtype
if issubclass(values.dtype.type,
(np.datetime64, np.timedelta64)) or is_period:
if is_period:
values = PeriodIndex(values)
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna:
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
result = Series(counts, index=com._values_from_object(keys))
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)), fill_value=0)
if not is_category:
result.index = bins[:-1]
else:
result.index = cat.categories
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result