From 3d86c8681c5d43f5a0237eb322a1cde068b38b78 Mon Sep 17 00:00:00 2001
From: Uwe Schmitt <uwe.schmitt@id.ethz.ch>
Date: Mon, 7 Jan 2019 17:42:25 +0100
Subject: [PATCH] changes after review session with Mik
---
01_introduction.ipynb | 211 +++++++++++++++++++-----------------------
1 file changed, 96 insertions(+), 115 deletions(-)
diff --git a/01_introduction.ipynb b/01_introduction.ipynb
index 313f532..4d7452a 100644
--- a/01_introduction.ipynb
+++ b/01_introduction.ipynb
@@ -86,8 +86,8 @@
" 1957-65: \"k-means\" clustering algorithm\n",
" 1959: Term \"machine learning\" is coined by Arthur Samuel, an AI pioneer\n",
" 1969: Book \"Perceptrons\": Limitations of Neural Networks\n",
- " 1984: Book \"Classification And Regression Trees\"\n",
" 1974-86: Neural networks learning breakthrough: backpropagation method\n",
+ " 1984: Book \"Classification And Regression Trees\"\n",
" 1995: Randomized Forests and Support Vector Machines methods\n",
" 1998: Public appearance: first ML implementations of spam filtering methods; naive Bayes Classifier method\n",
" 2006-12: Neural networks learning breakthrough: deep learning\n",
@@ -327,6 +327,39 @@
"print(dir(dd))"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "DESCR:\n",
+ " Optical Recognition of Handwritten Digits Data Set\n",
+ "===================================================\n",
+ "\n",
+ "Notes\n",
+ "-----\n",
+ "Data Set Characteristics:\n",
+ " :Number of Instances: 5620\n",
+ " :Number of Attributes: 64\n",
+ " :Attribute Information: 8x8 image of integer pixels in the range 0..16.\n",
+ " :Missing Attribute Values: None\n",
+ " :Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)\n",
+ " :Date: July; 1998\n",
+ "\n",
+ "This is a copy of the test set of the UCI ML hand-written digits datasets\n",
+ "http://archive.ics.uci.edu/ml/datas \n",
+ "[...]\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(\"DESCR:\\n\", dd.DESCR[:500], \"\\n[...]\") # description of the dataset"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -336,7 +369,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -371,15 +404,15 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "images.ndim: 3\n",
"images[0].shape: (8, 8)\n",
+ "\n",
"images[0]:\n",
" [[ 0. 0. 5. 13. 9. 1. 0. 0.]\n",
" [ 0. 0. 13. 15. 10. 15. 5. 0.]\n",
@@ -388,44 +421,14 @@
" [ 0. 5. 8. 0. 0. 9. 8. 0.]\n",
" [ 0. 4. 11. 0. 1. 12. 7. 0.]\n",
" [ 0. 2. 14. 5. 10. 12. 0. 0.]\n",
- " [ 0. 0. 6. 13. 10. 0. 0. 0.]]\n",
- "images.shape: (1797, 8, 8)\n",
- "images.size: 115008\n",
- "images.dtype: float64\n",
- "images.itemsize: 8\n",
- "target.size: 1797\n",
- "target_names: [0 1 2 3 4 5 6 7 8 9]\n",
- "DESCR:\n",
- " Optical Recognition of Handwritten Digits Data Set\n",
- "===================================================\n",
- "\n",
- "Notes\n",
- "-----\n",
- "Data Set Characteristics:\n",
- " :Number of Instances: 5620\n",
- " :Number of Attributes: 64\n",
- " :Attribute Information: 8x8 image of integer pixels in the range 0..16.\n",
- " :Missing Attribute Values: None\n",
- " :Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)\n",
- " :Date: July; 1998\n",
- "\n",
- "This is a copy of the test set of the UCI ML hand-written digits datasets\n",
- "http://archive.ics.uci.edu/ml/datas \n",
- "[...]\n"
+ " [ 0. 0. 6. 13. 10. 0. 0. 0.]]\n"
]
}
],
"source": [
- "print(\"images.ndim:\", dd.images.ndim) # number of dimensions of the array\n",
"print(\"images[0].shape:\", dd.images[0].shape) # dimensions of a first sample array\n",
- "print(\"images[0]:\\n\", dd.images[0]) # first sample array\n",
- "print(\"images.shape:\", dd.images.shape) # dimensions of the array of all samples\n",
- "print(\"images.size:\", dd.images.size) # total number of elements of the array\n",
- "print(\"images.dtype:\", dd.images.dtype) # type of the elements in the array\n",
- "print(\"images.itemsize:\", dd.images.itemsize) # size in bytes of each element of the array\n",
- "print(\"target.size:\", dd.target.size) # size of the target feature vector (labels of samples)\n",
- "print(\"target_names:\", dd.target_names) # classes vector\n",
- "print(\"DESCR:\\n\", dd.DESCR[:500], \"\\n[...]\") # description of the dataset"
+ "print()\n",
+ "print(\"images[0]:\\n\", dd.images[0]) # first sample array"
]
},
{
@@ -437,7 +440,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -458,33 +461,6 @@
"print(\"image_vector:\", image_vector)"
]
},
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "(1797, 8, 8)\n",
- "(1797, 64)\n",
- "[ 0. 0. 5. 13. 9. 1. 0. 0. 0. 0. 13. 15. 10. 15. 5. 0. 0. 3.\n",
