def amazon_vd(base):
from verticapy.datasets import load_amazon
amazon = load_amazon(cursor=base.cursor)
yield amazon
with warnings.catch_warnings(record=True) as w:
drop(name="public.titanic", cursor=base.cursor)
def iris_vd(base):
from verticapy.datasets import load_iris
iris = load_iris(cursor=base.cursor)
yield iris
with warnings.catch_warnings(record=True) as w:
drop(name="public.iris", cursor=base.cursor)
def winequality_vd(base):
from verticapy.datasets import load_winequality
winequality = load_winequality(cursor=base.cursor)
yield winequality
with warnings.catch_warnings(record=True) as w:
drop(name="public.winequality", cursor=base.cursor)
def tr_data_vd(base):
base.cursor.execute("DROP TABLE IF EXISTS public.tr_data")
base.cursor.execute(
'CREATE TABLE IF NOT EXISTS public.tr_data(Id INT, transportation INT, gender VARCHAR, "owned cars" INT, cost VARCHAR, income CHAR(4))'
)
base.cursor.execute(
"INSERT INTO tr_data VALUES (1, 0, 'Male', 0, 'Cheap', 'Low')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (2, 0, 'Male', 1, 'Cheap', 'Med')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (3, 1, 'Female', 1, 'Cheap', 'Med')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (4, 0, 'Female', 0, 'Cheap', 'Low')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (5, 0, 'Male', 1, 'Cheap', 'Med')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (6, 1, 'Male', 0, 'Standard', 'Med')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (7, 1, 'Female', 1, 'Standard', 'Med')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (8, 2, 'Female', 1, 'Expensive', 'Hig')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (9, 2, 'Male', 2, 'Expensive', 'Med')")
base.cursor.execute(
"INSERT INTO tr_data VALUES (10, 2, 'Female', 2, 'Expensive', 'Hig')")
base.cursor.execute("COMMIT")
tr_data = vDataFrame(input_relation="public.tr_data", cursor=base.cursor)
yield tr_data
with warnings.catch_warnings(record=True) as w:
drop(name="public.tr_data", cursor=base.cursor)
def titanic_vd(base):
from verticapy.datasets import load_titanic
titanic = load_titanic(cursor=base.cursor)
yield titanic
with warnings.catch_warnings(record=True) as w:
drop(name="public.titanic", cursor=base.cursor)
def smart_meters_vd(base):
from verticapy.datasets import load_smart_meters
smart_meters = load_smart_meters(cursor=base.cursor)
yield smart_meters
with warnings.catch_warnings(record=True) as w:
drop(name="public.smart_meters", cursor=base.cursor)
def commodities_vd(base):
from verticapy.datasets import load_commodities
commodities = load_commodities(cursor=base.cursor)
yield commodities
with warnings.catch_warnings(record=True) as w:
drop(name="public.commodities", cursor=base.cursor)
def market_vd(base):
from verticapy.datasets import load_market
market = load_market(cursor=base.cursor)
yield market
with warnings.catch_warnings(record=True) as w:
drop(
name="public.market", cursor=base.cursor,
)
def amazon_vd(base):
from verticapy.datasets import load_amazon
amazon = load_amazon(cursor=base.cursor)
yield amazon
drop(
name="public.amazon",
cursor=base.cursor,
)
def iris_vd(base):
from verticapy.datasets import load_iris
iris = load_iris(cursor=base.cursor)
yield iris
drop(
name="public.iris",
cursor=base.cursor,
)
def commodities_vd(base):
from verticapy.datasets import load_commodities
commodities = load_commodities(cursor=base.cursor)
