CLN-23123 Add missing sparse tests

Author: JustinZhengBC

pandas/tests/arrays/sparse/common.py

@@ -0,0 +1,40 @@
+import pytest
+import numpy as np
+from pandas import SparseDataFrame, DataFrame, SparseSeries
+from pandas.util import testing as tm
+
+
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_quantile():
+    # GH 17386
+    data = [[1, 1], [2, 10], [3, 100], [np.nan, np.nan]]
+    q = 0.1
+
+    sparse_df = SparseDataFrame(data)
+    result = sparse_df.quantile(q)
+
+    dense_df = DataFrame(data)
+    dense_expected = dense_df.quantile(q)
+    sparse_expected = SparseSeries(dense_expected)
+
+    tm.assert_series_equal(result, dense_expected)
+    tm.assert_sp_series_equal(result, sparse_expected)
+
+
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_quantile_multi():
+    # GH 17386
+    data = [[1, 1], [2, 10], [3, 100], [np.nan, np.nan]]
+    q = [0.1, 0.5]
+
+    sparse_df = SparseDataFrame(data)
+    result = sparse_df.quantile(q)
+
+    dense_df = DataFrame(data)
+    dense_expected = dense_df.quantile(q)
+    sparse_expected = SparseDataFrame(dense_expected)
+
+    tm.assert_frame_equal(result, dense_expected)
+    tm.assert_sp_frame_equal(result, sparse_expected)

pandas/tests/arrays/sparse/frame/test_analytics.py

@@ -0,0 +1,113 @@
+import pytest
+import numpy as np
+from pandas import SparseDataFrame, DataFrame
+from pandas.util import testing as tm
+
+
+pytestmark = pytest.mark.skip("Wrong SparseBlock initialization (GH 17386)")
+
+
+@pytest.mark.parametrize('data', [
+    [[1, 1], [2, 2], [3, 3], [4, 4], [0, 0]],
+    [[1.0, 1.0], [2.0, 2.0], [3.0, 3.0], [4.0, 4.0], [np.nan, np.nan]],
+    [
+        [1.0, 1.0 + 1.0j],
+        [2.0 + 2.0j, 2.0],
+        [3.0, 3.0 + 3.0j],
+        [4.0 + 4.0j, 4.0],
+        [np.nan, np.nan]
+    ]
+])
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_where_with_numeric_data(data):
+    # GH 17386
+    lower_bound = 1.5
+
+    sparse = SparseDataFrame(data)
+    result = sparse.where(sparse > lower_bound)
+
+    dense = DataFrame(data)
+    dense_expected = dense.where(dense > lower_bound)
+    sparse_expected = SparseDataFrame(dense_expected)
+
+    tm.assert_frame_equal(result, dense_expected)
+    tm.assert_sp_frame_equal(result, sparse_expected)
+
+
+@pytest.mark.parametrize('data', [
+    [[1, 1], [2, 2], [3, 3], [4, 4], [0, 0]],
+    [[1.0, 1.0], [2.0, 2.0], [3.0, 3.0], [4.0, 4.0], [np.nan, np.nan]],
+    [
+        [1.0, 1.0 + 1.0j],
+        [2.0 + 2.0j, 2.0],
+        [3.0, 3.0 + 3.0j],
+        [4.0 + 4.0j, 4.0],
+        [np.nan, np.nan]
+    ]
+])
+@pytest.mark.parametrize('other', [
+    True,
+    -100,
+    0.1,
+    100.0 + 100.0j
+])
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_where_with_numeric_data_and_other(data, other):
+    # GH 17386
+    lower_bound = 1.5
+
+    sparse = SparseDataFrame(data)
+    result = sparse.where(sparse > lower_bound, other)
+
+    dense = DataFrame(data)
+    dense_expected = dense.where(dense > lower_bound, other)
+    sparse_expected = SparseDataFrame(dense_expected,
+                                      default_fill_value=other)
+
+    tm.assert_frame_equal(result, dense_expected)
+    tm.assert_sp_frame_equal(result, sparse_expected)
+
+
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_where_with_bool_data():
+    # GH 17386
+    data = [[False, False], [True, True], [False, False]]
+    cond = True
+
+    sparse = SparseDataFrame(data)
+    result = sparse.where(sparse == cond)
+
+    dense = DataFrame(data)
+    dense_expected = dense.where(dense == cond)
+    sparse_expected = SparseDataFrame(dense_expected)
+
+    tm.assert_frame_equal(result, dense_expected)
+    tm.assert_sp_frame_equal(result, sparse_expected)
+
+
+@pytest.mark.parametrize('other', [
+    True,
+    0,
+    0.1,
+    100.0 + 100.0j
+])
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_where_with_bool_data_and_other(other):
+    # GH 17386
+    data = [[False, False], [True, True], [False, False]]
+    cond = True
+
+    sparse = SparseDataFrame(data)
+    result = sparse.where(sparse == cond, other)
+
+    dense = DataFrame(data)
+    dense_expected = dense.where(dense == cond, other)
+    sparse_expected = SparseDataFrame(dense_expected,
+                                      default_fill_value=other)
+
+    tm.assert_frame_equal(result, dense_expected)
+    tm.assert_sp_frame_equal(result, sparse_expected)

