JasonJarvan · JasonJarvan · Sep 15, 2020 · Sep 15, 2020 · Sep 15, 2020 · Sep 20, 2020
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,29 @@
+# LaTeX build artifacts
+*.aux
+*.log
+*.out
+*.toc
+*.lof
+*.lot
+*.fls
+*.fdb_latexmk
+*.synctex.gz
+*.bbl
+*.blg
+
+# Jupyter notebook checkpoints
+.ipynb_checkpoints/
+
+# Python cache and environment
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.mypy_cache/
+.venv/
+.env
+
+# OS-specific clutter
+.DS_Store
+Thumbs.db
+
diff --git a/lectures/CourseAdmin.pdf b/lectures/CourseAdmin.pdf
diff --git a/lectures/CourseAdmin.pptx b/lectures/CourseAdmin.pptx
diff --git a/lectures/Lect01_IntroML.pdf b/lectures/Lect01_IntroML.pdf
diff --git a/lectures/Lect01_IntroML.pptx b/lectures/Lect01_IntroML.pptx
diff --git a/lectures/Lect03_MultLinRegression.pptx b/lectures/Lect03_MultLinRegression.pptx
diff --git a/lectures/Lect05_Lasso.pdf b/lectures/Lect05_Lasso.pdf
diff --git a/lectures/Lect05_Lasso.pptx b/lectures/Lect05_Lasso.pptx
diff --git a/lectures/Lect06_LogisticReg.pdf b/lectures/Lect06_LogisticReg.pdf
diff --git a/lectures/Lect06_LogisticReg.pptx b/lectures/Lect06_LogisticReg.pptx
diff --git a/lectures/Lect07_Optim.pdf b/lectures/Lect07_Optim.pdf
diff --git a/lectures/Lect07_Optim.pptx b/lectures/Lect07_Optim.pptx
diff --git a/lectures/Lect08_SVM.pdf b/lectures/Lect08_SVM.pdf
diff --git a/lectures/Lect08_SVM.pptx b/lectures/Lect08_SVM.pptx
diff --git a/lectures/Lect08b_Kernel.pdf b/lectures/Lect08b_Kernel.pdf
diff --git a/lectures/Lect08b_Kernel.pptx b/lectures/Lect08b_Kernel.pptx
diff --git a/lectures/Lect09_NeuralNet.pdf b/lectures/Lect09_NeuralNet.pdf
diff --git a/lectures/Lect09_NeuralNet.pptx b/lectures/Lect09_NeuralNet.pptx
diff --git a/lectures/Lect10_ConvNet.pptx b/lectures/Lect10_ConvNet.pptx
diff --git a/lectures/Lect10_ConvNet_TF.pptx b/lectures/Lect10_ConvNet_TF.pptx
diff --git a/lectures/Lect11_PCA.pdf b/lectures/Lect11_PCA.pdf
diff --git a/lectures/Lect11_PCA.pptx b/lectures/Lect11_PCA.pptx
diff --git a/lectures/Lect12_IntroText.pdf b/lectures/Lect12_IntroText.pdf
diff --git a/lectures/Lect12_IntroText.pptx b/lectures/Lect12_IntroText.pptx
diff --git a/lectures/Lect12_Clustering.pdf → lectures/Lect13_Clustering.pdf b/lectures/Lect12_Clustering.pdf → lectures/Lect13_Clustering.pdf
diff --git a/lectures/Lect12_Clustering.pptx → lectures/Lect13_Clustering.pptx b/lectures/Lect12_Clustering.pptx → lectures/Lect13_Clustering.pptx
diff --git a/lectures/Lect13_Trees.pdf → lectures/Lect14_Trees.pdf b/lectures/Lect13_Trees.pdf → lectures/Lect14_Trees.pdf
diff --git a/lectures/Lect13_Trees.pptx → lectures/Lect14_Trees.pptx b/lectures/Lect13_Trees.pptx → lectures/Lect14_Trees.pptx
diff --git a/lectures/Lect13_Review.pdf → lectures/Lect15_Review.pdf b/lectures/Lect13_Review.pdf → lectures/Lect15_Review.pdf
diff --git a/lectures/Lect13_Review.pptx → lectures/Lect15_Review.pptx b/lectures/Lect13_Review.pptx → lectures/Lect15_Review.pptx
diff --git a/online_class.md b/online_class.md
@@ -30,13 +30,21 @@ YouTube video.  You can also like the video and subscribe to the channel.
