diff --git a/doc/Projects/2021/Project1/html/._Project1-bs000.html b/doc/Projects/2021/Project1/html/._Project1-bs000.html index af8e05322..fc4f5eaf6 100644 --- a/doc/Projects/2021/Project1/html/._Project1-bs000.html +++ b/doc/Projects/2021/Project1/html/._Project1-bs000.html @@ -622,11 +622,6 @@ of code developers and contributors keeps increasing. --> -
- © 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license -
- - diff --git a/doc/Projects/2021/Project1/html/Project1-bs.html b/doc/Projects/2021/Project1/html/Project1-bs.html index af8e05322..fc4f5eaf6 100644 --- a/doc/Projects/2021/Project1/html/Project1-bs.html +++ b/doc/Projects/2021/Project1/html/Project1-bs.html @@ -622,11 +622,6 @@ of code developers and contributors keeps increasing. --> -
- © 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license -
- - diff --git a/doc/Projects/2021/Project1/html/Project1.html b/doc/Projects/2021/Project1/html/Project1.html index 45c385855..50ecb34e5 100644 --- a/doc/Projects/2021/Project1/html/Project1.html +++ b/doc/Projects/2021/Project1/html/Project1.html @@ -562,11 +562,6 @@ of code developers and contributors keeps increasing. -
- © 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license -
- - diff --git a/doc/Projects/2021/Project1/ipynb/Project1.ipynb b/doc/Projects/2021/Project1/ipynb/Project1.ipynb index eddf25d11..099b6ad84 100644 --- a/doc/Projects/2021/Project1/ipynb/Project1.ipynb +++ b/doc/Projects/2021/Project1/ipynb/Project1.ipynb @@ -12,12 +12,6 @@ "\n", "Date: **Sep 10, 2021**\n", "\n", - "Copyright 1999-2021, [Data Analysis and Machine Learning FYS-STK3155/FYS4155](http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html). Released under CC Attribution-NonCommercial 4.0 license\n", - "\n", - "\n", - "\n", - "\n", - "\n", "## Regression analysis and resampling methods\n", "\n", "The main aim of this project is to study in more detail various\n", diff --git a/doc/Projects/2021/Project1/ipynb/ipynb-Project1-src.tar.gz b/doc/Projects/2021/Project1/ipynb/ipynb-Project1-src.tar.gz index 17ccd89ef..84f5a51a2 100644 Binary files a/doc/Projects/2021/Project1/ipynb/ipynb-Project1-src.tar.gz and b/doc/Projects/2021/Project1/ipynb/ipynb-Project1-src.tar.gz differ diff --git a/doc/Projects/2021/Project1/pdf/Project1.p.tex b/doc/Projects/2021/Project1/pdf/Project1.p.tex index 8e37ea274..920e810a0 100644 --- a/doc/Projects/2021/Project1/pdf/Project1.p.tex +++ b/doc/Projects/2021/Project1/pdf/Project1.p.tex @@ -77,29 +77,6 @@ final, % draft: marks overfull hboxes, figures with paths \setcounter{tocdepth}{2} % levels in table of contents -% --- fancyhdr package for fancy headers --- -\usepackage{fancyhdr} -\fancyhf{} % sets both header and footer to nothing -\renewcommand{\headrulewidth}{0pt} -\fancyfoot[LE,RO]{\thepage} -% Ensure copyright on titlepage (article style) and chapter pages (book style) -\fancypagestyle{plain}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} -% \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} -% Ensure copyright on titlepages with \thispagestyle{empty} -\fancypagestyle{empty}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} - \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} - -\pagestyle{fancy} - - % prevent orhpans and widows \clubpenalty = 10000 \widowpenalty = 10000 diff --git a/doc/Projects/2021/Project1/pdf/Project1.pdf b/doc/Projects/2021/Project1/pdf/Project1.pdf index 6d70acd44..6aad9e23d 100644 Binary files a/doc/Projects/2021/Project1/pdf/Project1.pdf and b/doc/Projects/2021/Project1/pdf/Project1.pdf differ diff --git a/doc/Projects/2021/Project1/pdf/Project1.tex b/doc/Projects/2021/Project1/pdf/Project1.tex index 63acd18f6..147556fe6 100644 --- a/doc/Projects/2021/Project1/pdf/Project1.tex +++ b/doc/Projects/2021/Project1/pdf/Project1.tex @@ -48,29 +48,6 @@ final, % draft: marks overfull hboxes, figures with paths \setcounter{tocdepth}{2} % levels in table of contents -% --- fancyhdr package for fancy headers --- -\usepackage{fancyhdr} -\fancyhf{} % sets both header and footer to nothing -\renewcommand{\headrulewidth}{0pt} -\fancyfoot[LE,RO]{\thepage} -% Ensure copyright on titlepage (article style) and chapter pages (book style) -\fancypagestyle{plain}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} -% \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} -% Ensure copyright on titlepages with \thispagestyle{empty} -\fancypagestyle{empty}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} - \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} - -\pagestyle{fancy} - - % prevent orhpans and widows \clubpenalty = 10000 \widowpenalty = 10000 diff --git a/doc/src/Projects/2021/Project1/._Project1-bs000.html b/doc/src/Projects/2021/Project1/._Project1-bs000.html deleted file mode 100644 index af8e05322..000000000 --- a/doc/src/Projects/2021/Project1/._Project1-bs000.html +++ /dev/null @@ -1,633 +0,0 @@ - - - - - - - - -Project 1 on Machine Learning, deadline October 4, 2020 - - - - - - - - - - - - - - - - - - - - - - - -
-
- - Project 1 on Machine Learning, deadline October 4, 2020 -
- -
- -
-
- - -
- -

 

 

 

- - - - - - -
-

Project 1 on Machine Learning, deadline October 4, 2020

- -

- - -

-Data Analysis and Machine Learning FYS-STK3155/FYS4155 -
- -

- - -

University of Oslo, Norway
-
-

-

Sep 10, 2021

-
-

-

- -

Regression analysis and resampling methods

- -

-The main aim of this project is to study in more detail various -regression methods, including the Ordinary Least Squares (OLS) method, -The total score is 100 points. Each subtask has its own final score. - -

-We will first study how to fit polynomials to a specific -two-dimensional function called Franke's -function. This -is a function which has been widely used when testing various -interpolation and fitting algorithms. Furthermore, after having -established the model and the method, we will employ resamling -techniques such as cross-validation and/or bootstrap in order to perform a -proper assessment of our models. We will also study in detail the -so-called Bias-Variance trade off. - -

-The Franke function, which is a weighted sum of four exponentials reads as follows -$$ -\begin{align*} -f(x,y) &= \frac{3}{4}\exp{\left(-\frac{(9x-2)^2}{4} - \frac{(9y-2)^2}{4}\right)}+\frac{3}{4}\exp{\left(-\frac{(9x+1)^2}{49}- \frac{(9y+1)}{10}\right)} \\ -&+\frac{1}{2}\exp{\left(-\frac{(9x-7)^2}{4} - \frac{(9y-3)^2}{4}\right)} -\frac{1}{5}\exp{\left(-(9x-4)^2 - (9y-7)^2\right) }. -\end{align*} -$$ - -

-The function will be defined for \( x,y\in [0,1] \). Our first step will -be to perform an OLS regression analysis of this function, trying out -a polynomial fit with an \( x \) and \( y \) dependence of the form \( [x, y, -x^2, y^2, xy, \dots] \). We will also include bootstrap first as -a resampling technique. After that we will include the cross-validation technique. As in homeworks 1 and 2, we can use a uniform -distribution to set up the arrays of values for \( x \) and \( y \), or as in -the example below just a set of fixed -values for \( x \) and \( y \) with a given step -size. We will fit a -function (for example a polynomial) of \( x \) and \( y \). Thereafter we -will repeat much of the same procedure using the Ridge and Lasso -regression methods, introducing thus a dependence on the bias -(penalty) \( \lambda \). - -

-Finally we are going to use (real) digital terrain data and try to -reproduce these data using the same methods. We will also try to go -beyond the second-order polynomials metioned above and explore -which polynomial fits the data best. - -

-The Python code for the Franke function is included here (it performs also a three-dimensional plot of it) -

- - -

from mpl_toolkits.mplot3d import Axes3D
-import matplotlib.pyplot as plt
-from matplotlib import cm
-from matplotlib.ticker import LinearLocator, FormatStrFormatter
-import numpy as np
-from random import random, seed
-
-fig = plt.figure()
-ax = fig.gca(projection='3d')
-
-# Make data.
-x = np.arange(0, 1, 0.05)
-y = np.arange(0, 1, 0.05)
-x, y = np.meshgrid(x,y)
-
-
-def FrankeFunction(x,y):
-    term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))
-    term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))
-    term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))
-    term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)
-    return term1 + term2 + term3 + term4
-
-
-z = FrankeFunction(x, y)
-
-# Plot the surface.
-surf = ax.plot_surface(x, y, z, cmap=cm.coolwarm,
-                       linewidth=0, antialiased=False)
-
-# Customize the z axis.
-ax.set_zlim(-0.10, 1.40)
-ax.zaxis.set_major_locator(LinearLocator(10))
-ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
-
-# Add a color bar which maps values to colors.
-fig.colorbar(surf, shrink=0.5, aspect=5)
-
-plt.show()
-
- -

Exercise 1: Ordinary Least Square (OLS) on the Franke function (score 10 points)

- -

-We will generate our own dataset for a function -\( \mathrm{FrankeFunction}(x,y) \) with \( x,y \in [0,1] \). The function -\( f(x,y) \) is the Franke function. You should explore also the addition -of an added stochastic noise to this function using the normal -distribution \( \cal{N}(0,1) \). - -

-Write your own code (using either a matrix inversion or a singular -value decomposition from e.g., numpy ) or use your code from -homeworks 1 and 2 and perform a standard least square regression -analysis using polynomials in \( x \) and \( y \) up to fifth order. Find the -confidence intervals of the parameters (estimators) \( \beta \) by computing their -variances, evaluate the Mean Squared error (MSE) - -$$ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n} -\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2, -$$ - -

-and the \( R^2 \) score function. If \( \tilde{\hat{y}}_i \) is the predicted -value of the \( i-th \) sample and \( y_i \) is the corresponding true value, -then the score \( R^2 \) is defined as - -$$ -R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2}, -$$ - -

-where we have defined the mean value of \( \hat{y} \) as - -$$ -\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i. -$$ - -

-Your code has to include a scaling of the data (for example by -subtracting the mean value), and -a split of the data in training and test data. For this part you can -either write your own code or use for example the function for -splitting training data provided by the library Scikit-Learn (make -sure you have installed it). This function is called -\( train\_test\_split \). You should present a critical discussion of why and how you have scaled or not scaled the data. - -

-It is normal in essentially all Machine Learning studies to split the -data in a training set and a test set (eventually also an additional -validation set). There -is no explicit recipe for how much data should be included as training -data and say test data. An accepted rule of thumb is to use -approximately \( 2/3 \) to \( 4/5 \) of the data as training data. - -

Exercise 2: Bias-variance trade-off and resampling techniques (score 15 points)

- -

-Our aim here is to study the bias-variance trade-off by implementing the bootstrap resampling technique. - -

-With a code which does OLS and includes resampling techniques, -we will now discuss the bias-variance trade-off in the context of -continuous predictions such as regression. However, many of the -intuitions and ideas discussed here also carry over to classification -tasks and basically all Machine Learning algorithms. - -

-Before you perform an analysis of the bias-variance trade-off on your test data, make -first a figure similar to Fig. 2.11 of Hastie, Tibshirani, and -Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to -indicate possible regions of low/high bias and variance. You will most likely not get an -equally smooth curve! - -

-With this result we move on to the bias-variance trade-off analysis. - -

-Consider a -dataset \( \mathcal{L} \) consisting of the data -\( \mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\} \). - -

-Let us assume that the true data is generated from a noisy model - -$$ -\boldsymbol{y}=f(\boldsymbol{x}) + \boldsymbol{\epsilon}. -$$ - -

-Here \( \epsilon \) is normally distributed with mean zero and standard -deviation \( \sigma^2 \). - -

-In our derivation of the ordinary least squares method we defined then -an approximation to the function \( f \) in terms of the parameters -\( \boldsymbol{\beta} \) and the design matrix \( \boldsymbol{X} \) which embody our model, -that is \( \boldsymbol{\tilde{y}}=\boldsymbol{X}\boldsymbol{\beta} \). - -

-The parameters \( \boldsymbol{\beta} \) are in turn found by optimizing the means -squared error via the so-called cost function - -$$ -C(\boldsymbol{X},\boldsymbol{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]. -$$ - -Here the expected value \( \mathbb{E} \) is the sample value. - -

-Show that you can rewrite this as -$$ -\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]=\frac{1}{n}\sum_i(f_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2+\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2+\sigma^2. -$$ - -

-Explain what the terms mean, which one is the bias and which one is -the variance and discuss their interpretations. - -

-Perform then a bias-variance analysis of the Franke function by -studying the MSE value as function of the complexity of your model. - -

-Discuss the bias and variance trade-off as function -of your model complexity (the degree of the polynomial) and the number -of data points, and possibly also your training and test data using the bootstrap resampling method. - -

-Note also that when you calculate the bias, in all applications you don't know the function values \( f_i \). You would hence replace them with the actual data points \( y_i \). - -

Exercise 3: Cross-validation as resampling techniques, adding more complexity (score 15 points)