pandas/tests/arrays/sparse/frame/test_indexing.py

@@ -0,0 +1,20 @@
+import numpy as np
+import pytest
+from pandas import SparseDataFrame, read_csv
+from pandas.util import testing as tm
+
+
+class TestSparseDataFrameToCsv(object):
+    fill_values = [np.nan, 0, None, 1]
+
+    @pytest.mark.parametrize('fill_value', fill_values)
+    def test_to_csv_sparse_dataframe(self, fill_value):
+        # GH19384
+        sdf = SparseDataFrame({'a': type(self).fill_values},
+                              default_fill_value=fill_value)
+
+        with tm.ensure_clean('sparse_df.csv') as path:
+            sdf.to_csv(path, index=False)
+            df = read_csv(path, skip_blank_lines=False)
+
+            tm.assert_sp_frame_equal(df.to_sparse(fill_value=fill_value), sdf)

pandas/tests/arrays/sparse/frame/test_to_csv.py

@@ -0,0 +1,113 @@
+import pytest
+import numpy as np
+from pandas import SparseSeries, Series
+from pandas.util import testing as tm
+
+
+pytestmark = pytest.mark.skip("Wrong SparseBlock initialization (GH 17386)")
+
+
+@pytest.mark.parametrize('data', [
+    [1, 1, 2, 2, 3, 3, 4, 4, 0, 0],
+    [1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 4.0, 4.0, np.nan, np.nan],
+    [
+        1.0, 1.0 + 1.0j,
+        2.0 + 2.0j, 2.0,
+        3.0, 3.0 + 3.0j,
+        4.0 + 4.0j, 4.0,
+        np.nan, np.nan
+    ]
+])
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_where_with_numeric_data(data):
+    # GH 17386
+    lower_bound = 1.5
+
+    sparse = SparseSeries(data)
+    result = sparse.where(sparse > lower_bound)
+
+    dense = Series(data)
+    dense_expected = dense.where(dense > lower_bound)
+    sparse_expected = SparseSeries(dense_expected)
+
+    tm.assert_series_equal(result, dense_expected)
+    tm.assert_sp_series_equal(result, sparse_expected)
+
+
+@pytest.mark.parametrize('data', [
+    [1, 1, 2, 2, 3, 3, 4, 4, 0, 0],
+    [1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 4.0, 4.0, np.nan, np.nan],
+    [
+        1.0, 1.0 + 1.0j,
+        2.0 + 2.0j, 2.0,
+        3.0, 3.0 + 3.0j,
+        4.0 + 4.0j, 4.0,
+        np.nan, np.nan
+    ]
+])
+@pytest.mark.parametrize('other', [
+    True,
+    -100,
+    0.1,
+    100.0 + 100.0j
+])
+@pytest.mark.skip(reason='Wrong SparseBlock initialization '
+                         '(Segfault) '
+                         '(GH 17386)')
+def test_where_with_numeric_data_and_other(data, other):
+    # GH 17386
+    lower_bound = 1.5
+
+    sparse = SparseSeries(data)
+    result = sparse.where(sparse > lower_bound, other)
+
+    dense = Series(data)
+    dense_expected = dense.where(dense > lower_bound, other)
+    sparse_expected = SparseSeries(dense_expected, fill_value=other)
+
+    tm.assert_series_equal(result, dense_expected)
+    tm.assert_sp_series_equal(result, sparse_expected)
+
+
+@pytest.mark.xfail(reason='Wrong SparseBlock initialization (GH#17386)',
+                   strict=True)
+def test_where_with_bool_data():
+    # GH 17386
+    data = [False, False, True, True, False, False]
+    cond = True
+
+    sparse = SparseSeries(data)
+    result = sparse.where(sparse == cond)
+
+    dense = Series(data)
+    dense_expected = dense.where(dense == cond)
+    sparse_expected = SparseSeries(dense_expected)
+
+    tm.assert_series_equal(result, dense_expected)
+    tm.assert_sp_series_equal(result, sparse_expected)
+
+
+@pytest.mark.parametrize('other', [
+    True,
+    0,
+    0.1,
+    100.0 + 100.0j
+])
+@pytest.mark.skip(reason='Wrong SparseBlock initialization '
+                         '(Segfault) '
+                         '(GH 17386)')
+def test_where_with_bool_data_and_other(other):
+    # GH 17386
+    data = [False, False, True, True, False, False]
+    cond = True
+
+    sparse = SparseSeries(data)
+    result = sparse.where(sparse == cond, other)
+
+    dense = Series(data)
+    dense_expected = dense.where(dense == cond, other)
+    sparse_expected = SparseSeries(dense_expected, fill_value=other)
+
+    tm.assert_series_equal(result, dense_expected)
+    tm.assert_sp_series_equal(result, sparse_expected)