diff --git a/doc/pub/week34/html/._week34-bs001.html b/doc/pub/week34/html/._week34-bs001.html
index e3eba6dc2..983e098b2 100644
--- a/doc/pub/week34/html/._week34-bs001.html
+++ b/doc/pub/week34/html/._week34-bs001.html
@@ -363,7 +363,10 @@ MathJax.Hub.Config({
- Friday August 26: Linear regression
+ Friday August 26: Linear regression
+
Computer lab: Wednesdays, 8am-6pm and Thursdays 8am-12pm and additional self study 4pm-6pm. First time: Wednesday August 24.
diff --git a/doc/pub/week34/html/week34-reveal.html b/doc/pub/week34/html/week34-reveal.html
index 99ef952cb..137166d82 100644
--- a/doc/pub/week34/html/week34-reveal.html
+++ b/doc/pub/week34/html/week34-reveal.html
@@ -214,6 +214,11 @@ MathJax.Hub.Config({
Friday August 26: Linear regression
+
+
Computer lab: Wednesdays, 8am-6pm and Thursdays 8am-12pm and additional self study 4pm-6pm. First time: Wednesday August 24.
diff --git a/doc/pub/week34/html/week34-solarized.html b/doc/pub/week34/html/week34-solarized.html
index 02b109637..7d9df3ed5 100644
--- a/doc/pub/week34/html/week34-solarized.html
+++ b/doc/pub/week34/html/week34-solarized.html
@@ -314,7 +314,10 @@ MathJax.Hub.Config({
- Friday August 26: Linear regression
+ Friday August 26: Linear regression
+
Computer lab: Wednesdays, 8am-6pm and Thursdays 8am-12pm and additional self study 4pm-6pm. First time: Wednesday August 24.
diff --git a/doc/pub/week34/html/week34.html b/doc/pub/week34/html/week34.html
index 4f4fdcdd9..7771b5a4b 100644
--- a/doc/pub/week34/html/week34.html
+++ b/doc/pub/week34/html/week34.html
@@ -391,7 +391,10 @@ MathJax.Hub.Config({
- Friday August 26: Linear regression
+ Friday August 26: Linear regression
+
Computer lab: Wednesdays, 8am-6pm and Thursdays 8am-12pm and additional self study 4pm-6pm. First time: Wednesday August 24.
diff --git a/doc/pub/week34/ipynb/ipynb-week34-src.tar.gz b/doc/pub/week34/ipynb/ipynb-week34-src.tar.gz
index 62df3bd05..17e063443 100644
Binary files a/doc/pub/week34/ipynb/ipynb-week34-src.tar.gz and b/doc/pub/week34/ipynb/ipynb-week34-src.tar.gz differ
diff --git a/doc/pub/week34/ipynb/week34.ipynb b/doc/pub/week34/ipynb/week34.ipynb
index a67ffa2ee..2a6a6eabe 100644
--- a/doc/pub/week34/ipynb/week34.ipynb
+++ b/doc/pub/week34/ipynb/week34.ipynb
@@ -2,8 +2,10 @@
"cells": [
{
"cell_type": "markdown",
- "id": "23821382",
- "metadata": {},
+ "id": "d9cbfa6a",
+ "metadata": {
+ "editable": true
+ },
"source": [
"\n",
@@ -12,8 +14,10 @@
},
{
"cell_type": "markdown",
- "id": "c469d11a",
- "metadata": {},
+ "id": "865d3a9a",
+ "metadata": {
+ "editable": true
+ },
"source": [
"# Week 34: Introduction to the course, Logistics and Practicalities\n",
"**Morten Hjorth-Jensen**, Department of Physics and Center for Computing in Science Education, University of Oslo, Norway and Department of Physics and Astronomy and Facility for Rare Isotope Beams, Michigan State University, USA\n",
@@ -23,8 +27,10 @@
},
{
"cell_type": "markdown",
- "id": "aec7aa11",
- "metadata": {},
+ "id": "dfeeec30",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Overview of first week\n",
"\n",
@@ -36,15 +42,19 @@
"\n",
" * [Video of lecture](https://youtu.be/KL0m3-yhd5w)\n",
"\n",
- " * Friday August 26: Linear regression \n",
+ " * Friday August 26: Linear regression\n",
+ "\n",
+ " * [Video of lecture](https://www.youtube.com/watch?v=ne_xCL2ctM0)\n",
"\n",
" * Computer lab: Wednesdays, 8am-6pm and Thursdays 8am-12pm and additional self study 4pm-6pm. First time: Wednesday August 24."
]
},
{
"cell_type": "markdown",
- "id": "a5cf1430",
- "metadata": {},
+ "id": "9d064fe3",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Reading Recommendations\n",
"\n",
@@ -62,8 +72,10 @@
},
{
"cell_type": "markdown",
- "id": "48e8c897",
- "metadata": {},
+ "id": "50bf001c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Thursday August 25\n",
"\n",
@@ -76,8 +88,10 @@
},
{
"cell_type": "markdown",
- "id": "15954f7e",
- "metadata": {},
+ "id": "e5c34a73",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Lectures and ComputerLab\n",
"\n",
@@ -96,8 +110,10 @@
},
{
"cell_type": "markdown",
- "id": "c4dc19b7",
- "metadata": {},
+ "id": "48d4a4e7",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Communication channels\n",
"\n",
@@ -108,8 +124,10 @@
},
{
"cell_type": "markdown",
- "id": "b0ebeb01",
- "metadata": {},
+ "id": "3f8debef",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Course Format\n",
"\n",
@@ -130,8 +148,10 @@
},
{
"cell_type": "markdown",
- "id": "6472d61c",
- "metadata": {},
+ "id": "ef988c00",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Teachers\n",
"\n",
@@ -161,8 +181,10 @@
},
{
"cell_type": "markdown",
- "id": "3f3971e2",
- "metadata": {},
+ "id": "a65485cd",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Deadlines for projects (tentative)\n",
"\n",
@@ -177,8 +199,10 @@
},
{
"cell_type": "markdown",
- "id": "61795a44",
- "metadata": {},
+ "id": "a39c5071",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Recommended textbooks\n",
"\n",
@@ -199,8 +223,10 @@
},
{
"cell_type": "markdown",
- "id": "4069e392",
- "metadata": {},
+ "id": "0d246167",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Prerequisites\n",
"\n",
@@ -217,8 +243,10 @@
},
{
"cell_type": "markdown",
- "id": "790fc0cb",
- "metadata": {},
+ "id": "20d6c1ba",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Learning outcomes\n",
"\n",
@@ -259,8 +287,10 @@
},
{
"cell_type": "markdown",
- "id": "6d0591e9",
- "metadata": {},
+ "id": "21a789c1",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Topics covered in this course: Statistical analysis and optimization of data\n",
"\n",
@@ -292,8 +322,10 @@
},
{
"cell_type": "markdown",
- "id": "927ac19c",
- "metadata": {},
+ "id": "4579992e",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Topics covered in this course: Machine Learning\n",
"\n",
@@ -317,8 +349,10 @@
},
{
"cell_type": "markdown",
- "id": "b2e304c2",
- "metadata": {},
+ "id": "2410fc76",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Extremely useful tools, strongly recommended\n",
"\n",
@@ -331,8 +365,10 @@
},
{
"cell_type": "markdown",
- "id": "b3778a4a",
- "metadata": {},
+ "id": "90b58039",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Other courses on Data science and Machine Learning at UiO\n",
"\n",
@@ -363,8 +399,10 @@
},
{
"cell_type": "markdown",
- "id": "9afcb9bd",
- "metadata": {},
+ "id": "9e668f10",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Introduction\n",
"\n",
@@ -404,8 +442,10 @@
},
{
"cell_type": "markdown",
- "id": "171edcce",
- "metadata": {},
+ "id": "168dd1e0",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## What is Machine Learning?\n",
"\n",
@@ -475,8 +515,10 @@
},
{
"cell_type": "markdown",
- "id": "09e377d7",
- "metadata": {},
+ "id": "fca4b5c2",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Types of Machine Learning\n",
"\n",
@@ -502,8 +544,10 @@
},
{
"cell_type": "markdown",
- "id": "fa11b82a",
- "metadata": {},
+ "id": "31cceb2e",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Essential elements of ML\n",
"\n",
@@ -518,8 +562,10 @@
},
{
"cell_type": "markdown",
- "id": "2b5e75d3",
- "metadata": {},
+ "id": "211578d0",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## An optimization/minimization problem\n",
"\n",
@@ -528,8 +574,10 @@
},
{
"cell_type": "markdown",
- "id": "68c077de",
- "metadata": {},
+ "id": "4cc1958d",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## A Frequentist approach to data analysis\n",
"\n",
@@ -561,8 +609,10 @@
},
{
"cell_type": "markdown",
- "id": "8eff8ace",
- "metadata": {},
+ "id": "18717b89",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## What is a good model?\n",
"\n",
@@ -589,8 +639,10 @@
},
{
"cell_type": "markdown",
- "id": "50d341fd",
- "metadata": {},
+ "id": "7ad0f4f3",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## What is a good model? Can we define it?\n",
"\n",