 
 ## Material Contents
 
-Right now, we have only completed a few units, but more will be added.
+Some videos still being created.  
 
 * [Unit 1:  What is Machine Learning?](./unit01_intro/online/readme.md)
 * Unit 2:  Simple Linear Regression
     * This material will be skipped for the graduate students
 * [Unit 3:  Multiple Linear Regression](./unit03_mult_lin_reg/online/readme.md)
 * [Unit 4:  Model Order Selection](./unit04_model_sel/online/readme.md)
+* [Unit 5:  LASSO Regularization](./unit05_lasso/online/readme.md)
+* [Unit 6:  Logistic Regression](./unit06_logistic/online/readme.md)
+* [Unit 7:  Non-linear Optimization](./unit07_optim/online/readme.md)
+* [Unit 8:  SVM](./unit08_svm/online/readme.md)
+* [Unit 9:  Neural Networks](./unit09_neural/online/readme.md)
+* [Unit 10: Convolutional and Deep Networks](./unit10_cnn/online/readme.md)
+* [Unit 11: PCA](./unit11_pca/online/readme.md)
+* [Unit 12: Clustering](./unit12_cluster/online/readme.md)
 
 
 

diff --git a/sequence.md b/sequence.md
@@ -38,12 +38,14 @@ to documents that don't match the number of the unit.  We will fix these soon!
     * Lecture:  Introduction to Machine Learning [[pdf]](./lectures/Lect01_IntroML.pdf)
      [[Powerpoint]](./lectures/Lect01_IntroML.pptx)    
      * [Lecture videos](./unit01_intro/online/readme.md)
-     * [Demo:  Introduction to numpy vectors](./unit01_intro/demo_intro_vectors.ipynb)
+     * [Demo:  Introduction to numpy vectors](./unit01_intro/demo_intro_vectors.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sdrangan/introml/blob/master/unit01_intro/demo_intro_vectors.ipynb)
 * Unit 2:  Simple linear regression
     * Lecture:  Simple linear regression [[pdf]](./lectures/Lect02_SimpRegression.pdf)
      [[Powerpoint]](./lectures/Lect02_SimpRegression.pptx)        
     * [Demo:  Understanding automobile mpg](./unit02_simp_lin_reg/demo_auto_mpg.ipynb)
+   [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sdrangan/introml/blob/master/unit02_simp_lin_reg/demo_auto_mpg.ipynb)
     * [Lab: Boston housing data](./unit02_simp_lin_reg/lab_housing_partial.ipynb) 
+    [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sdrangan/introml/blob/master/unit02_simp_lin_reg/lab_housing_partial.ipynb)
     * Problems [[pdf]](./unit02_simp_lin_reg/prob/prob_simp_lin_reg.pdf) [[Latex]](./unit02_simp_lin_reg/prob/prob_simp_lin_reg.tex)
 * Unit 3:  Multiple linear regression
     * Lecture:  Multiple linear regression [[pdf]](./lectures/Lect03_MultLinRegression.pdf)
@@ -58,7 +60,8 @@ to documents that don't match the number of the unit.  We will fix these soon!
     * Lecture:  Model selection [[pdf]](./lectures/Lect04_ModelSelection.pdf)
      [[Powerpoint]](./lectures/Lect04_ModelSelection.pptx)    
     * [Lecture videos](./unit04_model_sel/online/readme.md)     
-    * [Demo:  Polynomial order selection with cross-validation](./unit04_model_sel/demo_polyfit.ipynb)
+    * [Demo 1:  Polynomial order selection with cross-validation](./unit04_model_sel/demo_polyfit.ipynb)
+    * [Demo 2:  Feature transforms and model validation](./unit04_model_sel/demo2_transform.ipynb)
     * [Lab: Neural decoding motor cortex signals](./unit04_model_sel/lab_neural_partial.ipynb)          
     * Problems [[pdf]](./unit04_model_sel/prob/prob_model_sel.pdf) [[Latex]](./unit03_model_sel/hw/hw03_model_sel.tex)    
 * Unit 5:  Regularization and LASSO
@@ -72,7 +75,8 @@ to documents that don't match the number of the unit.  We will fix these soon!
