IIS_2023_1/shadaev_anton_lab_2/main.py
2023-11-03 14:17:51 +04:00

67 lines
2.0 KiB
Python

from sklearn.linear_model import Lasso
from sklearn.ensemble import RandomForestRegressor
from sklearn.feature_selection import f_regression
from sklearn.preprocessing import MinMaxScaler
import numpy as np
np.random.seed(0)
# Генерация данных
size = 500
X = np.random.uniform(0, 1, (size, 15))
Y = (10 * np.sin(np.pi * X[:, 0] * X[:, 1]) + 20 * (X[:, 2] - .5) ** 2 +
10 * X[:, 3] + 5 * X[:, 4] ** 5 + np.random.normal(0, 1))
X[:, 10:] = X[:, :5] + np.random.normal(0, .025, (size, 5))
# Имена признаков
names = ["x%s" % i for i in range(1, 16)]
# Ранги признаков
ranks = {}
# Функция для расчета рангов
def calculate_ranks(method, X, Y):
if method == "Lasso":
model = Lasso(alpha=0.5)
elif method == "Random Forest":
model = RandomForestRegressor(n_estimators=100)
elif method == "f_regression":
f_scores, _ = f_regression(X, Y)
return dict(zip(names, f_scores))
model.fit(X, Y)
return dict(zip(names, model.coef_ if method == "Lasso" else model.feature_importances_))
# Ранг для каждого метода
for method in ["Lasso", "Random Forest", "f_regression"]:
ranks[method] = calculate_ranks(method, X, Y)
# Нормализация рангов
def create_normalized_rank_dict(ranks, names):
ranks = np.abs(ranks)
minmax = MinMaxScaler()
ranks = minmax.fit_transform(
np.array(ranks).reshape(15, 1)).ravel()
ranks = map(lambda x: round(x, 2), ranks)
return dict(zip(names, ranks))
# Среднее значение рангов
mean = {}
for key, value in ranks.items():
for item in value.items():
if (item[0] not in mean):
mean[item[0]] = 0
mean[item[0]] += item[1]
# Сортируем признаки по среднему значению рангов
sorted_mean = sorted(mean.items(), key=lambda x: x[1], reverse=True)
# Вывод признаков и их рангов
result = {}
for item in sorted_mean:
result[item[0]] = item[1]
print(f'{item[0]}: {item[1]}')