def test_mixed_inner_concat():
df, df2 = generate_dfs()
df3 = df.copy()
mixed_dfs = [from_pandas(df, 2), from_pandas(df2, 2), df3]
with pytest.raises(NotImplementedError):
rdf.concat(mixed_dfs, join="inner")
def test_ray_concat_on_column():
df, df2 = generate_dfs()
ray_df, ray_df2 = from_pandas(df, 2), from_pandas(df2, 2)
assert ray_df_equals_pandas(pd.concat([ray_df, ray_df2], axis=1),
pandas.concat([df, df2], axis=1))
assert ray_df_equals_pandas(pd.concat([ray_df, ray_df2], axis="columns"),
pandas.concat([df, df2], axis="columns"))
def test_ray_concat_on_column():
df, df2 = generate_dfs()
ray_df, ray_df2 = from_pandas(df, 2), from_pandas(df2, 2)
with pytest.raises(NotImplementedError):
rdf.concat([ray_df, ray_df2], axis=1)
with pytest.raises(NotImplementedError):
rdf.concat([ray_df, ray_df2], axis="columns")
def test_ray_concat_on_index():
df, df2 = generate_dfs()
ray_df, ray_df2 = from_pandas(df, 2), from_pandas(df2, 2)
assert ray_df_equals_pandas(pd.concat([ray_df, ray_df2], axis='index'),
pandas.concat([df, df2], axis='index'))
assert ray_df_equals_pandas(pd.concat([ray_df, ray_df2], axis='rows'),
pandas.concat([df, df2], axis='rows'))
assert ray_df_equals_pandas(pd.concat([ray_df, ray_df2], axis=0),
pandas.concat([df, df2], axis=0))
def test_mixed_concat():
df, df2 = generate_dfs()
df3 = df.copy()
mixed_dfs = [from_pandas(df, 2), from_pandas(df2, 2), df3]
assert(ray_df_equals_pandas(pd.concat(mixed_dfs),
pandas.concat([df, df2, df3])))
def merge_set(ray_df):
# Merge
ray_payments = pd.DataFrame({'num':[1, 2, 3, 4, 5, 6],
'payment_name':['Credit Card', 'Cash', 'No Charge',
'Dispute', 'Unknown', 'Voided trip']})
ray_df2 = ray_df.merge(ray_payments, left_on="payment_type", right_on="num")
# Groupby on Merge
ray2_groupby = ray_df2.groupby(ray_df2.payment_name)
# Ray does not support getting column from groupby below
# result = ray2_groupby.tip_amount.mean()
# Boolean correlation
ray_bool1 = ray_df2.tip_amount == 0
ray_bool2 = ray_df2.payment_name == 'Cash'
ray_bools = pd.concat([ray_bool1, ray_bool2], axis=1)
print(' new DataFrame finished. Result:')
print(ray_payments)
ray_df2 = ray_df.merge(ray_payments, left_on="payment_type", right_on="num")
print(' merge finished. Result:')
print(ray_df2.head(3))
ray2_groupby = ray_df2.groupby(ray_df2.payment_name)
print(' groupby on merge finished. Result:')
print(ray2_groupby.head(3))
# Ray does not support getting column from groupby below
# result = ray2_groupby.tip_amount.mean()
# print(' mean on groupby finished. Result:')
# print(result)
ray_bool1 = ray_df2.tip_amount == 0
ray_bool2 = ray_df2.payment_name == 'Cash'
print(' booleans finished. Result:')
print(ray_bool1.head(3))
ray_bools = pd.concat([ray_bool1, ray_bool2], axis=1)
print(' concat of booleans finished. Result:')
print(ray_bools.head(3))
# Ray does not support correlation
# result = ray_bools.corr()
# print(' correlation finished. Result:')
# print(result)
print(' Set of merge tests finished.')
def test_invalid_axis_errors():
df, df2 = generate_dfs()
ray_df, ray_df2 = from_pandas(df, 2), from_pandas(df2, 2)
with pytest.raises(ValueError):
pd.concat([ray_df, ray_df2], axis=2)
def test_ray_concat():
df, df2 = generate_dfs()
ray_df, ray_df2 = from_pandas(df, 2), from_pandas(df2, 2)
assert ray_df_equals_pandas(pd.concat([ray_df, ray_df2]),
pandas.concat([df, df2]))
def test_df_concat():
df, df2 = generate_dfs()
assert(ray_df_equals_pandas(pd.concat([df, df2]),
pandas.concat([df, df2])))
