def test_empty_df():
df = pd.DataFrame(index=["a", "b"])
df_is_empty(df)
tm.assert_index_equal(df.index, pd.Index(["a", "b"]))
assert len(df.columns) == 0
df = pd.DataFrame(columns=["a", "b"])
df_is_empty(df)
assert len(df.index) == 0
tm.assert_index_equal(df.columns, pd.Index(["a", "b"]))
df = pd.DataFrame()
df_is_empty(df)
assert len(df.index) == 0
assert len(df.columns) == 0
df = pd.DataFrame(index=["a", "b"])
df_is_empty(df)
tm.assert_index_equal(df.index, pd.Index(["a", "b"]))
assert len(df.columns) == 0
df = pd.DataFrame(columns=["a", "b"])
df_is_empty(df)
assert len(df.index) == 0
tm.assert_index_equal(df.columns, pd.Index(["a", "b"]))
df = pd.DataFrame()
df_is_empty(df)
assert len(df.index) == 0
assert len(df.columns) == 0
df = pd.DataFrame()
pd_df = pandas.DataFrame()
df["a"] = [1, 2, 3, 4, 5]
pd_df["a"] = [1, 2, 3, 4, 5]
df_equals(df, pd_df)
df = pd.DataFrame()
pd_df = pandas.DataFrame()
df["a"] = list("ABCDEF")
pd_df["a"] = list("ABCDEF")
df_equals(df, pd_df)
df = pd.DataFrame()
pd_df = pandas.DataFrame()
df["a"] = pd.Series([1, 2, 3, 4, 5])
pd_df["a"] = pandas.Series([1, 2, 3, 4, 5])
df_equals(df, pd_df)
def test_unique():
modin_result = pd.unique([2, 1, 3, 3])
pandas_result = pandas.unique([2, 1, 3, 3])
assert_array_equal(modin_result, pandas_result)
modin_result = pd.unique(pd.Series([2] + [1] * 5))
pandas_result = pandas.unique(pandas.Series([2] + [1] * 5))
assert_array_equal(modin_result, pandas_result)
modin_result = pd.unique(
pd.Series([pd.Timestamp("20160101"), pd.Timestamp("20160101")])
)
pandas_result = pandas.unique(
pandas.Series([pandas.Timestamp("20160101"), pandas.Timestamp("20160101")])
)
assert_array_equal(modin_result, pandas_result)
modin_result = pd.unique(
pd.Series(
[
pd.Timestamp("20160101", tz="US/Eastern"),
pd.Timestamp("20160101", tz="US/Eastern"),
]
)
)
pandas_result = pandas.unique(
pandas.Series(
[
pandas.Timestamp("20160101", tz="US/Eastern"),
pandas.Timestamp("20160101", tz="US/Eastern"),
]
)
)
assert_array_equal(modin_result, pandas_result)
modin_result = pd.unique(
pd.Index(
[
pd.Timestamp("20160101", tz="US/Eastern"),
pd.Timestamp("20160101", tz="US/Eastern"),
]
)
)
pandas_result = pandas.unique(
pandas.Index(
[
pandas.Timestamp("20160101", tz="US/Eastern"),
pandas.Timestamp("20160101", tz="US/Eastern"),
]
)
)
assert_array_equal(modin_result, pandas_result)
modin_result = pd.unique(pd.Series(pd.Categorical(list("baabc"))))
pandas_result = pandas.unique(pandas.Series(pandas.Categorical(list("baabc"))))
assert_array_equal(modin_result, pandas_result)
def test_mixed_type_column():
df = pd.DataFrame({"A": [1.2, "xy", 4], "B": [3, 4, 5]})
df = df.set_index(pd.Index(["yz", 7, 3.2]))
view = SpreadsheetWidget(df=df)
view._handle_view_msg_helper({
"type": "change_sort",
"sort_field": "A",
"sort_ascending": True
})
view._handle_view_msg_helper({
"type": "show_filter_dropdown",
"field": "A",
"search_val": None
})
def test_join(test_data, test_data2):
modin_df = pd.DataFrame(
test_data,
columns=["col{}".format(i) for i in range(test_data.shape[1])],
index=pd.Index([i for i in range(1, test_data.shape[0] + 1)],
