stud203836/4laba
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

гитигноре

Browse Source
This commit is contained in:
Тимофей Шаров 2026-05-05 19:22:10 +03:00
commit eb7671247d
4 changed files with 680 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

164
.gitignore vendored Normal file
View File

@ -0,0 +1,164 @@
# ---> Python
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
.idea
.venv
.ipynb_checkpoints

161
4444/Untitled.ipynb Normal file
View File

@ -0,0 +1,161 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "42259e56-f030-4f9a-b2f7-696736dc4439",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'StandardScaler' is not defined",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mNameError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 14\u001b[39m\n\u001b[32m 10\u001b[39m y_real = y_real.astype(int)\n\u001b[32m 11\u001b[39m \n\u001b[32m 12\u001b[39m \u001b[38;5;66;03m# Разбиение (теперь функция импортирована и сработает без ошибок)\u001b[39;00m\n\u001b[32m 13\u001b[39m X_train_r, X_test_r, y_train_r, y_test_r = train_test_split(X_real, y_real, test_size=\u001b[32m0.2\u001b[39m, random_state=\u001b[32m42\u001b[39m)\n\u001b[32m---> \u001b[39m\u001b[32m14\u001b[39m scaler_r = StandardScaler()\n\u001b[32m 15\u001b[39m X_train_r_scaled = scaler_r.fit_transform(X_train_r)\n\u001b[32m 16\u001b[39m X_test_r_scaled = scaler_r.transform(X_test_r)\n\u001b[32m 17\u001b[39m \u001b[38;5;66;03m# Обучение с L1\u001b[39;00m\n",
"\u001b[31mNameError\u001b[39m: name 'StandardScaler' is not defined"
]
}
],
"source": [
"import openml\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import accuracy_score\n",
"\n",
"# Загрузка датасета Spambase (ID 44)\n",
"dataset = openml.datasets.get_dataset(44)\n",
"X_real, y_real, _, _ = dataset.get_data(target=dataset.default_target_attribute)\n",
"\n",
"# Преобразование целевой переменной в числовой формат (0 и 1)\n",
"y_real = y_real.astype(int)\n",
"\n",
"# Разбиение (теперь функция импортирована и сработает без ошибок)\n",
"X_train_r, X_test_r, y_train_r, y_test_r = train_test_split(X_real, y_real, test_size=0.2, random_state=42)\n",
"scaler_r = StandardScaler()\n",
"X_train_r_scaled = scaler_r.fit_transform(X_train_r)\n",
"X_test_r_scaled = scaler_r.transform(X_test_r)\n",
"# Обучение с L1\n",
"sgd_real_l1 = SGDClassifier(loss='log_loss', penalty='l1', alpha=0.01, random_state=42)\n",
"sgd_real_l1.fit(X_train_r_scaled, y_train_r)\n",
"\n",
"# Обучение с L2\n",
"sgd_real_l2 = SGDClassifier(loss='log_loss', penalty='l2', alpha=0.01, random_state=42)\n",
"sgd_real_l2.fit(X_train_r_scaled, y_train_r)\n",
"\n",
"# Точность моделей\n",
"acc_l1 = accuracy_score(y_test_r, sgd_real_l1.predict(X_test_r_scaled))\n",
"acc_l2 = accuracy_score(y_test_r, sgd_real_l2.predict(X_test_r_scaled))\n",
"\n",
"print(f\"Точность модели с L1-регуляризацией: {acc_l1:.4f}\")\n",
"print(f\"Точность модели с L2-регуляризацией: {acc_l2:.4f}\")\n",
"print(f\"Количество ненулевых весов (L1): {np.sum(sgd_real_l1.coef_ != 0)} из {X_real.shape[1]}\")\n",
"print(f\"Количество ненулевых весов (L2): {np.sum(sgd_real_l2.coef_ != 0)} из {X_real.shape[1]}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c186361c-aa9b-4f87-8df5-34b2caff07a7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--- Результаты L1 (Lasso) ---\n",
"Accuracy: 0.8686\n",
"Полезных признаков (вес != 0): 22 из 57\n",
"\n",
"--- Результаты L2 (Ridge) ---\n",
"Accuracy: 0.9055\n",
"Полезных признаков (вес != 0): 57 из 57\n"
]
}
],
"source": [
"import openml\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.linear_model import SGDClassifier\n",
"from sklearn.metrics import accuracy_score, classification_report\n",
"\n",
"# 1. Загрузка датасета Spambase (ID 44) — классификация спам-писем\n",
"dataset = openml.datasets.get_dataset(44)\n",
"X_real, y_real, _, _ = dataset.get_data(target=dataset.default_target_attribute)\n",
"\n",
"# Преобразование целевой переменной в числа (0 - не спам, 1 - спам)\n",
"y_real = y_real.astype(int)\n",
"\n",
"# 2. Разбиение на обучающую и тестовую выборки\n",
"X_train_r, X_test_r, y_train_r, y_test_r = train_test_split(\n",
" X_real, y_real, test_size=0.2, random_state=42\n",
")\n",
"# Инициализация и обучение скалера\n",
"scaler_r = StandardScaler()\n",
"X_train_r_scaled = scaler_r.fit_transform(X_train_r)\n",
"X_test_r_scaled = scaler_r.transform(X_test_r)\n",
"# Параметры: loss='log_loss' делает из SGD логистическую регрессию\n",
"# alpha — сила регуляризации (чем выше, тем сильнее сжимаем веса)\n",
"\n",
"# Модель с L1 (Lasso) — должна занулить часть признаков\n",
"sgd_l1 = SGDClassifier(loss='log_loss', penalty='l1', alpha=0.02, random_state=42)\n",
"sgd_l1.fit(X_train_r_scaled, y_train_r)\n",
"\n",
"# Модель с L2 (Ridge) — просто уменьшает веса\n",
"sgd_l2 = SGDClassifier(loss='log_loss', penalty='l2', alpha=0.02, random_state=42)\n",
"sgd_l2.fit(X_train_r_scaled, y_train_r)\n",
"\n",
"# Предсказания\n",
"y_pred_l1 = sgd_l1.predict(X_test_r_scaled)\n",
"y_pred_l2 = sgd_l2.predict(X_test_r_scaled)\n",
"print(\"--- Результаты L1 (Lasso) ---\")\n",
"print(f\"Accuracy: {accuracy_score(y_test_r, y_pred_l1):.4f}\")\n",
"print(f\"Полезных признаков (вес != 0): {np.sum(sgd_l1.coef_ != 0)} из {X_real.shape[1]}\")\n",
"\n",
"print(\"\\n--- Результаты L2 (Ridge) ---\")\n",
"print(f\"Accuracy: {accuracy_score(y_test_r, y_pred_l2):.4f}\")\n",
"print(f\"Полезных признаков (вес != 0): {np.sum(sgd_l2.coef_ != 0)} из {X_real.shape[1]}\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "52c23789-f6f5-4ef4-9efc-0dda66562e71",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "559b4093-337c-4897-9e51-45d8e24c1be3",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