@@ -618,8 +670,10 @@
},
{
"cell_type": "markdown",
- "id": "267b6500",
- "metadata": {},
+ "id": "f7b5ea61",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Software and needed installations\n",
"\n",
@@ -655,8 +709,10 @@
},
{
"cell_type": "markdown",
- "id": "0693b025",
- "metadata": {},
+ "id": "b2223314",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Python installers\n",
"\n",
@@ -686,8 +742,10 @@
},
{
"cell_type": "markdown",
- "id": "11750c35",
- "metadata": {},
+ "id": "327436b1",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Useful Python libraries\n",
"Here we list several useful Python libraries we strongly recommend (if you use anaconda many of these are already there)\n",
@@ -717,8 +775,10 @@
},
{
"cell_type": "markdown",
- "id": "437ff79d",
- "metadata": {},
+ "id": "67e712a0",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Installing R, C++, cython or Julia\n",
"\n",
@@ -739,8 +799,10 @@
},
{
"cell_type": "markdown",
- "id": "22cf44f9",
- "metadata": {},
+ "id": "035dbd1c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Installing R, C++, cython, Numba etc\n",
"\n",
@@ -764,16 +826,20 @@
},
{
"cell_type": "markdown",
- "id": "092aa1f4",
- "metadata": {},
+ "id": "e6dbe44b",
+ "metadata": {
+ "editable": true
+ },
"source": [
" pycod jupyter nbconvert filename.ipynb --to latex \n"
]
},
{
"cell_type": "markdown",
- "id": "5fb4d966",
- "metadata": {},
+ "id": "fdd5bce4",
+ "metadata": {
+ "editable": true
+ },
"source": [
"And to add more versatility, the Python package [SymPy](http://www.sympy.org/en/index.html) is a Python library for symbolic mathematics. It aims to become a full-featured computer algebra system (CAS) and is entirely written in Python. \n",
"\n",
@@ -784,8 +850,10 @@
},
{
"cell_type": "markdown",
- "id": "81967a6d",
- "metadata": {},
+ "id": "e2f95320",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Numpy examples and Important Matrix and vector handling packages\n",
"\n",
@@ -803,8 +871,10 @@
},
{
"cell_type": "markdown",
- "id": "f899fe44",
- "metadata": {},
+ "id": "2432e22e",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Basic Matrix Features\n",
"\n",
@@ -813,8 +883,10 @@
},
{
"cell_type": "markdown",
- "id": "e7153ce7",
- "metadata": {},
+ "id": "d0c5ee79",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\mathbf{A} =\n",
@@ -834,16 +906,20 @@
},
{
"cell_type": "markdown",
- "id": "039c9d2b",
- "metadata": {},
+ "id": "eb0becd4",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The inverse of a matrix is defined by"
]
},
{
"cell_type": "markdown",
- "id": "f5513bd7",
- "metadata": {},
+ "id": "94f65e0c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\mathbf{A}^{-1} \\cdot \\mathbf{A} = I\n",
@@ -852,8 +928,10 @@
},
{
"cell_type": "markdown",
- "id": "15e6ca3c",
- "metadata": {},
+ "id": "7bda9633",
+ "metadata": {
+ "editable": true
+ },
"source": [
"\n",
"\n",
@@ -871,8 +949,10 @@
},
{
"cell_type": "markdown",
- "id": "e980e643",
- "metadata": {},
+ "id": "17aba36b",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### Some famous Matrices\n",
"\n",
@@ -897,8 +977,10 @@
},
{
"cell_type": "markdown",
- "id": "b76014b3",
- "metadata": {},
+ "id": "3473472d",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### More Basic Matrix Features\n",
"\n",
@@ -921,8 +1003,10 @@
},
{
"cell_type": "markdown",
- "id": "48a15a71",
- "metadata": {},
+ "id": "7c53dc8f",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Numpy and arrays\n",
"[Numpy](http://www.numpy.org/) provides an easy way to handle arrays in Python. The standard way to import this library is as"
@@ -931,8 +1015,11 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "d355379c",
- "metadata": {},
+ "id": "efc58746",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np"
@@ -940,8 +1027,10 @@
},
{
"cell_type": "markdown",
- "id": "875b0c57",
- "metadata": {},
+ "id": "c4b61837",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Here follows a simple example where we set up an array of ten elements, all determined by random numbers drawn according to the normal distribution,"
]
@@ -949,8 +1038,11 @@
{
"cell_type": "code",
"execution_count": 2,
- "id": "b8435832",
- "metadata": {},
+ "id": "8c5d5085",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"n = 10\n",
@@ -960,8 +1052,10 @@
},
{
"cell_type": "markdown",
- "id": "aff17b91",
- "metadata": {},
+ "id": "bbee0f2c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We defined a vector $x$ with $n=10$ elements with its values given by the Normal distribution $N(0,1)$.\n",
"Another alternative is to declare a vector as follows"
@@ -970,8 +1064,11 @@
{
"cell_type": "code",
"execution_count": 3,
- "id": "1628226b",
- "metadata": {},
+ "id": "de7aff47",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -981,8 +1078,10 @@
},
{
"cell_type": "markdown",
- "id": "d2504d4f",
- "metadata": {},
+ "id": "938b786b",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Here we have defined a vector with three elements, with $x_0=1$, $x_1=2$ and $x_2=3$. Note that both Python and C++\n",
"start numbering array elements from $0$ and on. This means that a vector with $n$ elements has a sequence of entities $x_0, x_1, x_2, \\dots, x_{n-1}$. We could also let (recommended) Numpy to compute the logarithms of a specific array as"
@@ -991,8 +1090,11 @@
{
"cell_type": "code",
"execution_count": 4,
- "id": "3b227ba8",
- "metadata": {},
+ "id": "d29b7360",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1002,8 +1104,10 @@
},
{
"cell_type": "markdown",
- "id": "8e993172",
- "metadata": {},
+ "id": "c1927ab8",
+ "metadata": {
+ "editable": true
+ },
"source": [
"In the last example we used Numpy's unary function $np.log$. This function is\n",
"highly tuned to compute array elements since the code is vectorized\n",
@@ -1017,8 +1121,11 @@
{
"cell_type": "code",
"execution_count": 5,
- "id": "49e5616c",
- "metadata": {},
+ "id": "a2a2a97f",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1031,8 +1138,10 @@
},
{
"cell_type": "markdown",
- "id": "8b7a130d",
- "metadata": {},
+ "id": "f73d7ab1",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We note that our code is much longer already and we need to import the **log** function from the **math** module. \n",
"The attentive reader will also notice that the output is $[1, 1, 2]$. Python interprets automagically our numbers as integers (like the **automatic** keyword in C++). To change this we could define our array elements to be double precision numbers as"
@@ -1041,8 +1150,11 @@
{
"cell_type": "code",
"execution_count": 6,
- "id": "d59a3734",
- "metadata": {},
+ "id": "9fde0ac1",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1052,8 +1164,10 @@
},
{
"cell_type": "markdown",
- "id": "7ccc9342",
- "metadata": {},
+ "id": "aec73a81",
+ "metadata": {
+ "editable": true
+ },
"source": [
"or simply write them as double precision numbers (Python uses 64 bits as default for floating point type variables), that is"
]
@@ -1061,8 +1175,11 @@
{
"cell_type": "code",
"execution_count": 7,
- "id": "1f0ef993",
- "metadata": {},
+ "id": "a8837e56",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1072,8 +1189,10 @@
},
{
"cell_type": "markdown",
- "id": "26ce093e",
- "metadata": {},
+ "id": "e36ad709",
+ "metadata": {
+ "editable": true
+ },
"source": [
"To check the number of bytes (remember that one byte contains eight bits for double precision variables), you can use simple use the **itemsize** functionality (the array $x$ is actually an object which inherits the functionalities defined in Numpy) as"
]
@@ -1081,8 +1200,11 @@
{
"cell_type": "code",
"execution_count": 8,
- "id": "208f43ac",
- "metadata": {},
+ "id": "164ad990",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1092,8 +1214,10 @@
},
{
"cell_type": "markdown",
- "id": "93ec757f",
- "metadata": {},
+ "id": "04208aa9",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Matrices in Python\n",