name="key"),
)
pandas_df = pandas.DataFrame(
test_data,
columns=["col{}".format(i) for i in range(test_data.shape[1])],
index=pandas.Index([i for i in range(1, test_data.shape[0] + 1)],
name="key"),
)
modin_df2 = pd.DataFrame(
test_data2,
columns=["col{}".format(i) for i in range(test_data2.shape[1])],
index=pd.Index([i for i in range(1, test_data2.shape[0] + 1)],
name="key"),
)
pandas_df2 = pandas.DataFrame(
test_data2,
columns=["col{}".format(i) for i in range(test_data2.shape[1])],
index=pandas.Index([i for i in range(1, test_data2.shape[0] + 1)],
name="key"),
)
hows = ["inner", "left", "right", "outer"]
ons = ["col33", "col34"]
sorts = [False, True]
for i in range(4):
for j in range(2):
modin_result = modin_df.join(
modin_df2,
how=hows[i],
on=ons[j],
sort=sorts[j],
lsuffix="_caller",
rsuffix="_other",
)
pandas_result = pandas_df.join(
pandas_df2,
how=hows[i],
on=ons[j],
sort=sorts[j],
lsuffix="_caller",
rsuffix="_other",
)
df_equals(modin_result, pandas_result)
frame_data = {
"col1": [0, 1, 2, 3],
"col2": [4, 5, 6, 7],
"col3": [8, 9, 0, 1],
"col4": [2, 4, 5, 6],
}
modin_df = pd.DataFrame(frame_data)
pandas_df = pandas.DataFrame(frame_data)
frame_data2 = {"col5": [0], "col6": [1]}
modin_df2 = pd.DataFrame(frame_data2)
pandas_df2 = pandas.DataFrame(frame_data2)
join_types = ["left", "right", "outer", "inner"]
for how in join_types:
modin_join = modin_df.join(modin_df2, how=how)
pandas_join = pandas_df.join(pandas_df2, how=how)
df_equals(modin_join, pandas_join)
frame_data3 = {"col7": [1, 2, 3, 5, 6, 7, 8]}
modin_df3 = pd.DataFrame(frame_data3)
pandas_df3 = pandas.DataFrame(frame_data3)
join_types = ["left", "outer", "inner"]
for how in join_types:
modin_join = modin_df.join([modin_df2, modin_df3], how=how)
pandas_join = pandas_df.join([pandas_df2, pandas_df3], how=how)
df_equals(modin_join, pandas_join)
def test_merge(test_data, test_data2):
modin_df = pd.DataFrame(
test_data,
columns=["col{}".format(i) for i in range(test_data.shape[1])],
index=pd.Index([i for i in range(1, test_data.shape[0] + 1)],
name="key"),
)
pandas_df = pandas.DataFrame(
test_data,
columns=["col{}".format(i) for i in range(test_data.shape[1])],
index=pandas.Index([i for i in range(1, test_data.shape[0] + 1)],
name="key"),
)
modin_df2 = pd.DataFrame(
test_data2,
columns=["col{}".format(i) for i in range(test_data2.shape[1])],
index=pd.Index([i for i in range(1, test_data2.shape[0] + 1)],
name="key"),
)
pandas_df2 = pandas.DataFrame(
test_data2,
columns=["col{}".format(i) for i in range(test_data2.shape[1])],
index=pandas.Index([i for i in range(1, test_data2.shape[0] + 1)],
name="key"),
)
hows = ["left", "inner"]
ons = ["col33", ["col33", "col34"]]
sorts = [False, True]
for i in range(2):
for j in range(2):
modin_result = modin_df.merge(modin_df2,
how=hows[i],
on=ons[j],
sort=sorts[j])
pandas_result = pandas_df.merge(pandas_df2,
how=hows[i],
on=ons[j],
sort=sorts[j])
df_equals(modin_result, pandas_result)
modin_result = modin_df.merge(
modin_df2,
how=hows[i],
left_on="key",
right_on="key",
sort=sorts[j],
)
pandas_result = pandas_df.merge(
pandas_df2,
how=hows[i],
