Organized setup instructions (#115)

* Organized setup instructions

* update tets

* link checker action

* raise error upon broken link

* fix links

* fix links

* delete duplicated paragraph

setup/02_installing-python-libraries/README.md

@@ -0,0 +1,60 @@
+# Installing Libraries Used In This Book
+
+This document provides more information on double-checking your installed Python version and packages. (Please see the [../01_optional-python-setup-preferences](../01_optional-python-setup-preferences) folder for more information on installing Python and Python packages.)
+
+I used the following libraries listed [here](https://github.com/rasbt/LLMs-from-scratch/blob/main/requirements.txt) for this book. Newer versions of these libraries are likely compatible as well. However, if you experience any problems with the code, you can try these library versions as a fallback.
+
+To install these requirements most conveniently, you can use the `requirements.txt` file in the root directory for this code repository and execute the following command:
+
+```
+pip install -r requirements.txt
+```
+
+
+Then, after completing the installation, please check if all the packages are installed and are up to date using
+
+```
+python python_environment_check.py
+```
+
+<img src="figures/check_1.jpg" width="600px">
+
+It's also recommended to check the versions in JupyterLab by running the `jupyter_environment_check.ipynb` in this directory, which should ideally give you the same results as above.
+
+<img src="figures/check_2.jpg" width="500px">
+
+If you see the following issues, it's likely that your JupyterLab instance is connected to wrong conda environment:
+
+<img src="figures/jupyter-issues.jpg" width="450px">
+
+In this case, you may want to use `watermark` to check if you opened the JupyterLab instance in the right conda environment using the `--conda` flag:
+
+<img src="figures/watermark.jpg" width="350px">
+
+
+<br>
+<br>
+
+
+## Installing PyTorch
+
+PyTorch can be installed just like any other Python library or package using pip. For example:
+
+```bash
+pip install torch==2.0.1
+```
+
+However, since PyTorch is a comprehensive library featuring CPU- and GPU-compatible codes, the installation may require additional settings and explanation (see the *A.1.3 Installing PyTorch in the book for more information*).
+
+It's also highly recommended to consult the installation guide menu on the official PyTorch website at [https://pytorch.org](https://pytorch.org).
+
+<img src="figures/pytorch-installer.jpg" width="600px">
+
+
+
+---
+
+
+
+
+Any questions? Please feel free to reach out in the [Discussion Forum](https://github.com/rasbt/LLMs-from-scratch/discussions).

setup/02_installing-python-libraries/python_environment_check.ipynb

@@ -0,0 +1,64 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c31e08b0-f551-4d67-b95e-41f49de3b392",
+   "metadata": {},
+   "source": [
+    "<font size=\"1\">\n",
+    "Supplementary code for \"Build a Large Language Model From Scratch\": <a href=\"https://www.manning.com/books/build-a-large-language-model-from-scratch\">https://www.manning.com/books/build-a-large-language-model-from-scratch</a> by <a href=\"https://sebastianraschka.com\">Sebastian Raschka</a><br>\n",
+    "Code repository: <a href=\"https://github.com/rasbt/LLMs-from-scratch\">https://github.com/rasbt/LLMs-from-scratch</a>\n",
+    "</font>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "67f6f7ed-b67d-465b-bf6f-a99b0d996930",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[OK] Your Python version is 3.10.12\n",
+      "[OK] numpy 1.26.0\n",
+      "[OK] matplotlib 3.8.2\n",
+      "[OK] jupyterlab 4.0.6\n",
+      "[OK] tensorflow 2.15.0\n",
+      "[OK] torch 2.2.1\n",
+      "[OK] tqdm 4.66.1\n",
+      "[OK] tiktoken 0.5.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "from python_environment_check import check_packages, get_requirements_dict\n",
+    "\n",
+    "d = get_requirements_dict()\n",
+    "check_packages(d)"
+   ]
+  }
+ ],
+ "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": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

setup/02_installing-python-libraries/python_environment_check.py

@@ -0,0 +1,77 @@
+# Copyright (c) Sebastian Raschka under Apache License 2.0 (see LICENSE.txt).
+# Source for "Build a Large Language Model From Scratch"
+#   - https://www.manning.com/books/build-a-large-language-model-from-scratch
+# Code: https://github.com/rasbt/LLMs-from-scratch
+
+from importlib.metadata import PackageNotFoundError, import_module
+import importlib.metadata
+from os.path import dirname, join, realpath
+from packaging.version import parse as version_parse
+import platform
+import sys
+
+if version_parse(platform.python_version()) < version_parse('3.9'):
+    print('[FAIL] We recommend Python 3.9 or newer but'
+          ' found version %s' % (sys.version))
+else:
+    print('[OK] Your Python version is %s' % (platform.python_version()))
+
+
+def get_packages(pkgs):
+    versions = []
+    for p in pkgs:
+        try:
+            imported = import_module(p)
+            try:
+                version = (getattr(imported, '__version__', None) or
+                           getattr(imported, 'version', None) or
+                           getattr(imported, 'version_info', None))
+                if version is None:
+                    # If common attributes don't exist, use importlib.metadata
+                    version = importlib.metadata.version(p)
+                versions.append(version)
+            except PackageNotFoundError:
+                # Handle case where package is not installed
+                versions.append('0.0')
+        except ImportError:
+            # Fallback if importlib.import_module fails for unexpected reasons
+            versions.append('0.0')
+    return versions
+
+
+def get_requirements_dict():
+    PROJECT_ROOT = dirname(realpath(__file__))
+    PROJECT_ROOT_UP_TWO = dirname(dirname(PROJECT_ROOT))
+    REQUIREMENTS_FILE = join(PROJECT_ROOT_UP_TWO, "requirements.txt")
+    d = {}
+    with open(REQUIREMENTS_FILE) as f:
+        for line in f:
+            if not line.strip():
+                continue
+            line = line.split("#")[0].strip()
+            line = line.split(" ")
+            line = [l.strip() for l in line]
+            d[line[0]] = line[-1]
+    return d
+
+
+def check_packages(d):
+    versions = get_packages(d.keys())
+
+    for (pkg_name, suggested_ver), actual_ver in zip(d.items(), versions):
+        if actual_ver == 'N/A':
+            continue
+        actual_ver, suggested_ver = version_parse(actual_ver), version_parse(suggested_ver)
+        if actual_ver < suggested_ver:
+            print(f'[FAIL] {pkg_name} {actual_ver}, please upgrade to >= {suggested_ver}')
+        else:
+            print(f'[OK] {pkg_name} {actual_ver}')
+
+
+def main():
+    d = get_requirements_dict()
+    check_packages(d)
+
+
+if __name__ == '__main__':
+    main()

setup/02_installing-python-libraries/tests.py

@@ -0,0 +1,14 @@
+# Copyright (c) Sebastian Raschka under Apache License 2.0 (see LICENSE.txt).
+# Source for "Build a Large Language Model From Scratch"
+#   - https://www.manning.com/books/build-a-large-language-model-from-scratch
+# Code: https://github.com/rasbt/LLMs-from-scratch
+
+# File for internal use (unit tests)
+
+from python_environment_check import main
+
+
+def test_main(capsys):
+    main()
+    captured = capsys.readouterr()
+    assert "FAIL" not in captured.out