ai-med-edu/seminars/Тема 1.1/Dataset.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "553zXx91g7fz"
   },
   "source": [
    "Пример загрузки данных с сайта Breast Cancer Wisconsin (Original)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "JYb7HU1k9lFC",
    "outputId": "7a608a7c-9f85-4cc8-9b72-65a67381e960"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "# 1) Ссылка на датасет\n",
    "dataset_url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data\"\n",
    "\n",
    "# 2) Имена столбцов (по документации UCI)\n",
    "col_names = [\n",
    "    \"Sample_code_number\",\n",
    "    \"Clump_Thickness\",\n",
    "    \"Uniformity_of_Cell_Size\",\n",
    "    \"Uniformity_of_Cell_Shape\",\n",
    "    \"Marginal_Adhesion\",\n",
    "    \"Single_Epithelial_Cell_Size\",\n",
    "    \"Bare_Nuclei\",\n",
    "    \"Bland_Chromatin\",\n",
    "    \"Normal_Nucleoli\",\n",
    "    \"Mitoses\",\n",
    "    \"Class\"\n",
    "]\n",
    "\n",
    "# 3) Считываем csv\n",
    "df = pd.read_csv(\n",
    "    dataset_url,\n",
    "    names=col_names,\n",
    "    na_values=[\"?\"],\n",
    "    header=None\n",
    ")\n",
    "\n",
    "# 4) Быстрый осмотр\n",
    "print(df.head())\n",
    "print(df.info())\n",
    "\n",
    "# 5) Удалим строки с пропусками\n",
    "df.dropna(inplace=True)\n",
    "\n",
    "# 6) Разделим на признаки (X) и целевую переменную (y)\n",
    "y = df[\"Class\"]\n",
    "X = df.drop([\"Sample_code_number\", \"Class\"], axis=1)\n",
    "\n",
    "# 7) Разделим на train и test\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)\n",
    "\n",
    "# 8) Обучим модель (DecisionTree)\n",
    "clf = DecisionTreeClassifier(random_state=42)\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "# 9) Предсказание и оценка\n",
    "predictions = clf.predict(X_test)\n",
    "acc = accuracy_score(y_test, predictions)\n",
    "print(f\"Accuracy: {acc:.3f}\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2t5p4Mt7hKSw"
   },
   "source": [
    "Пример кода с requests + BeautifulSoup. Подставить нужную ссылку"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "1L4ZnJL5iDMm"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 321
    },
    "id": "SqUDAUG0esKO",
    "outputId": "150062f1-72e8-4f8e-b006-12ef211609ab"
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "import pandas as pd\n",
    "\n",
    "url = \"https://opendata.some-region.ru/datasets/interesting-table\"\n",
    "response = requests.get(url)\n",
    "soup = BeautifulSoup(response.text, \"html.parser\")\n",
    "\n",
    "# Предположим, на странице есть <table> с классом \"data-table\"\n",
    "table_html = soup.find(\"table\", {\"class\": \"data-table\"})\n",
    "\n",
    "# Преобразуем в DataFrame, если таблица более-менее стандартная\n",
    "df_list = pd.read_html(str(table_html))  # возвращает список df\n",
    "df = df_list[0]  # берем первую таблицу\n",
    "\n",
    "df.head()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "dl9b0hqOiFII"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "excel_url = \"https://data.gov.ru/files/dataset.xls\"\n",
    "df_excel = pd.read_excel(excel_url, sheet_name=\"Sheet1\")\n",
    "print(df_excel.columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "A_13q1K9iMr2"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "json_url = \"https://data.gov.ru/files/dataset.json\"\n",
    "df_json = pd.read_json(json_url, orient=\"records\")\n",
    "print(df_json.info())\n"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "name": "python3"
  },
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}