76 lines
2.4 KiB
Python
76 lines
2.4 KiB
Python
|
import numpy as np
|
||
|
|
from sklearn.ensemble import RandomForestRegressor
|
||
|
|
from sklearn.feature_selection import f_regression
|
||
|
|
from sklearn.linear_model import Ridge
|
||
|
|
from sklearn.preprocessing import MinMaxScaler
|
||
|
|
|
||
|
|
|
||
|
|
def rank_to_dict(ranks, names):
|
||
|
|
ranks = np.abs(ranks)
|
||
|
|
minmax = MinMaxScaler()
|
||
|
|
ranks = minmax.fit_transform(np.array(ranks).reshape(14, 1)).ravel()
|
||
|
|
ranks = map(lambda x: round(x, 2), ranks)
|
||
|
|
return dict(zip(names, ranks))
|
||
|
|
|
||
|
|
|
||
|
|
# генерируем исходные данные: 750 строк-наблюдений и 14 столбцов-признаков
|
||
|
|
np.random.seed(0)
|
||
|
|
size = 750
|
||
|
|
X = np.random.uniform(0, 1, (size, 14))
|
||
|
|
# Задаем функцию-выход: регрессионную проблему Фридмана
|
||
|
|
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))
|
||
|
|
# Добавляем зависимость признаков
|
||
|
|
X[:, 10:] = X[:, :4] + np.random.normal(0, .025, (size, 4))
|
||
|
|
|
||
|
|
|
||
|
|
# Гребневая регрессия
|
||
|
|
ridge = Ridge(alpha=7)
|
||
|
|
ridge.fit(X, Y)
|
||
|
|
# Сокращение признаков случайными деревьями
|
||
|
|
rf = RandomForestRegressor()
|
||
|
|
rf.fit(X, Y)
|
||
|
|
# Линейная корреляция
|
||
|
|
f_values, _ = f_regression(X, Y)
|
||
|
|
|
||
|
|
names = ["x%s" % i for i in range(1, 15)]
|
||
|
|
|
||
|
|
ranks = dict()
|
||
|
|
ranks["Гребневая регрессия"] = rank_to_dict(ridge.coef_, names)
|
||
|
|
ranks["Сокращение признаков случайными деревьями"] = rank_to_dict(rf.feature_importances_, names)
|
||
|
|
ranks["Линейная корреляция"] = rank_to_dict(f_values, names)
|
||
|
|
|
||
|
|
# Создаем пустой список для данных
|
||
|
|
mean = {}
|
||
|
|
# «Бежим» по списку ranks
|
||
|
|
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]
|
||
|
|
for key, value in mean.items():
|
||
|
|
res = value / len(ranks)
|
||
|
|
mean[key] = round(res, 2)
|
||
|
|
|
||
|
|
mean = sorted(mean.items(), key=lambda x: x[1], reverse=True)
|
||
|
|
print("Средние оценки:")
|
||
|
|
print(mean)
|
||
|
|
print()
|
||
|
|
|
||
|
|
for key, value in ranks.items():
|
||
|
|
ranks[key] = sorted(value.items(), key=lambda x: x[1], reverse=True)
|
||
|
|
for key, value in ranks.items():
|
||
|
|
print(key)
|
||
|
|
print(value)
|
||
|
|
|
||
|
|
print()
|
||
|
|
|
||
|
|
print("Средние оценки:")
|
||
|
|
print(mean[:4])
|
||
|
|
|
||
|
|
for key, value in ranks.items():
|
||
|
|
print(f"Главные признаки для модели '{key}':")
|
||
|
|
print(value[:4])
|
||
|
|
|
||
|
|
|