- -

-The aim here is to write your own code for another widely popular -resampling technique, the so-called cross-validation method. Again, -before you start with cross-validation approach, you should scale your -data. - -

-Implement the \( k \)-fold cross-validation algorithm (write your own -code) and evaluate again the MSE function resulting -from the test folds. You can compare your own code with that from -Scikit-Learn if needed. - -

-Compare the MSE you get from your cross-validation code with the one -you got from your bootstrap code. Comment your results. Try \( 5-10 \) -folds. You can also compare your own cross-validation code with the -one provided by Scikit-Learn. - -

Exercise 4: Ridge Regression on the Franke function with resampling (score 20 points)

- -

-Write your own code for the Ridge method, either using matrix -inversion or the singular value decomposition as done in the previous -exercise. Perform the same bootstrap analysis as in the -Exercise 2 (for the same polynomials) and the cross-validation part in part c) but now for different values of \( \lambda \). Compare and -analyze your results with those obtained in exercises 1-3. Study the -dependence on \( \lambda \). - -

-Study also the bias-variance trade-off as function of various values of -the parameter \( \lambda \). For the bias-variance trade-off, use the bootstrap resampling method. Comment your results. - -

Exercise 5: Lasso Regression on the Franke function with resampling (Score 10 points))

- -

-This exercise is essentially a repeat of the previous two ones, but now -with Lasso regression. Write either your own code (difficult and optional) or, in this case, -you can also use the functionalities of Scikit-Learn (recommended). -Give a -critical discussion of the three methods and a judgement of which -model fits the data best. Perform here as well an analysis of the bias-variance trade-off using the bootstrap resampling technique and an analysis of the mean squared error using cross-validation. - -

Exercise 6: Analysis of real data (score 30 points)

- -

-With our codes functioning and having been tested properly on a -simpler function we are now ready to look at real data. We will -essentially repeat in part g) what was done in parts a-e). However, we -need first to download the data and prepare properly the inputs to our -codes. We are going to download digital terrain data from the website -https://earthexplorer.usgs.gov/, - -

-In order to obtain data for a specific region, you need to register as -a user (free) at this website and then decide upon which area you want -to fetch the digital terrain data from. In order to be able to read -the data properly, you need to specify that the format should be SRTM -Arc-Second Global and download the data as a GeoTIF file. The -files are then stored in tif format which can be imported into a -Python program using - -

- - -

scipy.misc.imread
-
-

-Here is a simple part of a Python code which reads and plots the data -from such files - -

- - -

import numpy as np
-from imageio import imread
-import matplotlib.pyplot as plt
-from mpl_toolkits.mplot3d import Axes3D
-from matplotlib import cm
-
-# Load the terrain
-terrain1 = imread('SRTM_data_Norway_1.tif')
-# Show the terrain
-plt.figure()
-plt.title('Terrain over Norway 1')
-plt.imshow(terrain1, cmap='gray')
-plt.xlabel('X')
-plt.ylabel('Y')
-plt.show()
-
-

-If you should have problems in downloading the digital terrain data, -we provide two examples under the data folder of project 1. One is -from a region close to Stavanger in Norway and the other Møsvatn -Austfjell, again in Norway. -Feel free to produce your own terrain data. - -

-Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example kaggle.com for examples. - -

-Our final part deals with the parameterization of your digital terrain -data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial -approximation and cross-validation as resampling technique to evaluate which -model fits the data best. - -

-At the end, you should present a critical evaluation of your results -and discuss the applicability of these regression methods to the type -of data presented here (either the terrain data we propose or other data sets). - -

Background literature

- -
    -
  1. For a discussion and derivation of the variances and mean squared errors using linear regression, see the Lecture notes on ridge regression by Wessel N. van Wieringen
    2. -
  2. The textbook of Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer, chapters 3 and 7 are the most relevant ones for the analysis here.
    3. -
- -

Introduction to numerical projects

- -

-Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers. Note that you can answer question by question and there is no need to structure your report as a scientific report with abstract, introduction, theory, results and discussions, conclusions etc. But you have the following elements in mind when you answer the various questions. - -

- -

Format for electronic delivery of report and programs

- -

-The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report: - -

- -Finally, -we encourage you to collaborate. Optimal working groups consist of -2-3 students. You can then hand in a common report. - -

Software and needed installations

- -

-If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages, -we recommend that you install the following Python packages via pip as - -

    -
  1. pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow
    2. -
- -For Python3, replace pip with pip3. - -

-See below for a discussion of tensorflow and scikit-learn. - -

-For OSX users we recommend also, after having installed Xcode, to install brew. Brew allows -for a seamless installation of additional software via for example - -

    -
  1. brew install python3
    2. -
- -For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution -you can use pip as well and simply install Python as - -
    -
  1. sudo apt-get install python3 (or python for python2.7)
    2. -
- -etc etc. - -

-If you don't want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely - -

    -
  1. Anaconda Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system conda
    2. -
  2. Enthought canopy is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license.
    3. -
- -Popular software packages written in Python for ML are - - - -These are all freely available at their respective GitHub sites. They -encompass communities of developers in the thousands or more. And the number -of code developers and contributors keeps increasing. - -

- -

- -

- - -
- - - - - - - -
- © 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license -
- - - - - - diff --git a/doc/src/Projects/2021/Project1/Project1-bs.html b/doc/src/Projects/2021/Project1/Project1-bs.html deleted file mode 100644 index af8e05322..000000000 --- a/doc/src/Projects/2021/Project1/Project1-bs.html +++ /dev/null @@ -1,633 +0,0 @@ - - - - - - - - -Project 1 on Machine Learning, deadline October 4, 2020 - - - - - - - - - - - - - - - - - - - - - - - -
-
- - Project 1 on Machine Learning, deadline October 4, 2020 -
- -
- -
-
- - -
- -

 

 

 

- - - - - - -
-

Project 1 on Machine Learning, deadline October 4, 2020

- -

- - -

-Data Analysis and Machine Learning FYS-STK3155/FYS4155 -
- -

- - -

University of Oslo, Norway
-
-

-

Sep 10, 2021

-
-

-

- -

Regression analysis and resampling methods

- -

-The main aim of this project is to study in more detail various -regression methods, including the Ordinary Least Squares (OLS) method, -The total score is 100 points. Each subtask has its own final score. - -

-We will first study how to fit polynomials to a specific -two-dimensional function called Franke's -function. This -is a function which has been widely used when testing various -interpolation and fitting algorithms. Furthermore, after having -established the model and the method, we will employ resamling -techniques such as cross-validation and/or bootstrap in order to perform a -proper assessment of our models. We will also study in detail the -so-called Bias-Variance trade off. - -

-The Franke function, which is a weighted sum of four exponentials reads as follows -$$ -\begin{align*} -f(x,y) &= \frac{3}{4}\exp{\left(-\frac{(9x-2)^2}{4} - \frac{(9y-2)^2}{4}\right)}+\frac{3}{4}\exp{\left(-\frac{(9x+1)^2}{49}- \frac{(9y+1)}{10}\right)} \\ -&+\frac{1}{2}\exp{\left(-\frac{(9x-7)^2}{4} - \frac{(9y-3)^2}{4}\right)} -\frac{1}{5}\exp{\left(-(9x-4)^2 - (9y-7)^2\right) }. -\end{align*} -$$ - -

-The function will be defined for \( x,y\in [0,1] \). Our first step will -be to perform an OLS regression analysis of this function, trying out -a polynomial fit with an \( x \) and \( y \) dependence of the form \( [x, y, -x^2, y^2, xy, \dots] \). We will also include bootstrap first as -a resampling technique. After that we will include the cross-validation technique. As in homeworks 1 and 2, we can use a uniform -distribution to set up the arrays of values for \( x \) and \( y \), or as in -the example below just a set of fixed -values for \( x \) and \( y \) with a given step -size. We will fit a -function (for example a polynomial) of \( x \) and \( y \). Thereafter we -will repeat much of the same procedure using the Ridge and Lasso -regression methods, introducing thus a dependence on the bias -(penalty) \( \lambda \). - -

-Finally we are going to use (real) digital terrain data and try to -reproduce these data using the same methods. We will also try to go -beyond the second-order polynomials metioned above and explore -which polynomial fits the data best. - -

-The Python code for the Franke function is included here (it performs also a three-dimensional plot of it) -

- - -

from mpl_toolkits.mplot3d import Axes3D
-import matplotlib.pyplot as plt
-from matplotlib import cm
-from matplotlib.ticker import LinearLocator, FormatStrFormatter
-import numpy as np
-from random import random, seed
-
-fig = plt.figure()
-ax = fig.gca(projection='3d')
-
-# Make data.
-x = np.arange(0, 1, 0.05)
-y = np.arange(0, 1, 0.05)
-x, y = np.meshgrid(x,y)
-
-
-def FrankeFunction(x,y):
-    term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))
-    term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))
-    term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))
-    term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)
-    return term1 + term2 + term3 + term4
-
-
-z = FrankeFunction(x, y)
-
-# Plot the surface.
-surf = ax.plot_surface(x, y, z, cmap=cm.coolwarm,
-                       linewidth=0, antialiased=False)
-
-# Customize the z axis.
-ax.set_zlim(-0.10, 1.40)
-ax.zaxis.set_major_locator(LinearLocator(10))
-ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
-
-# Add a color bar which maps values to colors.
-fig.colorbar(surf, shrink=0.5, aspect=5)
-
-plt.show()
-
- -

Exercise 1: Ordinary Least Square (OLS) on the Franke function (score 10 points)

- -

-We will generate our own dataset for a function -\( \mathrm{FrankeFunction}(x,y) \) with \( x,y \in [0,1] \). The function -\( f(x,y) \) is the Franke function. You should explore also the addition -of an added stochastic noise to this function using the normal -distribution \( \cal{N}(0,1) \). - -

-Write your own code (using either a matrix inversion or a singular -value decomposition from e.g., numpy ) or use your code from -homeworks 1 and 2 and perform a standard least square regression -analysis using polynomials in \( x \) and \( y \) up to fifth order. Find the -confidence intervals of the parameters (estimators) \( \beta \) by computing their -variances, evaluate the Mean Squared error (MSE) - -$$ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n} -\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2, -$$ - -

-and the \( R^2 \) score function. If \( \tilde{\hat{y}}_i \) is the predicted -value of the \( i-th \) sample and \( y_i \) is the corresponding true value, -then the score \( R^2 \) is defined as - -$$ -R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2}, -$$ - -

-where we have defined the mean value of \( \hat{y} \) as - -$$ -\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i. -$$ - -

-Your code has to include a scaling of the data (for example by -subtracting the mean value), and -a split of the data in training and test data. For this part you can -either write your own code or use for example the function for -splitting training data provided by the library Scikit-Learn (make -sure you have installed it). This function is called -\( train\_test\_split \). You should present a critical discussion of why and how you have scaled or not scaled the data. - -

-It is normal in essentially all Machine Learning studies to split the -data in a training set and a test set (eventually also an additional -validation set). There -is no explicit recipe for how much data should be included as training -data and say test data. An accepted rule of thumb is to use -approximately \( 2/3 \) to \( 4/5 \) of the data as training data. - -

Exercise 2: Bias-variance trade-off and resampling techniques (score 15 points)

- -

-Our aim here is to study the bias-variance trade-off by implementing the bootstrap resampling technique. - -

-With a code which does OLS and includes resampling techniques, -we will now discuss the bias-variance trade-off in the context of -continuous predictions such as regression. However, many of the -intuitions and ideas discussed here also carry over to classification -tasks and basically all Machine Learning algorithms. - -

-Before you perform an analysis of the bias-variance trade-off on your test data, make -first a figure similar to Fig. 2.11 of Hastie, Tibshirani, and -Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to -indicate possible regions of low/high bias and variance. You will most likely not get an -equally smooth curve! - -

-With this result we move on to the bias-variance trade-off analysis. - -

-Consider a -dataset \( \mathcal{L} \) consisting of the data -\( \mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\} \). - -

-Let us assume that the true data is generated from a noisy model - -$$ -\boldsymbol{y}=f(\boldsymbol{x}) + \boldsymbol{\epsilon}. -$$ - -

-Here \( \epsilon \) is normally distributed with mean zero and standard -deviation \( \sigma^2 \). - -

-In our derivation of the ordinary least squares method we defined then -an approximation to the function \( f \) in terms of the parameters -\( \boldsymbol{\beta} \) and the design matrix \( \boldsymbol{X} \) which embody our model, -that is \( \boldsymbol{\tilde{y}}=\boldsymbol{X}\boldsymbol{\beta} \). - -

-The parameters \( \boldsymbol{\beta} \) are in turn found by optimizing the means -squared error via the so-called cost function - -$$ -C(\boldsymbol{X},\boldsymbol{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]. -$$ - -Here the expected value \( \mathbb{E} \) is the sample value. - -

-Show that you can rewrite this as -$$ -\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]=\frac{1}{n}\sum_i(f_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2+\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2+\sigma^2. -$$ - -

-Explain what the terms mean, which one is the bias and which one is -the variance and discuss their interpretations. - -

-Perform then a bias-variance analysis of the Franke function by -studying the MSE value as function of the complexity of your model. - -

-Discuss the bias and variance trade-off as function -of your model complexity (the degree of the polynomial) and the number -of data points, and possibly also your training and test data using the bootstrap resampling method. - -

-Note also that when you calculate the bias, in all applications you don't know the function values \( f_i \). You would hence replace them with the actual data points \( y_i \). - -

