def test_series_argsort(nelem, dtype, asc):
np.random.seed(0)
sr = Series((100 * np.random.random(nelem)).astype(dtype))
res = sr.argsort(ascending=asc)
if asc:
expected = np.argsort(sr.to_array(), kind='mergesort')
else:
expected = np.argsort(-sr.to_array(), kind='mergesort')
np.testing.assert_array_equal(expected, res.to_array())
def test_categorical_missing():
cat = pd.Categorical(['a', '_', '_', 'c', 'a'], categories=['a', 'b', 'c'])
pdsr = pd.Series(cat)
sr = Series(cat)
np.testing.assert_array_equal(cat.codes, sr.to_array(fillna='pandas'))
assert sr.null_count == 2
np.testing.assert_array_equal(pdsr.cat.codes.data,
sr.cat.codes.fillna(-1).to_array())
np.testing.assert_equal(pdsr.cat.codes.dtype, sr.cat.codes.dtype)
# integer doesn't have nan value
with pytest.raises(TypeError) as raises:
sr.cat.codes.to_array(fillna='pandas')
raises.match('NaN value')
string = str(sr)
expect_str = """
0 a
1
2
3 c
4 a
"""
assert string.split() == expect_str.split()
def test_series_sort_index(nelem, asc):
np.random.seed(0)
sr = Series((100 * np.random.random(nelem)))
orig = sr.to_array()
got = sr.sort_values().sort_index(ascending=asc).to_array()
if not asc:
# Reverse the array for descending sort
got = got[::-1]
np.testing.assert_array_equal(orig, got)
def test_series_basic():
# Make series from buffer
a1 = np.arange(10, dtype=np.float64)
series = Series(a1)
assert len(series) == 10
np.testing.assert_equal(series.to_array(), np.hstack([a1]))
# Add new buffer
a2 = np.arange(5)
series = series.append(a2)
assert len(series) == 15
np.testing.assert_equal(series.to_array(), np.hstack([a1, a2]))
# Ensure appending to previous buffer
a3 = np.arange(3)
series = series.append(a3)
assert len(series) == 18
a4 = np.hstack([a1, a2, a3])
np.testing.assert_equal(series.to_array(), a4)
def test_categorical_empty():
cat = pd.Categorical([])
pdsr = pd.Series(cat)
sr = Series(cat)
np.testing.assert_array_equal(cat.codes, sr.to_array())
assert sr.dtype == pdsr.dtype
# Test attributes
assert tuple(pdsr.cat.categories) == tuple(sr.cat.categories)
assert pdsr.cat.ordered == sr.cat.ordered
np.testing.assert_array_equal(pdsr.cat.codes.data, sr.cat.codes.to_array())
np.testing.assert_array_equal(pdsr.cat.codes.dtype, sr.cat.codes.dtype)
def test_categorical_integer():
cat = pd.Categorical(['a', '_', '_', 'c', 'a'], categories=['a', 'b', 'c'])
pdsr = pd.Series(cat)
sr = Series(cat)
np.testing.assert_array_equal(cat.codes, sr.to_array(fillna='pandas'))
assert sr.null_count == 2
np.testing.assert_array_equal(pdsr.cat.codes.data,
sr.cat.codes.fillna(-1).to_array())
np.testing.assert_equal(pdsr.cat.codes.dtype, sr.cat.codes.dtype)
string = str(sr)
expect_str = """
0 a
1
2
3 c
4 a
"""
assert string.split() == expect_str.split()
def test_categorical_missing():
cat = pd.Categorical(['a', '_', '_', 'c', 'a'], categories=['a', 'b', 'c'])
pdsr = pd.Series(cat)
sr = Series(cat)
fillna = lambda x: np.where(np.isnan(x), -1, x)
np.testing.assert_array_equal(cat.codes, fillna(sr.to_array(fillna='pandas')))
assert sr.null_count == 2
np.testing.assert_array_equal(pdsr.cat.codes.data,
fillna(sr.cat.codes.to_array(fillna='pandas')))
np.testing.assert_equal(pdsr.cat.codes.dtype, sr.cat.codes.dtype)
string = str(sr)
expect_str = """
0 a
1
2
3 c
4 a
"""
assert string.split() == expect_str.split()
def test_categorical_basic():
cat = pd.Categorical(['a', 'a', 'b', 'c', 'a'], categories=['a', 'b', 'c'])
pdsr = pd.Series(cat)
sr = Series(cat)
np.testing.assert_array_equal(cat.codes, sr.to_array())
assert sr.dtype == pdsr.dtype
# Test attributes
assert tuple(pdsr.cat.categories) == tuple(sr.cat.categories)
assert pdsr.cat.ordered == sr.cat.ordered
np.testing.assert_array_equal(pdsr.cat.codes.data, sr.cat.codes.to_array())
np.testing.assert_array_equal(pdsr.cat.codes.dtype, sr.cat.codes.dtype)
string = str(sr)
expect_str = """
0 a
1 a
2 b
3 c
4 a
"""
assert all(x == y for x, y in zip(string.split(), expect_str.split()))
