代做LM Data Mining and Machine Learning (2024) Lab 2 – Clustering and PCA帮做Matlab程序

LM Data Mining and Machine Learning (2024)

Lab 2 – Clustering and PCA

Objectives

The objective of this lab is to use the methods described in lectures to discover the structure of a particular data set. At the end of the lab your task is to write down an intuitive textual description of the data.  The techniques that you should apply are clustering and PCA.

What you will need

All of the files that you will need are in the zip archive lab2-2024.zip which is on the Canvas page.

The Data

The data is stored in a text file called lab2Data (contained in the lab2-2024.zip file).  The data consists of 1050 points in 6 dimensional space.  Each point appears as a row in the data file – have a look at the file to see its structure.  There is a ‘header’ at the top of the file that specifies the number of columns and rows.

Part 1: Clustering

Your first task is to use clustering to try to determine whether there are natural clusters in the data, and if there are, how many.  To do this you need to apply clustering to the data.  You need two C programs agglom.c and k-means.c.  Use the provided .exe files (or compile these two source C programs if needed).

The  program  agglom.c is  an   implementation  of  the  agglomerative  clustering  algorithm described in lecture material.  You should apply this to the data set to obtain a set of K initial centroids  for  k-means  clustering  (see  the  lecture  notes  to  understand  how).     Then  use k-means.c to locally optimize the centroids.   As well as producing a locally optimized set of centroids,  k-means.c returns the distortion for that set of centroids relative to the data.   I recommend 15 iterations of k-means clustering.

Usage of agglom program:      agglom dataFile centFile numCent

Runs  agglomerative  clustering  on  the  data  in  dataFile  until  the  number  of  centroids  is numCent.  Writes the centroid coordinates to centFile.

Usage of k-means program:   k-means dataFile centFile opFile numIter

Runs  numIter iterations  of  k-means  clustering  on  the  data  in  dataFile starting  with  the centroids in centFile.  After each iteration writes distortion and new centroids to opFile.

You should use agglom.c and k-means.c to plot a graph of distortion as a function of K, the number of clusters.  Plot distortion for values of K between 1 and 12.  To clarify:

for K=1 to 12

•    Apply agglom.c to the data set to obtain K initial centroids

•    Apply 15 iterations of k-means clustering.  A list of 15 numbers will appear on the screen. What are they?  For each K make a note of the final number.

Plot a graph of these 12 final numbers against K.   Note that to analyse data structure, it might sometimes be useful to plot the distortion in a log-scale or to plot the ratio of the distortion for K clusters to the distortion for K+1 clusters.

Conclusion to Part 1:  What does the graph tell you about the structure of the data?

Part 2: Principle Components Analysis (PCA)

To apply PCA to the data you will need to use MATLAB.  MATLAB will complain about the header at the start of the data file lab2Data.  Therefore I have created a version of this file without the header, called lab2Data-Matlab.  Use this file with MATLAB.

The procedure for applying and interpreting PCA is described in lecture material.   In  brief, the stages are as follows:

1. Load the data into a matrix, X say, in MATLAB.

2. Compute the covariance matrix of the data. You can either do this by implementing the formula for covariance given in the lectures, or you can simply use the MATLAB cov function:

>> C = cov(X)

3. Apply eigenvector/eigenvalue decomposition to the covariance matrix: >> [U,D] = eig(C)

Conclusion to  Part  2:   Write  down  the  eigenvalues.    What  does  the  eigenvector/eigenvalue decomposition of the covariance matrix C  tell you about the structure of the data set?

Explain how your Part 2 conclusion is likely to change if each sample in the dataset was modified by adding the value of 15 in the dimension 1 and value of 30 in the dimension 4 (e.g., considering original data sample was [1, 3, 5, 0, 2, 3], the new data sample would be [16, 3, 5, 30, 2, 3]).


 



热门主题

课程名

mktg2509 csci 2600 38170 lng302 csse3010 phas3226 77938 arch1162 engn4536/engn6536 acx5903 comp151101 phl245 cse12 comp9312 stat3016/6016 phas0038 comp2140 6qqmb312 xjco3011 rest0005 ematm0051 5qqmn219 lubs5062m eee8155 cege0100 eap033 artd1109 mat246 etc3430 ecmm462 mis102 inft6800 ddes9903 comp6521 comp9517 comp3331/9331 comp4337 comp6008 comp9414 bu.231.790.81 man00150m csb352h math1041 eengm4100 isys1002 08 6057cem mktg3504 mthm036 mtrx1701 mth3241 eeee3086 cmp-7038b cmp-7000a ints4010 econ2151 infs5710 fins5516 fin3309 fins5510 gsoe9340 math2007 math2036 soee5010 mark3088 infs3605 elec9714 comp2271 ma214 comp2211 infs3604 600426 sit254 acct3091 bbt405 msin0116 com107/com113 mark5826 sit120 comp9021 eco2101 eeen40700 cs253 ece3114 ecmm447 chns3000 math377 itd102 comp9444 comp(2041|9044) econ0060 econ7230 mgt001371 ecs-323 cs6250 mgdi60012 mdia2012 comm221001 comm5000 ma1008 engl642 econ241 com333 math367 mis201 nbs-7041x meek16104 econ2003 comm1190 mbas902 comp-1027 dpst1091 comp7315 eppd1033 m06 ee3025 msci231 bb113/bbs1063 fc709 comp3425 comp9417 econ42915 cb9101 math1102e chme0017 fc307 mkt60104 5522usst litr1-uc6201.200 ee1102 cosc2803 math39512 omp9727 int2067/int5051 bsb151 mgt253 fc021 babs2202 mis2002s phya21 18-213 cege0012 mdia1002 math38032 mech5125 07 cisc102 mgx3110 cs240 11175 fin3020s eco3420 ictten622 comp9727 cpt111 de114102d mgm320h5s bafi1019 math21112 efim20036 mn-3503 fins5568 110.807 bcpm000028 info6030 bma0092 bcpm0054 math20212 ce335 cs365 cenv6141 ftec5580 math2010 ec3450 comm1170 ecmt1010 csci-ua.0480-003 econ12-200 ib3960 ectb60h3f cs247—assignment tk3163 ics3u ib3j80 comp20008 comp9334 eppd1063 acct2343 cct109 isys1055/3412 math350-real math2014 eec180 stat141b econ2101 msinm014/msing014/msing014b fit2004 comp643 bu1002 cm2030
联系我们
EMail: 99515681@qq.com
QQ: 99515681
留学生作业帮-留学生的知心伴侣!
工作时间:08:00-21:00
python代写
微信客服:codinghelp
站长地图