Exercise 3: Cross-validation as resampling techniques, adding more complexity (score 15 points)

- -

-The aim here is to write your own code for another widely popular -resampling technique, the so-called cross-validation method. Again, -before you start with cross-validation approach, you should scale your -data. - -

-Implement the \( k \)-fold cross-validation algorithm (write your own -code) and evaluate again the MSE function resulting -from the test folds. You can compare your own code with that from -Scikit-Learn if needed. - -

-Compare the MSE you get from your cross-validation code with the one -you got from your bootstrap code. Comment your results. Try \( 5-10 \) -folds. You can also compare your own cross-validation code with the -one provided by Scikit-Learn. - -

Exercise 4: Ridge Regression on the Franke function with resampling (score 20 points)

- -

-Write your own code for the Ridge method, either using matrix -inversion or the singular value decomposition as done in the previous -exercise. Perform the same bootstrap analysis as in the -Exercise 2 (for the same polynomials) and the cross-validation part in part c) but now for different values of \( \lambda \). Compare and -analyze your results with those obtained in exercises 1-3. Study the -dependence on \( \lambda \). - -

-Study also the bias-variance trade-off as function of various values of -the parameter \( \lambda \). For the bias-variance trade-off, use the bootstrap resampling method. Comment your results. - -

Exercise 5: Lasso Regression on the Franke function with resampling (Score 10 points))

- -

-This exercise is essentially a repeat of the previous two ones, but now -with Lasso regression. Write either your own code (difficult and optional) or, in this case, -you can also use the functionalities of Scikit-Learn (recommended). -Give a -critical discussion of the three methods and a judgement of which -model fits the data best. Perform here as well an analysis of the bias-variance trade-off using the bootstrap resampling technique and an analysis of the mean squared error using cross-validation. - -

Exercise 6: Analysis of real data (score 30 points)

- -

-With our codes functioning and having been tested properly on a -simpler function we are now ready to look at real data. We will -essentially repeat in part g) what was done in parts a-e). However, we -need first to download the data and prepare properly the inputs to our -codes. We are going to download digital terrain data from the website -https://earthexplorer.usgs.gov/, - -

-In order to obtain data for a specific region, you need to register as -a user (free) at this website and then decide upon which area you want -to fetch the digital terrain data from. In order to be able to read -the data properly, you need to specify that the format should be SRTM -Arc-Second Global and download the data as a GeoTIF file. The -files are then stored in tif format which can be imported into a -Python program using - -

- - -

scipy.misc.imread
-
-

-Here is a simple part of a Python code which reads and plots the data -from such files - -

- - -

import numpy as np
-from imageio import imread
-import matplotlib.pyplot as plt
-from mpl_toolkits.mplot3d import Axes3D
-from matplotlib import cm
-
-# Load the terrain
-terrain1 = imread('SRTM_data_Norway_1.tif')
-# Show the terrain
-plt.figure()
-plt.title('Terrain over Norway 1')
-plt.imshow(terrain1, cmap='gray')
-plt.xlabel('X')
-plt.ylabel('Y')
-plt.show()
-
-

-If you should have problems in downloading the digital terrain data, -we provide two examples under the data folder of project 1. One is -from a region close to Stavanger in Norway and the other Møsvatn -Austfjell, again in Norway. -Feel free to produce your own terrain data. - -

-Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example kaggle.com for examples. - -

-Our final part deals with the parameterization of your digital terrain -data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial -approximation and cross-validation as resampling technique to evaluate which -model fits the data best. - -

-At the end, you should present a critical evaluation of your results -and discuss the applicability of these regression methods to the type -of data presented here (either the terrain data we propose or other data sets). - -

Background literature

- -
    -
  1. For a discussion and derivation of the variances and mean squared errors using linear regression, see the Lecture notes on ridge regression by Wessel N. van Wieringen
    2. -
  2. The textbook of Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer, chapters 3 and 7 are the most relevant ones for the analysis here.
    3. -
- -

Introduction to numerical projects

- -

-Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers. Note that you can answer question by question and there is no need to structure your report as a scientific report with abstract, introduction, theory, results and discussions, conclusions etc. But you have the following elements in mind when you answer the various questions. - -

- -

Format for electronic delivery of report and programs

- -

-The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report: - -

- -Finally, -we encourage you to collaborate. Optimal working groups consist of -2-3 students. You can then hand in a common report. - -

Software and needed installations

- -

-If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages, -we recommend that you install the following Python packages via pip as - -

    -
  1. pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow
    2. -
- -For Python3, replace pip with pip3. - -

-See below for a discussion of tensorflow and scikit-learn. - -

-For OSX users we recommend also, after having installed Xcode, to install brew. Brew allows -for a seamless installation of additional software via for example - -

    -
  1. brew install python3
    2. -
- -For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution -you can use pip as well and simply install Python as - -
    -
  1. sudo apt-get install python3 (or python for python2.7)
    2. -
- -etc etc. - -

-If you don't want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely - -

    -
  1. Anaconda Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system conda
    2. -
  2. Enthought canopy is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license.
    3. -
- -Popular software packages written in Python for ML are - - - -These are all freely available at their respective GitHub sites. They -encompass communities of developers in the thousands or more. And the number -of code developers and contributors keeps increasing. - -

- -

- -

- - -
- - - - - - - -
- © 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license -
- - - - - - diff --git a/doc/src/Projects/2021/Project1/Project1.do.txt b/doc/src/Projects/2021/Project1/Project1.do.txt index 5acfcc61e..0e398e95a 100644 --- a/doc/src/Projects/2021/Project1/Project1.do.txt +++ b/doc/src/Projects/2021/Project1/Project1.do.txt @@ -1,5 +1,5 @@ TITLE: Project 1 on Machine Learning, deadline October 4, 2020 -AUTHOR: "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html" {copyright, 1999-present|CC BY-NC} at University of Oslo, Norway +AUTHOR: "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html" at University of Oslo, Norway DATE: today diff --git a/doc/src/Projects/2021/Project1/Project1.html b/doc/src/Projects/2021/Project1/Project1.html deleted file mode 100644 index 45c385855..000000000 --- a/doc/src/Projects/2021/Project1/Project1.html +++ /dev/null @@ -1,573 +0,0 @@ - - - - - - - - -Project 1 on Machine Learning, deadline October 4, 2020 - - - - - - - - - - - - - - - - - - - - - - - -

Project 1 on Machine Learning, deadline October 4, 2020

- -

- - -

-Data Analysis and Machine Learning FYS-STK3155/FYS4155 -
- -

- - -

University of Oslo, Norway
-
-

-

Sep 10, 2021

-
- -

Regression analysis and resampling methods

- -

-The main aim of this project is to study in more detail various -regression methods, including the Ordinary Least Squares (OLS) method, -The total score is 100 points. Each subtask has its own final score. - -

-We will first study how to fit polynomials to a specific -two-dimensional function called Franke's -function. This -is a function which has been widely used when testing various -interpolation and fitting algorithms. Furthermore, after having -established the model and the method, we will employ resamling -techniques such as cross-validation and/or bootstrap in order to perform a -proper assessment of our models. We will also study in detail the -so-called Bias-Variance trade off. - -

-The Franke function, which is a weighted sum of four exponentials reads as follows -$$ -\begin{align*} -f(x,y) &= \frac{3}{4}\exp{\left(-\frac{(9x-2)^2}{4} - \frac{(9y-2)^2}{4}\right)}+\frac{3}{4}\exp{\left(-\frac{(9x+1)^2}{49}- \frac{(9y+1)}{10}\right)} \\ -&+\frac{1}{2}\exp{\left(-\frac{(9x-7)^2}{4} - \frac{(9y-3)^2}{4}\right)} -\frac{1}{5}\exp{\left(-(9x-4)^2 - (9y-7)^2\right) }. -\end{align*} -$$ - -

-The function will be defined for \( x,y\in [0,1] \). Our first step will -be to perform an OLS regression analysis of this function, trying out -a polynomial fit with an \( x \) and \( y \) dependence of the form \( [x, y, -x^2, y^2, xy, \dots] \). We will also include bootstrap first as -a resampling technique. After that we will include the cross-validation technique. As in homeworks 1 and 2, we can use a uniform -distribution to set up the arrays of values for \( x \) and \( y \), or as in -the example below just a set of fixed -values for \( x \) and \( y \) with a given step -size. We will fit a -function (for example a polynomial) of \( x \) and \( y \). Thereafter we -will repeat much of the same procedure using the Ridge and Lasso -regression methods, introducing thus a dependence on the bias -(penalty) \( \lambda \). - -

-Finally we are going to use (real) digital terrain data and try to -reproduce these data using the same methods. We will also try to go -beyond the second-order polynomials metioned above and explore -which polynomial fits the data best. - -

-The Python code for the Franke function is included here (it performs also a three-dimensional plot of it) -

- - -

from mpl_toolkits.mplot3d import Axes3D
-import matplotlib.pyplot as plt
-from matplotlib import cm
-from matplotlib.ticker import LinearLocator, FormatStrFormatter
-import numpy as np
-from random import random, seed
-
-fig = plt.figure()
-ax = fig.gca(projection='3d')
-
-# Make data.
-x = np.arange(0, 1, 0.05)
-y = np.arange(0, 1, 0.05)
-x, y = np.meshgrid(x,y)
-
-
-def FrankeFunction(x,y):
-    term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))
-    term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))
-    term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))
-    term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)
-    return term1 + term2 + term3 + term4
-
-
-z = FrankeFunction(x, y)
-
-# Plot the surface.
-surf = ax.plot_surface(x, y, z, cmap=cm.coolwarm,
-                       linewidth=0, antialiased=False)
-
-# Customize the z axis.
-ax.set_zlim(-0.10, 1.40)
-ax.zaxis.set_major_locator(LinearLocator(10))
-ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
-
-# Add a color bar which maps values to colors.
-fig.colorbar(surf, shrink=0.5, aspect=5)
-
-plt.show()
-
- -

Exercise 1: Ordinary Least Square (OLS) on the Franke function (score 10 points)

- -

-We will generate our own dataset for a function -\( \mathrm{FrankeFunction}(x,y) \) with \( x,y \in [0,1] \). The function -\( f(x,y) \) is the Franke function. You should explore also the addition -of an added stochastic noise to this function using the normal -distribution \( \cal{N}(0,1) \). - -

-Write your own code (using either a matrix inversion or a singular -value decomposition from e.g., numpy ) or use your code from -homeworks 1 and 2 and perform a standard least square regression -analysis using polynomials in \( x \) and \( y \) up to fifth order. Find the -confidence intervals of the parameters (estimators) \( \beta \) by computing their -variances, evaluate the Mean Squared error (MSE) - -$$ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n} -\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2, -$$ - -

-and the \( R^2 \) score function. If \( \tilde{\hat{y}}_i \) is the predicted -value of the \( i-th \) sample and \( y_i \) is the corresponding true value, -then the score \( R^2 \) is defined as - -$$ -R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2}, -$$ - -

-where we have defined the mean value of \( \hat{y} \) as - -$$ -\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i. -$$ - -

-Your code has to include a scaling of the data (for example by -subtracting the mean value), and -a split of the data in training and test data. For this part you can -either write your own code or use for example the function for -splitting training data provided by the library Scikit-Learn (make -sure you have installed it). This function is called -\( train\_test\_split \). You should present a critical discussion of why and how you have scaled or not scaled the data. - -

-It is normal in essentially all Machine Learning studies to split the -data in a training set and a test set (eventually also an additional -validation set). There -is no explicit recipe for how much data should be included as training -data and say test data. An accepted rule of thumb is to use -approximately \( 2/3 \) to \( 4/5 \) of the data as training data. - -

Exercise 2: Bias-variance trade-off and resampling techniques (score 15 points)

- -

-Our aim here is to study the bias-variance trade-off by implementing the bootstrap resampling technique. - -

-With a code which does OLS and includes resampling techniques, -we will now discuss the bias-variance trade-off in the context of -continuous predictions such as regression. However, many of the -intuitions and ideas discussed here also carry over to classification -tasks and basically all Machine Learning algorithms. - -

-Before you perform an analysis of the bias-variance trade-off on your test data, make -first a figure similar to Fig. 2.11 of Hastie, Tibshirani, and -Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to -indicate possible regions of low/high bias and variance. You will most likely not get an -equally smooth curve! - -

-With this result we move on to the bias-variance trade-off analysis. - -

-Consider a -dataset \( \mathcal{L} \) consisting of the data -\( \mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\} \). - -

-Let us assume that the true data is generated from a noisy model - -$$ -\boldsymbol{y}=f(\boldsymbol{x}) + \boldsymbol{\epsilon}. -$$ - -

-Here \( \epsilon \) is normally distributed with mean zero and standard -deviation \( \sigma^2 \). - -

-In our derivation of the ordinary least squares method we defined then -an approximation to the function \( f \) in terms of the parameters -\( \boldsymbol{\beta} \) and the design matrix \( \boldsymbol{X} \) which embody our model, -that is \( \boldsymbol{\tilde{y}}=\boldsymbol{X}\boldsymbol{\beta} \). - -

-The parameters \( \boldsymbol{\beta} \) are in turn found by optimizing the means -squared error via the so-called cost function - -$$ -C(\boldsymbol{X},\boldsymbol{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]. -$$ - -Here the expected value \( \mathbb{E} \) is the sample value. - -

-Show that you can rewrite this as -$$ -\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]=\frac{1}{n}\sum_i(f_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2+\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2+\sigma^2. -$$ - -