"\n",
@@ -1105,8 +1229,11 @@
{
"cell_type": "code",
"execution_count": 9,
- "id": "b8996f96",
- "metadata": {},
+ "id": "fde60b9d",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1116,8 +1243,10 @@
},
{
"cell_type": "markdown",
- "id": "e0932c59",
- "metadata": {},
+ "id": "4c5d1c05",
+ "metadata": {
+ "editable": true
+ },
"source": [
"If we use the **shape** function we would get $(3, 3)$ as output, that is verifying that our matrix is a $3\\times 3$ matrix. We can slice the matrix and print for example the first column (Python organized matrix elements in a row-major order, see below) as"
]
@@ -1125,8 +1254,11 @@
{
"cell_type": "code",
"execution_count": 10,
- "id": "c6f27f9c",
- "metadata": {},
+ "id": "d17ce8b3",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1137,8 +1269,10 @@
},
{
"cell_type": "markdown",
- "id": "73723a49",
- "metadata": {},
+ "id": "954a4c11",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We can continue this was by printing out other columns or rows. The example here prints out the second column"
]
@@ -1146,8 +1280,11 @@
{
"cell_type": "code",
"execution_count": 11,
- "id": "37d2fd90",
- "metadata": {},
+ "id": "885eb576",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1158,8 +1295,10 @@
},
{
"cell_type": "markdown",
- "id": "05cc834e",
- "metadata": {},
+ "id": "f5fb4f10",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Numpy contains many other functionalities that allow us to slice, subdivide etc etc arrays. We strongly recommend that you look up the [Numpy website for more details](http://www.numpy.org/). Useful functions when defining a matrix are the **np.zeros** function which declares a matrix of a given dimension and sets all elements to zero"
]
@@ -1167,8 +1306,11 @@
{
"cell_type": "code",
"execution_count": 12,
- "id": "e15a4fff",
- "metadata": {},
+ "id": "8d18a490",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1180,8 +1322,10 @@
},
{
"cell_type": "markdown",
- "id": "0b1ebc4d",
- "metadata": {},
+ "id": "4fd2ba07",
+ "metadata": {
+ "editable": true
+ },
"source": [
"or initializing all elements to"
]
@@ -1189,8 +1333,11 @@
{
"cell_type": "code",
"execution_count": 13,
- "id": "f83b67d9",
- "metadata": {},
+ "id": "0b3c8b18",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1202,8 +1349,10 @@
},
{
"cell_type": "markdown",
- "id": "c28a9cd9",
- "metadata": {},
+ "id": "2eeca10d",
+ "metadata": {
+ "editable": true
+ },
"source": [
"or as unitarily distributed random numbers (see the material on random number generators in the statistics part)"
]
@@ -1211,8 +1360,11 @@
{
"cell_type": "code",
"execution_count": 14,
- "id": "9aa190b7",
- "metadata": {},
+ "id": "767878e7",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1224,8 +1376,10 @@
},
{
"cell_type": "markdown",
- "id": "3e3ab3a4",
- "metadata": {},
+ "id": "3175e298",
+ "metadata": {
+ "editable": true
+ },
"source": [
"As we will see throughout these lectures, there are several extremely useful functionalities in Numpy.\n",
"As an example, consider the discussion of the covariance matrix. Suppose we have defined three vectors\n",
@@ -1234,8 +1388,10 @@
},
{
"cell_type": "markdown",
- "id": "23bddd16",
- "metadata": {},
+ "id": "6849c5c1",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{\\Sigma} = \\begin{bmatrix} \\sigma_{xx} & \\sigma_{xy} & \\sigma_{xz} \\\\\n",
@@ -1247,16 +1403,20 @@
},
{
"cell_type": "markdown",
- "id": "d256ad80",
- "metadata": {},
+ "id": "8ee6d204",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where for example"
]
},
{
"cell_type": "markdown",
- "id": "fa974adf",
- "metadata": {},
+ "id": "860e8963",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\sigma_{xy} =\\frac{1}{n} \\sum_{i=0}^{n-1}(x_i- \\overline{x})(y_i- \\overline{y}).\n",
@@ -1265,8 +1425,10 @@
},
{
"cell_type": "markdown",
- "id": "943d22f1",
- "metadata": {},
+ "id": "b22355b7",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The Numpy function **np.cov** calculates the covariance elements using the factor $1/(n-1)$ instead of $1/n$ since it assumes we do not have the exact mean values. \n",
"The following simple function uses the **np.vstack** function which takes each vector of dimension $1\\times n$ and produces a $3\\times n$ matrix $\\boldsymbol{W}$"
@@ -1274,8 +1436,10 @@
},
{
"cell_type": "markdown",
- "id": "88370719",
- "metadata": {},
+ "id": "c15bf196",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{W} = \\begin{bmatrix} x_0 & x_1 & x_2 & \\dots & x_{n-2} & x_{n-1} \\\\\n",
@@ -1287,8 +1451,10 @@
},
{
"cell_type": "markdown",
- "id": "4cd9bb68",
- "metadata": {},
+ "id": "5dbe0eb8",
+ "metadata": {
+ "editable": true
+ },
"source": [
"which in turn is converted into into the $3\\times 3$ covariance matrix\n",
"$\\boldsymbol{\\Sigma}$ via the Numpy function **np.cov()**. We note that we can also calculate\n",
@@ -1300,8 +1466,11 @@
{
"cell_type": "code",
"execution_count": 15,
- "id": "89cfecda",
- "metadata": {},
+ "id": "8d9dad34",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"# Importing various packages\n",
@@ -1324,8 +1493,11 @@
{
"cell_type": "code",
"execution_count": 16,
- "id": "1dc7eb64",
- "metadata": {},
+ "id": "1a738699",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"%matplotlib inline\n",
@@ -1345,8 +1517,10 @@
},
{
"cell_type": "markdown",
- "id": "4c0484d8",
- "metadata": {},
+ "id": "72b1dc52",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Meet the Pandas\n",
"\n",
@@ -1369,8 +1543,11 @@
{
"cell_type": "code",
"execution_count": 17,
- "id": "bc5fb71a",
- "metadata": {},
+ "id": "a68224b0",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import pandas as pd\n",
@@ -1386,8 +1563,10 @@
},
{
"cell_type": "markdown",
- "id": "b7a91093",
- "metadata": {},
+ "id": "25c07190",
+ "metadata": {
+ "editable": true
+ },
"source": [
"In the above we have imported **pandas** with the shorthand **pd**, the latter has become the standard way we import **pandas**. We make then a list of various variables\n",
"and reorganize the aboves lists into a **DataFrame** and then print out a neat table with specific column labels as *Name*, *place of birth* and *date of birth*.\n",
@@ -1398,8 +1577,11 @@
{
"cell_type": "code",
"execution_count": 18,
- "id": "1f0d35dd",
- "metadata": {},
+ "id": "ae9da215",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"data_pandas = pd.DataFrame(data,index=['Frodo','Bilbo','Aragorn','Sam'])\n",
@@ -1408,8 +1590,10 @@
},
{
"cell_type": "markdown",
- "id": "e377afba",
- "metadata": {},
+ "id": "d669a93f",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Thereafter we display the content of the row which begins with the index **Aragorn**"
]
@@ -1417,8 +1601,11 @@
{
"cell_type": "code",
"execution_count": 19,
- "id": "01d60f31",
- "metadata": {},
+ "id": "65067f63",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"display(data_pandas.loc['Aragorn'])"
@@ -1426,8 +1613,10 @@
},
{
"cell_type": "markdown",
- "id": "91710aa0",
- "metadata": {},
+ "id": "46fec574",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We can easily append data to this, for example"
]
@@ -1435,8 +1624,11 @@
{
"cell_type": "code",
"execution_count": 20,
- "id": "8fbef305",
- "metadata": {},
+ "id": "7e8ca81f",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"new_hobbit = {'First Name': [\"Peregrin\"],\n",
@@ -1450,8 +1642,10 @@
},
{
"cell_type": "markdown",
- "id": "a43653e3",
- "metadata": {},
+ "id": "fc87b940",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Here are other examples where we use the **DataFrame** functionality to handle arrays, now with more interesting features for us, namely numbers. We set up a matrix \n",
"of dimensionality $10\\times 5$ and compute the mean value and standard deviation of each column. Similarly, we can perform mathematial operations like squaring the matrix elements and many other operations."