- " 15. 2. 0. 11. 8. 0. 0. 4. 12. 0. 0. 8. 8. 0. 0. 5. 8. 0.\n",
- " 0. 9. 8. 0. 0. 4. 11. 0. 1. 12. 7. 0. 0. 2. 14. 5. 10. 12.\n",
- " 0. 0. 0. 0. 6. 13. 10. 0. 0. 0.]\n"
- ]
- }
- ],
- "source": [
- "print(dd.images.shape)\n",
- "\n",
- "# reashape to 1797, 64:\n",
- "images_flat = dd.images.reshape(-1, 64)\n",
- "print(images_flat.shape)\n",
- "print(images_flat[0])"
- ]
- },
{
"cell_type": "markdown",
"metadata": {},
@@ -496,7 +472,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "If we start a machine learning project for texts, we first have to choose a dictionary - set of words for this project. The final representation of a text as a feature vector depends on this dictionary.\n",
+ "If we start a machine learning project for texts, we first have to choose a dictionary (a set of words) for this project. The words in the dictionary are enumerated. The final representation of a text as a feature vector depends on this dictionary.\n",
"\n",
"Such a dictionary can be very large, but for the sake of simplicity we use a very small enumerated dictionary to explain the overall procedure:\n",
"\n",
@@ -582,6 +558,11 @@
"source": [
"## ML lingo: What are the different types of datasets?\n",
"\n",
+ "<div class=\"alert alert-block alert-danger\">\n",
+ "<strong>TODO:</strong> move to later section about cross validation.</div>\n",
+ "\n",
+ "\n",
+ "\n",
"<div class=\"alert alert-block alert-warning\">\n",
"<i class=\"fa fa-warning\"></i> <strong>Definitions</strong>\n",
"\n",
@@ -702,7 +683,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# Exercise section 1"
+ "# Hands-on section"
]
},
{
@@ -710,8 +691,9 @@
"metadata": {},
"source": [
"<div class=\"alert alert-block alert-danger\">\n",
- "<strong>TODO:</strong> transform to az set of small exercises (instead of a tutorial/example as it is now).\n",
- "</div>"
+ "<strong>TODO:</strong> transform to a set of small exercises (instead of a tutorial/example as it is now).\n",
+ "</div>\n",
+ "\n"
]
},
{
@@ -1102,13 +1084,6 @@
"</div>"
]
},
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
{
"cell_type": "code",
"execution_count": 14,
@@ -1161,42 +1136,43 @@
]
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": 15,
"metadata": {},
+ "outputs": [
+ {
+ "ename": "NotFittedError",
+ "evalue": "This LogisticRegression instance is not fitted yet",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNotFittedError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-15-9e1ed3d39774>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Sanity check: can't predict if not fitted (trained)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mclassifier\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_features\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;32m~/Projects/machinelearning-introduction-workshop/venv3.6/lib/python3.6/site-packages/sklearn/linear_model/base.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, X)\u001b[0m\n\u001b[1;32m 322\u001b[0m \u001b[0mPredicted\u001b[0m \u001b[0;32mclass\u001b[0m \u001b[0mlabel\u001b[0m \u001b[0mper\u001b[0m \u001b[0msample\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 323\u001b[0m \"\"\"\n\u001b[0;32m--> 324\u001b[0;31m \u001b[0mscores\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecision_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 325\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscores\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 326\u001b[0m \u001b[0mindices\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mscores\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;32m~/Projects/machinelearning-introduction-workshop/venv3.6/lib/python3.6/site-packages/sklearn/linear_model/base.py\u001b[0m in \u001b[0;36mdecision_function\u001b[0;34m(self, X)\u001b[0m\n\u001b[1;32m 296\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'coef_'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcoef_\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 297\u001b[0m raise NotFittedError(\"This %(name)s instance is not fitted \"\n\u001b[0;32m--> 298\u001b[0;31m \"yet\" % {'name': type(self).__name__})\n\u001b[0m\u001b[1;32m 299\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 300\u001b[0m \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'csr'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+ "\u001b[0;31mNotFittedError\u001b[0m: This LogisticRegression instance is not fitted yet"
+ ]
+ }
+ ],
"source": [
- "<div class=\"alert alert-block alert-warning\">\n",