left_on="key",
right_on="key",
sort=sorts[j],
)
df_equals(modin_result, pandas_result)
# Test for issue #1771
modin_df = pd.DataFrame({"name": np.arange(40)})
modin_df2 = pd.DataFrame({"name": [39], "position": [0]})
pandas_df = pandas.DataFrame({"name": np.arange(40)})
pandas_df2 = pandas.DataFrame({"name": [39], "position": [0]})
modin_result = modin_df.merge(modin_df2, on="name", how="inner")
pandas_result = pandas_df.merge(pandas_df2, on="name", how="inner")
df_equals(modin_result, pandas_result)
frame_data = {
"col1": [0, 1, 2, 3],
"col2": [4, 5, 6, 7],
"col3": [8, 9, 0, 1],
"col4": [2, 4, 5, 6],
}
modin_df = pd.DataFrame(frame_data)
pandas_df = pandas.DataFrame(frame_data)
frame_data2 = {"col1": [0, 1, 2], "col2": [1, 5, 6]}
modin_df2 = pd.DataFrame(frame_data2)
pandas_df2 = pandas.DataFrame(frame_data2)
join_types = ["outer", "inner"]
for how in join_types:
# Defaults
modin_result = modin_df.merge(modin_df2, how=how)
pandas_result = pandas_df.merge(pandas_df2, how=how)
df_equals(modin_result, pandas_result)
# left_on and right_index
modin_result = modin_df.merge(modin_df2,
how=how,
left_on="col1",
right_index=True)
pandas_result = pandas_df.merge(pandas_df2,
how=how,
left_on="col1",
right_index=True)
df_equals(modin_result, pandas_result)
# left_index and right_on
modin_result = modin_df.merge(modin_df2,
how=how,
left_index=True,
right_on="col1")
pandas_result = pandas_df.merge(pandas_df2,
how=how,
left_index=True,
right_on="col1")
df_equals(modin_result, pandas_result)
# left_on and right_on col1
modin_result = modin_df.merge(modin_df2,
how=how,
left_on="col1",
right_on="col1")
pandas_result = pandas_df.merge(pandas_df2,
how=how,
left_on="col1",
right_on="col1")
df_equals(modin_result, pandas_result)
# left_on and right_on col2
modin_result = modin_df.merge(modin_df2,
how=how,
left_on="col2",
right_on="col2")
pandas_result = pandas_df.merge(pandas_df2,
how=how,
left_on="col2",
right_on="col2")
df_equals(modin_result, pandas_result)
# left_index and right_index
modin_result = modin_df.merge(modin_df2,
how=how,
left_index=True,
right_index=True)
pandas_result = pandas_df.merge(pandas_df2,
how=how,
left_index=True,
right_index=True)
df_equals(modin_result, pandas_result)
# Named Series promoted to DF
s = pd.Series(frame_data2.get("col1"))
with pytest.raises(ValueError):
modin_df.merge(s)
s = pd.Series(frame_data2.get("col1"), name="col1")
df_equals(modin_df.merge(s), modin_df.merge(modin_df2[["col1"]]))
with pytest.raises(TypeError):
modin_df.merge("Non-valid type")
def test_asof_large(lookup, subset):
data = test_data["float_nan_data"]
index = list(range(NROWS))
modin_where = pd.Index(lookup)
pandas_where = pandas.Index(lookup)
compare_asof(data, index, modin_where, pandas_where, subset)
-0.815727,
0.785291,
1.180861,
],
1: [
1.272731,
1.272731,
1.272731,
1.272731,
0.638028,
0.638028,
0.638028,
0.638028,
-0.683739,
-0.683739,
-0.683739,
-0.683739,
-1.227020,
-1.227020,
-1.227020,
-1.227020,
],
},
index=pd.Index(
data=[1, 1, 0, 0, 1, 1, 0, 0, 3, 3, 2, 2, 3, 3, 2, 2,], name="cluster"
),
)
print(df)
df1 = df.sort_values(by=['distance'])
print(df1)
