up 2026.3.21

Author: lianxhcn

.quarto/idx/body/00_intro.ipynb.json

@@ -1 +1 @@
-{"entries":[],"headings":["课程内容","参考资料","python-语言","数据分析","金融","因果推断和机器学习","因果推断和机器学习-1","分析工具"],"options":{"chapters":true}}
+{"entries":[],"headings":["课程内容","参考资料","ai-tools","python-语言","数据分析","金融","因果推断和机器学习","分析工具"],"options":{"chapters":true}}

.quarto/idx/body/test_AB_test.ipynb.json

@@ -48,13 +48,26 @@
    "source": [
     "## 参考资料\n",
     "\n",
+    "### AI tools\n",
+    "\n",
+    "- [Awesome AI for Economists](https://github.com/hanlulong/awesome-ai-for-economists)\n",
+    "  - A curated list of AI tools, libraries, and resources for economics research, teaching, and policy analysis.\n",
+    "- Gábor Békés. (2026). **Doing Data Analysis with AI**. [Link](https://gabors-data-analysis.com/ai-course/).\n",
+    "\n",
+    "Author\n",
+    "Gábor Békés, Central European University (Austria, EU)\n",
+    "\n",
+    "Published\n",
+    "January 30, 2026\n",
+    "\n",
     "### Python 语言\n",
     "- Allen Downey, 2012. Think Python: How to Think Like a Computer Scientist. [-PDF-](https://greenteapress.com/thinkpython/thinkpython.pdf)\n",
     "  - Python 入门，通俗易懂\n",
     "- Johansson, R., 2024, Numerical Python: Scientific Computing and Data Science Applications with Numpy, SciPy and Matplotlib. Apress Berkeley, CA. [Link](https://link.springer.com/book/10.1007/979-8-8688-0413-7), [PDF](https://link.springer.com/content/pdf/10.1007/979-8-8688-0413-7.pdf) (需要用校园 ID 登录), [github](https://github.com/Apress/Numerical-Python-3rd-ed/fork)\n",
     "  - Python 入门，绘图，科学计算，偏微分方程，统计和机器学习初步\n",
     "  - CHAPTER 4 Plotting and Visualization, 介绍绘图的基本元素. \n",
-    "\n",
+    "- QuantEcon. [Link](https://quantecon.org/lectures/), [github](https://github.com/QuantEcon)\n",
+    "  - QuantEcon is a nonprofit organization dedicated to development and documentation of open source computational tools for economics, econometrics, and decision making.\n",
     "\n",
     "### 数据分析\n",
     "\n",
@@ -65,6 +78,9 @@
     "  - 数据分析 + 可视化 + 机器学习\n",
     "  - 提供了 Colab版本，可以无需安装 Python，直接在线运行\n",
     "  - 本地已经下载：**VanderPlas_2023_PDSH_Python_Data_Science_Handbook-2E.pdf**\n",
+    "- [Github 仓库：数据分析](https://github.com/search?q=Data+science+created%3A%3E2024-01-01+&type=repositories&p=2)\n",
+    "\n",
+    "\n",
     "\n",
     "### 金融\n",
     "\n",
@@ -79,27 +95,6 @@
     "\n"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "cebf60fc",
-   "metadata": {},
-   "source": [
-    "### 因果推断和机器学习\n",
-    "\n",
-    "- {before} Facure, Matheus (2022). Causal Inference for The Brave and True. Online: https://matheusfacure.github.io/python-causality-handbook/landing-page.html. GitHub: https://github.com/matheusfacure/python-causality-handbook.（覆盖 IV、DID、SDID、PSM、Matching、Panel、SCM、RDD；包含完整 Jupyter Notebook；使用 causalml 与 dowhy。）\n",
-    "- {after} Facure, Matheus (2022). Causal Inference for The Brave and True. [Link](https://matheusfacure.github.io/python-causality-handbook/landing-page.html). [GitHub](https://github.com/matheusfacure/python-causality-handbook).\n",
-    "  - Note: 覆盖 IV、DID、SDID、PSM、Matching、Panel、SCM、RDD；包含完整 Jupyter Notebook；使用 `causalml` 与 `dowhy`。\n",
-    "\n",
