def test_error_if_df_contains_negative_values(df_vartypes):
# test error when data contains negative values
df_neg = df_vartypes.copy()
df_neg.loc[1, "Age"] = -1
# test case 5: when variable contains negative value, fit
with pytest.raises(ValueError):
transformer = LogTransformer()
transformer.fit(df_neg)
# test case 6: when variable contains negative value, transform
with pytest.raises(ValueError):
transformer = LogTransformer()
transformer.fit(df_vartypes)
transformer.transform(df_neg)
def test_non_fitted_error(df_vartypes):
with pytest.raises(NotFittedError):
transformer = LogTransformer()
transformer.transform(df_vartypes)
def test_transform_raises_error_if_na_in_df(df_vartypes, df_na):
# test case 4: when dataset contains na, transform method
with pytest.raises(ValueError):
transformer = LogTransformer()
transformer.fit(df_vartypes)
transformer.transform(df_na[["Name", "City", "Age", "Marks", "dob"]])
print(mean_imputer.imputer_dict_)
X_train = mean_imputer.transform(X_train)
X_test = mean_imputer.transform(X_test)
# %% Varief whether there are missing value.
X_train[cat_vars_with_na].isnull().sum()
[var for var in cat_vars_with_na if X_test[var].isnull().sum() > 0]
#%% Temporal variables.
def elapsed_years(df, var):
df[var] = df['YrSold'] - df[var]
return df
for var in ['YearBuilt', 'YearRemodAdd', 'GarageYrBlt']：
X_train = elapsed_years(X_train, var)
X_test = elapsed_years(X_test, var)
# now we drop YrSold.
drop_features = DropFeatures(features_to_drop=['YrSold'])
X_train = mean_imputer.fit_transform(X_train)
X_test = mean_imputer.transform(X_test)
# %% Numerical variable -- transformation.
log_transformer = LogTransformer(
variables=["LotFrontage", "1stFlrSF", "GrLivArea"],
)
X_train = log_transformer.fit_transform(X_train)
X_test = log_transformer.transform(X_test)
# check that test set does not contain null values in the engineered variables
[var for var in ["LotFrontage", "1stFlrSF", "GrLivArea"] if X_test[var].isnull().sum() > 0]