41 lines
1.7 KiB
Python
41 lines
1.7 KiB
Python
|
import pandas as pd
|
||
|
|
from sklearn.model_selection import train_test_split
|
||
|
|
from sklearn.tree import DecisionTreeRegressor
|
||
|
|
from sklearn.metrics import mean_squared_error
|
||
|
|
from sklearn.preprocessing import LabelEncoder
|
||
|
|
|
||
|
|
# Загрузка данных
|
||
|
|
data = pd.read_csv('economica.csv')
|
||
|
|
|
||
|
|
# Преобразование строковых значений в числовые
|
||
|
|
le = LabelEncoder()
|
||
|
|
data['country'] = le.fit_transform(data['country'])
|
||
|
|
|
||
|
|
# Определение признаков и целевой переменной
|
||
|
|
X = data[['country', 'year']]
|
||
|
|
y = data['oil_prices']
|
||
|
|
|
||
|
|
# Разделение данных на тренировочный и тестовый наборы
|
||
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.01, random_state=42)
|
||
|
|
|
||
|
|
# Создание и обучение дерева решений
|
||
|
|
clf = DecisionTreeRegressor(random_state=42)
|
||
|
|
clf.fit(X_train, y_train)
|
||
|
|
|
||
|
|
# Прогнозирование на тестовом наборе
|
||
|
|
y_pred = clf.predict(X_test)
|
||
|
|
|
||
|
|
# Оценка качества модели на тестовом наборе
|
||
|
|
mse = mean_squared_error(y_test, y_pred)
|
||
|
|
|
||
|
|
# Прогнозирование на оставшемся проценте данных
|
||
|
|
X_remaining = data.drop(X_train.index)
|
||
|
|
y_remaining_true = X_remaining['oil_prices']
|
||
|
|
X_remaining = X_remaining[['country', 'year']]
|
||
|
|
y_remaining_pred = clf.predict(X_remaining)
|
||
|
|
|
||
|
|
# Оценка качества модели на оставшемся проценте данных
|
||
|
|
mse_remaining = mean_squared_error(y_remaining_true, y_remaining_pred)
|
||
|
|
mse_remaining_percent = (mse_remaining / y.mean()) * 100
|
||
|
|
print(f'Среднеквадратичная ошибка на 1%: {mse_remaining}({mse_remaining_percent:.2f}%)')
|