-    "- James, G., Witten, D., Hastie, T., & Tibshirani, R. (2023). An Introduction to Statistical Learning: With Applications in Python (ISLP). Springer. Website: https://www.statlearning.com/. Python 资源与实验：https://intro-stat-learning.github.io/ISLP/，GitHub: https://github.com/intro-stat-learning/ISLP_labs。PDF: https://bayanbox.ir/view/1060725898744657072/An-Introduction-to-Statistical-Learning-with-Applications-in-Python.pdf\n",
-    "\n",
-    "- Tatsat, H., Puri, S., & Lookabaugh, B. (2020). Machine Learning and Data Science Blueprints for Finance. O'Reilly Media. PDF: https://soclibrary.futa.edu.ng/books/Machine%20Learning%20and%20Data%20Science%20Blueprints%20for%20Finance%20(Hariom%20Tatsat,%20Sahil%20Puri,%20Brad%20Lookabaugh)%20(Z-Library).pdf。GitHub: https://github.com/tatsath/fin-ml，案例可在 Binder 在线运行: https://mybinder.org/v2/gh/tatsath/fin-ml/master。\n",
-    "\n",
-    "- Chollet, François (2021). Deep Learning with Python (2nd ed.). Manning. ISBN: 9781617296864. 代码示例: https://www.manning.com/books/deep-learning-with-python-second-edition。GitHub: https://github.com/fchollet/deep-learning-with-python-notebooks。\n",
-    "- Buduma, N., Buduma, N., & Papa, J. (2022). Fundamentals of deep learning. [-PDF-](https://webfiles.amrita.edu/2025/02/deep-learning-material-dept-ece-ase-blr-1.pdf)\n",
-    "\n",
-    "- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. URL: <http://www.deeplearningbook.org>, [TensorFlow-Excercises](https://www.tensorflow.org/tutorials?hl=zh-cn), [Slides](https://www.deeplearningbook.org/lecture_slides.html), [-PDF1-](http://alvarestech.com/temp/deep/Deep%20Learning%20by%20Ian%20Goodfellow,%20Yoshua%20Bengio,%20Aaron%20Courville%20(z-lib.org).pdf), [-PDF2-](https://github.com/janishar/mit-deep-learning-book-pdf/blob/master/complete-book-pdf/Ian%20Goodfellow%2C%20Yoshua%20Bengio%2C%20Aaron%20Courville%20-%20Deep%20Learning%20(2017%2C%20MIT).pdf)\n"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "d8f75925",
@@ -111,6 +106,9 @@
    "source": [
     "### 因果推断和机器学习\n",
     "\n",
+    "* Nick Huntington-Klein. **The Effect**: An Introduction to Research Design and Causality, [Link](https://theeffectbook.net/), [github](https://github.com/NickCH-K/causalbook), [Slides-Causality](https://github.com/NickCH-K/CausalitySlides), [Slides-Econometrics](https://github.com/NickCH-K/EconometricsSlides)\n",
+    "  - 以因果图和反事实框架为基础，介绍了一些常用的因果推断方法，包括：DID，TWFE，SCM，RDD，PSM，Matching，Panel 等；配有在线阅读版本和 GitHub 代码仓库。 \n",
+    "\n",
     "* Facure, Matheus (2022). Causal Inference for The Brave and True. [Link](https://matheusfacure.github.io/python-causality-handbook/landing-page.html). [GitHub](https://github.com/matheusfacure/python-causality-handbook).\n",
     "  - Note: 覆盖 IV、DID、SDID、PSM、Matching、Panel、SCM、RDD；包含完整 Jupyter Notebook；使用 `causalml` 与 `dowhy`。\n",
     "* James, G., Witten, D., Hastie, T., & Tibshirani, R. (2023). An Introduction to Statistical Learning: With Applications in Python (ISLP). Springer. [Link](https://www.statlearning.com/). [Python 资源与实验](https://intro-stat-learning.github.io/ISLP/). [GitHub](https://github.com/intro-stat-learning/ISLP_labs). [PDF](https://bayanbox.ir/view/1060725898744657072/An-Introduction-to-Statistical-Learning-with-Applications-in-Python.pdf).\n",

