Merge pull request #31 from FNALLPC/2024-update

2024 update
FNALLPC · Sep 6, 2024 · 90263e7 · 90263e7
2 parents cb06282 + 43f2ae9
commit 90263e7
Show file tree

Hide file tree

Showing 16 changed files with 632 additions and 473 deletions.
diff --git a/README.md b/README.md
@@ -25,15 +25,19 @@ ______________________________________________________________________
 ## Introduction
 
 This is a set of tutorials for the CMS Machine Learning Hands-on Advanced Tutorial Session (HATS). 
-They are intended to show you how to build machine learning models in python, using `Keras`, `TensorFlow`, and `PyTorch`, and use them in your `ROOT`-based analyses. 
-We will build event-level classifiers for differentiating VBF Higgs and standard model background 4 muon events and jet-level classifiers for differentiating boosted W boson jets from QCD jets using dense and convolutional neural networks.
+They are intended to show you how to build machine learning models in python, using `xgboost`, `Keras`, `TensorFlow`, and `PyTorch`, and use them in your `ROOT`-based analyses. 
+ We will build event-level classifiers for differentiating VBF Higgs and standard model background 4 muon events and jet-level classifiers for differentiating boosted W boson jets from QCD jets using BDTs, and dense and convolutional neural networks.
 We will also explore more advanced models such as graph neural networks (GNNs), variational autoencoders (VAEs), and generative adversarial networks (GANs) on simple datasets.
 
 ## Setup
 
-### Vanderbilt Jupyterhub (Recommended!)
+### Purdue Analysis Facility (New and recommended!)
 
-The recommended method for running the tutorials live is the Vanderbilt Jupyterhub, follow the instructions [here](https://fnallpc.github.io/machine-learning-hats/setup/vanderbilt-jupyterhub/vanderbilt.html).
+The recommended method for running the tutorials live is the Purdue AF, follow the instructions [here](https://fnallpc.github.io/machine-learning-hats/setup/purdue/purdue.html).
+
+### Vanderbilt Jupyterhub
+
+Another option is the Vanderbilt Jupyterhub, instructions [here](https://fnallpc.github.io/machine-learning-hats/setup/vanderbilt-jupyterhub/vanderbilt.html).
 
 ### FNAL LPC
 

diff --git a/machine-learning-hats/_toc.yml b/machine-learning-hats/_toc.yml
@@ -6,6 +6,7 @@ root: index
 parts:
   - caption: Setup
     chapters:
+    - file: setup/purdue/purdue
     - file: setup/vanderbilt-jupyterhub/vanderbilt
     - file: setup/lpc
     - file: setup-libraries
@@ -14,12 +15,13 @@ parts:
     maxdepth: 2
     chapters:
     - file: notebooks/1-datasets-uproot
-    - file: notebooks/2-dense
+    - file: notebooks/2-boosted-decision-tree
+    - file: notebooks/3-dense
       sections:
-        - file: notebooks/2.1-dense-keras
-        - file: notebooks/2.2-dense-pytorch
-        - file: notebooks/2.3-dense-bayesian-optimization
-    - file: notebooks/3-conv2d
-    - file: notebooks/4-gnn-cora
-    - file: notebooks/5-vae-mnist
-    - file: notebooks/6-gan-mnist
+        - file: notebooks/3.1-dense-keras
+        - file: notebooks/3.2-dense-pytorch
+        - file: notebooks/3.3-dense-bayesian-optimization
+    - file: notebooks/4-conv2d
+    - file: notebooks/5-gnn-cora
+    - file: notebooks/6-vae-mnist
+    - file: notebooks/7-gan-mnist
diff --git a/machine-learning-hats/notebooks/1-datasets-uproot.ipynb b/machine-learning-hats/notebooks/1-datasets-uproot.ipynb
diff --git a/machine-learning-hats/notebooks/2-boosted-decision-tree.ipynb b/machine-learning-hats/notebooks/2-boosted-decision-tree.ipynb
diff --git a/machine-learning-hats/notebooks/2-dense.md → machine-learning-hats/notebooks/3-dense.md b/machine-learning-hats/notebooks/2-dense.md → machine-learning-hats/notebooks/3-dense.md
diff --git a/...ning-hats/notebooks/2.1-dense-keras.ipynb → ...ning-hats/notebooks/3.1-dense-keras.ipynb b/...ning-hats/notebooks/2.1-dense-keras.ipynb → ...ning-hats/notebooks/3.1-dense-keras.ipynb
diff --git a/...ng-hats/notebooks/2.2-dense-pytorch.ipynb → ...ng-hats/notebooks/3.2-dense-pytorch.ipynb b/...ng-hats/notebooks/2.2-dense-pytorch.ipynb → ...ng-hats/notebooks/3.2-dense-pytorch.ipynb
diff --git a/...oks/2.3-dense-bayesian-optimization.ipynb → ...oks/3.3-dense-bayesian-optimization.ipynb b/...oks/2.3-dense-bayesian-optimization.ipynb → ...oks/3.3-dense-bayesian-optimization.ipynb
diff --git a/...ne-learning-hats/notebooks/3-conv2d.ipynb → ...ne-learning-hats/notebooks/4-conv2d.ipynb b/...ne-learning-hats/notebooks/3-conv2d.ipynb → ...ne-learning-hats/notebooks/4-conv2d.ipynb
@@ -55,14 +55,13 @@
     "### Convolution Operation\n",
     "Two-dimensional convolutional layer for image height $H$, width $W$, number of input channels $C$, number of output kernels (filters) $N$, and kernel height $J$ and width $K$ is given by:\n",
     "\n",
-    "\\begin{align}\n",
-    "\\label{convLayer}\n",
-    "\\boldsymbol{Y}[v,u,n] &= \\boldsymbol{\\beta}[n] + \\sum_{c=1}^{C} \\sum_{j=1}^{J} \\sum_{k=1}^{K} \\boldsymbol{X}[v+j,u+k,c]\\, \\boldsymbol{W}[j,k,c,n]\\,,\n",
-    "\\end{align}\n",
+    "$$\n",
+    "\\boldsymbol{Y}[v,u,n] = \\boldsymbol{\\beta}[n] + \\sum_{c=1}^{C} \\sum_{j=1}^{J} \\sum_{k=1}^{K} \\boldsymbol{X}[v+j,u+k,c]\\, \\boldsymbol{W}[j,k,c,n]\\,,\n",
+    "$$\n",
     "\n",
     "where $Y$ is the output tensor of size $V \\times U \\times N$, $W$ is the weight tensor of size $J \\times K \\times C \\times N$ and $\\beta$ is the bias vector of length $N$ .\n",
     "\n",
-    "The example below has $C=1$ input channel and $N=1$ ($J\\times K=3\\times 3$) kernel [credit](https://towardsdatascience.com/types-of-convolution-kernels-simplified-f040cb307c37):\n",
+    "The example below has $C=1$ input channel and $N=1$ ($J\\times K=3\\times 3$) kernel ([credit](https://towardsdatascience.com/types-of-convolution-kernels-simplified-f040cb307c37)):\n",
     "\n",
     "![convolution](https://miro.medium.com/v2/resize:fit:780/1*Eai425FYQQSNOaahTXqtgg.gif)"
    ]
@@ -84,7 +83,7 @@
    "source": [
     "### Pooling\n",
     "\n",
-    "We also add pooling layers to reduce the image size between layers. For example, max pooling: (also from [here]([page](https://cs231n.github.io/convolutional-networks/))\n",
+    "We also add pooling layers to reduce the image size between layers. For example, max pooling (also from [here]([page](https://cs231n.github.io/convolutional-networks/))):\n",
     "\n",
     "![maxpool](https://cs231n.github.io/assets/cnn/maxpool.jpeg)"
    ]