 * [Unit 6:  Logistic regression](./unit06_logistic/readme.md)
     * Lecture:  Linear classification and logistic regression
     [[pdf]](./lectures/Lect06_LogisticReg.pdf)
-    [[Powerpoint]](./lectures/Lect06_LogisticReg.pptx)         
+    [[Powerpoint]](./lectures/Lect06_LogisticReg.pptx) 
+    * [Lecture videos](./unit06_logistic/online/readme.md)            
     * [Demo:  Breast cancer diagnosis via logistic regression](./unit06_logistic/demo_breast_cancer.ipynb)
     * [Lab: Genetic analysis of Down's syndrome in mice](./unit06_logistic/lab_gene_partial.ipynb)
     * Problems [[pdf]](./unit06_logistic/prob/prob_logistic.pdf)
@@ -81,31 +85,36 @@ to documents that don't match the number of the unit.  We will fix these soon!
     * Lecture:  Nonlinear optimization and gradient descent
     [[pdf]](./lectures/Lect07_Optim.pdf)
     [[Powerpoint]](./lectures/Lect07_Optim.pptx)         
+    * [Lecture videos](./unit07_optim/online/readme.md)      
     * [Demo 1:  Computing gradients](./unit07_optim/demo1_computing_gradients.ipynb)
     * [Demo 2:  Simple gradient descent optimization](./unit07_optim/demo2_grad_descent.ipynb)    
     * [Lab: Nonlinear least squares material modeling](./unit07_optim/lab_nlls_partial.ipynb)
     * Problems [[pdf]](./unit07_optim/prob/prob_optim.pdf)
     [[Latex]](./unit07_optim/prob/prob_optim.tex)
 * [Unit 8:  Support vector machines](./unit08_svm/readme.md)
     * Lecture:  SVM [[pdf]](./lectures/Lect08_SVM.pdf)
-    [[Powerpoint]](./lectures/Lect08_SVM.pptx)         
-    * [Demo:  MNIST digit classification](./unit08_svm/demo_mnist_svm.ipynb)
+    [[Powerpoint]](./lectures/Lect08_SVM.pptx)      
+    * [Lecture videos](./unit08_svm/online/readme.md)   
+    * [Demo 1:  MNIST digit classification](./unit08_svm/demo_mnist_svm.ipynb)
+    * [Demo 2:  Visualizing kernels](./unit08_svm/demo2_kernels.ipynb)
     * [Lab: Extended MNIST with letters](./unit08_svm/lab_emnist_partial.ipynb)    
     * Problems [[pdf]](./unit08_svm/prob/prob_svm.pdf) [[Latex]](./unit08_svm/prob/prob_svm.tex) 
 * [Unit 9: Neural networks with Keras and Tensorflow](./unit09_neural/readme.md)
     * Lecture:  Neural networks [[pdf]](./lectures/Lect09_NeuralNet.pdf)
     [[Powerpoint]](./lectures/Lect09_NeuralNet.pptx)         
+    * [Lecture videos](./unit09_neural/online/readme.md)   
     * Supplementary notes with solved problems [[pdf]](./unit09_neural/prob/supplementary_neural.pdf) [[Latex]](./unit09_neural/prob/supplementary_neural.tex)
     * [Demo 1: First neural network in Keras](./unit09_neural/demo1_synthetic.ipynb)
     * [Demo 2: MNIST neural network classification](./unit09_neural/demo2_mnist_neural.ipynb)
     * [Lab:  Music instrument classification](./unit09_neural/lab_music_partial.ipynb)
-    * [In-class Exercise](./unit09_neural/in_class_exercise.ipynb)
-    * Problems: [[pdf]](./unit09_neural/prob/prob_neural.pdf) [[Latex]](./unit97_neural/prob/prob_neural.tex)    
+    * [In-class Exercise](./unit09_neural/neural_inclass.ipynb)
+    * Problems: [[pdf]](./unit09_neural/prob/prob_neural.pdf) [[Latex]](./unit09_neural/prob/prob_neural.tex)    
 * [Unit 10:  Convolutional and deep networks](./unit10_cnn/readme.md)
     * Lecture:  Convolutional and deep networks
     [[pdf]](./lectures/Lect10_ConvNet.pdf)
     [[Powerpoint]](./lectures/Lect10_ConvNet.pptx)         
     * [Setting up a GPU instance](./GCP/gpu_setup.md) (Recommended)
+    * [Lecture videos](./unit10_cnn/online/readme.md)   
     * [Demo 1: 2D convolutions and convolutional layers in keras](./unit10_cnn/demo1_convolutions.ipynb)
     * [Demo 2: Creating an image set using the Flickr API](./unit10_cnn/demo2_flickr_images.ipynb)
     * [Demo 3: Exploring the deep VGG16 network](./unit10_cnn/demo3_vgg16.ipynb)
@@ -117,13 +126,18 @@ to documents that don't match the number of the unit.  We will fix these soon!
