def test_aggregate_csql():
ctx = Prosto("My Prosto")
facts_df = pd.DataFrame({
'A': ['a', 'a', 'b', 'b'],
'M': [1.0, 2.0, 3.0, 4.0],
'N': [4.0, 3.0, 2.0, 1.0]
})
groups_df = pd.DataFrame({'A': ['a', 'b', 'c']})
ctx.column_sql("TABLE Facts (A, M, N)", lambda **m: facts_df)
ctx.column_sql("TABLE Groups (A)", lambda **m: groups_df)
ctx.column_sql("LINK Facts (A) -> new_column -> Groups (A)")
ctx.column_sql("AGGREGATE Facts (M) -> new_column -> Groups (Aggregate)",
lambda x, bias, **model: x.sum() + bias, {"bias": 0.0})
assert ctx.get_table("Facts")
assert ctx.get_table("Groups")
assert ctx.get_column("Facts", "new_column")
ctx.run()
assert list(
ctx.get_table("Groups").get_series('Aggregate')) == [3.0, 7.0, 0.0]
def test_calc_csql():
#
# Test 2: function in-query
#
ctx = Prosto("My Prosto")
ctx.column_sql("TABLE My_table (A) FUNC lambda **m: pd.DataFrame({'A': [1, 2, 3]})")
ctx.column_sql("CALCULATE My_table (A) -> new_column FUNC lambda x: float(x)")
assert ctx.get_table("My_table")
assert ctx.get_column("My_table", "new_column")
ctx.run()
assert list(ctx.get_table("My_table").get_series('new_column')) == [1.0, 2.0, 3.0]
#
# Test 2: function by-reference
#
ctx = Prosto("My Prosto")
df = pd.DataFrame({'A': [1, 2, 3]}) # Use FUNC "lambda **m: df" (df cannot be resolved during population)
ctx.column_sql("TABLE My_table (A)", df)
ctx.column_sql("CALCULATE My_table (A) -> new_column", lambda x: float(x))
assert ctx.get_table("My_table")
assert ctx.get_column("My_table", "new_column")
ctx.run()
assert list(ctx.get_table("My_table").get_series('new_column')) == [1.0, 2.0, 3.0]
def test_roll_csql():
ctx = Prosto("My Prosto")
df = pd.DataFrame({'A': [1.0, 2.0, 3.0]})
ctx.column_sql("TABLE My_table (A)", lambda **m: df)
ctx.column_sql("ROLL My_table (A) -> new_column WINDOW 2",
lambda x: x.sum())
assert ctx.get_table("My_table")
assert ctx.get_column("My_table", "new_column")
ctx.run()
assert list(ctx.get_table("My_table").get_series('new_column')) == [
None, 3.0, 5.0
]
def test_link_csql():
ctx = Prosto("My Prosto")
facts_df = pd.DataFrame({'A': ['a', 'a', 'b', 'b']})
groups_df = pd.DataFrame({'A': ['a', 'b', 'c']})
ctx.column_sql("TABLE Facts (A)", lambda **m: facts_df)
ctx.column_sql("TABLE Groups (A)", lambda **m: groups_df)
ctx.column_sql("LINK Facts (A) -> new_column -> Groups (A)")
assert ctx.get_table("Facts")
assert ctx.get_table("Groups")
assert ctx.get_column("Facts", "new_column")
ctx.run()
assert list(ctx.get_table("Facts").get_series('new_column')) == [0, 0, 1, 1]
def test_csql_project():
ctx = Prosto("My Prosto")
facts_df = pd.DataFrame({'A': ['a', 'a', 'b', 'b']})
ctx.column_sql("TABLE Facts (A)", lambda **m: facts_df)
ctx.column_sql("PROJECT Facts (A) -> new_column -> Groups (A)")
assert ctx.get_table("Facts")
assert ctx.get_table("Groups")
assert ctx.get_column("Facts", "new_column")
ctx.run()
assert len(ctx.get_table("Groups").get_df()) == 2
assert len(ctx.get_table("Groups").get_df().columns) == 1
assert list(ctx.get_table("Facts").get_series('new_column')) == [0, 0, 1, 1]
def test_product_csql():
