def missing_inputation():
# Load dataset
data = pd.read_csv("creditApprovalUCI.csv")
# Separate into train and test sets
X_train, X_test, y_train, y_test = train_test_split(
data.drop("A16", axis=1), data["A16"], test_size=0.3, random_state=0
)
# Set up the imputer
median_imputer = MeanMedianImputer(
imputation_method="median", variables=["A2", "A3", "A8", "A11", "A15"]
)
# fit the imputer
median_imputer.fit(X_train)
# transform the data
X_train = median_imputer.transform(X_train)
X_test = median_imputer.transform(X_test)
def test_non_fitted_error(df_na):
with pytest.raises(NotFittedError):
imputer = MeanMedianImputer()
imputer.transform(df_na)
missing_ind = AddMissingIndicator(variables=vars_with_na)
missing_ind.fit(X_train)
X_train = missing_ind.transform(X_train)
X_test = missing_ind.transform(X_test)
# check the binary missing indicator variables
X_train[['LotFrontage_na', 'MasVnrArea_na', 'GarageYrBlt_na']].head()
# %% # %% Missing values -- Numerical -- add missing indicator.
mean_imputer = MeanMedianImputer(
imputer_method='mean',
variables=vars_with_na
)
mean_imputer.fit(X_train)
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.