from sklearn.linear_model import LinearRegression, Lasso
from sklearn.feature_selection import RFE
from sklearn.preprocessing import MinMaxScaler
import numpy as np


# Генерация синтетических данных
def create_data():
    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))
    return X, Y


# Нормализация значений рангов
def rank_to_dict(ranks):
    ranks = np.abs(ranks)
    names = ["x%s" % i for i in range(1, 15)]
    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))


# Вывод отсортированных признаков по важности в табличном виде
def print_sorted_features_by_models(ranks_by_model: {}):
    sorted_ranks = sorted(ranks_by_model.items(), key=lambda item: sum(item[1].values()), reverse=True)

    print("{:<40}".format(""), end="")
    for i in range(1, 15):
        print("{:<10}".format(i), end="")
    print()

    for model, rank_dict in sorted_ranks:
        sorted_features = sorted(rank_dict.items(), key=lambda item: item[1], reverse=True)
        print("{:<40}".format(model), end="")
        for feature, rank in sorted_features:
            print("{:<10}".format(f"{feature}: {rank}"), end="")
        print()
    print()


# Получение средних значений моделей и ТОП 4 самых важных признака
def average_values(ranks_by_model: {}):
    mean = {}
    for model, rank_dict in ranks_by_model.items():
        for feature, rank in rank_dict.items():
            if feature not in mean:
                mean[feature] = 0
            mean[feature] += rank
    mean = {feature: round(rank / len(ranks_by_model), 2) for feature, rank in mean.items()}
    mean_sorted = sorted(mean.items(), key=lambda item: item[1], reverse=True)
    print("Средние значения")
    print(mean_sorted)
    print("\nТОП 4 самых важных признака по среднему значению: ")
    for feature, rank in mean_sorted[:4]:
        print('Признак - {0}, значение важности - {1}'.format(feature, rank))


X, Y = create_data()
# ЛИНЕЙНАЯ РЕГРЕССИЯ
linear_regression = LinearRegression()
linear_regression.fit(X, Y)
# ЛАССО
lasso = Lasso(alpha=.01)
lasso.fit(X, Y)
# РЕКУРСИВНОЕ СОКРАЩЕНИЕ ПРИЗНАКОВ
rfe = RFE(linear_regression)
rfe.fit(X, Y)

ranks_by_model = {
    "Линейная регрессия": rank_to_dict(linear_regression.coef_),
    "Лассо": rank_to_dict(lasso.coef_),
    "РЕКУРСИВНОЕ СОКРАЩЕНИЕ ПРИЗНАКОВ (RFE)": rank_to_dict(rfe.ranking_),
}
print_sorted_features_by_models(ranks_by_model)
average_values(ranks_by_model)