.quarto/xref/53dd7b6d

@@ -177,7 +177,7 @@
    "id": "29a3ebe9",
    "metadata": {},
    "source": [
-    "#### Python 和 Jupyter 插件\n",
+    "### Python 和 Jupyter 插件\n",
     "\n",
     "为了能够在 VScode 中使用 Jupyter Notebook 运行 Python 代码，并借助 AI 提升工作效率，你需要安装以下插件：\n",
     "\n",
@@ -207,7 +207,7 @@
    "id": "f5b2c4cf",
    "metadata": {},
    "source": [
-    "#### Markdown 插件\n",
+    "### Markdown 插件\n",
     "\n",
     "VScode 支持 Markdown 语法，可以用来编写文档、笔记等。安装 Markdown 插件可以增强 VScode 对 Markdown 的支持，比如预览、语法高亮、制作幻灯片等。多数情况下，安装如下三个插件就可以满足需求：\n",
     "\n",
@@ -222,25 +222,12 @@
     "你也可以点击 VScode 左边栏中的 `四个小方块` 图标，在搜索框中输入 `markdown`，酌情安装其他插件。"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "8740de3b",
-   "metadata": {},
-   "source": [
-    "#### 其他插件\n",
-    "\n",
-    "根据个人需求，可以安装其他插件来增强 VScode 的功能，比如：\n",
-    "\n",
-    "- [Data Wrangler](https://marketplace.visualstudio.com/items?itemName=DataWrangler) (可选)：表格呈现效果很美观。\n",
-    "- [Rainbow CSV](https://marketplace.visualstudio.com/items?itemName=mechatroner.rainbow-csv) (by *mechatroner*) 和 [CSV](https://marketplace.visualstudio.com/items?itemName=ReprEng.csv) (by *ReprEng*)：CSV 文件的高亮显示和表格预览功能很棒。"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "26526398",
    "metadata": {},
    "source": [
-    "#### Stata 插件 \n",
+    "### Stata 插件 \n",
     "\n",
     "::: {.callout-important}\n",
     "### 提示！\n",
@@ -257,14 +244,27 @@
     "要顺利运行 Stata 代码，还需要安装 `nbstata` 包，下文将详细介绍。\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "7fe2a2e3",
+   "metadata": {},
+   "source": [
+    "### 其他插件\n",
+    "\n",
+    "根据个人需求，可以安装其他插件来增强 VScode 的功能，比如：\n",
+    "\n",
+    "- [Data Wrangler](https://marketplace.visualstudio.com/items?itemName=DataWrangler) (可选)：表格呈现效果很美观。\n",
+    "- [Rainbow CSV](https://marketplace.visualstudio.com/items?itemName=mechatroner.rainbow-csv) (by *mechatroner*) 和 [CSV](https://marketplace.visualstudio.com/items?itemName=ReprEng.csv) (by *ReprEng*)：CSV 文件的高亮显示和表格预览功能很棒。"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "62ceab58",
    "metadata": {},
    "source": [
     "## 配置 Stata 环境：nbstata\n",
     "\n",
-    "为了在 VS Code 中的 `.ipynb` 文档中直接运行 Stata 代码，我们可以借助 [nbstata](https://hugetim.github.io/nbstata/) 扩展包 (注意：`nbstata` 是 Python 包，不是 VScode 插件)。下面介绍如何在已有 Python + Jupyter 环境基础上完成配置。\n",
+    "如需在 VS Code 中的 `.ipynb` 文档中运行 Stata 代码，我们可以借助 [nbstata](https://hugetim.github.io/nbstata/) 扩展包 (注意：`nbstata` 是 Python 包，不是 VScode 插件)。下面介绍如何在已有 Python + Jupyter 环境基础上完成配置。\n",
     "\n",
     "::: {.callout-important}\n",
     "### 前提条件：你已经完成以下配置\n",
@@ -281,27 +281,28 @@
     "- Stata 的安装路径中不要包含中文字符和空格 (在 Stata 中输入 `sysdir` 可以查看你的 Stata 安装路径)；\n",
     "- Stata 安装目录下有 `STATA.LIC` 文件：该文件是 Stata 的授权文件，里面记录了 Stata 软件的序列号等信息。\n",
     "  - 有些用户使用的不是官方发布的 Stata 版本，或没有正确完成安装程序，都会导致该文件缺失，从而导致 `nbstata` 无法正常工作。\n",
-    "- `nbstata` 是在 Python 3.12 版本下开发和测试的，如果你在 Python 3.13 或更高版本环境下安装了 `nbstata`，可能会遇到兼容性问题，导致无法正常使用。因此，建议大家创建一个专属于 Stata 的虚拟环境。详情参见 **nbstata 安装和使用常见问题 🍎** 小节。\n",
-    "\n",
+    "- `nbstata` 是在 Python 3.12 版本下开发和测试的，如果你在 Python 3.13 或更高版本环境下安装了 `nbstata`，可能会遇到兼容性问题，导致无法正常使用。因此，建议大家创建一个专属于 Stata 的虚拟环境，并在其中安装 Python 3.12 或更低的版本。详情参见 **nbstata 安装和使用常见问题 🍎** 小节。\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "386a95f5",