-Explain what the terms mean, which one is the bias and which one is -the variance and discuss their interpretations. - -

-Perform then a bias-variance analysis of the Franke function by -studying the MSE value as function of the complexity of your model. - -

-Discuss the bias and variance trade-off as function -of your model complexity (the degree of the polynomial) and the number -of data points, and possibly also your training and test data using the bootstrap resampling method. - -

-Note also that when you calculate the bias, in all applications you don't know the function values \( f_i \). You would hence replace them with the actual data points \( y_i \). - -

Exercise 3: Cross-validation as resampling techniques, adding more complexity (score 15 points)

- -

-The aim here is to write your own code for another widely popular -resampling technique, the so-called cross-validation method. Again, -before you start with cross-validation approach, you should scale your -data. - -

-Implement the \( k \)-fold cross-validation algorithm (write your own -code) and evaluate again the MSE function resulting -from the test folds. You can compare your own code with that from -Scikit-Learn if needed. - -

-Compare the MSE you get from your cross-validation code with the one -you got from your bootstrap code. Comment your results. Try \( 5-10 \) -folds. You can also compare your own cross-validation code with the -one provided by Scikit-Learn. - -

Exercise 4: Ridge Regression on the Franke function with resampling (score 20 points)

- -

-Write your own code for the Ridge method, either using matrix -inversion or the singular value decomposition as done in the previous -exercise. Perform the same bootstrap analysis as in the -Exercise 2 (for the same polynomials) and the cross-validation part in part c) but now for different values of \( \lambda \). Compare and -analyze your results with those obtained in exercises 1-3. Study the -dependence on \( \lambda \). - -

-Study also the bias-variance trade-off as function of various values of -the parameter \( \lambda \). For the bias-variance trade-off, use the bootstrap resampling method. Comment your results. - -

Exercise 5: Lasso Regression on the Franke function with resampling (Score 10 points))

- -

-This exercise is essentially a repeat of the previous two ones, but now -with Lasso regression. Write either your own code (difficult and optional) or, in this case, -you can also use the functionalities of Scikit-Learn (recommended). -Give a -critical discussion of the three methods and a judgement of which -model fits the data best. Perform here as well an analysis of the bias-variance trade-off using the bootstrap resampling technique and an analysis of the mean squared error using cross-validation. - -

Exercise 6: Analysis of real data (score 30 points)

- -

-With our codes functioning and having been tested properly on a -simpler function we are now ready to look at real data. We will -essentially repeat in part g) what was done in parts a-e). However, we -need first to download the data and prepare properly the inputs to our -codes. We are going to download digital terrain data from the website -https://earthexplorer.usgs.gov/, - -

-In order to obtain data for a specific region, you need to register as -a user (free) at this website and then decide upon which area you want -to fetch the digital terrain data from. In order to be able to read -the data properly, you need to specify that the format should be SRTM -Arc-Second Global and download the data as a GeoTIF file. The -files are then stored in tif format which can be imported into a -Python program using - -

- - -

scipy.misc.imread
-
-

-Here is a simple part of a Python code which reads and plots the data -from such files - -

- - -

import numpy as np
-from imageio import imread
-import matplotlib.pyplot as plt
-from mpl_toolkits.mplot3d import Axes3D
-from matplotlib import cm
-
-# Load the terrain
-terrain1 = imread('SRTM_data_Norway_1.tif')
-# Show the terrain
-plt.figure()
-plt.title('Terrain over Norway 1')
-plt.imshow(terrain1, cmap='gray')
-plt.xlabel('X')
-plt.ylabel('Y')
-plt.show()
-
-

-If you should have problems in downloading the digital terrain data, -we provide two examples under the data folder of project 1. One is -from a region close to Stavanger in Norway and the other Møsvatn -Austfjell, again in Norway. -Feel free to produce your own terrain data. - -

-Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example kaggle.com for examples. - -

-Our final part deals with the parameterization of your digital terrain -data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial -approximation and cross-validation as resampling technique to evaluate which -model fits the data best. - -

-At the end, you should present a critical evaluation of your results -and discuss the applicability of these regression methods to the type -of data presented here (either the terrain data we propose or other data sets). - -

Background literature

- -
    -
  1. For a discussion and derivation of the variances and mean squared errors using linear regression, see the Lecture notes on ridge regression by Wessel N. van Wieringen
    2. -
  2. The textbook of Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer, chapters 3 and 7 are the most relevant ones for the analysis here.
    3. -
- -

Introduction to numerical projects

- -

-Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers. Note that you can answer question by question and there is no need to structure your report as a scientific report with abstract, introduction, theory, results and discussions, conclusions etc. But you have the following elements in mind when you answer the various questions. - -

- -

Format for electronic delivery of report and programs

- -

-The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report: - -

- -Finally, -we encourage you to collaborate. Optimal working groups consist of -2-3 students. You can then hand in a common report. - -

Software and needed installations

- -

-If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages, -we recommend that you install the following Python packages via pip as - -

    -
  1. pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow
    2. -
- -For Python3, replace pip with pip3. - -

-See below for a discussion of tensorflow and scikit-learn. - -

-For OSX users we recommend also, after having installed Xcode, to install brew. Brew allows -for a seamless installation of additional software via for example - -

    -
  1. brew install python3
    2. -
- -For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution -you can use pip as well and simply install Python as - -
    -
  1. sudo apt-get install python3 (or python for python2.7)
    2. -
- -etc etc. - -

-If you don't want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely - -

    -
  1. Anaconda Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system conda
    2. -
  2. Enthought canopy is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license.
    3. -
- -Popular software packages written in Python for ML are - - - -These are all freely available at their respective GitHub sites. They -encompass communities of developers in the thousands or more. And the number -of code developers and contributors keeps increasing. - -

