def test_dataframe_join_cats():
lhs = DataFrame()
lhs['a'] = pd.Categorical(list('aababcabbc'), categories=list('abc'))
lhs['b'] = bb = np.arange(len(lhs))
lhs = lhs.set_index('a')
rhs = DataFrame()
rhs['a'] = pd.Categorical(list('abcac'), categories=list('abc'))
rhs['c'] = cc = np.arange(len(rhs))
rhs = rhs.set_index('a')
got = lhs.join(rhs)
expect = lhs.to_pandas().join(rhs.to_pandas())
# Note: pandas make a object Index after joining
pd.util.testing.assert_frame_equal(
got.sort_values(by='b').to_pandas().sort_index().reset_index(
drop=True), expect.reset_index(drop=True))
# Just do some rough checking here.
assert list(got.columns) == ['b', 'c']
assert len(got) > 0
assert set(got.index.values) & set('abc')
assert set(got['b']) & set(bb)
assert set(got['c']) & set(cc)
def test_dataframe_join_suffix():
np.random.seed(0)
df = DataFrame()
for k in 'abc':
df[k] = np.random.randint(0, 5, 5)
left = df.set_index('a')
right = df.set_index('c')
with pytest.raises(ValueError) as raises:
left.join(right)
raises.match("there are overlapping columns but lsuffix"
" and rsuffix are not defined")
got = left.join(right, lsuffix='_left', rsuffix='_right', sort=True)
# Get expected value
pddf = df.to_pandas()
expect = pddf.set_index('a').join(pddf.set_index('c'),
lsuffix='_left',
rsuffix='_right')
# Check
assert list(expect.columns) == list(got.columns)
assert np.all(expect.index.values == got.index.values)
for k in expect.columns:
_check_series(expect[k].fillna(-1), got[k].fillna(-1))
def test_df_cat_sort_index():
df = DataFrame()
df['a'] = pd.Categorical(list('aababcabbc'), categories=list('abc'))
df['b'] = np.arange(len(df))
got = df.set_index('a').sort_index()
expect = df.to_pandas().set_index('a').sort_index()
assert list(expect.columns) == list(got.columns)
assert list(expect.index.values) == list(got.index.values)
np.testing.assert_array_equal(expect.index.values, got.index.values)
np.testing.assert_array_equal(expect['b'].values, got['b'].to_array())
def test_df_set_index_from_series():
df = DataFrame()
df['a'] = list(range(10))
df['b'] = list(range(0, 20, 2))
# Check set_index(Series)
df2 = df.set_index(df['b'])
assert list(df2.columns) == ['a', 'b']
sliced_strided = df2.loc[2:6]
print(sliced_strided)
assert len(sliced_strided) == 3
assert list(sliced_strided.index.values) == [2, 4, 6]
def test_nonmatching_index_setitem(nrows):
np.random.seed(0)
gdf = DataFrame()
gdf['a'] = np.random.randint(2147483647, size=nrows)
gdf['b'] = np.random.randint(2147483647, size=nrows)
gdf = gdf.set_index('b')
test_values = np.random.randint(2147483647, size=nrows)
gdf['c'] = test_values
assert (len(test_values) == len(gdf['c']))
assert (gdf['c'].to_pandas().equals(
Series(test_values).set_index(gdf._index).to_pandas()))
def test_df_cat_set_index():
df = DataFrame()
df["a"] = pd.Categorical(list("aababcabbc"), categories=list("abc"))
df["b"] = np.arange(len(df))
got = df.set_index("a")
pddf = df.to_pandas()
expect = pddf.set_index("a")
assert list(expect.columns) == list(got.columns)
assert list(expect.index.values) == list(got.index.values)
np.testing.assert_array_equal(expect.index.values, got.index.values)
np.testing.assert_array_equal(expect["b"].values, got["b"].to_array())
def test_df_set_index_from_name():
df = DataFrame()
df['a'] = list(range(10))
df['b'] = list(range(0, 20, 2))
# Check set_index(column_name)
df2 = df.set_index('b')
print(df2)
# 1 less column because 'b' is used as index
assert list(df2.columns) == ['a']
sliced_strided = df2.loc[2:6]
print(sliced_strided)
assert len(sliced_strided) == 3
assert list(sliced_strided.index.values) == [2, 4, 6]
def test_categorical_index():
pdf = pd.DataFrame()
pdf['a'] = [1, 2, 3]
pdf['index'] = pd.Categorical(['a', 'b', 'c'])
pdf = pdf.set_index('index')
gdf1 = DataFrame.from_pandas(pdf)
gdf2 = DataFrame()
gdf2['a'] = [1, 2, 3]
gdf2['index'] = pd.Categorical(['a', 'b', 'c'])
gdf2 = gdf2.set_index('index')
assert isinstance(gdf1.index, CategoricalIndex)
assert_eq(pdf, gdf1)
assert_eq(pdf.index, gdf1.index)
assert isinstance(gdf2.index, CategoricalIndex)
assert_eq(pdf, gdf2)
assert_eq(pdf.index, gdf2.index)
def test_categorical_index():
pdf = pd.DataFrame()
pdf["a"] = [1, 2, 3]
pdf["index"] = pd.Categorical(["a", "b", "c"])
initial_df = DataFrame.from_pandas(pdf)
pdf = pdf.set_index("index")
gdf1 = DataFrame.from_pandas(pdf)
gdf2 = DataFrame()
gdf2["a"] = [1, 2, 3]
gdf2["index"] = pd.Categorical(["a", "b", "c"])
assert_eq(initial_df.index, gdf2.index)
gdf2 = gdf2.set_index("index")
assert isinstance(gdf1.index, CategoricalIndex)
assert_eq(pdf, gdf1)
assert_eq(pdf.index, gdf1.index)
assert_eq(pdf.index.codes, gdf1.index.codes.to_array())
assert isinstance(gdf2.index, CategoricalIndex)
assert_eq(pdf, gdf2)
assert_eq(pdf.index, gdf2.index)
assert_eq(pdf.index.codes, gdf2.index.codes.to_array())