from sklearn.linear_model import LassoCV
from sklearn.ensemble import RandomForestRegressor
from sklearn.feature_selection import RFE
from sklearn.preprocessing import MinMaxScaler
import numpy as np
import pandas as pd

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))

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, size))

X[:, 10:] = X[:, :4] + np.random.normal(0, .025, (size, 4))

lasso_cv = LassoCV(alphas=np.linspace(0.001, 1, 100), cv=5)
lasso_cv.fit(X, Y)

rf = RandomForestRegressor(n_estimators=100)
rfe = RFE(estimator=rf, n_features_to_select=1, step=1)
rfe.fit(X, Y)

#  названия признаков
names = ["x%s" % i for i in range(1, 15)]

# Stable Randomized Lasso Simulation
n_resampling = 200
rlasso_coefs = np.zeros((X.shape[1], n_resampling))
for i in range(n_resampling):
    Y_permuted = np.random.permutation(Y)
    rlasso = LassoCV(alphas=np.linspace(0.001, 1, 100), cv=5)
    rlasso.fit(X, Y_permuted)
    rlasso_coefs[:, i] = rlasso.coef_

rlasso_scores = np.std(rlasso_coefs, axis=1)

#  словарь для ранжирования
ranks = {"Lasso": rank_to_dict(lasso_cv.coef_, names),
         "RFE": rank_to_dict(rfe.ranking_, names),
         "RandomizedLassoSim": rank_to_dict(rlasso_scores, names)}

mean = {}
for method, values in ranks.items():
    for feature, score in values.items():
        # Если элемента с текущим ключом в mean нет - добавляем
        if feature not in mean:
            mean[feature] = 0
        # Суммируем значения по каждому ключу-имени признака
        mean[feature] += score
df_ranks = pd.DataFrame(ranks)

# Выводим ранжирование
print("ПО КАЖДОМУ МЕТОДУ:")
print(df_ranks)

# Находим среднее по каждому признаку
for feature, score in mean.items():
    mean[feature] = round(score / len(ranks), 2)

# Отсортированные средние значени
mean = sorted(mean.items(), key=lambda x: x[1], reverse=True)
print("СРЕДНИЕ")
print(mean)