- "<i class=\"fa fa-warning\"></i> <strong>`scikit-learn` API</strong>\n",
- "\n",
- "In <code>scikit-learn</code> all classifiers have:\n",
- "<ul>\n",
- " <li>a <strong><code>fit()</code></strong> method to learn from data, and</li>\n",
- " <li>and a subsequent <strong><code>predict()</code></strong> method for predicting classes from input features.</li>\n",
- "</ul>\n",
- "</div>"
+ "# Sanity check: can't predict if not fitted (trained)\n",
+ "classifier.predict(input_features)"
]
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "train first..\n",
"(225,)\n"
]
}
],
"source": [
- "# Sanity check: can't predict if not fitted (trained)\n",
- "from sklearn.exceptions import NotFittedError\n",
- "try:\n",
- " classifier.predict(input_features)\n",
- "except NotFittedError:\n",
- " print(\"train first..\")\n",
- "\n",
"# Fit\n",
"classifier.fit(input_features, labels)\n",
"\n",
@@ -1214,7 +1190,7 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 17,
"metadata": {},
"outputs": [
{
@@ -1245,7 +1221,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -1301,7 +1277,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# Exercise section 2"
+ "# Exercise section 1"
]
},
{
@@ -1334,7 +1310,7 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 19,
"metadata": {},
"outputs": [
{
@@ -1368,8 +1344,10 @@
"\n",
"<div class=\"alert alert-block alert-info\">\n",
"<i class=\"fa fa-info-circle\"></i>\n",
- "Better re-classification does not indicate here that <code>SVC</code> is better than <code>LogisticRegression</code>. At most it seems to fit better to our training data. We will learn later that this may be actually not a good thing.\n",
- "</div>\n"
+ "Better re-classification in our example does not indicate here that <code>SVC</code> is better than <code>LogisticRegression</code> in all cases. The performance of a classifier strongly depends on the data set.\n",
+ "</div>\n",
+ "\n",
+ "\n"
]
},
{
@@ -1383,12 +1361,15 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "Both `LogisticRegression` and `SVC` classifiers have a parameter `C` which allows to enforce a \"simplification\" (often called **regularization**) of the resulting model. Test the beers data \"re-classification\" with different values of this parameter.\n"
+ "Both `LogisticRegression` and `SVC` classifiers have a parameter `C` which allows to enforce a \"simplification\" (often called **regularization**) of the resulting model. Test the beers data \"re-classification\" with different values of this parameter.\n",
+ "\n",
+ "\n",
+ "**TOBE discussed**: is \"regularization\" to technical here ? decision surfaces and details of classifers come later. Original purpose (Uwe) was to demonstrate that classifiers can be tuned to the data set."
]
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
@@ -1409,7 +1390,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# Exercise section 3 (optional)"
+ "# Exercise section 2 (optional)"
]
},
{
@@ -1433,7 +1414,7 @@
},
{
"cell_type": "code",
- "execution_count": 20,
+ "execution_count": 21,
"metadata": {},
"outputs": [
{
@@ -1459,7 +1440,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -1551,7 +1532,7 @@
"4 0 "
]
},
- "execution_count": 21,
+ "execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -1565,7 +1546,7 @@
},
{
"cell_type": "code",
- "execution_count": 22,
+ "execution_count": 23,
"metadata": {},
"outputs": [
{
@@ -1687,7 +1668,7 @@
"max 2.500000 2.000000 "
]
},
- "execution_count": 22,
+ "execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
@@ -1698,7 +1679,7 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": 24,
"metadata": {},
"outputs": [
{
@@ -1739,16 +1720,16 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 25,
"metadata": {
- "collapsed": true
+ "scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "/Users/mikolajr/Workspace/SSDM/machinelearning-introduction-workshop/.venv/lib/python3.7/site-packages/ipykernel_launcher.py:9: UserWarning: get_ipython_dir has moved to the IPython.paths module since IPython 4.0.\n",
+ "/Users/uweschmitt/Projects/machinelearning-introduction-workshop/venv3.6/lib/python3.6/site-packages/ipykernel_launcher.py:9: UserWarning: get_ipython_dir has moved to the IPython.paths module since IPython 4.0.\n",
" if __name__ == '__main__':\n"
]
},
@@ -1853,7 +1834,7 @@
"<IPython.core.display.HTML object>"
]
},
- "execution_count": 24,
+ "execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
@@ -1983,7 +1964,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.1"
+ "version": "3.6.6"
}
},
"nbformat": 4,
--
GitLab