 * [Unit 11:  PCA](./pca/readme.md)
     * Lecture:  PCA [[pdf]](./lectures/Lect11_PCA.pdf), Modifed Note [[pdf]](./lectures/Lect11_PCA_modified.pdf)
     [[Powerpoint]](./lectures/Lect11_PCA_modified.pptx)         
+    * [Lecture videos](./unit11_pca/online/readme.md)   
     * [Demo 1:  PCA eigen-faces-SVM](./unit11_pca/demo1_eigen_face.ipynb)
     * [Demo 2:  Low-rank matrix completion via embedding layers](./unit11_pca/demo2_low_rank.ipynb)
     * [Lab:  PCA with hyper-parameter optimization](./unit11_pca/lab_wine_partial.ipynb)
     * Problems [[pdf]](./unit11_pca/prob/prob_PCA.pdf) [[Latex]](./unit11_pca/prob/prob_PCA.tex)
-* [Unit 12:  Clustering and EM](./unit12_cluster/readme.md)
-    * Lecture:  Clustering and EM [[pdf]](./lectures/Lect12_Clustering.pdf)
-    [[Powerpoint]](./lectures/Lect12_Clustering.pptx)         
+* [Unit 12:  Introduction to Text](./unit12_text)
+    * Lecture:  Introduction to Text [[pdf](./lectures/Lect12_IntroText.pdf)] [[Powerpoint](./lectures/Lect12_IntroText.pptx)]
+    * [Demo 1: Tokenization](./unit12_text/demo_tokenization.ipynb)
+    * [Demo 2: Movie reviews](./unit12_text/demo_movie_reviews.ipynb)
+* [Unit 13:  Clustering and EM](./unit13_cluster/readme.md)
+    * Lecture:  Clustering and EM [[pdf]](./lectures/Lect13_Clustering.pdf)
+    [[Powerpoint]](./lectures/Lect13_Clustering.pptx)         
     * [Demo 1: Document clustering via k-means and latent semantic analysis](./unit12_cluster/demo1_doc_cluster.ipynb)
     * [Demo 2: Color quantization via k-means and EM-GMM](./unit12_cluster/demo2_kmeans_GMM_color_quantization.ipynb)    
     * Homework [[pdf]](./unit12_cluster/prob/prob_clustering.pdf) [[Latex]](./unit12_cluster/prob/prob_clustering.tex)

diff --git a/unit02_simp_lin_reg/demo_auto_mpg.ipynb b/unit02_simp_lin_reg/demo_auto_mpg.ipynb
diff --git a/unit02_simp_lin_reg/lab_housing_partial.ipynb b/unit02_simp_lin_reg/lab_housing_partial.ipynb
@@ -310,7 +310,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.6"
+   "version": "3.8.3"
   }
  },
  "nbformat": 4,

diff --git a/unit03_mult_lin_reg/lab_robot_calib_partial.ipynb b/unit03_mult_lin_reg/lab_robot_calib_partial.ipynb
@@ -8,9 +8,9 @@
     "\n",
     "In this lab, we will illustrate the use of multiple linear regression for calibrating robot control.  In addition to reviewing the concepts in the [multiple linear regression demo](./glucose.ipynb), you will see how to use multiple linear regression for time series data -- an important concept in dynamical systems such as robotics.\n",
     "\n",
-    "The robot data for the lab is taken generously from the TU Dortmund's [Multiple Link Robot Arms Project](http://www.rst.e-technik.tu-dortmund.de/cms/en/research/robotics/TUDOR_engl/index.html).  As part of the project, they have created an excellent public dataset: [MERIt](http://www.rst.e-technik.tu-dortmund.de/cms/en/research/robotics/TUDOR_engl/index.html#h3MERIt) -- A Multi-Elastic-Link Robot Identification Dataset that can be used for understanding robot dynamics.  The data is from a three link robot:\n",
+    "The robot data for the lab is taken generously from the TU Dortmund's [TUDOR project](https://rst.etit.tu-dortmund.de/en/forschung/robotik/leichtbau/details-tudor/), TU Dortmund Omni-Elastic Robot.  As part of the project, they have created an excellent public dataset: [MERIt](https://rst.etit.tu-dortmund.de/en/forschung/robotik/leichtbau/details-tudor/#c11560) -- A Multi-Elastic-Link Robot Identification Dataset that can be used for understanding robot dynamics.  The data is from a three link robot:\n",
     "\n",
-    "<img src=\"http://www.rst.e-technik.tu-dortmund.de/cms/Medienpool/redaktionelleBilder/Forschung/Schwerpunkte/TUDOR_engl/TUDORBild.png\" height=\"200\" width=\"200\">\n",
+    "<img src=\"https://rst.etit.tu-dortmund.de/storages/rst-etit/r/Media_Forschung/Robotik/Leichtbau/TUDORBild.png\" height=\"200\" width=\"200\">\n",
     "\n",
     "\n",
     "We will focus on predicting the current draw into one of the joints as a function of the robot motion.  Such models are essential in predicting the overall robot power consumption.  Several other models could also be used."