yield commodities
drop(
name="public.commodities",
cursor=base.cursor,
)
def airline_vd(base):
from verticapy.datasets import load_airline_passengers
airline = load_airline_passengers(cursor=base.cursor)
yield airline
with warnings.catch_warnings(record=True) as w:
drop(
name="public.airline_passengers",
cursor=base.cursor,
)
def gapminder_vd(base):
from verticapy.datasets import load_gapminder
gapminder = load_gapminder(cursor=base.cursor)
yield gapminder
with warnings.catch_warnings(record=True) as w:
drop(
name="public.gapminder",
cursor=base.cursor,
)
def pop_growth_vd(base):
from verticapy.datasets import load_pop_growth
pop_growth = load_pop_growth(cursor=base.cursor)
yield pop_growth
with warnings.catch_warnings(record=True) as w:
drop(
name="public.pop_growth",
cursor=base.cursor,
)
def world_vd(base):
from verticapy.datasets import load_world
cities = load_world(cursor=base.cursor)
yield cities
with warnings.catch_warnings(record=True) as w:
drop(
name="public.world",
cursor=base.cursor,
)
def test_create_verticapy_schema(self, base):
with warnings.catch_warnings(record=True) as w:
drop("verticapy", base.cursor, method="schema")
create_verticapy_schema(base.cursor)
base.cursor.execute(
"SELECT table_name FROM columns WHERE table_schema = 'verticapy' GROUP BY 1 ORDER BY 1;"
)
result = [elem[0] for elem in base.cursor.fetchall()]
assert result == ["attr", "models"]
drop("verticapy", base.cursor, method="schema")
def test_vDF_to_shp(self, cities_vd):
drop(name="public.cities_test")
cities_vd.to_shp("cities_test", "/home/dbadmin/", shape="Point")
vdf = read_shp("/home/dbadmin/cities_test.shp")
assert vdf.shape() == (202, 3)
try:
os.remove("/home/dbadmin/cities_test.shp")
os.remove("/home/dbadmin/cities_test.shx")
os.remove("/home/dbadmin/cities_test.dbf")
except:
pass
drop(name="public.cities_test")
def test_read_json(self, base):
with warnings.catch_warnings(record=True) as w:
drop(
"public.titanic_verticapy_test",
base.cursor,
)
result = read_json(
os.path.dirname(verticapy.__file__) +
"/tests/utilities/titanic-passengers.json",
base.cursor,
table_name="titanic_verticapy_test",
schema="public",
)
assert result.shape() == (891, 15)
drop("titanic_verticapy_test", base.cursor)
with warnings.catch_warnings(record=True) as w:
drop(
"v_temp_schema.titanic_verticapy_test",
base.cursor,
)
result = read_json(
os.path.dirname(verticapy.__file__) +
"/tests/utilities/titanic-passengers.json",
base.cursor,
table_name="titanic_verticapy_test",
)
assert result.shape() == (891, 15)
drop("v_temp_schema.titanic_verticapy_test", base.cursor)
def test_pandas_to_vertica(self, titanic_vd):
df = titanic_vd.to_pandas()
with warnings.catch_warnings(record=True) as w:
drop(
"titanic_pandas",
titanic_vd._VERTICAPY_VARIABLES_["cursor"],
)
vdf = pandas_to_vertica(
df=df,
cursor=titanic_vd._VERTICAPY_VARIABLES_["cursor"],
)
assert vdf.shape() == (1234, 14)
drop(
"titanic_pandas",
titanic_vd._VERTICAPY_VARIABLES_["cursor"],
)
def test_cochrane_orcutt(self, airline_vd):
airline_copy = airline_vd.copy()
airline_copy["passengers_bias"] = (airline_copy["passengers"]**2 -
50 * st.random())
drop("lin_cochrane_orcutt_model_test", method="model")
model = LinearRegression("lin_cochrane_orcutt_model_test")
model.fit(airline_copy, ["passengers_bias"], "passengers")
result = st.cochrane_orcutt(
model,
airline_copy,
ts="date",
prais_winsten=True,
)