- - - - -

- © 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license -
- - - - - - diff --git a/doc/src/Projects/2021/Project1/Project1.ipynb b/doc/src/Projects/2021/Project1/Project1.ipynb deleted file mode 100644 index eddf25d11..000000000 --- a/doc/src/Projects/2021/Project1/Project1.ipynb +++ /dev/null @@ -1,533 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "\n", - "# Project 1 on Machine Learning, deadline October 4, 2020\n", - "\n", - " \n", - "**[Data Analysis and Machine Learning FYS-STK3155/FYS4155](http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html)**, University of Oslo, Norway\n", - "\n", - "Date: **Sep 10, 2021**\n", - "\n", - "Copyright 1999-2021, [Data Analysis and Machine Learning FYS-STK3155/FYS4155](http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html). Released under CC Attribution-NonCommercial 4.0 license\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "## Regression analysis and resampling methods\n", - "\n", - "The main aim of this project is to study in more detail various\n", - "regression methods, including the Ordinary Least Squares (OLS) method,\n", - "The total score is **100** points. Each subtask has its own final score.\n", - "\n", - "\n", - "We will first study how to fit polynomials to a specific\n", - "two-dimensional function called [Franke's\n", - "function](http://www.dtic.mil/dtic/tr/fulltext/u2/a081688.pdf). This\n", - "is a function which has been widely used when testing various\n", - "interpolation and fitting algorithms. Furthermore, after having\n", - "established the model and the method, we will employ resamling\n", - "techniques such as cross-validation and/or bootstrap in order to perform a\n", - "proper assessment of our models. We will also study in detail the\n", - "so-called Bias-Variance trade off.\n", - "\n", - "\n", - "The Franke function, which is a weighted sum of four exponentials reads as follows" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "\\begin{align*}\n", - "f(x,y) &= \\frac{3}{4}\\exp{\\left(-\\frac{(9x-2)^2}{4} - \\frac{(9y-2)^2}{4}\\right)}+\\frac{3}{4}\\exp{\\left(-\\frac{(9x+1)^2}{49}- \\frac{(9y+1)}{10}\\right)} \\\\\n", - "&+\\frac{1}{2}\\exp{\\left(-\\frac{(9x-7)^2}{4} - \\frac{(9y-3)^2}{4}\\right)} -\\frac{1}{5}\\exp{\\left(-(9x-4)^2 - (9y-7)^2\\right) }.\n", - "\\end{align*}\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "The function will be defined for $x,y\\in [0,1]$. Our first step will\n", - "be to perform an OLS regression analysis of this function, trying out\n", - "a polynomial fit with an $x$ and $y$ dependence of the form $[x, y,\n", - "x^2, y^2, xy, \\dots]$. We will also include bootstrap first as\n", - "a resampling technique. After that we will include the cross-validation technique. As in homeworks 1 and 2, we can use a uniform\n", - "distribution to set up the arrays of values for $x$ and $y$, or as in\n", - "the example below just a set of fixed \n", - "values for $x$ and $y$ with a given step\n", - "size. We will fit a\n", - "function (for example a polynomial) of $x$ and $y$. Thereafter we\n", - "will repeat much of the same procedure using the Ridge and Lasso\n", - "regression methods, introducing thus a dependence on the bias\n", - "(penalty) $\\lambda$.\n", - "\n", - "Finally we are going to use (real) digital terrain data and try to\n", - "reproduce these data using the same methods. We will also try to go\n", - "beyond the second-order polynomials metioned above and explore \n", - "which polynomial fits the data best.\n", - "\n", - "\n", - "The Python code for the Franke function is included here (it performs also a three-dimensional plot of it)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], - "source": [ - "%matplotlib inline\n", - "\n", - "from mpl_toolkits.mplot3d import Axes3D\n", - "import matplotlib.pyplot as plt\n", - "from matplotlib import cm\n", - "from matplotlib.ticker import LinearLocator, FormatStrFormatter\n", - "import numpy as np\n", - "from random import random, seed\n", - "\n", - "fig = plt.figure()\n", - "ax = fig.gca(projection='3d')\n", - "\n", - "# Make data.\n", - "x = np.arange(0, 1, 0.05)\n", - "y = np.arange(0, 1, 0.05)\n", - "x, y = np.meshgrid(x,y)\n", - "\n", - "\n", - "def FrankeFunction(x,y):\n", - " term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))\n", - " term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))\n", - " term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))\n", - " term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)\n", - " return term1 + term2 + term3 + term4\n", - "\n", - "\n", - "z = FrankeFunction(x, y)\n", - "\n", - "# Plot the surface.\n", - "surf = ax.plot_surface(x, y, z, cmap=cm.coolwarm,\n", - " linewidth=0, antialiased=False)\n", - "\n", - "# Customize the z axis.\n", - "ax.set_zlim(-0.10, 1.40)\n", - "ax.zaxis.set_major_locator(LinearLocator(10))\n", - "ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))\n", - "\n", - "# Add a color bar which maps values to colors.\n", - "fig.colorbar(surf, shrink=0.5, aspect=5)\n", - "\n", - "plt.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Exercise 1: Ordinary Least Square (OLS) on the Franke function (score 10 points)\n", - "\n", - "We will generate our own dataset for a function\n", - "$\\mathrm{FrankeFunction}(x,y)$ with $x,y \\in [0,1]$. The function\n", - "$f(x,y)$ is the Franke function. You should explore also the addition\n", - "of an added stochastic noise to this function using the normal\n", - "distribution $\\cal{N}(0,1)$.\n", - "\n", - "*Write your own code* (using either a matrix inversion or a singular\n", - "value decomposition from e.g., **numpy** ) or use your code from\n", - "homeworks 1 and 2 and perform a standard least square regression\n", - "analysis using polynomials in $x$ and $y$ up to fifth order. Find the\n", - "[confidence intervals](https://en.wikipedia.org/wiki/Confidence_interval) of the parameters (estimators) $\\beta$ by computing their\n", - "variances, evaluate the Mean Squared error (MSE)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "MSE(\\hat{y},\\hat{\\tilde{y}}) = \\frac{1}{n}\n", - "\\sum_{i=0}^{n-1}(y_i-\\tilde{y}_i)^2,\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "and the $R^2$ score function. If $\\tilde{\\hat{y}}_i$ is the predicted\n", - "value of the $i-th$ sample and $y_i$ is the corresponding true value,\n", - "then the score $R^2$ is defined as" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "R^2(\\hat{y}, \\tilde{\\hat{y}}) = 1 - \\frac{\\sum_{i=0}^{n - 1} (y_i - \\tilde{y}_i)^2}{\\sum_{i=0}^{n - 1} (y_i - \\bar{y})^2},\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "where we have defined the mean value of $\\hat{y}$ as" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "\\bar{y} = \\frac{1}{n} \\sum_{i=0}^{n - 1} y_i.\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Your code has to include a scaling of the data (for example by\n", - "subtracting the mean value), and\n", - "a split of the data in training and test data. For this part you can\n", - "either write your own code or use for example the function for\n", - "splitting training data provided by the library **Scikit-Learn** (make\n", - "sure you have installed it). This function is called\n", - "$train\\_test\\_split$. **You should present a critical discussion of why and how you have scaled or not scaled the data**.\n", - "\n", - "It is normal in essentially all Machine Learning studies to split the\n", - "data in a training set and a test set (eventually also an additional\n", - "validation set). There\n", - "is no explicit recipe for how much data should be included as training\n", - "data and say test data. An accepted rule of thumb is to use\n", - "approximately $2/3$ to $4/5$ of the data as training data.\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "### Exercise 2: Bias-variance trade-off and resampling techniques (score 15 points)\n", - "\n", - "Our aim here is to study the bias-variance trade-off by implementing the **bootstrap** resampling technique.\n", - "\n", - "With a code which does OLS and includes resampling techniques, \n", - "we will now discuss the bias-variance trade-off in the context of\n", - "continuous predictions such as regression. However, many of the\n", - "intuitions and ideas discussed here also carry over to classification\n", - "tasks and basically all Machine Learning algorithms. \n", - "\n", - "Before you perform an analysis of the bias-variance trade-off on your test data, make\n", - "first a figure similar to Fig. 2.11 of Hastie, Tibshirani, and\n", - "Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to \n", - "indicate possible regions of low/high bias and variance. You will most likely not get an\n", - "equally smooth curve!\n", - "\n", - "With this result we move on to the bias-variance trade-off analysis.\n", - "\n", - "Consider a\n", - "dataset $\\mathcal{L}$ consisting of the data\n", - "$\\mathbf{X}_\\mathcal{L}=\\{(y_j, \\boldsymbol{x}_j), j=0\\ldots n-1\\}$.\n", - "\n", - "Let us assume that the true data is generated from a noisy model" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "\\boldsymbol{y}=f(\\boldsymbol{x}) + \\boldsymbol{\\epsilon}.\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Here $\\epsilon$ is normally distributed with mean zero and standard\n", - "deviation $\\sigma^2$.\n", - "\n", - "In our derivation of the ordinary least squares method we defined then\n", - "an approximation to the function $f$ in terms of the parameters\n", - "$\\boldsymbol{\\beta}$ and the design matrix $\\boldsymbol{X}$ which embody our model,\n", - "that is $\\boldsymbol{\\tilde{y}}=\\boldsymbol{X}\\boldsymbol{\\beta}$.\n", - "\n", - "The parameters $\\boldsymbol{\\beta}$ are in turn found by optimizing the means\n", - "squared error via the so-called cost function" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "C(\\boldsymbol{X},\\boldsymbol{\\beta}) =\\frac{1}{n}\\sum_{i=0}^{n-1}(y_i-\\tilde{y}_i)^2=\\mathbb{E}\\left[(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}})^2\\right].\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Here the expected value $\\mathbb{E}$ is the sample value. \n", - "\n", - "Show that you can rewrite this as" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "$$\n", - "\\mathbb{E}\\left[(\\boldsymbol{y}-\\boldsymbol{\\tilde{y}})^2\\right]=\\frac{1}{n}\\sum_i(f_i-\\mathbb{E}\\left[\\boldsymbol{\\tilde{y}}\\right])^2+\\frac{1}{n}\\sum_i(\\tilde{y}_i-\\mathbb{E}\\left[\\boldsymbol{\\tilde{y}}\\right])^2+\\sigma^2.\n", - "$$" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Explain what the terms mean, which one is the bias and which one is\n", - "the variance and discuss their interpretations.\n", - "\n", - "Perform then a bias-variance analysis of the Franke function by\n", - "studying the MSE value as function of the complexity of your model.\n", - "\n", - "Discuss the bias and variance trade-off as function\n", - "of your model complexity (the degree of the polynomial) and the number\n", - "of data points, and possibly also your training and test data using the **bootstrap** resampling method.\n", - "\n", - "Note also that when you calculate the bias, in all applications you don't know the function values $f_i$. You would hence replace them with the actual data points $y_i$.\n", - "\n", - "\n", - "### Exercise 3: Cross-validation as resampling techniques, adding more complexity (score 15 points)\n", - "\n", - "The aim here is to write your own code for another widely popular\n", - "resampling technique, the so-called cross-validation method. Again,\n", - "before you start with cross-validation approach, you should scale your\n", - "data.\n", - "\n", - "Implement the $k$-fold cross-validation algorithm (write your own\n", - "code) and evaluate again the MSE function resulting\n", - "from the test folds. You can compare your own code with that from\n", - "**Scikit-Learn** if needed. \n", - "\n", - "Compare the MSE you get from your cross-validation code with the one\n", - "you got from your **bootstrap** code. Comment your results. Try $5-10$\n", - "folds. You can also compare your own cross-validation code with the\n", - "one provided by **Scikit-Learn**.\n", - "\n", - "\n", - "### Exercise 4: Ridge Regression on the Franke function with resampling (score 20 points)\n", - "\n", - "Write your own code for the Ridge method, either using matrix\n", - "inversion or the singular value decomposition as done in the previous\n", - "exercise. Perform the same bootstrap analysis as in the\n", - "Exercise 2 (for the same polynomials) and the cross-validation part in part c) but now for different values of $\\lambda$. Compare and\n", - "analyze your results with those obtained in exercises 1-3. Study the\n", - "dependence on $\\lambda$.\n", - "\n", - "Study also the bias-variance trade-off as function of various values of\n", - "the parameter $\\lambda$. For the bias-variance trade-off, use the **bootstrap** resampling method. Comment your results. \n", - "\n", - "### Exercise 5: Lasso Regression on the Franke function with resampling (Score 10 points))\n", - "\n", - "This exercise is essentially a repeat of the previous two ones, but now\n", - "with Lasso regression. Write either your own code (difficult and optional) or, in this case,\n", - "you can also use the functionalities of **Scikit-Learn** (recommended). \n", - "Give a\n", - "critical discussion of the three methods and a judgement of which\n", - "model fits the data best. Perform here as well an analysis of the bias-variance trade-off using the **bootstrap** resampling technique and an analysis of the mean squared error using cross-validation. \n", - "\n", - "### Exercise 6: Analysis of real data (score 30 points)\n", - "\n", - "With our codes functioning and having been tested properly on a\n", - "simpler function we are now ready to look at real data. We will\n", - "essentially repeat in part g) what was done in parts a-e). However, we\n", - "need first to download the data and prepare properly the inputs to our\n", - "codes. We are going to download digital terrain data from the website\n", - ",\n", - "\n", - "In order to obtain data for a specific region, you need to register as\n", - "a user (free) at this website and then decide upon which area you want\n", - "to fetch the digital terrain data from. In order to be able to read\n", - "the data properly, you need to specify that the format should be **SRTM\n", - "Arc-Second Global** and download the data as a **GeoTIF** file. The\n", - "files are then stored in *tif* format which can be imported into a\n", - "Python program using" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], - "source": [ - "scipy.misc.imread" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Here is a simple part of a Python code which reads and plots the data\n", - "from such files" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": false, - "editable": true - }, - "outputs": [], - "source": [ - "import numpy as np\n", - "from imageio import imread\n", - "import matplotlib.pyplot as plt\n", - "from mpl_toolkits.mplot3d import Axes3D\n", - "from matplotlib import cm\n", - "\n", - "# Load the terrain\n", - "terrain1 = imread('SRTM_data_Norway_1.tif')\n", - "# Show the terrain\n", - "plt.figure()\n", - "plt.title('Terrain over Norway 1')\n", - "plt.imshow(terrain1, cmap='gray')\n", - "plt.xlabel('X')\n", - "plt.ylabel('Y')\n", - "plt.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "If you should have problems in downloading the digital terrain data,\n", - "we provide two examples under the data folder of project 1. One is\n", - "from a region close to Stavanger in Norway and the other Møsvatn\n", - "Austfjell, again in Norway.\n", - "Feel free to produce your own terrain data.\n", - "\n", - "\n", - "Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example [kaggle.com](https://www.kaggle.com/datasets) for examples.\n", - "\n", - "\n", - "Our final part deals with the parameterization of your digital terrain\n", - "data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial\n", - "approximation and cross-validation as resampling technique to evaluate which\n", - "model fits the data best.\n", - "\n", - "At the end, you should present a critical evaluation of your results\n", - "and discuss the applicability of these regression methods to the type\n", - "of data presented here (either the terrain data we propose or other data sets).\n", - "\n", - "\n", - "\n", - "\n", - "## Background literature\n", - "\n", - "1. For a discussion and derivation of the variances and mean squared errors using linear regression, see the [Lecture notes on ridge regression by Wessel N. van Wieringen](https://arxiv.org/abs/1509.09169)\n", - "\n", - "2. The textbook of [Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer](https://www.springer.com/gp/book/9780387848570), chapters 3 and 7 are the most relevant ones for the analysis here. \n", - "\n", - "## Introduction to numerical projects\n", - "\n", - "Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers. Note that you can answer question by question and there is no need to structure your report as a scientific report with abstract, introduction, theory, results and discussions, conclusions etc. But you have the following elements in mind when you answer the various questions.