192
4444/Untitled1.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

163
4444/week4_scikit_learn.ipynb Normal file
View File

@ -0,0 +1,163 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "6c3666d4-5898-4253-90ed-a4750c2e1306",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 1.00 1.00 1.00 12\n",
" 1 1.00 0.89 0.94 9\n",
" 2 0.90 1.00 0.95 9\n",
"\n",
" accuracy 0.97 30\n",
" macro avg 0.97 0.96 0.96 30\n",
"weighted avg 0.97 0.97 0.97 30\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\timsh\\PycharmProjects\\4444\\.venv\\Lib\\site-packages\\sklearn\\neural_network\\_multilayer_perceptron.py:785: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (500) reached and the optimization hasn't converged yet.\n",
" warnings.warn(\n"
]
}
],
"source": [
"from sklearn.datasets import load_iris\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.neural_network import MLPClassifier\n",
"from sklearn.metrics import classification_report\n",
"\n",
"# Загрузка и разбиение данных\n",
"X, y = load_iris(return_X_y=True)\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
"\n",
"# Модель MLP — многослойный перцептрон\n",
"clf = MLPClassifier(hidden_layer_sizes=(10,), activation='relu', max_iter=500)\n",
"clf.fit(X_train, y_train)\n",
"\n",
"# Отчёт о точности\n",
"print(classification_report(y_test, clf.predict(X_test)))"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "182f69f2-a498-4adc-b06d-f8cbc6979c1d",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'sd' is not defined",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mNameError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m sd\n",
"\u001b[31mNameError\u001b[39m: name 'sd' is not defined"
]
}
],
"source": [
"sd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "96a73d41-6a38-4608-9f77-bd442dfcafd1",
"metadata": {},
"outputs": [
{
"name": "stdin",
"output_type": "stream",
"text": [
"Once deleted, variables cannot be recovered. Proceed (y/[n])? y\n"
]
}
],
"source": [
"reset\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "51de2ae0-7584-47c2-a5a3-27f546bc6f1d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 1.00 1.00 1.00 9\n",
" 1 1.00 0.91 0.95 11\n",
" 2 0.91 1.00 0.95 10\n",
"\n",
" accuracy 0.97 30\n",
" macro avg 0.97 0.97 0.97 30\n",
"weighted avg 0.97 0.97 0.97 30\n",
"\n"
]
}
],
"source": [
"from sklearn.datasets import load_iris\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.neural_network import MLPClassifier\n",
"from sklearn.metrics import classification_report\n",
"\n",
"# Загрузка и разбиение данных\n",
"X, y = load_iris(return_X_y=True)\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n",
"\n",
"# Модель MLP — многослойный перцептрон\n",
"clf = MLPClassifier(hidden_layer_sizes=(10,), activation='relu', max_iter=2500)\n",
"clf.fit(X_train, y_train)\n",
"\n",
"# Отчёт о точности\n",
"print(classification_report(y_test, clf.predict(X_test)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9f58322b-0064-4173-88fd-1c173a9bf3a9",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}