@@ -1460,8 +1654,11 @@
{
"cell_type": "code",
"execution_count": 21,
- "id": "23b64767",
- "metadata": {},
+ "id": "68f9eb6c",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1481,8 +1678,10 @@
},
{
"cell_type": "markdown",
- "id": "04086382",
- "metadata": {},
+ "id": "8d1c3ea9",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Thereafter we can select specific columns only and plot final results"
]
@@ -1490,8 +1689,11 @@
{
"cell_type": "code",
"execution_count": 22,
- "id": "200065c9",
- "metadata": {},
+ "id": "4398e5ef",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"df.columns = ['First', 'Second', 'Third', 'Fourth', 'Fifth']\n",
@@ -1516,8 +1718,10 @@
},
{
"cell_type": "markdown",
- "id": "87c4af21",
- "metadata": {},
+ "id": "27632773",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We can produce a $4\\times 4$ matrix"
]
@@ -1525,8 +1729,11 @@
{
"cell_type": "code",
"execution_count": 23,
- "id": "0f0e2ea4",
- "metadata": {},
+ "id": "b63aacb0",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"b = np.arange(16).reshape((4,4))\n",
@@ -1537,8 +1744,10 @@
},
{
"cell_type": "markdown",
- "id": "7c8e41f2",
- "metadata": {},
+ "id": "9b0a4630",
+ "metadata": {
+ "editable": true
+ },
"source": [
"and many other operations. \n",
"\n",
@@ -1552,8 +1761,10 @@
},
{
"cell_type": "markdown",
- "id": "ff56b741",
- "metadata": {},
+ "id": "8af50030",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Friday August 27\n",
"\n",
@@ -1564,8 +1775,10 @@
},
{
"cell_type": "markdown",
- "id": "95f8b206",
- "metadata": {},
+ "id": "5f487905",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### Simple linear regression model using **scikit-learn**\n",
"\n",
@@ -1593,8 +1806,10 @@
},
{
"cell_type": "markdown",
- "id": "15f8e533",
- "metadata": {},
+ "id": "fb9fa628",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"y = 2x+N(0,1),\n",
@@ -1603,8 +1818,10 @@
},
{
"cell_type": "markdown",
- "id": "6def5844",
- "metadata": {},
+ "id": "fceda949",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $N(0,1)$ represents random numbers generated by the normal\n",
"distribution. From **Scikit-Learn** we import then the\n",
@@ -1629,8 +1846,11 @@
{
"cell_type": "code",
"execution_count": 24,
- "id": "3e056e1e",
- "metadata": {},
+ "id": "3d5c8dbb",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"# Importing various packages\n",
@@ -1656,8 +1876,10 @@
},
{
"cell_type": "markdown",
- "id": "79d3bd41",
- "metadata": {},
+ "id": "e86fd526",
+ "metadata": {
+ "editable": true
+ },
"source": [
"This example serves several aims. It allows us to demonstrate several\n",
"aspects of data analysis and later machine learning algorithms. The\n",
@@ -1671,8 +1893,10 @@
},
{
"cell_type": "markdown",
- "id": "efe6d89d",
- "metadata": {},
+ "id": "4e79d7ec",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"y = 10x+0.01 \\times N(0,1),\n",
@@ -1681,8 +1905,10 @@
},
{
"cell_type": "markdown",
- "id": "d66300c2",
- "metadata": {},
+ "id": "fadb5acd",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $x$ is defined as before. Does the fit look better? Indeed, by\n",
"reducing the role of the noise given by the normal distribution we see immediately that\n",
@@ -1700,8 +1926,10 @@
},
{
"cell_type": "markdown",
- "id": "a73d3b9e",
- "metadata": {},
+ "id": "79fc29f2",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\chi^2 = \\frac{1}{n}\n",
@@ -1711,8 +1939,10 @@
},
{
"cell_type": "markdown",
- "id": "2cf633a8",
- "metadata": {},
+ "id": "4a7d1bed",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $\\sigma_i^2$ is the variance (to be defined later) of the entry\n",
"$y_i$. We may not know the explicit value of $\\sigma_i^2$, it serves\n",
@@ -1740,8 +1970,10 @@
},
{
"cell_type": "markdown",
- "id": "97c9029a",
- "metadata": {},
+ "id": "7c0baa1a",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\epsilon_{\\mathrm{relative}}= \\frac{\\vert \\boldsymbol{y} -\\boldsymbol{\\tilde{y}}\\vert}{\\vert \\boldsymbol{y}\\vert}.\n",
@@ -1750,8 +1982,10 @@
},
{
"cell_type": "markdown",
- "id": "84956e1c",
- "metadata": {},
+ "id": "db76656b",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The squared cost function results in an arithmetic mean-unbiased\n",
"estimator, and the absolute-value cost function results in a\n",
@@ -1766,8 +2000,11 @@
{
"cell_type": "code",
"execution_count": 25,
- "id": "204b76db",
- "metadata": {},
+ "id": "d52683dc",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np\n",
@@ -1790,8 +2027,10 @@
},
{
"cell_type": "markdown",
- "id": "bb1efc74",
- "metadata": {},
+ "id": "a9e73991",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Depending on the parameter in front of the normal distribution, we may\n",
"have a small or larger relative error. Try to play around with\n",
@@ -1810,8 +2049,11 @@
{
"cell_type": "code",
"execution_count": 26,
- "id": "90a40d1f",
- "metadata": {},
+ "id": "be779369",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import numpy as np \n",
@@ -1845,8 +2087,10 @@
},
{
"cell_type": "markdown",
- "id": "1918b0a3",
- "metadata": {},
+ "id": "10113aff",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The function **coef** gives us the parameter $\\beta$ of our fit while **intercept** yields \n",
"$\\alpha$. Depending on the constant in front of the normal distribution, we get values near or far from $\\alpha =2$ and $\\beta =5$. Try to play around with different parameters in front of the normal distribution. The function **meansquarederror** gives us the mean square error, a risk metric corresponding to the expected value of the squared (quadratic) error or loss defined as"
@@ -1854,8 +2098,10 @@
},
{
"cell_type": "markdown",
- "id": "078f7289",
- "metadata": {},
+ "id": "2f76f721",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"MSE(\\boldsymbol{y},\\boldsymbol{\\tilde{y}}) = \\frac{1}{n}\n",
@@ -1865,8 +2111,10 @@
},
{
"cell_type": "markdown",
- "id": "23899ec9",
- "metadata": {},
+ "id": "e103b773",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The smaller the value, the better the fit. Ideally we would like to\n",
"have an MSE equal zero. The attentive reader has probably recognized\n",
@@ -1884,8 +2132,10 @@
},
{
"cell_type": "markdown",
- "id": "881285ea",
- "metadata": {},
+ "id": "3b74cdd1",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"R^2(\\boldsymbol{y}, \\tilde{\\boldsymbol{y}}) = 1 - \\frac{\\sum_{i=0}^{n - 1} (y_i - \\tilde{y}_i)^2}{\\sum_{i=0}^{n - 1} (y_i - \\bar{y})^2},\n",
@@ -1894,16 +2144,20 @@
},
{
"cell_type": "markdown",
- "id": "ea902970",
- "metadata": {},
+ "id": "b5f06c54",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where we have defined the mean value of $\\boldsymbol{y}$ as"
]
},
{
"cell_type": "markdown",
- "id": "e60da213",
- "metadata": {},
+ "id": "b72af80d",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\bar{y} = \\frac{1}{n} \\sum_{i=0}^{n - 1} y_i.\n",