+   "metadata": {},
+   "source": [
     "### 配置步骤\n",
     "\n",
     "::: {.callout-important}\n",
-    "### 注意\n",
+    "### 注意：\n",
     "\n",
     "- 下面的配置步骤需要在 VS Code 的终端中完成，而不是在 Jupyter Notebook 中。\n",
     "- 打开 VS Code 的终端的快捷键为 `Ctrl + ~`。详见 [Python 安装常见问题](01_03_install_FAQs.html)。\n",
     "- 如果按下面的方法无法配置成功，可以参阅 [nbstata User Guide](https://hugetim.github.io/nbstata/user_guide.html) 和 [Jupyter + Stata 配置方法](https://industry.pengxianzhe.org/posts/jupyter-stata/#sec-vscode) (第 4 小节)。也可以打开 [豆包](https://www.douban.com/group/topic/297885930/)，把你的错误代码截图和粘贴给它，多数情况下你都能在它的引导下完成配置。\n",
     "- 我的学生倪璐同学写了一份详细的笔记，也可以参考：[如何在 VScode 的 Jupyter Notebook 中创建 Stata 代码单元](https://github.com/arlionn/Financial-Econometrics/blob/main/FAQs/How-to-create-a-Stata-code-cell_by-NiLu.md)。\n",
     "\n",
     ":::\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0312eedb",
-   "metadata": {},
-   "source": [
+    "\n",
+    "\n",
     "按快捷键 `Ctrl + ~` 打开 VS Code 的**终端**，依次执行以下命令：\n",
     "\n",
     "```bash\n",
@@ -316,14 +317,14 @@
     "C:\\Users\\Administrator\\.config\\nbstata\\nbstata.conf\n",
     "```\n",
     "\n",
-    "你可以到此文件夹下，用 VScode 打开 `nbstata.conf` 文件，查看或修改配置。我的配置如下：\n",
+    "你可以定位到上述路径，用 VScode 打开 `nbstata.conf` 文件，查看或修改配置。我的配置如下：\n",
     "\n",
     "```py\n",
     "[nbstata]\n",
     "stata_dir = D:\\stata17\n",
     "edition = mp\n",
     "splash = False\n",
-    "graph_format = png\n",
+    "graph_format = png    # 可选值：png, svg, pystata\n",
     "graph_width = 7.5in\n",
     "graph_height = 5.0in\n",
     "echo = None\n",
@@ -404,21 +405,6 @@
     "\n"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "978b29af",
-   "metadata": {},
-   "source": [
-    "### nbstata 扩展信息\n",
-    "\n",
-    "有关 nbstata 的更多信息和使用方法，参见：\n",
-    "\n",
-    "- [nbstata 文档](https://hugetim.github.io/nbstata/)，以及 [nbstata User Guide](https://hugetim.github.io/nbstata/user_guide.html)\n",
-    "- [Jupyter + Stata 配置方法](https://industry.pengxianzhe.org/posts/jupyter-stata/#sec-vscode)，第 4 小节。\n",
-    "- 黄晨晨, 2023, [Jupyter Notebook 与 Stata 交互：nbstata](https://www.lianxh.cn/details/1309.html)\n",
-    "- 韩少真, 展金永, 2020, [珠联璧合 I：Jupyter Notebook 和 Stata 关联 (windows系统)](https://www.lianxh.cn/details/114.html)。这个推文介绍了如何在原生 Jupyter Notebook 中安装 `nbstata` 包。"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "a06bdb87",
@@ -526,6 +512,21 @@
     "   ```"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "90aa8734",
+   "metadata": {},
+   "source": [
+    "### nbstata 扩展信息\n",
+    "\n",
+    "有关 nbstata 的更多信息和使用方法，参见：\n",
+    "\n",
+    "- [nbstata 文档](https://hugetim.github.io/nbstata/)，以及 [nbstata User Guide](https://hugetim.github.io/nbstata/user_guide.html)\n",
+    "- [Jupyter + Stata 配置方法](https://industry.pengxianzhe.org/posts/jupyter-stata/#sec-vscode)，第 4 小节。\n",
+    "- 黄晨晨, 2023, [Jupyter Notebook 与 Stata 交互：nbstata](https://www.lianxh.cn/details/1309.html)\n",
+    "- 韩少真, 展金永, 2020, [珠联璧合 I：Jupyter Notebook 和 Stata 关联 (windows系统)](https://www.lianxh.cn/details/114.html)。这个推文介绍了如何在原生 Jupyter Notebook 中安装 `nbstata` 包。"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b190c802",