\n", - "\n", - "\n", - " * Give a short description of the nature of the problem and the eventual numerical methods you have used.\n", - "\n", - " * Describe the algorithm you have used and/or developed. Here you may find it convenient to use pseudocoding. In many cases you can describe the algorithm in the program itself.\n", - "\n", - " * Include the source code of your program. Comment your program properly. You should have the code at your GitHub/GitLab link. You can also place the code in an appendix of your report.\n", - "\n", - " * If possible, try to find analytic solutions, or known limits in order to test your program when developing the code.\n", - "\n", - " * Include your results either in figure form or in a table. Remember to label your results. All tables and figures should have relevant captions and labels on the axes.\n", - "\n", - " * Try to evaluate the reliabilty and numerical stability/precision of your results. If possible, include a qualitative and/or quantitative discussion of the numerical stability, eventual loss of precision etc.\n", - "\n", - " * Try to give an interpretation of you results in your answers to the problems.\n", - "\n", - " * Critique: if possible include your comments and reflections about the exercise, whether you felt you learnt something, ideas for improvements and other thoughts you've made when solving the exercise. We wish to keep this course at the interactive level and your comments can help us improve it.\n", - "\n", - " * Try to establish a practice where you log your work at the computerlab. You may find such a logbook very handy at later stages in your work, especially when you don't properly remember what a previous test version of your program did. Here you could also record the time spent on solving the exercise, various algorithms you may have tested or other topics which you feel worthy of mentioning.\n", - "\n", - "## Format for electronic delivery of report and programs\n", - "\n", - "The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report:\n", - "\n", - " * Use Canvas to hand in your projects, log in at with your normal UiO username and password.\n", - "\n", - " * Upload **only** the report file or the link to your GitHub/GitLab or similar typo of repos! For the source code file(s) you have developed please provide us with your link to your GitHub/GitLab or similar domain. The report file should include all of your discussions and a list of the codes you have developed. Do not include library files which are available at the course homepage, unless you have made specific changes to them.\n", - "\n", - " * In your GitHub/GitLab or similar repository, please include a folder which contains selected results. These can be in the form of output from your code for a selected set of runs and input parameters.\n", - "\n", - "Finally, \n", - "we encourage you to collaborate. Optimal working groups consist of \n", - "2-3 students. You can then hand in a common report. \n", - "\n", - "\n", - "\n", - "## Software and needed installations\n", - "\n", - "If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages, \n", - "we recommend that you install the following Python packages via **pip** as\n", - "1. pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow\n", - "\n", - "For Python3, replace **pip** with **pip3**.\n", - "\n", - "See below for a discussion of **tensorflow** and **scikit-learn**. \n", - "\n", - "For OSX users we recommend also, after having installed Xcode, to install **brew**. Brew allows \n", - "for a seamless installation of additional software via for example\n", - "1. brew install python3\n", - "\n", - "For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution\n", - "you can use **pip** as well and simply install Python as \n", - "1. sudo apt-get install python3 (or python for python2.7)\n", - "\n", - "etc etc. \n", - "\n", - "If you don't want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely\n", - "1. [Anaconda](https://docs.anaconda.com/) Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system **conda**\n", - "\n", - "2. [Enthought canopy](https://www.enthought.com/product/canopy/) is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license.\n", - "\n", - "Popular software packages written in Python for ML are\n", - "\n", - "* [Scikit-learn](http://scikit-learn.org/stable/), \n", - "\n", - "* [Tensorflow](https://www.tensorflow.org/),\n", - "\n", - "* [PyTorch](http://pytorch.org/) and \n", - "\n", - "* [Keras](https://keras.io/).\n", - "\n", - "These are all freely available at their respective GitHub sites. They \n", - "encompass communities of developers in the thousands or more. And the number\n", - "of code developers and contributors keeps increasing." - ] - } - ], - "metadata": {}, - "nbformat": 4, - "nbformat_minor": 4 -} diff --git a/doc/src/Projects/2021/Project1/Project1.p.tex b/doc/src/Projects/2021/Project1/Project1.p.tex deleted file mode 100644 index 8e37ea274..000000000 --- a/doc/src/Projects/2021/Project1/Project1.p.tex +++ /dev/null @@ -1,583 +0,0 @@ -%% -%% Automatically generated file from DocOnce source -%% (https://github.com/hplgit/doconce/) -%% -%% -% #ifdef PTEX2TEX_EXPLANATION -%% -%% The file follows the ptex2tex extended LaTeX format, see -%% ptex2tex: https://code.google.com/p/ptex2tex/ -%% -%% Run -%% ptex2tex myfile -%% or -%% doconce ptex2tex myfile -%% -%% to turn myfile.p.tex into an ordinary LaTeX file myfile.tex. -%% (The ptex2tex program: https://code.google.com/p/ptex2tex) -%% Many preprocess options can be added to ptex2tex or doconce ptex2tex -%% -%% ptex2tex -DMINTED myfile -%% doconce ptex2tex myfile envir=minted -%% -%% ptex2tex will typeset code environments according to a global or local -%% .ptex2tex.cfg configure file. doconce ptex2tex will typeset code -%% according to options on the command line (just type doconce ptex2tex to -%% see examples). If doconce ptex2tex has envir=minted, it enables the -%% minted style without needing -DMINTED. -% #endif - -% #define PREAMBLE - -% #ifdef PREAMBLE -%-------------------- begin preamble ---------------------- - -\documentclass[% -oneside, % oneside: electronic viewing, twoside: printing -final, % draft: marks overfull hboxes, figures with paths -10pt]{article} - -\listfiles % print all files needed to compile this document - -\usepackage{relsize,makeidx,color,setspace,amsmath,amsfonts,amssymb} -\usepackage[table]{xcolor} -\usepackage{bm,ltablex,microtype} - -\usepackage[pdftex]{graphicx} - -\usepackage{ptex2tex} -% #ifdef MINTED -\usepackage{minted} -\usemintedstyle{default} -% #endif - -\usepackage[T1]{fontenc} -%\usepackage[latin1]{inputenc} -\usepackage{ucs} -\usepackage[utf8x]{inputenc} - -\usepackage{lmodern} % Latin Modern fonts derived from Computer Modern - -% Hyperlinks in PDF: -\definecolor{linkcolor}{rgb}{0,0,0.4} -\usepackage{hyperref} -\hypersetup{ - breaklinks=true, - colorlinks=true, - linkcolor=linkcolor, - urlcolor=linkcolor, - citecolor=black, - filecolor=black, - %filecolor=blue, - pdfmenubar=true, - pdftoolbar=true, - bookmarksdepth=3 % Uncomment (and tweak) for PDF bookmarks with more levels than the TOC - } -%\hyperbaseurl{} % hyperlinks are relative to this root - -\setcounter{tocdepth}{2} % levels in table of contents - -% --- fancyhdr package for fancy headers --- -\usepackage{fancyhdr} -\fancyhf{} % sets both header and footer to nothing -\renewcommand{\headrulewidth}{0pt} -\fancyfoot[LE,RO]{\thepage} -% Ensure copyright on titlepage (article style) and chapter pages (book style) -\fancypagestyle{plain}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} -% \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} -% Ensure copyright on titlepages with \thispagestyle{empty} -\fancypagestyle{empty}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} - \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} - -\pagestyle{fancy} - - -% prevent orhpans and widows -\clubpenalty = 10000 -\widowpenalty = 10000 - -% --- end of standard preamble for documents --- - - -% insert custom LaTeX commands... - -\raggedbottom -\makeindex -\usepackage[totoc]{idxlayout} % for index in the toc -\usepackage[nottoc]{tocbibind} % for references/bibliography in the toc - -%-------------------- end preamble ---------------------- - -\begin{document} - -% matching end for #ifdef PREAMBLE -% #endif - -\newcommand{\exercisesection}[1]{\subsection*{#1}} - - -% ------------------- main content ---------------------- - - - -% ----------------- title ------------------------- - -\thispagestyle{empty} - -\begin{center} -{\LARGE\bf -\begin{spacing}{1.25} -Project 1 on Machine Learning, deadline October 4, 2020 -\end{spacing} -} -\end{center} - -% ----------------- author(s) ------------------------- - -\begin{center} -{\bf \href{{http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html}}{Data Analysis and Machine Learning FYS-STK3155/FYS4155}} -\end{center} - - \begin{center} -% List of all institutions: -\centerline{{\small University of Oslo, Norway}} -\end{center} - -% ----------------- end author(s) ------------------------- - -% --- begin date --- -\begin{center} -Sep 10, 2021 -\end{center} -% --- end date --- - -\vspace{1cm} - - -\subsection{Regression analysis and resampling methods} - -The main aim of this project is to study in more detail various -regression methods, including the Ordinary Least Squares (OLS) method, -The total score is \textbf{100} points. Each subtask has its own final score. - - -We will first study how to fit polynomials to a specific -two-dimensional function called \href{{http://www.dtic.mil/dtic/tr/fulltext/u2/a081688.pdf}}{Franke's -function}. This -is a function which has been widely used when testing various -interpolation and fitting algorithms. Furthermore, after having -established the model and the method, we will employ resamling -techniques such as cross-validation and/or bootstrap in order to perform a -proper assessment of our models. We will also study in detail the -so-called Bias-Variance trade off. - - -The Franke function, which is a weighted sum of four exponentials reads as follows -\begin{align*} -f(x,y) &= \frac{3}{4}\exp{\left(-\frac{(9x-2)^2}{4} - \frac{(9y-2)^2}{4}\right)}+\frac{3}{4}\exp{\left(-\frac{(9x+1)^2}{49}- \frac{(9y+1)}{10}\right)} \\ -&+\frac{1}{2}\exp{\left(-\frac{(9x-7)^2}{4} - \frac{(9y-3)^2}{4}\right)} -\frac{1}{5}\exp{\left(-(9x-4)^2 - (9y-7)^2\right) }. -\end{align*} - -The function will be defined for $x,y\in [0,1]$. Our first step will -be to perform an OLS regression analysis of this function, trying out -a polynomial fit with an $x$ and $y$ dependence of the form $[x, y, -x^2, y^2, xy, \dots]$. We will also include bootstrap first as -a resampling technique. After that we will include the cross-validation technique. As in homeworks 1 and 2, we can use a uniform -distribution to set up the arrays of values for $x$ and $y$, or as in -the example below just a set of fixed -values for $x$ and $y$ with a given step -size. We will fit a -function (for example a polynomial) of $x$ and $y$. Thereafter we -will repeat much of the same procedure using the Ridge and Lasso -regression methods, introducing thus a dependence on the bias -(penalty) $\lambda$. - -Finally we are going to use (real) digital terrain data and try to -reproduce these data using the same methods. We will also try to go -beyond the second-order polynomials metioned above and explore -which polynomial fits the data best. - - -The Python code for the Franke function is included here (it performs also a three-dimensional plot of it) -\bpycod -from mpl_toolkits.mplot3d import Axes3D -import matplotlib.pyplot as plt -from matplotlib import cm -from matplotlib.ticker import LinearLocator, FormatStrFormatter -import numpy as np -from random import random, seed - -fig = plt.figure() -ax = fig.gca(projection='3d') - -# Make data. -x = np.arange(0, 1, 0.05) -y = np.arange(0, 1, 0.05) -x, y = np.meshgrid(x,y) - - -def FrankeFunction(x,y): - term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2)) - term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1)) - term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2)) - term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2) - return term1 + term2 + term3 + term4 - - -z = FrankeFunction(x, y) - -# Plot the surface. -surf = ax.plot_surface(x, y, z, cmap=cm.coolwarm, - linewidth=0, antialiased=False) - -# Customize the z axis. -ax.set_zlim(-0.10, 1.40) -ax.zaxis.set_major_locator(LinearLocator(10)) -ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f')) - -# Add a color bar which maps values to colors. -fig.colorbar(surf, shrink=0.5, aspect=5) - -plt.show() - -\epycod - - -\paragraph{Exercise 1: Ordinary Least Square (OLS) on the Franke function (score 10 points).} -We will generate our own dataset for a function -$\mathrm{FrankeFunction}(x,y)$ with $x,y \in [0,1]$. The function -$f(x,y)$ is the Franke function. You should explore also the addition -of an added stochastic noise to this function using the normal -distribution $\cal{N}(0,1)$. - -\emph{Write your own code} (using either a matrix inversion or a singular -value decomposition from e.g., \textbf{numpy} ) or use your code from -homeworks 1 and 2 and perform a standard least square regression -analysis using polynomials in $x$ and $y$ up to fifth order. Find the -\href{{https://en.wikipedia.org/wiki/Confidence_interval}}{confidence intervals} of the parameters (estimators) $\beta$ by computing their -variances, evaluate the Mean Squared error (MSE) - -\[ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n} -\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2, -\] - -and the $R^2$ score function. If $\tilde{\hat{y}}_i$ is the predicted -value of the $i-th$ sample and $y_i$ is the corresponding true value, -then the score $R^2$ is defined as - -\[ -R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2}, -\] - -where we have defined the mean value of $\hat{y}$ as - -\[ -\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i. -\] - -Your code has to include a scaling of the data (for example by -subtracting the mean value), and -a split of the data in training and test data. For this part you can -either write your own code or use for example the function for -splitting training data provided by the library \textbf{Scikit-Learn} (make -sure you have installed it). This function is called -$train\_test\_split$. \textbf{You should present a critical discussion of why and how you have scaled or not scaled the data}. - -It is normal in essentially all Machine Learning studies to split the -data in a training set and a test set (eventually also an additional -validation set). There -is no explicit recipe for how much data should be included as training -data and say test data. An accepted rule of thumb is to use -approximately $2/3$ to $4/5$ of the data as training data. - - - - - - -\paragraph{Exercise 2: Bias-variance trade-off and resampling techniques (score 15 points).} -Our aim here is to study the bias-variance trade-off by implementing the \textbf{bootstrap} resampling technique. - -With a code which does OLS and includes resampling techniques, -we will now discuss the bias-variance trade-off in the context of -continuous predictions such as regression. However, many of the -intuitions and ideas discussed here also carry over to classification -tasks and basically all Machine Learning algorithms. - -Before you perform an analysis of the bias-variance trade-off on your test data, make -first a figure similar to Fig.~2.11 of Hastie, Tibshirani, and -Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to -indicate possible regions of low/high bias and variance. You will most likely not get an -equally smooth curve! - -With this result we move on to the bias-variance trade-off analysis. - -Consider a -dataset $\mathcal{L}$ consisting of the data -$\mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\}$. - -Let us assume that the true data is generated from a noisy model - -\[ -\bm{y}=f(\boldsymbol{x}) + \bm{\epsilon}. -\] - -Here $\epsilon$ is normally distributed with mean zero and standard -deviation $\sigma^2$. - -In our derivation of the ordinary least squares method we defined then -an approximation to the function $f$ in terms of the parameters -$\bm{\beta}$ and the design matrix $\bm{X}$ which embody our model, -that is $\bm{\tilde{y}}=\bm{X}\bm{\beta}$. - -The parameters $\bm{\beta}$ are in turn found by optimizing the means -squared error via the so-called cost function - -\[ -C(\bm{X},\bm{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\bm{y}-\bm{\tilde{y}})^2\right]. -\] -Here the expected value $\mathbb{E}$ is the sample value. - -Show that you can rewrite this as -\[ -\mathbb{E}\left[(\bm{y}-\bm{\tilde{y}})^2\right]=\frac{1}{n}\sum_i(f_i-\mathbb{E}\left[\bm{\tilde{y}}\right])^2+\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\bm{\tilde{y}}\right])^2+\sigma^2. -\] - -Explain what the terms mean, which one is the bias and which one is -the variance and discuss their interpretations. - -Perform then a bias-variance analysis of the Franke function by -studying the MSE value as function of the complexity of your model. - -Discuss the bias and variance trade-off as function -of your model complexity (the degree of the polynomial) and the number -of data points, and possibly also your training and test data using the \textbf{bootstrap} resampling method. - -Note also that when you calculate the bias, in all applications you don't know the function values $f_i$. You would hence replace them with the actual data points $y_i$. - - -\paragraph{Exercise 3: Cross-validation as resampling techniques, adding more complexity (score 15 points).