@@ -1912,8 +2166,10 @@
},
{
"cell_type": "markdown",
- "id": "3f6be08b",
- "metadata": {},
+ "id": "b60ef3d8",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Another quantity taht we will meet again in our discussions of regression analysis is \n",
" the mean absolute error (MAE), a risk metric corresponding to the expected value of the absolute error loss or what we call the $l1$-norm loss. In our discussion above we presented the relative error.\n",
@@ -1922,8 +2178,10 @@
},
{
"cell_type": "markdown",
- "id": "440c7b62",
- "metadata": {},
+ "id": "fa0a6d87",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\text{MAE}(\\boldsymbol{y}, \\boldsymbol{\\tilde{y}}) = \\frac{1}{n} \\sum_{i=0}^{n-1} \\left| y_i - \\tilde{y}_i \\right|.\n",
@@ -1932,8 +2190,10 @@
},
{
"cell_type": "markdown",
- "id": "b05a3f98",
- "metadata": {},
+ "id": "2bfcd372",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We present the \n",
"squared logarithmic (quadratic) error"
@@ -1941,8 +2201,10 @@
},
{
"cell_type": "markdown",
- "id": "4cd33173",
- "metadata": {},
+ "id": "9776ac5a",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\text{MSLE}(\\boldsymbol{y}, \\boldsymbol{\\tilde{y}}) = \\frac{1}{n} \\sum_{i=0}^{n - 1} (\\log_e (1 + y_i) - \\log_e (1 + \\tilde{y}_i) )^2,\n",
@@ -1951,8 +2213,10 @@
},
{
"cell_type": "markdown",
- "id": "77f5461f",
- "metadata": {},
+ "id": "0230e208",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $\\log_e (x)$ stands for the natural logarithm of $x$. This error\n",
"estimate is best to use when targets having exponential growth, such\n",
@@ -1971,8 +2235,10 @@
},
{
"cell_type": "markdown",
- "id": "96e7b86e",
- "metadata": {},
+ "id": "47b1dd17",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"H_{\\delta}(\\boldsymbol{a})=\\left\\{\\begin{array}{cc}\\frac{1}{2} \\boldsymbol{a}^{2}& \\text{for }|\\boldsymbol{a}|\\leq \\delta\\\\ \\delta (|\\boldsymbol{a}|-\\frac{1}{2}\\delta ),&\\text{otherwise}.\\end{array}\\right.\n",
@@ -1981,8 +2247,10 @@
},
{
"cell_type": "markdown",
- "id": "a91d5d7b",
- "metadata": {},
+ "id": "39224cd7",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Here $\\boldsymbol{a}=\\boldsymbol{y} - \\boldsymbol{\\tilde{y}}$.\n",
"\n",
@@ -1995,8 +2263,11 @@
{
"cell_type": "code",
"execution_count": 27,
- "id": "cc7c950e",
- "metadata": {},
+ "id": "39adece0",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
@@ -2033,8 +2304,10 @@
},
{
"cell_type": "markdown",
- "id": "dc81b198",
- "metadata": {},
+ "id": "5872aea6",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### To our real data: nuclear binding energies. Brief reminder on masses and binding energies\n",
"\n",
@@ -2048,8 +2321,10 @@
},
{
"cell_type": "markdown",
- "id": "c647a2bb",
- "metadata": {},
+ "id": "b7c6dae2",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\Delta M(N, Z) = M(N, Z) - uA,\n",
@@ -2058,16 +2333,20 @@
},
{
"cell_type": "markdown",
- "id": "6bf735eb",
- "metadata": {},
+ "id": "c62f966f",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $u$ is the Atomic Mass Unit"
]
},
{
"cell_type": "markdown",
- "id": "21bc983d",
- "metadata": {},
+ "id": "47368466",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"u = M(^{12}\\mathrm{C})/12 = 931.4940954(57) \\hspace{0.1cm} \\mathrm{MeV}/c^2.\n",
@@ -2076,16 +2355,20 @@
},
{
"cell_type": "markdown",
- "id": "29f11904",
- "metadata": {},
+ "id": "13a094a5",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The nucleon masses are"
]
},
{
"cell_type": "markdown",
- "id": "7066ba82",
- "metadata": {},
+ "id": "3312c3c6",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"m_p = 1.00727646693(9)u,\n",
@@ -2094,16 +2377,20 @@
},
{
"cell_type": "markdown",
- "id": "b6551094",
- "metadata": {},
+ "id": "c6952f2f",
+ "metadata": {
+ "editable": true
+ },
"source": [
"and"
]
},
{
"cell_type": "markdown",
- "id": "d7e2c32e",
- "metadata": {},
+ "id": "5267bb9e",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"m_n = 939.56536(8)\\hspace{0.1cm} \\mathrm{MeV}/c^2 = 1.0086649156(6)u.\n",
@@ -2112,8 +2399,10 @@
},
{
"cell_type": "markdown",
- "id": "a2b7b470",
- "metadata": {},
+ "id": "73a6e16b",
+ "metadata": {
+ "editable": true
+ },
"source": [
"In the [2016 mass evaluation of by W.J.Huang, G.Audi, M.Wang, F.G.Kondev, S.Naimi and X.Xu](http://nuclearmasses.org/resources_folder/Wang_2017_Chinese_Phys_C_41_030003.pdf)\n",
"there are data on masses and decays of 3437 nuclei.\n",
@@ -2126,8 +2415,10 @@
},
{
"cell_type": "markdown",
- "id": "682b0bd1",
- "metadata": {},
+ "id": "42edd599",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"BE(N, Z) = ZM_H c^2 + Nm_n c^2 - M(N, Z)c^2 ,\n",
@@ -2136,8 +2427,10 @@
},
{
"cell_type": "markdown",
- "id": "f8b5e709",
- "metadata": {},
+ "id": "27ee40e3",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $M_H$ is the mass of the hydrogen atom and $m_n$ is the mass of the neutron.\n",
"In terms of the mass excess the binding energy is given by"
@@ -2145,8 +2438,10 @@
},
{
"cell_type": "markdown",
- "id": "3da0afe2",
- "metadata": {},
+ "id": "d5f3afc6",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"BE(N, Z) = Z\\Delta_H c^2 + N\\Delta_n c^2 -\\Delta(N, Z)c^2 ,\n",
@@ -2155,8 +2450,10 @@
},
{
"cell_type": "markdown",
- "id": "b241cf42",
- "metadata": {},
+ "id": "fd13dd49",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $\\Delta_H c^2 = 7.2890$ MeV and $\\Delta_n c^2 = 8.0713$ MeV.\n",
"\n",
@@ -2167,8 +2464,10 @@
},
{
"cell_type": "markdown",
- "id": "0f78c0ba",
- "metadata": {},
+ "id": "4d36ccc4",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"BE(N,Z) = a_1A-a_2A^{2/3}-a_3\\frac{Z^2}{A^{1/3}}-a_4\\frac{(N-Z)^2}{A},\n",
@@ -2177,8 +2476,10 @@
},
{
"cell_type": "markdown",
- "id": "f63cba5f",
- "metadata": {},
+ "id": "1b05d2e4",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $A$ stands for the number of nucleons and the $a_i$s are parameters which are determined by a fit \n",
"to the experimental data. \n",
@@ -2200,8 +2501,10 @@
},
{
"cell_type": "markdown",
- "id": "2284d6ec",
- "metadata": {},
+ "id": "b5190fab",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### Organizing our data\n",
"\n",
@@ -2214,9 +2517,12 @@
},
{
"cell_type": "code",
- "execution_count": 10,
- "id": "bd7aa620",
- "metadata": {},
+ "execution_count": 28,
+ "id": "59df45d2",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"# Common imports\n",
@@ -2256,17 +2562,22 @@
},
{
"cell_type": "markdown",
- "id": "df2c8ccf",
- "metadata": {},
+ "id": "7dc133ae",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Before we proceed, we define also a function for making our plots. You can obviously avoid this and simply set up various **matplotlib** commands every time you need them. You may however find it convenient to collect all such commands in one function and simply call this function."