diff --git a/...-learning-hats/notebooks/4-gnn-cora.ipynb → ...-learning-hats/notebooks/5-gnn-cora.ipynb b/...-learning-hats/notebooks/4-gnn-cora.ipynb → ...-learning-hats/notebooks/5-gnn-cora.ipynb
diff --git a/...learning-hats/notebooks/5-vae-mnist.ipynb → ...learning-hats/notebooks/6-vae-mnist.ipynb b/...learning-hats/notebooks/5-vae-mnist.ipynb → ...learning-hats/notebooks/6-vae-mnist.ipynb
diff --git a/...learning-hats/notebooks/6-gan-mnist.ipynb → ...learning-hats/notebooks/7-gan-mnist.ipynb b/...learning-hats/notebooks/6-gan-mnist.ipynb → ...learning-hats/notebooks/7-gan-mnist.ipynb
diff --git a/machine-learning-hats/setup/purdue/folders.png b/machine-learning-hats/setup/purdue/folders.png
diff --git a/machine-learning-hats/setup/purdue/git.png b/machine-learning-hats/setup/purdue/git.png
diff --git a/machine-learning-hats/setup/purdue/purdue.md b/machine-learning-hats/setup/purdue/purdue.md
@@ -0,0 +1,33 @@
+# Purdue Analysis Facility
+
+## 1. Sign-in
+
+See the [Getting Started](https://analysis-facility.physics.purdue.edu/en/latest/doc-getting-started.html) guide and the rest of the documentation for details.
+
+Point your browser to https://cms.geddes.rcac.purdue.edu/hub and log in with your CERN or FNAL account.
+
+Create an instance with the default resources.
+
+
+## 2. Clone this repository
+
+1. Once the session starts, open the Git sidebar menu:
+
+![git menu](git.png)
+
+2. Click "Clone a Repository". 
+
+3. Copy and paste the repository URL: https://github.com/FNALLPC/machine-learning-hats.git and Clone with the default options.
+
+4. You should now see the `machine-learning-hats` directory in your file browser:
+
+![folders](folders.png)
+
+Open it and navigate to `machine-learning-hats` -> `notebooks` 
+
+
+## 3. Notebooks
+
+Open up a notebook and use the `Python3 kernel (default)` kernel.  You can now the run the notebook by pressing `Shift + Enter`, one cell at a time.
+
+
diff --git a/requirements.txt b/requirements.txt
@@ -10,4 +10,5 @@ pandas
 torch
 ipykernel
 tqdm
-jupyter
+jupyter
+xgboost
-Original file line number
+Diff line change
@@ Expand Up / @@ -10,4 +10,5 @@ pandas @@
     torch
     ipykernel
     tqdm
-    jupyter
+    jupyter
+    xgboost