} -The aim here is to write your own code for another widely popular -resampling technique, the so-called cross-validation method. Again, -before you start with cross-validation approach, you should scale your -data. - -Implement the $k$-fold cross-validation algorithm (write your own -code) and evaluate again the MSE function resulting -from the test folds. You can compare your own code with that from -\textbf{Scikit-Learn} if needed. - -Compare the MSE you get from your cross-validation code with the one -you got from your \textbf{bootstrap} code. Comment your results. Try $5-10$ -folds. You can also compare your own cross-validation code with the -one provided by \textbf{Scikit-Learn}. - - -\paragraph{Exercise 4: Ridge Regression on the Franke function with resampling (score 20 points).} -Write your own code for the Ridge method, either using matrix -inversion or the singular value decomposition as done in the previous -exercise. Perform the same bootstrap analysis as in the -Exercise 2 (for the same polynomials) and the cross-validation part in part c) but now for different values of $\lambda$. Compare and -analyze your results with those obtained in exercises 1-3. Study the -dependence on $\lambda$. - -Study also the bias-variance trade-off as function of various values of -the parameter $\lambda$. For the bias-variance trade-off, use the \textbf{bootstrap} resampling method. Comment your results. - -\paragraph{Exercise 5: Lasso Regression on the Franke function with resampling (Score 10 points)).} -This exercise is essentially a repeat of the previous two ones, but now -with Lasso regression. Write either your own code (difficult and optional) or, in this case, -you can also use the functionalities of \textbf{Scikit-Learn} (recommended). -Give a -critical discussion of the three methods and a judgement of which -model fits the data best. Perform here as well an analysis of the bias-variance trade-off using the \textbf{bootstrap} resampling technique and an analysis of the mean squared error using cross-validation. - -\paragraph{Exercise 6: Analysis of real data (score 30 points).} -With our codes functioning and having been tested properly on a -simpler function we are now ready to look at real data. We will -essentially repeat in part g) what was done in parts a-e). However, we -need first to download the data and prepare properly the inputs to our -codes. We are going to download digital terrain data from the website -\href{{https://earthexplorer.usgs.gov/}}{\nolinkurl{https://earthexplorer.usgs.gov/}}, - -In order to obtain data for a specific region, you need to register as -a user (free) at this website and then decide upon which area you want -to fetch the digital terrain data from. In order to be able to read -the data properly, you need to specify that the format should be \textbf{SRTM -Arc-Second Global} and download the data as a \textbf{GeoTIF} file. The -files are then stored in \emph{tif} format which can be imported into a -Python program using - -\bpycod -scipy.misc.imread -\epycod - -Here is a simple part of a Python code which reads and plots the data -from such files - -\bpycod -import numpy as np -from imageio import imread -import matplotlib.pyplot as plt -from mpl_toolkits.mplot3d import Axes3D -from matplotlib import cm - -# Load the terrain -terrain1 = imread('SRTM_data_Norway_1.tif') -# Show the terrain -plt.figure() -plt.title('Terrain over Norway 1') -plt.imshow(terrain1, cmap='gray') -plt.xlabel('X') -plt.ylabel('Y') -plt.show() -\epycod - -If you should have problems in downloading the digital terrain data, -we provide two examples under the data folder of project 1. One is -from a region close to Stavanger in Norway and the other Møsvatn -Austfjell, again in Norway. -Feel free to produce your own terrain data. - - -Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example \href{{https://www.kaggle.com/datasets}}{kaggle.com} for examples. - - -Our final part deals with the parameterization of your digital terrain -data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial -approximation and cross-validation as resampling technique to evaluate which -model fits the data best. - -At the end, you should present a critical evaluation of your results -and discuss the applicability of these regression methods to the type -of data presented here (either the terrain data we propose or other data sets). - - - - -\subsection{Background literature} - -\begin{enumerate} -\item For a discussion and derivation of the variances and mean squared errors using linear regression, see the \href{{https://arxiv.org/abs/1509.09169}}{Lecture notes on ridge regression by Wessel N. van Wieringen} - -\item The textbook of \href{{https://www.springer.com/gp/book/9780387848570}}{Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer}, chapters 3 and 7 are the most relevant ones for the analysis here. -\end{enumerate} - -\noindent -\subsection{Introduction to numerical projects} - -Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers. Note that you can answer question by question and there is no need to structure your report as a scientific report with abstract, introduction, theory, results and discussions, conclusions etc. But you have the following elements in mind when you answer the various questions. - - -\begin{itemize} - \item Give a short description of the nature of the problem and the eventual numerical methods you have used. - - \item Describe the algorithm you have used and/or developed. Here you may find it convenient to use pseudocoding. In many cases you can describe the algorithm in the program itself. - - \item Include the source code of your program. Comment your program properly. You should have the code at your GitHub/GitLab link. You can also place the code in an appendix of your report. - - \item If possible, try to find analytic solutions, or known limits in order to test your program when developing the code. - - \item Include your results either in figure form or in a table. Remember to label your results. All tables and figures should have relevant captions and labels on the axes. - - \item Try to evaluate the reliabilty and numerical stability/precision of your results. If possible, include a qualitative and/or quantitative discussion of the numerical stability, eventual loss of precision etc. - - \item Try to give an interpretation of you results in your answers to the problems. - - \item Critique: if possible include your comments and reflections about the exercise, whether you felt you learnt something, ideas for improvements and other thoughts you've made when solving the exercise. We wish to keep this course at the interactive level and your comments can help us improve it. - - \item Try to establish a practice where you log your work at the computerlab. You may find such a logbook very handy at later stages in your work, especially when you don't properly remember what a previous test version of your program did. Here you could also record the time spent on solving the exercise, various algorithms you may have tested or other topics which you feel worthy of mentioning. -\end{itemize} - -\noindent -\subsection{Format for electronic delivery of report and programs} - -The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report: - -\begin{itemize} - \item Use Canvas to hand in your projects, log in at \href{{https://www.uio.no/english/services/it/education/canvas/}}{\nolinkurl{https://www.uio.no/english/services/it/education/canvas/}} with your normal UiO username and password. - - \item Upload \textbf{only} the report file or the link to your GitHub/GitLab or similar typo of repos! For the source code file(s) you have developed please provide us with your link to your GitHub/GitLab or similar domain. The report file should include all of your discussions and a list of the codes you have developed. Do not include library files which are available at the course homepage, unless you have made specific changes to them. - - \item In your GitHub/GitLab or similar repository, please include a folder which contains selected results. These can be in the form of output from your code for a selected set of runs and input parameters. -\end{itemize} - -\noindent -Finally, -we encourage you to collaborate. Optimal working groups consist of -2-3 students. You can then hand in a common report. - - - -\subsection{Software and needed installations} - -If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages, -we recommend that you install the following Python packages via \textbf{pip} as -\begin{enumerate} -\item pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow -\end{enumerate} - -\noindent -For Python3, replace \textbf{pip} with \textbf{pip3}. - -See below for a discussion of \textbf{tensorflow} and \textbf{scikit-learn}. - -For OSX users we recommend also, after having installed Xcode, to install \textbf{brew}. Brew allows -for a seamless installation of additional software via for example -\begin{enumerate} -\item brew install python3 -\end{enumerate} - -\noindent -For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution -you can use \textbf{pip} as well and simply install Python as -\begin{enumerate} -\item sudo apt-get install python3 (or python for python2.7) -\end{enumerate} - -\noindent -etc etc. - -If you don't want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely -\begin{enumerate} -\item \href{{https://docs.anaconda.com/}}{Anaconda} Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system \textbf{conda} - -\item \href{{https://www.enthought.com/product/canopy/}}{Enthought canopy} is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license. -\end{enumerate} - -\noindent -Popular software packages written in Python for ML are - -\begin{itemize} -\item \href{{http://scikit-learn.org/stable/}}{Scikit-learn}, - -\item \href{{https://www.tensorflow.org/}}{Tensorflow}, - -\item \href{{http://pytorch.org/}}{PyTorch} and - -\item \href{{https://keras.io/}}{Keras}. -\end{itemize} - -\noindent -These are all freely available at their respective GitHub sites. They -encompass communities of developers in the thousands or more. And the number -of code developers and contributors keeps increasing. - - - - - -% ------------------- end of main content --------------- - -% #ifdef PREAMBLE -\end{document} -% #endif - diff --git a/doc/src/Projects/2021/Project1/Project1.pdf b/doc/src/Projects/2021/Project1/Project1.pdf deleted file mode 100644 index 6d70acd44..000000000 Binary files a/doc/src/Projects/2021/Project1/Project1.pdf and /dev/null differ diff --git a/doc/src/Projects/2021/Project1/Project1.tex b/doc/src/Projects/2021/Project1/Project1.tex deleted file mode 100644 index 63acd18f6..000000000 --- a/doc/src/Projects/2021/Project1/Project1.tex +++ /dev/null @@ -1,551 +0,0 @@ -%% -%% Automatically generated file from DocOnce source -%% (https://github.com/hplgit/doconce/) -%% -%% - - -%-------------------- begin preamble ---------------------- - -\documentclass[% -oneside, % oneside: electronic viewing, twoside: printing -final, % draft: marks overfull hboxes, figures with paths -10pt]{article} - -\listfiles % print all files needed to compile this document - -\usepackage{relsize,makeidx,color,setspace,amsmath,amsfonts,amssymb} -\usepackage[table]{xcolor} -\usepackage{bm,ltablex,microtype} - -\usepackage[pdftex]{graphicx} - -\usepackage{fancyvrb} % packages needed for verbatim environments - -\usepackage[T1]{fontenc} -%\usepackage[latin1]{inputenc} -\usepackage{ucs} -\usepackage[utf8x]{inputenc} - -\usepackage{lmodern} % Latin Modern fonts derived from Computer Modern - -% Hyperlinks in PDF: -\definecolor{linkcolor}{rgb}{0,0,0.4} -\usepackage{hyperref} -\hypersetup{ - breaklinks=true, - colorlinks=true, - linkcolor=linkcolor, - urlcolor=linkcolor, - citecolor=black, - filecolor=black, - %filecolor=blue, - pdfmenubar=true, - pdftoolbar=true, - bookmarksdepth=3 % Uncomment (and tweak) for PDF bookmarks with more levels than the TOC - } -%\hyperbaseurl{} % hyperlinks are relative to this root - -\setcounter{tocdepth}{2} % levels in table of contents - -% --- fancyhdr package for fancy headers --- -\usepackage{fancyhdr} -\fancyhf{} % sets both header and footer to nothing -\renewcommand{\headrulewidth}{0pt} -\fancyfoot[LE,RO]{\thepage} -% Ensure copyright on titlepage (article style) and chapter pages (book style) -\fancypagestyle{plain}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} -% \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} -% Ensure copyright on titlepages with \thispagestyle{empty} -\fancypagestyle{empty}{ - \fancyhf{} - \fancyfoot[C]{{\footnotesize \copyright\ 1999-2021, "Data Analysis and Machine Learning FYS-STK3155/FYS4155":"http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html". Released under CC Attribution-NonCommercial 4.0 license}} - \renewcommand{\footrulewidth}{0mm} - \renewcommand{\headrulewidth}{0mm} -} - -\pagestyle{fancy} - - -% prevent orhpans and widows -\clubpenalty = 10000 -\widowpenalty = 10000 - -% --- end of standard preamble for documents --- - - -% insert custom LaTeX commands... - -\raggedbottom -\makeindex -\usepackage[totoc]{idxlayout} % for index in the toc -\usepackage[nottoc]{tocbibind} % for references/bibliography in the toc - -%-------------------- end preamble ---------------------- - -\begin{document} - -% matching end for #ifdef PREAMBLE - -\newcommand{\exercisesection}[1]{\subsection*{#1}} - - -% ------------------- main content ---------------------- - - - -% ----------------- title ------------------------- - -\thispagestyle{empty} - -\begin{center} -{\LARGE\bf -\begin{spacing}{1.25} -Project 1 on Machine Learning, deadline October 4, 2020 -\end{spacing} -} -\end{center} - -% ----------------- author(s) ------------------------- - -\begin{center} -{\bf \href{{http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html}}{Data Analysis and Machine Learning FYS-STK3155/FYS4155}} -\end{center} - - \begin{center} -% List of all institutions: -\centerline{{\small University of Oslo, Norway}} -\end{center} - -% ----------------- end author(s) ------------------------- - -% --- begin date --- -\begin{center} -Sep 10, 2021 -\end{center} -% --- end date --- - -\vspace{1cm} - - -\subsection*{Regression analysis and resampling methods} - -The main aim of this project is to study in more detail various -regression methods, including the Ordinary Least Squares (OLS) method, -The total score is \textbf{100} points. Each subtask has its own final score. - - -We will first study how to fit polynomials to a specific -two-dimensional function called \href{{http://www.dtic.mil/dtic/tr/fulltext/u2/a081688.pdf}}{Franke's -function}. This -is a function which has been widely used when testing various -interpolation and fitting algorithms. Furthermore, after having -established the model and the method, we will employ resamling -techniques such as cross-validation and/or bootstrap in order to perform a -proper assessment of our models. We will also study in detail the -so-called Bias-Variance trade off. - - -The Franke function, which is a weighted sum of four exponentials reads as follows -\begin{align*} -f(x,y) &= \frac{3}{4}\exp{\left(-\frac{(9x-2)^2}{4} - \frac{(9y-2)^2}{4}\right)}+\frac{3}{4}\exp{\left(-\frac{(9x+1)^2}{49}- \frac{(9y+1)}{10}\right)} \\ -&+\frac{1}{2}\exp{\left(-\frac{(9x-7)^2}{4} - \frac{(9y-3)^2}{4}\right)} -\frac{1}{5}\exp{\left(-(9x-4)^2 - (9y-7)^2\right) }. -\end{align*} - -The function will be defined for $x,y\in [0,1]$. Our first step will -be to perform an OLS regression analysis of this function, trying out -a polynomial fit with an $x$ and $y$ dependence of the form $[x, y, -x^2, y^2, xy, \dots]$. We will also include bootstrap first as -a resampling technique. After that we will include the cross-validation technique. As in homeworks 1 and 2, we can use a uniform -distribution to set up the arrays of values for $x$ and $y$, or as in -the example below just a set of fixed -values for $x$ and $y$ with a given step -size. We will fit a -function (for example a polynomial) of $x$ and $y$. Thereafter we -will repeat much of the same procedure using the Ridge and Lasso -regression methods, introducing thus a dependence on the bias -(penalty) $\lambda$. - -Finally we are going to use (real) digital terrain data and try to -reproduce these data using the same methods. We will also try to go -beyond the second-order polynomials metioned above and explore -which polynomial fits the data best. - - -The Python code for the Franke function is included here (it performs also a three-dimensional plot of it) -\begin{verbatim} -from mpl_toolkits.mplot3d import Axes3D -import matplotlib.pyplot as plt -from matplotlib import cm -from matplotlib.ticker import LinearLocator, FormatStrFormatter -import numpy as np -from random import random, seed - -fig = plt.figure() -ax = fig.gca(projection='3d') - -# Make data. -x = np.arange(0, 1, 0.05) -y = np.arange(0, 1, 0.05) -x, y = np.meshgrid(x,y) - - -def FrankeFunction(x,y): - term1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2)) - term2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1)) - term3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2)) - term4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2) - return term1 + term2 + term3 + term4 - - -z = FrankeFunction(x, y) - -# Plot the surface. -surf = ax.plot_surface(x, y, z, cmap=cm.coolwarm, - linewidth=0, antialiased=False) - -# Customize the z axis. -ax.set_zlim(-0.10, 1.40) -ax.zaxis.set_major_locator(LinearLocator(10)) -ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f')) - -# Add a color bar which maps values to colors. -fig.colorbar(surf, shrink=0.5, aspect=5) - -plt.show() - -\end{verbatim} - - -\paragraph{Exercise 1: Ordinary Least Square (OLS) on the Franke function (score 10 points).