first sync

ch02/02_installing-python-libraries/README.md

@@ -0,0 +1,46 @@
+# Libraries Used In This Workshop
+
+We will be using the following libraries in this workshop, and I highly recommend installing them before attending the event:
+
+- numpy >= 1.24.3 (The fundamental package for scientific computing with Python)
+- scipy >= 1.10.1 (Additional functions for NumPy)
+- pandas >= 2.0.2 (A data frame library)
+- matplotlib >= 3.7.1 (A plotting library)
+- jupyterlab >= 4.0 (An application for running Jupyter notebooks)
+- ipywidgets >= 8.0.6 (Fixes progress bar issues in Jupyter Lab)
+- scikit-learn >= 1.2.2 (A general machine learning library)
+- watermark >= 2.4.2 (An IPython/Jupyter extension for printing package information)
+- torch >= 2.0.1 (The PyTorch deep learning library)
+- torchvision >= 0.15.2 (PyTorch utilities for computer vision)
+- torchmetrics >= 0.11.4 (Metrics for PyTorch)
+- transformers >= 4.30.2 (Language transformers and LLMs for PyTorch)
+- lightning >= 2.0.3 (A library for advanced PyTorch features: multi-GPU, mixed-precision etc.)
+
+To install these requirements most conveniently, you can use the `requirements.txt` file:
+
+```
+pip install -r requirements.txt
+```
+
+![install-requirements](figures/install-requirements.png)
+
+Then, after completing the installation, please check if all the packages are installed and are up to date using
+
+```
+python_environment_check.py
+```
+
+![check_1](figures/check_1.png)
+
+It's also recommended to check the versions in JupyterLab by running the `jupyter_environment_check.ipynb` in this directory. Ideally, it should look like as follows:
+
+![check_1](figures/check_2.png)
+
+If you see the following issues, it's likely that your JupyterLab instance is connected to wrong conda environment:
+
+![jupyter-issues](figures/jupyter-issues.png)
+
+
+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:
+
+![watermark](figures/watermark.png)

ch02/02_installing-python-libraries/jupyter_environment_check.ipynb

@@ -0,0 +1,123 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "18d54544-92d0-412c-8e28-f9083b2bab6f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[OK] Your Python version is 3.10.12\n"
+     ]
+    }
+   ],
+   "source": [
+    "from python_environment_check import check_packages, get_requirements_dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "60e03297-4337-4181-b8eb-f483f406954a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d = get_requirements_dict()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d982ddf9-c167-4ed2-9fce-e271f2b1e1de",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[OK] numpy 1.25.1\n",
+      "[OK] scipy 1.11.1\n",
+      "[OK] pandas 2.0.3\n",
+      "[OK] matplotlib 3.7.2\n",
+      "[OK] jupyterlab 4.0.3\n",
+      "[OK] ipywidgets 8.0.7\n",
+      "[OK] watermark 2.4.3\n",
+      "[OK] torch 2.0.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "check_packages(d)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0bdd547-333c-42a9-92f3-4e552f206cf3",
+   "metadata": {},
+   "source": [
+    "Same checks as above but using watermark:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9d696044-9272-4b96-8305-34602807bb94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext watermark"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ce321731-a15a-4579-b33b-035730371eb3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "numpy     : 1.25.1\n",
+      "scipy     : 1.11.1\n",
+      "pandas    : 2.0.3\n",
+      "matplotlib: 3.7.2\n",
+      "sklearn   : 1.3.0\n",
+      "watermark : 2.4.3\n",
+      "torch     : 2.0.1\n",
+      "\n",
+      "conda environment: LLMs\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "%watermark --conda -p numpy,scipy,pandas,matplotlib,sklearn,watermark,torch"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

ch02/02_installing-python-libraries/python_environment_check.py

@@ -0,0 +1,62 @@
+# Sebastian Raschka, 2023
+
+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__(p)
+            try:
+                versions.append(imported.__version__)
+            except AttributeError:
+                try:
+                    versions.append(imported.version)
+                except AttributeError:
+                    try:
+                        versions.append(imported.version_info)
+                    except AttributeError:
+                        versions.append('0.0')
+        except ImportError:
+            print(f'[FAIL]: {p} is not installed and/or cannot be imported.')
+            versions.append('N/A')
+    return versions
+
+
+def get_requirements_dict():
+    PROJECT_ROOT = dirname(realpath(__file__))
+    REQUIREMENTS_FILE = join(PROJECT_ROOT, "requirements.txt")
+    d = {}
+    with open(REQUIREMENTS_FILE) as f:
+        for line in f:
+            line = line.split(" ")
+            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}')
+
+
+if __name__ == '__main__':
+    d = get_requirements_dict()
+    check_packages(d)

ch02/02_installing-python-libraries/requirements.txt

@@ -0,0 +1,8 @@
+numpy >= 1.24.3
+scipy >= 1.10.1
+pandas >= 2.0.2
+matplotlib >= 3.7.1
+jupyterlab >= 4.0
+ipywidgets >= 8.0.6
+watermark >= 2.4.2
+torch >= 2.0.1