72 lines
2.3 KiB
Python
72 lines
2.3 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
|
|||
|
|
|
|||
|
|
# Генерация исходных данных
|
|||
|
|
np.random.seed(0)
|
|||
|
|
size = 750
|
|||
|
|
X = np.random.uniform(0, 1, (size, 14))
|
|||
|
|
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[:, :4] + np.random.normal(0, .025, (size, 4))
|
|||
|
|
|
|||
|
|
# Лассо
|
|||
|
|
lasso = Lasso(alpha=0.05)
|
|||
|
|
lasso.fit(X, Y)
|
|||
|
|
|
|||
|
|
# Случайные деревья
|
|||
|
|
rf = RandomForestRegressor(n_estimators=100, random_state=0)
|
|||
|
|
rf.fit(X, Y)
|
|||
|
|
|
|||
|
|
# Линейная корреляция (f_regression)
|
|||
|
|
correlation_coeffs, _ = f_regression(X, Y)
|
|||
|
|
|
|||
|
|
# Ранжирование с использованием 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))
|
|||
|
|
|
|||
|
|
# Ранжирование для каждой модели
|
|||
|
|
ranks = {}
|
|||
|
|
names = ["x%s" % i for i in range(1, 15)]
|
|||
|
|
|
|||
|
|
ranks["Lasso"] = rank_to_dict(lasso.coef_, names)
|
|||
|
|
ranks["Random Forest"] = rank_to_dict(rf.feature_importances_, names)
|
|||
|
|
ranks["Correlation"] = rank_to_dict(correlation_coeffs, names)
|
|||
|
|
|
|||
|
|
# Создание пустого словаря для данных
|
|||
|
|
mean = {}
|
|||
|
|
|
|||
|
|
# Обработка словаря 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]
|
|||
|
|
|
|||
|
|
# Нахождение среднего по каждому признаку
|
|||
|
|
for key, value in mean.items():
|
|||
|
|
res = value / len(ranks)
|
|||
|
|
mean[key] = round(res, 2)
|
|||
|
|
|
|||
|
|
# Сортировка и вывод списка средних значений
|
|||
|
|
mean_dict = dict(mean)
|
|||
|
|
print("MEAN")
|
|||
|
|
print(mean_dict)
|
|||
|
|
|
|||
|
|
# Вывод результатов ранжирования для каждой модели
|
|||
|
|
for key, value in ranks.items():
|
|||
|
|
print(key)
|
|||
|
|
print(value)
|
|||
|
|
|
|||
|
|
# Вывод топ-4 признаков с их значениями
|
|||
|
|
top_features = sorted(mean.items(), key=lambda x: x[1], reverse=True)[:4]
|
|||
|
|
print("Top 4 features with values:")
|
|||
|
|
for feature, value in top_features:
|
|||
|
|
print(f"{feature}: {value}")
|