def test_empty_weight_mapping(self):
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
with pytest.raises(ValueError):
params["ord_dict"]["Size"] = None
encoder = EncodeData(train_df=train_csv,
target_label="Price",
params=params)
encoder.encode()
def test_mapping(self):
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
encoder = EncodeData(train_df=train_csv,
target_label="Price",
params=params)
train = encoder.encode()
assert train[0]["ProfessionEncoded"].nunique() == 3
assert train[0]["ProfessionEncoded"][2] == 3
assert Counter(params["ord_dict"]["Profession"].values()) == Counter(
train[0]["ProfessionEncoded"].unique())
def test_ignore_cat_col():
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
params = {
"train_df": train_csv,
"target_label": "Price",
"cat_cols": ["Profession"],
"ord_dict": ord_dict,
"one_hot": True,
}
encoder = EncodeData()
encoder.encode(params=params)
assert "Profession_HOD" not in params["train_df"].columns
def test_one_hot_encoding():
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
params = {
"train_df": train_csv,
"target_label": "Price",
"cat_cols": ["Test", "Labels"],
"ord_dict": ord_dict,
"one_hot": True,
}
encoder = EncodeData()
encoder.encode(params=params)
assert "Test_Tata" in params["train_df"].columns
assert params["train_df"]["Test_Tata"][1] == 1
def test_empty_weight_mapping():
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
train_csv.drop(["Price"], axis=1, inplace=True)
ord_dict1 = ord_dict.copy()
ord_dict1["Size"] = None
params = {
"train_df": train_csv,
"target_label": "Price",
"ord_dict": ord_dict1,
}
with pytest.raises(ValueError):
encoder = EncodeData()
encoder.encode(params=params)
def test_mapping():
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
train_csv.drop(["Price"], axis=1, inplace=True)
params = {
"train_df": train_csv,
"target_label": "Price",
"ord_dict": ord_dict,
}
encoder = EncodeData()
encoder.encode(params=params)
assert params["train_df"]["ProfessionEncoded"].nunique() == 3
assert params["train_df"]["ProfessionEncoded"][2] == 3
assert Counter(params["ord_dict"]["Profession"].values()) == Counter(
params["train_df"]["ProfessionEncoded"].unique())
def test_warning():
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
params = {"train_df": train_csv, "ord_dict": ord_dict}
with pytest.warns(UserWarning):
encoder = EncodeData()
encoder.encode(params=params)
def test_empty_df():
params = {"target_label": "Price", "ord_dict": ord_dict}
with pytest.raises(ValueError):
encoder = EncodeData()
encoder.encode(params=params)
from preprocessy.encoding import EncodeData
import pandas as pd
ord_dict = {"Profession": {"Student": 1, "Teacher": 2, "HOD": 3}}
params = {"ord_dict": ord_dict}
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
# print(train_csv.dtypes)
# train_csv = train_csv.drop(['Unnamed: 5','Unnamed: 6'],axis=1)
k = EncodeData(train_df=train_csv, params=params)
train = k.encode()
print(train)
def test_warning(self):
train_csv = pd.read_csv("datasets/encoding/testnew.csv")
with pytest.warns(UserWarning):
encoder = EncodeData(train_df=train_csv, params=params)
encoder.encode()
def test_empty_df(self):
with pytest.raises(ValueError):
encoder = EncodeData(target_label="Price", params=params)
encoder.encode()