Sample of the house class for Kaggle housing prices in Iowa blog post

House class.py

class House():
    def __init__(self, train_data_file, test_data_file):
        train = pd.read_csv(train_data_file)
        test = pd.read_csv(test_data_file)
        self.all = pd.concat([train,test], ignore_index=True)
        self.all['test'] = self.all.SalePrice.isnull()

    def train(self):
        return(self.all[~self.all['test']])

    def test(self):
        return(self.all[self.all['test']])

    def log_transform(self, variable):
        plt.figure(figsize=(10,5))
        plt.subplot(1,2,1)
        sns.distplot(variable, bins=50)
        plt.title('Original')
        plt.subplot(1,2,2)
        sns.distplot(np.log1p(variable), bins=50)
        plt.title('Log transformed')
        plt.tight_layout()