]
},
{
"cell_type": "code",
- "execution_count": 11,
- "id": "cb52c00e",
- "metadata": {},
+ "execution_count": 29,
+ "id": "c8652d1b",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"from pylab import plt, mpl\n",
@@ -2284,8 +2595,10 @@
},
{
"cell_type": "markdown",
- "id": "38545028",
- "metadata": {},
+ "id": "1d731f52",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Our next step is to read the data on experimental binding energies and\n",
"reorganize them as functions of the mass number $A$, the number of\n",
@@ -2298,21 +2611,13 @@
},
{
"cell_type": "code",
- "execution_count": 12,
- "id": "079dae1b",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "' \\nThis is taken from the data file of the mass 2016 evaluation. \\nAll files are 3436 lines long with 124 character per line. \\n Headers are 39 lines long. \\n col 1 : Fortran character control: 1 = page feed 0 = line feed \\n format : a1,i3,i5,i5,i5,1x,a3,a4,1x,f13.5,f11.5,f11.3,f9.3,1x,a2,f11.3,f9.3,1x,i3,1x,f12.5,f11.5 \\n These formats are reflected in the pandas widths variable below, see the statement \\n widths=(1,3,5,5,5,1,3,4,1,13,11,11,9,1,2,11,9,1,3,1,12,11,1), \\n Pandas has also a variable header, with length 39 in this case. \\n'"
- ]
- },
- "execution_count": 12,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "execution_count": 30,
+ "id": "0a49a838",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
+ "outputs": [],
"source": [
"\"\"\" \n",
"This is taken from the data file of the mass 2016 evaluation. \n",
@@ -2328,8 +2633,10 @@
},
{
"cell_type": "markdown",
- "id": "eb12107a",
- "metadata": {},
+ "id": "b1b378d9",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The data we are interested in are in columns 2, 3, 4 and 11, giving us\n",
"the number of neutrons, protons, mass numbers and binding energies,\n",
@@ -2339,9 +2646,12 @@
},
{
"cell_type": "code",
- "execution_count": 13,
- "id": "206b12f1",
- "metadata": {},
+ "execution_count": 31,
+ "id": "80502a7c",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"# Read the experimental data with Pandas\n",
@@ -2366,8 +2676,10 @@
},
{
"cell_type": "markdown",
- "id": "c79ac328",
- "metadata": {},
+ "id": "21e01a99",
+ "metadata": {
+ "editable": true
+ },
"source": [
"We have now read in the data, grouped them according to the variables we are interested in. \n",
"We see how easy it is to reorganize the data using **pandas**. If we\n",
@@ -2383,32 +2695,13 @@
},
{
"cell_type": "code",
- "execution_count": 14,
- "id": "5e6b60e8",
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " N Z A Element Ebinding\n",
- "A \n",
- "4 0 1 3 4 Li 1.153760\n",
- "5 2 3 2 5 He 5.512132\n",
- "6 7 3 3 6 Li 5.332331\n",
- "7 12 4 3 7 Li 5.606439\n",
- "8 17 4 4 8 Be 7.062435\n",
- "... ... ... ... ... ...\n",
- "264 3297 156 108 264 Hs 7.298375\n",
- "265 3303 157 108 265 Hs 7.296247\n",
- "266 3310 158 108 266 Hs 7.298273\n",
- "269 3331 159 110 269 Ds 7.250154\n",
- "270 3337 160 110 270 Ds 7.253775\n",
- "\n",
- "[264 rows x 5 columns]\n"
- ]
- }
- ],
+ "execution_count": 32,
+ "id": "a256c99c",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
+ "outputs": [],
"source": [
"A = Masses['A']\n",
"Z = Masses['Z']\n",
@@ -2420,8 +2713,10 @@
},
{
"cell_type": "markdown",
- "id": "d35730c6",
- "metadata": {},
+ "id": "278edca6",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The next step, and we will define this mathematically later, is to set up the so-called **design matrix**. We will throughout call this matrix $\\boldsymbol{X}$.\n",
"It has dimensionality $p\\times n$, where $n$ is the number of data points and $p$ are the so-called predictors. In our case here they are given by the number of polynomials in $A$ we wish to include in the fit."
@@ -2429,9 +2724,12 @@
},
{
"cell_type": "code",
- "execution_count": 15,
- "id": "2975893e",
- "metadata": {},
+ "execution_count": 33,
+ "id": "3179ee55",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"# Now we set up the design matrix X\n",
@@ -2445,17 +2743,22 @@
},
{
"cell_type": "markdown",
- "id": "3160f4c5",
- "metadata": {},
+ "id": "0bb2787f",
+ "metadata": {
+ "editable": true
+ },
"source": [
"With **scikitlearn** we are now ready to use linear regression and fit our data."
]
},
{
"cell_type": "code",
- "execution_count": 16,
- "id": "dc828ff8",
- "metadata": {},
+ "execution_count": 34,
+ "id": "e3ecdb5a",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"clf = skl.LinearRegression().fit(X, Energies)\n",
@@ -2464,8 +2767,10 @@
},
{
"cell_type": "markdown",
- "id": "3744b3e4",
- "metadata": {},
+ "id": "8c5edc75",
+ "metadata": {
+ "editable": true
+ },
"source": [
"Pretty simple! \n",
"Now we can print measures of how our fit is doing, the coefficients from the fits and plot the final fit together with our data."
