def test_dataframe_setitem_from_masked_object():
ary = np.random.randn(100)
mask = np.zeros(100, dtype=bool)
mask[:20] = True
np.random.shuffle(mask)
ary[mask] = np.nan
test1_null = Series(ary, nan_as_null=True)
assert(test1_null.has_null_mask)
assert(test1_null.null_count == 20)
test1_nan = Series(ary, nan_as_null=False)
assert(test1_nan.null_count == 0)
test2_null = DataFrame.from_pandas(pd.DataFrame({'a': ary}),
nan_as_null=True)
assert(test2_null['a'].has_null_mask)
assert(test2_null['a'].null_count == 20)
test2_nan = DataFrame.from_pandas(pd.DataFrame({'a': ary}),
nan_as_null=False)
assert(test2_nan['a'].null_count == 0)
gpu_ary = rmm.to_device(ary)
test3_null = Series(gpu_ary, nan_as_null=True)
assert(test3_null.has_null_mask)
assert(test3_null.null_count == 20)
test3_nan = Series(gpu_ary, nan_as_null=False)
assert(test3_nan.null_count == 0)
test4 = DataFrame()
lst = [1, 2, None, 4, 5, 6, None, 8, 9]
test4['lst'] = lst
assert(test4['lst'].has_null_mask)
assert(test4['lst'].null_count == 2)
def test_dataframe_column_name_indexing():
df = DataFrame()
data = np.asarray(range(10), dtype=np.int32)
df['a'] = data
df[1] = data
np.testing.assert_equal(df['a'].to_array(),
np.asarray(range(10), dtype=np.int32))
np.testing.assert_equal(df[1].to_array(),
np.asarray(range(10), dtype=np.int32))
pdf = pd.DataFrame()
nelem = 10
pdf['key1'] = np.random.randint(0, 5, nelem)
pdf['key2'] = np.random.randint(0, 3, nelem)
pdf[1] = np.arange(1, 1 + nelem)
pdf[2] = np.random.random(nelem)
df = DataFrame.from_pandas(pdf)
for i in range(1, len(pdf.columns)+1):
for idx in combinations(pdf.columns, i):
assert(pdf[list(idx)].equals(df[list(idx)].to_pandas()))
# test for only numeric columns
df = pd.DataFrame()
for i in range(0, 10):
df[i] = range(nelem)
gdf = DataFrame.from_pandas(df)
assert_eq(gdf, df)
def test_kernel_shallow_copy():
pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=['a', 'b', 'c'])
gdf = DataFrame.from_pandas(pdf)
cdf = gdf.copy(deep=False)
sr = gdf['a']
add_one[1, len(sr)](sr.to_gpu_array())
assert_eq(gdf, cdf)
def test_kernel_deep_copy():
pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=['a', 'b', 'c'])
gdf = DataFrame.from_pandas(pdf)
cdf = gdf.copy(deep=True)
sr = gdf['b']
add_one[1, len(sr)](sr.to_gpu_array())
assert not gdf.to_string().split() == cdf.to_string().split()
def test_cudf_dataframe_copy(copy_fn, ncols, data_type):
pdf = pd.DataFrame()
for i in range(ncols):
pdf[chr(i+ord('a'))] = pd.Series(np.random.randint(0, 1000, 20))\
.astype(data_type)
df = DataFrame.from_pandas(pdf)
copy_df = copy_fn(df)
assert_eq(df, copy_df)
def test_dataframe_copy_shallow():
pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=['a', 'b', 'c'])
gdf = DataFrame.from_pandas(pdf)
copy_pdf = pdf.copy(deep=False)
copy_gdf = gdf.copy(deep=False)
copy_pdf['b'] = [0, 0, 0]
copy_gdf['b'] = [0, 0, 0]
assert_eq(pdf['b'], copy_pdf['b'])
assert_eq(gdf['b'], copy_gdf['b'])
def test_kernel_deep_copy():
pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=['a', 'b', 'c'])
gdf = DataFrame.from_pandas(pdf)
cdf = gdf.copy(deep=True)
sr = gdf['b']
# column.to_gpu_array calls to_dense_buffer which returns a copy
# need to access buffer directly and then call gpu_array
add_one[1, len(sr)](sr.data.to_gpu_array())
assert not gdf.to_string().split() == cdf.to_string().split()
def test_dataframe_deep_copy_and_insert(copy_parameters):
pdf = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]],
columns=['a', 'b', 'c'])
gdf = DataFrame.from_pandas(pdf)
copy_pdf = copy_parameters['fn'](pdf)
copy_gdf = copy_parameters['fn'](gdf)
copy_pdf['b'] = [0, 0, 0]
copy_gdf['b'] = [0, 0, 0]
pdf_is_equal = np.array_equal(pdf['b'].values, copy_pdf['b'].values)
gdf_is_equal = np.array_equal(gdf['b'].to_array(),
copy_gdf['b'].to_array())
assert pdf_is_equal == copy_parameters['expected_equality']
assert gdf_is_equal == copy_parameters['expected_equality']
def test_cudf_dataframe_copy_then_insert(copy_fn, ncols, data_type):
pdf = pd.DataFrame()
for i in range(ncols):
pdf[chr(i+ord('a'))] = pd.Series(np.random.randint(0, 1000, 20))\
.astype(data_type)
df = DataFrame.from_pandas(pdf)
copy_df = copy_fn(df)
copy_pdf = copy_fn(pdf)
copy_df['aa'] = pd.Series(np.random.randint(0, 1000, 20)).astype(data_type)
copy_pdf['aa'] = pd.Series(np.random.randint(0, 1000, 20))\
.astype(data_type)
assert not copy_pdf.to_string().split() == pdf.to_string().split()
assert not copy_df.to_string().split() == df.to_string().split()
def test_dataframe_append_empty():
pdf = pd.DataFrame({
"key": [1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4],
"value": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
})
gdf = DataFrame.from_pandas(pdf)
gdf['newcol'] = 100
pdf['newcol'] = 100
assert len(gdf['newcol']) == len(pdf)
assert len(pdf['newcol']) == len(pdf)
pd.testing.assert_frame_equal(gdf.to_pandas(), pdf)
def test_dataframe_deep_copy_and_insert(copy_parameters):
pdf = pd.DataFrame(
[[1, 2, 3], [4, 5, 6], [7, 8, 9]], columns=["a", "b", "c"]
)
gdf = DataFrame.from_pandas(pdf)
copy_pdf = copy_parameters["fn"](pdf)
copy_gdf = copy_parameters["fn"](gdf)
copy_pdf["b"] = [0, 0, 0]
copy_gdf["b"] = [0, 0, 0]
pdf_is_equal = np.array_equal(pdf["b"].values, copy_pdf["b"].values)
gdf_is_equal = np.array_equal(
gdf["b"].to_array(), copy_gdf["b"].to_array()
)
assert pdf_is_equal == copy_parameters["expected_equality"]
assert gdf_is_equal == copy_parameters["expected_equality"]
def test_dataframe_shape():
pdf = pd.DataFrame({'a': [0, 1, 2, 3], 'b': [0.1, 0.2, None, 0.3]})
gdf = DataFrame.from_pandas(pdf)
assert pdf.shape == gdf.shape
def test_dataframe_boolean_mask_with_None():
pdf = pd.DataFrame({'a': [0, 1, 2, 3], 'b': [0.1, 0.2, None, 0.3]})
gdf = DataFrame.from_pandas(pdf)
pdf_masked = pdf[[True, False, True, False]]
gdf_masked = gdf[[True, False, True, False]]
assert pdf_masked.to_string().split() == gdf_masked.to_string().split()
