Merge pull request 'lipatov_ilya_lab_2' (#46) from lipatov_ilya_lab_2 into main

Reviewed-on: http://student.git.athene.tech/Alexey/IIS_2023_1/pulls/46
This commit is contained in:
Alexey 2023-10-17 17:25:09 +04:00
commit 53a25975f9
5 changed files with 149 additions and 0 deletions

View File

@ -0,0 +1,38 @@
## Лабораторная работа №2
### Ранжирование признаков
## Выполнил студент группы ПИбд-41 Липатов Илья
### Как запустить лабораторную работу:
* установить python, numpy, matplotlib, sklearn
* запустить проект (стартовая точка класс lab2)
### Какие технологии использовались:
* Язык программирования `Python`, библиотеки numpy, matplotlib, sklearn
* Среда разработки `PyCharm`
### Что делает лабораторная работа:
* генерирует данные и обучает модели модели RandomizedLasso, Ridge,Random Forest Regressor.
* ранжирует признаки с помощью моделей RandomizedLasso, Ridge,Random Forest Regressor.
* отображает получившиеся значения\оценки каждого признака каждым методом\моделью и среднюю оценку.
### Примеры работы:
#### Результаты:
* RandomizedLasso: 1, 2, 4, 5
* Ridge: 4, 11, 12 и 1 или 2 (одинаковый результат)
* Random Forest Regressor: 4, 1 11, 12
#### Среднее: 4, 1, 2 и 5 признаки
#### Графики результатов ранжирования признаков по каждой модели и средняя оценка:
![Result](result.png)
#### Средние оценки для признаков у каждой модели и средние оценки моделей:
![Means](means.png)

View File

@ -0,0 +1,44 @@
from sklearn.utils import check_X_y, check_random_state
from sklearn.linear_model import Lasso
from scipy.sparse import issparse
from pandas._libs import sparse
def _rescale_data(x, weights):
if issparse(x):
size = weights.shape[0]
weight_dia = sparse.dia_matrix((1 - weights, 0), (size, size))
x_rescaled = x * weight_dia
else:
x_rescaled = x * (1 - weights)
return x_rescaled
class RandomizedLasso(Lasso):
def __init__(self, weakness=0.5, alpha=1.0, fit_intercept=True, normalize=False,
precompute=False, copy_x=True, max_iter=1000,
tol=1e-4, warm_start=False, positive=False,
random_state=None, selection='cyclic'):
self.weakness = weakness
super(RandomizedLasso, self).__init__(
alpha=alpha, fit_intercept=fit_intercept,
normalize=normalize, precompute=precompute, copy_X=copy_x,
max_iter=max_iter, tol=tol, warm_start=warm_start,
positive=positive, random_state=random_state,
selection=selection)
def fit(self, x, y):
if not isinstance(self.weakness, float) or not (0.0 < self.weakness <= 1.0):
raise ValueError('weakness should be a float in (0, 1], got %s' % self.weakness)
x, y = check_X_y(x, y, accept_sparse=True)
n_features = x.shape[1]
weakness = 1. - self.weakness
random_state = check_random_state(self.random_state)
weights = weakness * random_state.randint(0, 1 + 1, size=(n_features,))
x_rescaled = _rescale_data(x, weights)
return super(RandomizedLasso, self).fit(x_rescaled, y)

View File

@ -0,0 +1,67 @@
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import MinMaxScaler
from RandomizedLasso import RandomizedLasso
from sklearn.linear_model import Ridge
from matplotlib import pyplot as plt
import numpy as np
np.random.seed(0)
size = 1000
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))
ridge = Ridge(alpha=1.0)
ridge.fit(X, Y)
lasso = RandomizedLasso(alpha=0.007)
lasso.fit(X, Y)
randForestRegression = RandomForestRegressor(max_depth=4, min_samples_leaf=1, min_impurity_decrease=0, ccp_alpha=0)
randForestRegression.fit(X, Y)
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))
ranks = {'Ridge': {}, 'RandomizedLasso': {}, 'RandomForestRegressor': {}}
names = ["x%s" % i for i in range(1, 15)]
ranks["Ridge"] = rank_to_dict(ridge.coef_, names)
ranks["RandomizedLasso"] = rank_to_dict(lasso.coef_, names)
ranks["RandomForestRegressor"] = rank_to_dict(randForestRegression.feature_importances_, names)
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]
for key, value in mean.items():
res = value / len(ranks)
mean[key] = round(res, 2)
print('VALUES')
for r in ranks.items():
print(r)
print('MEAN')
print(mean)
for i, (model_name, features) in enumerate(ranks.items()):
subplot = plt.subplot(2, 2, i + 1)
subplot.set_title(model_name)
subplot.bar(list(features.keys()), list(features.values()))
subplot = plt.subplot(2, 2, 4)
subplot.set_title('Mean')
subplot.bar(list(mean.keys()), list(mean.values()))
plt.show()

Binary file not shown.

After

Width:  |  Height:  |  Size: 90 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 26 KiB