ЛММО. 9/24.6/11.6/7.Задача 6

Обучите модель, получите предсказания на тестовой выборке. Посчитайте метрику качества модели MAE на тестовых данных.

import pandas as pd
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_absolute_error

RANDOM_STATE = 42

df = pd.read_csv('real_estate_clean_cat.csv')
X = df.drop('price', axis=1)
y = df['price']

X_train, X_test, y_train, y_test = train_test_split(
    X, 
    y, 
    random_state=RANDOM_STATE)

cat_col_names = ['building_type', 'parking_place', 'rooms_number']
num_col_names = ['total_area',
                 'living_area',
                 'ceil_height',
                 'city_center_distance',
                 'years_after_repair']

## подготовка признаков (масштабирование и кодирование)

encoder = OneHotEncoder(drop='first', sparse=False)
X_train_ohe = encoder.fit_transform(X_train[cat_col_names])
X_test_ohe = encoder.transform(X_test[cat_col_names])

encoder_col_names = encoder.get_feature_names()

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train[num_col_names])
X_test_scaled = scaler.transform(X_test[num_col_names])

X_train_ohe = pd.DataFrame(X_train_ohe, columns=encoder_col_names)
X_test_ohe = pd.DataFrame(X_test_ohe, columns=encoder_col_names)

X_train_scaled = pd.DataFrame(X_train_scaled, columns=num_col_names)
X_test_scaled = pd.DataFrame(X_test_scaled, columns=num_col_names)

X_train = pd.concat([X_train_ohe, X_train_scaled], axis=1)
X_test = pd.concat([X_test_ohe, X_test_scaled], axis=1)

# инициализируйте модель линейной регрессии
model_lr  = LinearRegression()

# обучите модель на тренировочных данных
model_lr  = LinearRegression()
model_lr.fit(X_train, y_train)

# получите предсказания модели на тестовых данных 
# сохраните результат в переменную predictions
predictions = model_lr.predict(X_test)

# посчитайте среднюю абсолютную ошибку на тестовых данных и выведите её на экран
mae = mean_absolute_error(y_test, predictions)
print(f'MAE = {mae:.0f}')