@@ -33,19 +33,53 @@
     "import pandas as pd\n",
     "import numpy as np\n",
     "import matplotlib\n",
-    "import matplotlib.pyplot as plt\n",
-    "%matplotlib inline"
+    "import matplotlib.pyplot as plt"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The full MERIt dataset can be obtained from the [MERIt site](http://www.rst.e-technik.tu-dortmund.de/cms/en/research/robotics/TUDOR_engl/index.html#h3MERIt).  But, this dataset is large.  Included in this repository are two of the ten experiments.  Each experiments corresonds to 80 seconds of recorded motion.  We will use the following files:\n",
+    "The full MERIt dataset can be obtained from the [MERIt site](https://rst.etit.tu-dortmund.de/en/forschung/robotik/leichtbau/details-tudor/#c11560).  But, this dataset is large.  Included in this repository are two of the ten experiments.  Each experiments corresonds to 80 seconds of recorded motion.  We will use the following files:\n",
     "* [exp1.csv](./exp1.csv) for training\n",
     "* [exp2.csv](./exp2.csv) for test\n",
     "\n",
-    "Below, I have supplied the column headers in the `names` array.  Use the `pd.read_csv` command to load the data.  Use the `index_col` option to specify that column 0 (the one with time) is the *index* column.  You can review [simple linear regression demo](..\\simp_lin_reg\\auto_mpg.ipynb) for examples of using the `pd.read_csv` command."
+    "If you are running this notebook on Google colab, you will need to run the following commands to load the files onto your local machine.  Otherwise, if you have clone the repository, the files should be in the directory as the notebook and you can skip this step."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "File exp1.csv is already downloaded\n",
+      "File exp2.csv is already downloaded\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from six.moves import urllib\n",
+    "\n",
+    "for fn_dst in ['exp1.csv', 'exp2.csv']:\n",
+    "    fn_src = 'https://raw.githubusercontent.com/sdrangan/introml/master/unit03_mult_lin_reg/%s' % fn_dst\n",
+    "\n",
+    "    if os.path.isfile(fn_dst):\n",
+    "        print('File %s is already downloaded' % fn_dst)\n",
+    "    else:\n",
+    "        print('Downloaded %s' % fn_dst)\n",
+    "        urllib.request.urlretrieve(fn_src, fn_dst)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Below, I have supplied the column headers in the `names` array.  Use the `pd.read_csv` command to load the training data in `exp1.csv`.  Use the `index_col` option to specify that column 0 (the one with time) is the *index* column.  You can review [simple linear regression demo](..\\simp_lin_reg\\auto_mpg.ipynb) for examples of using the `pd.read_csv` command."