@@ -2473,32 +2778,13 @@
},
{
"cell_type": "code",
- "execution_count": 17,
- "id": "ac4670de",
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Mean squared error: 0.02\n",
- "Variance score: 0.95\n",
- "Mean absolute error: 0.05\n",
- "[ 0.00000000e+00 -2.96611194e-02 2.01719003e-01 1.08078025e+01\n",
- " -4.03097597e+01] 5.294399745619598\n"
- ]
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- ""
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "execution_count": 35,
+ "id": "4ecedb1d",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
+ "outputs": [],
"source": [
"# The mean squared error \n",
"print(\"Mean squared error: %.2f\" % mean_squared_error(Energies, fity))\n",
@@ -2524,8 +2810,10 @@
},
{
"cell_type": "markdown",
- "id": "7da29fb8",
- "metadata": {},
+ "id": "f91070e6",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### Seeing the wood for the trees\n",
"\n",
@@ -2534,50 +2822,20 @@
},
{
"cell_type": "code",
- "execution_count": 20,
- "id": "2c8f264b",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- ""
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " N Z A Element Ebinding Eapprox\n",
- "A \n",
- "4 0 1 3 4 Li 1.153760 1.153760\n",
- "5 2 3 2 5 He 5.512132 5.422231\n",
- "6 7 3 3 6 Li 5.332331 5.422231\n",
- "7 12 4 3 7 Li 5.606439 5.606439\n",
- "8 17 4 4 8 Be 7.062435 7.382774\n",
- "... ... ... ... ... ... ...\n",
- "264 3297 156 108 264 Hs 7.298375 7.512041\n",
- "265 3303 157 108 265 Hs 7.296247 7.512041\n",
- "266 3310 158 108 266 Hs 7.298273 7.512041\n",
- "269 3331 159 110 269 Ds 7.250154 7.512041\n",
- "270 3337 160 110 270 Ds 7.253775 7.512041\n",
- "\n",
- "[264 rows x 6 columns]\n",
- "0.007012403613997257\n"
- ]
- }
- ],
+ "execution_count": 36,
+ "id": "00c9d6a0",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
+ "outputs": [],
"source": [
"\n",
"#Decision Tree Regression\n",
"from sklearn.tree import DecisionTreeRegressor\n",
"regr_1=DecisionTreeRegressor(max_depth=5)\n",
"regr_2=DecisionTreeRegressor(max_depth=7)\n",
- "regr_3=DecisionTreeRegressor(max_depth=3)\n",
+ "regr_3=DecisionTreeRegressor(max_depth=9)\n",
"regr_1.fit(X, Energies)\n",
"regr_2.fit(X, Energies)\n",
"regr_3.fit(X, Energies)\n",
@@ -2590,8 +2848,8 @@
"# Plot the results\n",
"plt.figure()\n",
"plt.plot(A, Energies, color=\"blue\", label=\"Data\", linewidth=2)\n",
- "#plt.plot(A, y_1, color=\"red\", label=\"max_depth=5\", linewidth=2)\n",
- "#plt.plot(A, y_2, color=\"green\", label=\"max_depth=7\", linewidth=2)\n",
+ "plt.plot(A, y_1, color=\"red\", label=\"max_depth=5\", linewidth=2)\n",
+ "plt.plot(A, y_2, color=\"green\", label=\"max_depth=7\", linewidth=2)\n",
"plt.plot(A, y_3, color=\"m\", label=\"max_depth=9\", linewidth=2)\n",
"\n",
"plt.xlabel(\"$A$\")\n",
@@ -2606,8 +2864,10 @@
},
{
"cell_type": "markdown",
- "id": "5899eaad",
- "metadata": {},
+ "id": "235abfdb",
+ "metadata": {
+ "editable": true
+ },
"source": [
"### And what about using neural networks?\n",
"\n",
@@ -2618,8 +2878,11 @@
{
"cell_type": "code",
"execution_count": 37,
- "id": "0639aaf3",
- "metadata": {},
+ "id": "a8bd2055",
+ "metadata": {
+ "collapsed": false,
+ "editable": true
+ },
"outputs": [],
"source": [
"from sklearn.neural_network import MLPRegressor\n",
@@ -2655,8 +2918,10 @@
},
{
"cell_type": "markdown",
- "id": "bed3130b",
- "metadata": {},
+ "id": "5f72020b",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## A first summary\n",
"\n",
@@ -2673,8 +2938,10 @@
},
{
"cell_type": "markdown",
- "id": "d89a7826",
- "metadata": {},
+ "id": "6348b8ec",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Why Linear Regression (aka Ordinary Least Squares and family)\n",
"\n",
@@ -2703,8 +2970,10 @@
},
{
"cell_type": "markdown",
- "id": "481c6cb2",
- "metadata": {},
+ "id": "e17d80d6",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Regression analysis, overarching aims\n",
"\n",
@@ -2723,8 +2992,10 @@
},
{
"cell_type": "markdown",
- "id": "f1c09a01",
- "metadata": {},
+ "id": "3d1f271a",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Regression analysis, overarching aims II\n",
"\n",
@@ -2749,8 +3020,10 @@
},
{
"cell_type": "markdown",
- "id": "866b4aa9",
- "metadata": {},
+ "id": "fbfc6a20",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Examples\n",
"In order to understand the relation among the predictors $p$, the set of data $n$ and the target (outcome, output etc) $\\boldsymbol{y}$,\n",
@@ -2762,8 +3035,10 @@
},
{
"cell_type": "markdown",
- "id": "a3ae9da5",
- "metadata": {},
+ "id": "90d46cb3",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"BE(A) = a_0+a_1A+a_2A^{2/3}+a_3A^{-1/3}+a_4A^{-1},\n",
@@ -2772,8 +3047,10 @@
},
{
"cell_type": "markdown",
- "id": "672c981f",
- "metadata": {},
+ "id": "cb69e19b",
+ "metadata": {
+ "editable": true
+ },
"source": [
"we have five predictors, that is the intercept, the $A$ dependent term, the $A^{2/3}$ term and the $A^{-1/3}$ and $A^{-1}$ terms.\n",
"This gives $p=0,1,2,3,4$. Furthermore we have $n$ entries for each predictor. It means that our design matrix is a \n",
@@ -2785,8 +3062,10 @@
},
{
"cell_type": "markdown",
- "id": "6081f608",
- "metadata": {},
+ "id": "16c3470c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## General linear models\n",
"Before we proceed let us study a case from linear algebra where we aim at fitting a set of data $\\boldsymbol{y}=[y_0,y_1,\\dots,y_{n-1}]$. We could think of these data as a result of an experiment or a complicated numerical experiment. These data are functions of a series of variables $\\boldsymbol{x}=[x_0,x_1,\\dots,x_{n-1}]$, that is $y_i = y(x_i)$ with $i=0,1,2,\\dots,n-1$. The variables $x_i$ could represent physical quantities like time, temperature, position etc. We assume that $y(x)$ is a smooth function. \n",
@@ -2796,8 +3075,10 @@
},
{
"cell_type": "markdown",
- "id": "142a005f",
- "metadata": {},
+ "id": "7649ec95",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"y=y(x) \\rightarrow y(x_i)=\\tilde{y}_i+\\epsilon_i=\\sum_{j=0}^{n-1} \\beta_j x_i^j+\\epsilon_i,\n",
@@ -2806,16 +3087,20 @@
},
{
"cell_type": "markdown",
- "id": "49446a2f",
- "metadata": {},
+ "id": "f5ed6417",
+ "metadata": {
+ "editable": true
+ },
"source": [
"where $\\epsilon_i$ is the error in our approximation."
