{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 决策科学实践环境配置\n", "\n", "**学习目标**:\n", "- 配置完整的 Python 决策科学环境\n", "- 验证所有必要依赖已安装\n", "- 测试核心库功能\n", "\n", "**预计时间**: 30 分钟" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 1. 安装核心依赖" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 基础数据科学库\n", "pip install pandas numpy scipy matplotlib seaborn" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 机器学习库\n", "pip install scikit-learn xgboost lightgbm" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 统计与因果推断\n", "pip install statsmodels linearmodels dowhy" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 优化库\n", "pip install pyomo pulp networkx" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 贝叶斯与概率编程\n", "pip install pymc bambi arviz pgmpy" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 生存分析\n", "pip install lifelines" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "vscode": { "languageId": "shellscript" } }, "outputs": [], "source": [ "# 信用评分专用\n", "pip install scorecardpy optbinning" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 2. 验证安装" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "print(\"✓ 基础库加载成功\")\n", "print(f\" pandas: {pd.__version__}\")\n", "print(f\" numpy: {np.__version__}\")\n", "print(f\" matplotlib: {plt.matplotlib.__version__}\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.model_selection import train_test_split, cross_val_score\n", "from sklearn.metrics import classification_report, roc_auc_score, confusion_matrix\n", "\n", "print(\"✓ scikit-learn 加载成功\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import statsmodels.api as sm\n", "import scipy.stats as stats\n", "\n", "print(\"✓ 统计库加载成功\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pyomo.environ as pyo\n", "import pulp\n", "\n", "print(\"✓ 优化库加载成功\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pymc as pm\n", "import arviz as az\n", "\n", "print(\"✓ 贝叶斯库加载成功\")\n", "print(f\" PyMC: {pm.__version__}\")\n", "print(f\" ArviZ: {az.__version__}\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from lifelines import KaplanMeierFitter, CoxPHFitter\n", "\n", "print(\"✓ 生存分析库加载成功\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import scorecardpy as sc\n", "import optbinning as ob\n", "\n", "print(\"✓ 信用评分库加载成功\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 3. 快速测试" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 生成测试数据\n", "np.random.seed(42)\n", "n_samples = 1000\n", "\n", "X = np.random.randn(n_samples, 10)\n", "y = (X[:, 0] + X[:, 1] > 0).astype(int)\n", "\n", "# 训练简单模型\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n", "\n", "model = RandomForestClassifier(n_estimators=10, random_state=42)\n", "model.fit(X_train, y_train)\n", "\n", "y_pred = model.predict(X_test)\n", "y_pred_proba = model.predict_proba(X_test)[:, 1]\n", "\n", "print(\"模型评估:\")\n", "print(f\" 准确率：{model.score(X_test, y_test):.3f}\")\n", "print(f\" AUC: {roc_auc_score(y_test, y_pred_proba):.3f}\")\n", "print(\"\\n分类报告:\")\n", "print(classification_report(y_test, y_pred))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 4. 可视化测试" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 特征重要性可视化\n", "fig, ax = plt.subplots(figsize=(10, 6))\n", "\n", "importance = pd.DataFrame({\n", " 'feature': [f'Feature_{i}' for i in range(10)],\n", " 'importance': model.feature_importances_\n", "})\n", "importance = importance.sort_values('importance', ascending=True)\n", "\n", "ax.barh(importance['feature'], importance['importance'])\n", "ax.set_xlabel('Importance')\n", "ax.set_title('Feature Importance')\n", "ax.grid(axis='x', alpha=0.3)\n", "\n", "plt.tight_layout()\n", "plt.show()\n", "\n", "print(\"✓ 可视化测试成功\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 5. 环境信息" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import sys\n", "import platform\n", "\n", "print(\"=\" * 50)\n", "print(\"环境信息:\")\n", "print(\"=\" * 50)\n", "print(f\"Python 版本：{sys.version}\")\n", "print(f\"平台：{platform.platform()}\")\n", "print(f\"CPU 核心数：{len([None for _ in range(platform.cpu_count())])}\")\n", "print(\"=\" * 50)\n", "print(\"✓ 环境配置完成！可以开始学习案例了。\")" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.11.2" } }, "nbformat": 4, "nbformat_minor": 4 }