assert result.coef_["coefficient"][0] == pytest.approx(
25.8582027191416, 1e-2)
assert result.coef_["coefficient"][1] == pytest.approx(
0.00123563974547625, 1e-2)
model.drop()
def bsk_data_vd(base):
base.cursor.execute("DROP TABLE IF EXISTS public.bsk_data")
base.cursor.execute(
"CREATE TABLE IF NOT EXISTS public.bsk_data(Id INT, col1 FLOAT, col2 FLOAT, col3 FLOAT, col4 FLOAT)"
)
base.cursor.execute("INSERT INTO bsk_data VALUES (1, 7.2, 3.6, 6.1, 2.5)")
base.cursor.execute("INSERT INTO bsk_data VALUES (2, 7.7, 2.8, 6.7, 2.0)")
base.cursor.execute("INSERT INTO bsk_data VALUES (3, 7.7, 3.0, 6.1, 2.3)")
base.cursor.execute("INSERT INTO bsk_data VALUES (4, 7.9, 3.8, 6.4, 2.0)")
base.cursor.execute("INSERT INTO bsk_data VALUES (5, 4.4, 2.9, 1.4, 0.2)")
base.cursor.execute("INSERT INTO bsk_data VALUES (6, 4.6, 3.6, 1.0, 0.2)")
base.cursor.execute("INSERT INTO bsk_data VALUES (7, 4.7, 3.2, 1.6, 0.2)")
base.cursor.execute("INSERT INTO bsk_data VALUES (8, 6.5, 2.8, 4.6, 1.5)")
base.cursor.execute("INSERT INTO bsk_data VALUES (9, 6.8, 2.8, 4.8, 1.4)")
base.cursor.execute("INSERT INTO bsk_data VALUES (10, 7.0, 3.2, 4.7, 1.4)")
base.cursor.execute("COMMIT")
bsk_data = vDataFrame(input_relation="public.bsk_data", cursor=base.cursor)
yield bsk_data
with warnings.catch_warnings(record=True) as w:
drop(name="public.bsk_data", cursor=base.cursor)
def test_vDF_to_shp(self, cities_vd):
with warnings.catch_warnings(record=True) as w:
drop(
name="public.cities_test",
cursor=cities_vd._VERTICAPY_VARIABLES_["cursor"],
)
cities_vd.to_shp("cities_test", "/home/dbadmin/", shape="Point")
vdf = read_shp("/home/dbadmin/cities_test.shp",
cities_vd._VERTICAPY_VARIABLES_["cursor"])
assert vdf.shape() == (202, 3)
try:
os.remove("/home/dbadmin/cities_test.shp")
os.remove("/home/dbadmin/cities_test.shx")
os.remove("/home/dbadmin/cities_test.dbf")
except:
pass
with warnings.catch_warnings(record=True) as w:
drop(
name="public.cities_test",
cursor=cities_vd._VERTICAPY_VARIABLES_["cursor"],
)
def test_read_csv(self, base):
with warnings.catch_warnings(record=True) as w:
drop(
"public.titanic_verticapy_test",
base.cursor,
)
result = read_csv(os.path.dirname(verticapy.__file__) +
"/data/titanic.csv",
base.cursor,
table_name="titanic_verticapy_test",
schema="public")
assert result.shape() == (1234, 14)
with warnings.catch_warnings(record=True) as w:
drop(
"v_temp_schema.titanic_verticapy_test",
base.cursor,
)
result = read_csv(
os.path.dirname(verticapy.__file__) + "/data/titanic.csv",
base.cursor,
table_name="titanic_verticapy_test",
)
assert result.shape() == (1234, 14)
drop("titanic_verticapy_test", base.cursor)
def bsk_data_vd():
bsk_data = load_dataset_num(table_name="bsk_data", schema="public")
yield bsk_data
drop(name="public.bsk_data", method="table")
def winequality_vd():
winequality = load_winequality()
yield winequality
drop(name="public.winequality", )
def winequality_vd(base):
from verticapy.datasets import load_winequality
winequality = load_winequality(cursor=base.cursor)
yield winequality
drop(name="public.winequality", cursor=base.cursor)
def amazon_vd():
amazon = load_amazon()
yield amazon
drop(name="public.amazon")
def iris_vd():
iris = load_iris()
yield iris
drop(name="public.iris", )
def titanic_vd():
titanic = load_titanic()
yield titanic
drop(name="public.titanic")
def market_vd():
market = load_market()
yield market
drop(name="public.market")