]
},
{
"cell_type": "markdown",
- "id": "72044f3f",
- "metadata": {},
+ "id": "aaf67ddd",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Rewriting the fitting procedure as a linear algebra problem\n",
"For every set of values $y_i,x_i$ we have thus the corresponding set of equations"
@@ -2823,8 +3108,10 @@
},
{
"cell_type": "markdown",
- "id": "5978a866",
- "metadata": {},
+ "id": "f643cb97",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\begin{align*}\n",
@@ -2839,8 +3126,10 @@
},
{
"cell_type": "markdown",
- "id": "b13072e8",
- "metadata": {},
+ "id": "6d761dd7",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Rewriting the fitting procedure as a linear algebra problem, more details\n",
"Defining the vectors"
@@ -2848,8 +3137,10 @@
},
{
"cell_type": "markdown",
- "id": "6056f36e",
- "metadata": {},
+ "id": "6a133530",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{y} = [y_0,y_1, y_2,\\dots, y_{n-1}]^T,\n",
@@ -2858,16 +3149,20 @@
},
{
"cell_type": "markdown",
- "id": "34f71f52",
- "metadata": {},
+ "id": "e56ea64c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"and"
]
},
{
"cell_type": "markdown",
- "id": "2edeb755",
- "metadata": {},
+ "id": "7fef0140",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{\\beta} = [\\beta_0,\\beta_1, \\beta_2,\\dots, \\beta_{n-1}]^T,\n",
@@ -2876,16 +3171,20 @@
},
{
"cell_type": "markdown",
- "id": "e004a257",
- "metadata": {},
+ "id": "7aa38a92",
+ "metadata": {
+ "editable": true
+ },
"source": [
"and"
]
},
{
"cell_type": "markdown",
- "id": "636097f2",
- "metadata": {},
+ "id": "b33f7a32",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{\\epsilon} = [\\epsilon_0,\\epsilon_1, \\epsilon_2,\\dots, \\epsilon_{n-1}]^T,\n",
@@ -2894,16 +3193,20 @@
},
{
"cell_type": "markdown",
- "id": "8577dbb6",
- "metadata": {},
+ "id": "b503f481",
+ "metadata": {
+ "editable": true
+ },
"source": [
"and the design matrix"
]
},
{
"cell_type": "markdown",
- "id": "e76f9a38",
- "metadata": {},
+ "id": "e80416c1",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{X}=\n",
@@ -2919,16 +3222,20 @@
},
{
"cell_type": "markdown",
- "id": "aa89a70c",
- "metadata": {},
+ "id": "60236647",
+ "metadata": {
+ "editable": true
+ },
"source": [
"we can rewrite our equations as"
]
},
{
"cell_type": "markdown",
- "id": "c6ca5c9b",
- "metadata": {},
+ "id": "01f66bb5",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{y} = \\boldsymbol{X}\\boldsymbol{\\beta}+\\boldsymbol{\\epsilon}.\n",
@@ -2937,16 +3244,20 @@
},
{
"cell_type": "markdown",
- "id": "b657c2e4",
- "metadata": {},
+ "id": "c9ba9a94",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The above design matrix is called a [Vandermonde matrix](https://en.wikipedia.org/wiki/Vandermonde_matrix)."
]
},
{
"cell_type": "markdown",
- "id": "965e8d48",
- "metadata": {},
+ "id": "1d741baa",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Generalizing the fitting procedure as a linear algebra problem\n",
"\n",
@@ -2959,8 +3270,10 @@
},
{
"cell_type": "markdown",
- "id": "ef647144",
- "metadata": {},
+ "id": "20389a06",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\begin{align*}\n",
@@ -2977,16 +3290,20 @@
},
{
"cell_type": "markdown",
- "id": "e562da77",
- "metadata": {},
+ "id": "5e4cfce7",
+ "metadata": {
+ "editable": true
+ },
"source": [
"**Note that we have $p=n$ here. The matrix is symmetric. This is generally not the case!**"
]
},
{
"cell_type": "markdown",
- "id": "e8ba4531",
- "metadata": {},
+ "id": "fbcc79bf",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Generalizing the fitting procedure as a linear algebra problem\n",
"We redefine in turn the matrix $\\boldsymbol{X}$ as"
@@ -2994,8 +3311,10 @@
},
{
"cell_type": "markdown",
- "id": "528b1a26",
- "metadata": {},
+ "id": "e5ffed83",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{X}=\n",
@@ -3011,16 +3330,20 @@
},
{
"cell_type": "markdown",
- "id": "fd83859b",
- "metadata": {},
+ "id": "a47bae79",
+ "metadata": {
+ "editable": true
+ },
"source": [
"and without loss of generality we rewrite again our equations as"
]
},
{
"cell_type": "markdown",
- "id": "a31fc391",
- "metadata": {},
+ "id": "37c3002d",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\boldsymbol{y} = \\boldsymbol{X}\\boldsymbol{\\beta}+\\boldsymbol{\\epsilon}.\n",
@@ -3029,16 +3352,20 @@
},
{
"cell_type": "markdown",
- "id": "637b3c41",
- "metadata": {},
+ "id": "03cae64f",
+ "metadata": {
+ "editable": true
+ },
"source": [
"The left-hand side of this equation is kwown. Our error vector $\\boldsymbol{\\epsilon}$ and the parameter vector $\\boldsymbol{\\beta}$ are our unknow quantities. How can we obtain the optimal set of $\\beta_i$ values?"
]
},
{
"cell_type": "markdown",
- "id": "a449ee2e",
- "metadata": {},
+ "id": "ede0df9c",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Optimizing our parameters\n",
"We have defined the matrix $\\boldsymbol{X}$ via the equations"
@@ -3046,8 +3373,10 @@
},
{
"cell_type": "markdown",
- "id": "2f5357e7",
- "metadata": {},
+ "id": "b8d9cb9a",
+ "metadata": {
+ "editable": true
+ },
"source": [
"$$\n",
"\\begin{align*}\n",
@@ -3064,8 +3393,10 @@
},
{
"cell_type": "markdown",
- "id": "8618a946",
- "metadata": {},
+ "id": "dd2f9baa",
+ "metadata": {
+ "editable": true
+ },
"source": [
"As we noted above, we stayed with a system with the design matrix \n",
" $\\boldsymbol{X}\\in {\\mathbb{R}}^{n\\times n}$, that is we have $p=n$. For reasons to come later (algorithmic arguments) we will hereafter define \n",
@@ -3074,8 +3405,10 @@
},
{
"cell_type": "markdown",
- "id": "e17e4fbf",
- "metadata": {},
+ "id": "3f6c6a00",
+ "metadata": {
+ "editable": true
+ },
"source": [
"## Our model for the nuclear binding energies\n",
"\n",
@@ -3086,162 +3419,13 @@
},
{
"cell_type": "code",
- "execution_count": 1,
- "id": "585d5f0d",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " 1 | \n",
- " A | \n",
- " A^(2/3) | \n",
- " A^(-1/3) | \n",
- " 1/A | \n",
- "
\n",
- " \n",
- " | A | \n",
- " | \n",
- " | \n",
- " | \n",
- " | \n",
- " | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 4 | \n",
- " 1.0 | \n",
- " 4.0 | \n",
- " 2.519842 | \n",
- " 0.629961 | \n",
- " 0.250000 | \n",
- "
\n",
- " \n",
- " | 5 | \n",
- " 1.0 | \n",
- " 5.0 | \n",
- " 2.924018 | \n",
- " 0.584804 | \n",
- " 0.200000 | \n",
- "
\n",
- " \n",
- " | 6 | \n",
- " 1.0 | \n",
- " 6.0 | \n",
- " 3.301927 | \n",
- " 0.550321 | \n",
- " 0.166667 | \n",
- "
\n",
- " \n",
- " | 7 | \n",
- " 1.0 | \n",
- " 7.0 | \n",
- " 3.659306 | \n",
- " 0.522758 | \n",
- " 0.142857 | \n",
- "
\n",
- " \n",
- " | 8 | \n",
- " 1.0 | \n",
- " 8.0 | \n",
- " 4.000000 | \n",
- " 0.500000 | \n",
- " 0.125000 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 264 | \n",
- " 1.0 | \n",
- " 264.0 | \n",
- " 41.153106 | \n",
- " 0.155883 | \n",
- " 0.003788 | \n",
- "
\n",
- " \n",
- " | 265 | \n",
- " 1.0 | \n",
- " 265.0 | \n",
- " 41.256962 | \n",
- " 0.155687 | \n",
- " 0.003774 | \n",
- "
\n",
- " \n",
- " | 266 | \n",
- " 1.0 | \n",
- " 266.0 | \n",
- " 41.360688 | \n",
- " 0.155491 | \n",
- " 0.003759 | \n",
- "
\n",
- " \n",
- " | 269 | \n",
- " 1.0 | \n",
- " 269.0 | \n",
- " 41.671089 | \n",
- " 0.154911 | \n",
- " 0.003717 | \n",
- "
\n",
- " \n",
- " | 270 | \n",
- " 1.0 | \n",
- " 270.0 | \n",
- " 41.774300 | \n",
- " 0.154720 | \n",
- " 0.003704 | \n",
- "
\n",
- " \n",
- "
\n",
- "
264 rows × 5 columns
\n",
- "