ctx = Prosto("My Prosto")
t1_df = pd.DataFrame({'A': [1.0, 2.0, 3.0]})
t2_df = pd.DataFrame({'B': ['x', 'y', 'z']})
ctx.column_sql("TABLE Table_1 (A)", lambda **m: t1_df)
ctx.column_sql("TABLE Table_2 (B)", lambda **m: t2_df)
ctx.column_sql("PRODUCT Table_1; Table_2 -> t1; t2 -> Product")
assert ctx.get_table("Product")
ctx.run()
product = ctx.get_table("Product")
assert len(product.get_df().columns) == 2
assert len(product.get_df()) == 9
assert product.get_df().columns.to_list() == ["t1", "t2"]
def test_filter_csql():
ctx = Prosto("My Prosto")
base_df = pd.DataFrame({'A': [1.0, 2.0, 3.0], 'B': ['x', 'yy', 'zzz']})
ctx.column_sql("TABLE Base (A, B)", lambda **m: base_df)
ctx.column_sql("CALCULATE Base (A, B) -> filter_column", lambda x, param:
(x['A'] > param) & (len(x['B']) < 3), {"param": 1.5})
ctx.column_sql("FILTER Base (filter_column) -> super -> Filtered")
assert ctx.get_table("Base")
assert ctx.get_table("Filtered")
ctx.run()
assert list(ctx.get_table("Filtered").get_series('super')) == [1]
#
# Filter with a predicate function and no explicit calculate column
#
ctx = Prosto("My Prosto")
base_df = pd.DataFrame({'A': [1.0, 2.0, 3.0], 'B': ['x', 'yy', 'zzz']})
ctx.column_sql("TABLE Base (A, B)", base_df)
ctx.column_sql("FILTER Base (A, B) -> super -> Filtered", lambda x, param:
(x['A'] > param) & (len(x['B']) < 3), {"param": 1.5})
assert ctx.get_table("Base")
assert ctx.get_table("Filtered")
ctx.run()
assert list(ctx.get_table("Filtered").get_series('super')) == [1]
def test_filter_calculate():
"""
Test resolution of inherited attributes which do not exist in the filtered table but must be automatically merged from the base table.
Scenario: populate, filter, calculate column in filtered table using column in base table (which has to be inherited)
"""
ctx = Prosto("My Prosto")
base_df = pd.DataFrame({'A': [1.0, 2.0, 3.0], 'B': ['x', 'yy', 'zzz']})
ctx.column_sql("TABLE Base (A, B)", lambda **m: base_df)
ctx.column_sql("FILTER Base (A) -> super -> Filtered", lambda x: x < 3.0)
ctx.column_sql(
"CALCULATE Filtered (B) -> filter_column", # <-- Here we use columns A and B which exist only in the base table
lambda x: len(x))
ctx.run()
assert ctx.get_table("Filtered").get_series('filter_column').to_list() == [
1, 2
]
def test_filter_project():
"""
Test resolution of inherited attributes which do not exist in the filtered table but must be automatically merged from the base table.
Scenario: populate, filter, project the filtered table using a column in the base table (which has to be inherited)
"""
ctx = Prosto("My Prosto")
base_df = pd.DataFrame({
'A': [1.0, 2.0, 3.0, 4.0],
'B': ['x', 'x', 'y', 'zzz']
})
ctx.column_sql("TABLE Base(A, B)", lambda **m: base_df)
ctx.column_sql("FILTER Base (A, B) -> super -> Filtered",
lambda x: x['A'] < 4.0)
ctx.column_sql("FILTER Filtered (A) -> super -> Filtered_2",
lambda x: x < 3.0)
ctx.column_sql(
"PROJECT Filtered_2 (B) -> new_column -> Groups(C)"
) # <-- Here we use columns which exist only in the base table
ctx.run()
assert ctx.get_table("Groups").get_series('C').to_list() == ['x']