    ]
   },
   {
@@ -239,7 +273,7 @@
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -253,7 +287,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.6"
+   "version": "3.8.11"
   }
  },
  "nbformat": 4,

diff --git a/unit04_model_sel/demo2_transform.ipynb b/unit04_model_sel/demo2_transform.ipynb
diff --git a/unit04_model_sel/lab_neural_partial.ipynb b/unit04_model_sel/lab_neural_partial.ipynb
@@ -196,7 +196,7 @@
     "    \n",
     "where `p` is the number of features and `w[j,k]` is a matrix of coefficients.  In this model,  `yhat[i,:]` at time `i` was only dependent on the inputs  `X[i,:]` at time `i`.  In signal processing, this is called a *memoryless* model.  However, in many physical systems, such as those that arise in neuroscience, there is a delay between the inputs `X[i,:]` and the outputs `y[i]`.  For such cases, we can use a model of the form,\n",
     "\n",
-    "    yhat[i+d,k] = \\sum_{k=0}^d  \\sum_{j=0}^{p-1} \\sum_{m=0}^d X[i+m,j]*W[j,m,k] + b[k]\n",
+    "    yhat[i+d,k] = \\sum_{j=0}^{p-1} \\sum_{m=0}^d X[i+m,j]*W[j,m,k] + b[k]\n",
     "    \n",
     "where `W` is a 3-dim array of coefficients where:\n",
     "\n",
@@ -303,26 +303,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We will look at model orders up to `dmax=15`.  Create a delayed matrix data, `Xdly,ydly` from the reduced data, `Xred,yred` using `create_dly_data` with `dly=dmax`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dmax = 15\n",
+    "Now complete the following code to implement K-fold cross validation with `nfold=5` and values of delays `dtest = [0,1,...,dmax]`.  \n",
     "\n",
-    "# TODO\n",
-    "# Xdly, ydly = ..."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Complete the following code to implement K-fold cross validation with `nfold=5` and values of delays `dtest = [0,1,...,dmax]`."
+    "The code also includes a progress bar using the `tqdm` package.  This is very useful when you have a long computation.\n",
+    "\n",
+    "Note:  Some students appeared to use the `mse` metric (i.e. RSS per sample) instead of `R^2`.  That is fine.  For the solution, I have computed both."
    ]
   },
   {
@@ -332,9 +317,10 @@
    "outputs": [],
    "source": [
     "import  sklearn.model_selection \n",
+    "import tqdm.notebook\n",
     "\n",
-    "# Number of folds\n",
-    "nfold = 5\n",
+    "nfold = 5  # Number of folds\n",
+    "dmax = 15  # maximum number of delays\n",
     "\n",
     "# TODO:  Create a k-fold object\n",
     "# kf = sklearn.model_selection.KFold(...)\n",
@@ -345,31 +331,39 @@
     "\n",
     "# TODO.  \n",
     "# Initialize a matrix Rsq to hold values of the R^2 across the model orders and folds.\n",
-    "# Rsq = np.zeros(...)\n",
+    "# Alternatively, you can also create an RSS matrix\n",
+    "\n",
+    "# Create a progress bar.  Note there are nd*nfold total fits.\n",
+    "pbar = tqdm.notebook.tqdm(\n",
+    "    total=nfold*nd, initial=0,\n",
+    "    unit='fits', unit_divisor=nd, desc='Model order test')\n",
     "\n",
-    "# Loop over the folds\n",
-    "for isplit, Ind in enumerate(kf.split(Xdly)):\n",
-    "    \n",
-    "    print(\"fold = %d \" % isplit)\n",
-    "    \n",
-    "    # Get the training data in the split\n",
-    "    Itr, Its = Ind        \n",
     "\n",
-    "    for it, d in enumerate(dtest):\n",
-    "        # TODO:  \n",
-    "        # Xdly1 = Xdly with the columns corresponding to only the `d+1` most recent times.\n",
+    "for it, d in enumerate(dtest):\n",
+    "    # TODO:  \n",
+    "    # Create the delayed data using the create_dly_function from the reduced\n",
+    "    # data Xred, yred\n",
+    "    #     Xdly, ydly = create_dly_data(...)    \n",
     "        \n",
+    "    # Loop over the folds\n",
+    "    for isplit, Ind in enumerate(kf.split(Xdly)):\n",
+    "\n",
+    "        # Get the training data in the split\n",
+    "        Itr, Its = Ind        \n",
     "\n",
     "        # TODO\n",
-    "        # Split the data (Xdly1,ydly) into training and test\n",
+    "        # Split the data (Xdly,ydly) into training and test\n",
     "        # Xtr = ...\n",
     "        # ytr = ...\n",
     "        # Xts = ...\n",
     "        # yts = ...\n",
     "        \n",
-    "        # TODO:  Fit data on training data\n",
+    "        # TODO:  Fit data on training data        \n",
+    "\n",
+    "        # TODO:  Measure the R^2 vale on test data and store in the matrix Rsq\n",
     "        \n",
-    "        # TODO:  Measure the R^2 vale on test data and store in the matrix Rsq        "
+    "        pbar.update(1)\n",
+    "pbar.close()       "
    ]
   },
   {