body/00_intro.ipynb

@@ -198,95 +198,31 @@ marp: true
 ```markdown
 ---
 marp: true
-size: 16:9        # 宽版：4:3
-paginate: true  
+theme: default
+size: 16:9
+paginate: true
+lang: zh-CN
+math: mathjax
+header: '[lianxh.cn](https://www.lianxh.cn/news/46917f1076104.html)'
 footer: '[lianxh.cn](https://www.lianxh.cn) | [Books](https://www.lianxh.cn/Books.html)'
+style: |
+  section {
+    font-family: "Microsoft YaHei", "PingFang SC", sans-serif;
+    font-size: 22px;
+    line-height: 1.45;
+    padding: 48px 56px 40px 56px;
+  }
+  h1 { color: #222; font-size: 34px; }
+  h2 { color: #1f7a1f; font-size: 30px; }
+  h3 { color: #1f4e79; font-size: 26px; }
+  pre { font-size: 20px; }
+  section::after {
+    content: attr(data-marpit-pagination) '/' attr(data-marpit-pagination-total);
+    font-size: 14px;
+  }
 ---
 
-<style>
-/*一级标题局中*/
-section.lead h1 {
-  text-align: center; /*其他参数：left, right*/
-}
-section {
-  font-size: 22px;      /* 正文字号 */
-}
-h1 {
-  color: blackyellow;   /* 标题的颜色 */
-  /*font-size: 28px; */ /* 标题的字号, 其它标题也可以这样修改 */
-}
-h2 {
-  color: green;
-}
-h3 {
-  color: darkblue;
-}
-h4 {
-  color: brown;
-}
-/* 右下角添加页码 */
-section::after {
-  content: attr(data-marpit-pagination) '/' attr(data-marpit-pagination-total); 
-}
-header,
-footer {
-  position: absolute;
-  left: 50px;
-  right: 50px;
-  height: 25px;
-}
-/* 调整图片与文本之间的间距 */
-section img {
-  margin-right: 10px;   /* 设置图片右侧的间距 */
-  margin-left: 10px;   /* 设置图片左侧的间距 */
-}
-
-/* 设置正文区域的边距，确保文本能更紧凑地放置 */
-section {
-  #padding-right: 20px;  /* 设置右侧边距 */
-  #padding-left: 20px;  /* 设置左侧边距 */
-}
-
-/* ====== 新增：设置代码块字号 ====== */
-
-/* 默认代码块字号 */
-pre {
-  font-size: 22px;
-}
-
-/* 可选类：小字号代码块 */
-.small-code pre {
-  font-size: 12px;
-}
-
-/* 可选类：大字号代码块 */
-.large-code pre {
-  font-size: 20px;
-}
-</style>
-
-<!--顶部文字-->
-[lianxh.cn](https://www.lianxh.cn/news/46917f1076104.html) 
-
-<br>
-
-<!--封面图片-->
-![bg right:50% w:400 brightness:. sepia:50%](https://fig-lianxh.oss-cn-shenzhen.aliyuncs.com/20220722114227.png) 
-
-<!--幻灯片标题-->
-
-### 连享会 · 2025 暑期班 · 高级班
-
-# B1. 动态面板门槛模型
-
-<br>
-<br>
-
-<!--作者信息-->
-[连玉君](https://www.lianxh.cn) (中山大学)
-arlionn@163.com
-
-<br>
+<!-- _headingDivider: 2 -->
 
 ---
 <!-- backgroundColor: #FFFFF9 -->

body/01_01_install_anaconda.ipynb

@@ -39,6 +39,10 @@
     "  - 美国政府开放数据平台，涵盖农业、气候、教育、能源等众多领域，数据权威且更新及时。\n",
     "- [awesome-public-datasets](https://github.com/awesomedata/awesome-public-datasets)\n",
     "  - GitHub 开放数据集列表 \n",
+    "- [openecon.ai](https://openecon.ai/ \"https://openecon.ai\")\n",
+    "  - Query economic data from FRED, World Bank, IMF, and 10+ sources using plain English. MCP server + web app + API.\n",
+    "- [OSF](https://osf.io/)\n",
+    "  - OSF 是 Open Science Framework 的缩写，是一个开放科学平台，研究人员可以在上面存储、分享和管理他们的研究数据、代码、文档和其他相关材料。\n",
     "\n",
     "### 国内数据平台\n",
     "- [中国科学院科学数据中心](https://www.casdc.cn/home)\n",