} -We will generate our own dataset for a function -$\mathrm{FrankeFunction}(x,y)$ with $x,y \in [0,1]$. The function -$f(x,y)$ is the Franke function. You should explore also the addition -of an added stochastic noise to this function using the normal -distribution $\cal{N}(0,1)$. - -\emph{Write your own code} (using either a matrix inversion or a singular -value decomposition from e.g., \textbf{numpy} ) or use your code from -homeworks 1 and 2 and perform a standard least square regression -analysis using polynomials in $x$ and $y$ up to fifth order. Find the -\href{{https://en.wikipedia.org/wiki/Confidence_interval}}{confidence intervals} of the parameters (estimators) $\beta$ by computing their -variances, evaluate the Mean Squared error (MSE) - -\[ MSE(\hat{y},\hat{\tilde{y}}) = \frac{1}{n} -\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2, -\] - -and the $R^2$ score function. If $\tilde{\hat{y}}_i$ is the predicted -value of the $i-th$ sample and $y_i$ is the corresponding true value, -then the score $R^2$ is defined as - -\[ -R^2(\hat{y}, \tilde{\hat{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2}, -\] - -where we have defined the mean value of $\hat{y}$ as - -\[ -\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i. -\] - -Your code has to include a scaling of the data (for example by -subtracting the mean value), and -a split of the data in training and test data. For this part you can -either write your own code or use for example the function for -splitting training data provided by the library \textbf{Scikit-Learn} (make -sure you have installed it). This function is called -$train\_test\_split$. \textbf{You should present a critical discussion of why and how you have scaled or not scaled the data}. - -It is normal in essentially all Machine Learning studies to split the -data in a training set and a test set (eventually also an additional -validation set). There -is no explicit recipe for how much data should be included as training -data and say test data. An accepted rule of thumb is to use -approximately $2/3$ to $4/5$ of the data as training data. - - - - - - -\paragraph{Exercise 2: Bias-variance trade-off and resampling techniques (score 15 points).} -Our aim here is to study the bias-variance trade-off by implementing the \textbf{bootstrap} resampling technique. - -With a code which does OLS and includes resampling techniques, -we will now discuss the bias-variance trade-off in the context of -continuous predictions such as regression. However, many of the -intuitions and ideas discussed here also carry over to classification -tasks and basically all Machine Learning algorithms. - -Before you perform an analysis of the bias-variance trade-off on your test data, make -first a figure similar to Fig.~2.11 of Hastie, Tibshirani, and -Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to -indicate possible regions of low/high bias and variance. You will most likely not get an -equally smooth curve! - -With this result we move on to the bias-variance trade-off analysis. - -Consider a -dataset $\mathcal{L}$ consisting of the data -$\mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\}$. - -Let us assume that the true data is generated from a noisy model - -\[ -\bm{y}=f(\boldsymbol{x}) + \bm{\epsilon}. -\] - -Here $\epsilon$ is normally distributed with mean zero and standard -deviation $\sigma^2$. - -In our derivation of the ordinary least squares method we defined then -an approximation to the function $f$ in terms of the parameters -$\bm{\beta}$ and the design matrix $\bm{X}$ which embody our model, -that is $\bm{\tilde{y}}=\bm{X}\bm{\beta}$. - -The parameters $\bm{\beta}$ are in turn found by optimizing the means -squared error via the so-called cost function - -\[ -C(\bm{X},\bm{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\bm{y}-\bm{\tilde{y}})^2\right]. -\] -Here the expected value $\mathbb{E}$ is the sample value. - -Show that you can rewrite this as -\[ -\mathbb{E}\left[(\bm{y}-\bm{\tilde{y}})^2\right]=\frac{1}{n}\sum_i(f_i-\mathbb{E}\left[\bm{\tilde{y}}\right])^2+\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\bm{\tilde{y}}\right])^2+\sigma^2. -\] - -Explain what the terms mean, which one is the bias and which one is -the variance and discuss their interpretations. - -Perform then a bias-variance analysis of the Franke function by -studying the MSE value as function of the complexity of your model. - -Discuss the bias and variance trade-off as function -of your model complexity (the degree of the polynomial) and the number -of data points, and possibly also your training and test data using the \textbf{bootstrap} resampling method. - -Note also that when you calculate the bias, in all applications you don't know the function values $f_i$. You would hence replace them with the actual data points $y_i$. - - -\paragraph{Exercise 3: Cross-validation as resampling techniques, adding more complexity (score 15 points).} -The aim here is to write your own code for another widely popular -resampling technique, the so-called cross-validation method. Again, -before you start with cross-validation approach, you should scale your -data. - -Implement the $k$-fold cross-validation algorithm (write your own -code) and evaluate again the MSE function resulting -from the test folds. You can compare your own code with that from -\textbf{Scikit-Learn} if needed. - -Compare the MSE you get from your cross-validation code with the one -you got from your \textbf{bootstrap} code. Comment your results. Try $5-10$ -folds. You can also compare your own cross-validation code with the -one provided by \textbf{Scikit-Learn}. - - -\paragraph{Exercise 4: Ridge Regression on the Franke function with resampling (score 20 points).} -Write your own code for the Ridge method, either using matrix -inversion or the singular value decomposition as done in the previous -exercise. Perform the same bootstrap analysis as in the -Exercise 2 (for the same polynomials) and the cross-validation part in part c) but now for different values of $\lambda$. Compare and -analyze your results with those obtained in exercises 1-3. Study the -dependence on $\lambda$. - -Study also the bias-variance trade-off as function of various values of -the parameter $\lambda$. For the bias-variance trade-off, use the \textbf{bootstrap} resampling method. Comment your results. - -\paragraph{Exercise 5: Lasso Regression on the Franke function with resampling (Score 10 points)).} -This exercise is essentially a repeat of the previous two ones, but now -with Lasso regression. Write either your own code (difficult and optional) or, in this case, -you can also use the functionalities of \textbf{Scikit-Learn} (recommended). -Give a -critical discussion of the three methods and a judgement of which -model fits the data best. Perform here as well an analysis of the bias-variance trade-off using the \textbf{bootstrap} resampling technique and an analysis of the mean squared error using cross-validation. - -\paragraph{Exercise 6: Analysis of real data (score 30 points).} -With our codes functioning and having been tested properly on a -simpler function we are now ready to look at real data. We will -essentially repeat in part g) what was done in parts a-e). However, we -need first to download the data and prepare properly the inputs to our -codes. We are going to download digital terrain data from the website -\href{{https://earthexplorer.usgs.gov/}}{\nolinkurl{https://earthexplorer.usgs.gov/}}, - -In order to obtain data for a specific region, you need to register as -a user (free) at this website and then decide upon which area you want -to fetch the digital terrain data from. In order to be able to read -the data properly, you need to specify that the format should be \textbf{SRTM -Arc-Second Global} and download the data as a \textbf{GeoTIF} file. The -files are then stored in \emph{tif} format which can be imported into a -Python program using - -\begin{verbatim} -scipy.misc.imread -\end{verbatim} - -Here is a simple part of a Python code which reads and plots the data -from such files - -\begin{verbatim} -import numpy as np -from imageio import imread -import matplotlib.pyplot as plt -from mpl_toolkits.mplot3d import Axes3D -from matplotlib import cm - -# Load the terrain -terrain1 = imread('SRTM_data_Norway_1.tif') -# Show the terrain -plt.figure() -plt.title('Terrain over Norway 1') -plt.imshow(terrain1, cmap='gray') -plt.xlabel('X') -plt.ylabel('Y') -plt.show() -\end{verbatim} - -If you should have problems in downloading the digital terrain data, -we provide two examples under the data folder of project 1. One is -from a region close to Stavanger in Norway and the other Møsvatn -Austfjell, again in Norway. -Feel free to produce your own terrain data. - - -Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example \href{{https://www.kaggle.com/datasets}}{kaggle.com} for examples. - - -Our final part deals with the parameterization of your digital terrain -data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial -approximation and cross-validation as resampling technique to evaluate which -model fits the data best. - -At the end, you should present a critical evaluation of your results -and discuss the applicability of these regression methods to the type -of data presented here (either the terrain data we propose or other data sets). - - - - -\subsection*{Background literature} - -\begin{enumerate} -\item For a discussion and derivation of the variances and mean squared errors using linear regression, see the \href{{https://arxiv.org/abs/1509.09169}}{Lecture notes on ridge regression by Wessel N. van Wieringen} - -\item The textbook of \href{{https://www.springer.com/gp/book/9780387848570}}{Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer}, chapters 3 and 7 are the most relevant ones for the analysis here. -\end{enumerate} - -\noindent -\subsection*{Introduction to numerical projects} - -Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers. Note that you can answer question by question and there is no need to structure your report as a scientific report with abstract, introduction, theory, results and discussions, conclusions etc. But you have the following elements in mind when you answer the various questions. - - -\begin{itemize} - \item Give a short description of the nature of the problem and the eventual numerical methods you have used. - - \item Describe the algorithm you have used and/or developed. Here you may find it convenient to use pseudocoding. In many cases you can describe the algorithm in the program itself. - - \item Include the source code of your program. Comment your program properly. You should have the code at your GitHub/GitLab link. You can also place the code in an appendix of your report. - - \item If possible, try to find analytic solutions, or known limits in order to test your program when developing the code. - - \item Include your results either in figure form or in a table. Remember to label your results. All tables and figures should have relevant captions and labels on the axes. - - \item Try to evaluate the reliabilty and numerical stability/precision of your results. If possible, include a qualitative and/or quantitative discussion of the numerical stability, eventual loss of precision etc. - - \item Try to give an interpretation of you results in your answers to the problems. - - \item Critique: if possible include your comments and reflections about the exercise, whether you felt you learnt something, ideas for improvements and other thoughts you've made when solving the exercise. We wish to keep this course at the interactive level and your comments can help us improve it. - - \item Try to establish a practice where you log your work at the computerlab. You may find such a logbook very handy at later stages in your work, especially when you don't properly remember what a previous test version of your program did. Here you could also record the time spent on solving the exercise, various algorithms you may have tested or other topics which you feel worthy of mentioning. -\end{itemize} - -\noindent -\subsection*{Format for electronic delivery of report and programs} - -The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report: - -\begin{itemize} - \item Use Canvas to hand in your projects, log in at \href{{https://www.uio.no/english/services/it/education/canvas/}}{\nolinkurl{https://www.uio.no/english/services/it/education/canvas/}} with your normal UiO username and password. - - \item Upload \textbf{only} the report file or the link to your GitHub/GitLab or similar typo of repos! For the source code file(s) you have developed please provide us with your link to your GitHub/GitLab or similar domain. The report file should include all of your discussions and a list of the codes you have developed. Do not include library files which are available at the course homepage, unless you have made specific changes to them. - - \item In your GitHub/GitLab or similar repository, please include a folder which contains selected results. These can be in the form of output from your code for a selected set of runs and input parameters. -\end{itemize} - -\noindent -Finally, -we encourage you to collaborate. Optimal working groups consist of -2-3 students. You can then hand in a common report. - - - -\subsection*{Software and needed installations} - -If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages, -we recommend that you install the following Python packages via \textbf{pip} as -\begin{enumerate} -\item pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow -\end{enumerate} - -\noindent -For Python3, replace \textbf{pip} with \textbf{pip3}. - -See below for a discussion of \textbf{tensorflow} and \textbf{scikit-learn}. - -For OSX users we recommend also, after having installed Xcode, to install \textbf{brew}. Brew allows -for a seamless installation of additional software via for example -\begin{enumerate} -\item brew install python3 -\end{enumerate} - -\noindent -For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution -you can use \textbf{pip} as well and simply install Python as -\begin{enumerate} -\item sudo apt-get install python3 (or python for python2.7) -\end{enumerate} - -\noindent -etc etc. - -If you don't want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely -\begin{enumerate} -\item \href{{https://docs.anaconda.com/}}{Anaconda} Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system \textbf{conda} - -\item \href{{https://www.enthought.com/product/canopy/}}{Enthought canopy} is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license. -\end{enumerate} - -\noindent -Popular software packages written in Python for ML are - -\begin{itemize} -\item \href{{http://scikit-learn.org/stable/}}{Scikit-learn}, - -\item \href{{https://www.tensorflow.org/}}{Tensorflow}, - -\item \href{{http://pytorch.org/}}{PyTorch} and - -\item \href{{https://keras.io/}}{Keras}. -\end{itemize} - -\noindent -These are all freely available at their respective GitHub sites. They -encompass communities of developers in the thousands or more. And the number -of code developers and contributors keeps increasing. - - - - - -% ------------------- end of main content --------------- - -\end{document} - diff --git a/doc/src/Projects/2021/Project1/README.txt b/doc/src/Projects/2021/Project1/README.txt deleted file mode 100644 index 08cc9f17c..000000000 --- a/doc/src/Projects/2021/Project1/README.txt +++ /dev/null @@ -1,2 +0,0 @@ -This IPython notebook Project1.ipynb does not require any additional -programs. diff --git a/doc/src/Projects/2021/Project1/ipynb-Project1-src.tar.gz b/doc/src/Projects/2021/Project1/ipynb-Project1-src.tar.gz deleted file mode 100644 index 17ccd89ef..000000000 Binary files a/doc/src/Projects/2021/Project1/ipynb-Project1-src.tar.gz and /dev/null differ