{"id":5067,"date":"2023-02-25T02:22:05","date_gmt":"2023-02-25T02:22:05","guid":{"rendered":"https:\/\/www.goodacademic.com\/blog\/questions\/r-studio-question\/"},"modified":"2023-02-25T02:22:05","modified_gmt":"2023-02-25T02:22:05","slug":"r-studio-question","status":"publish","type":"questions","link":"https:\/\/www.goodacademic.com\/blog\/questions\/r-studio-question\/","title":{"rendered":"r studio question"},"content":{"rendered":"
\n Learning Goal: <\/b>I’m working on a databases question and need the explanation and answer to help me learn.<\/p>\n

At the end of this lab you will upload your RStudio script for points.<\/p>\n

For CIS 389 download this dataset: iris.csv<\/a>
\n \n <\/path>\n <\/svg>Download iris.csv<\/span><\/a><\/span><\/p>\n

first, we will need data to perform the algorithm on. We will take the classic iris dataset. UCI Machine Learning Repository: Iris Data Set
\n \n <\/path>\n <\/svg>Links to an external site.<\/span><\/span><\/a><\/span><\/p>\n

The example is wrong, as the book taught us the right way. Use<\/span><\/p>\n

For PC <\/span><\/p>\n

iris <- read.csv(“C:\/Users\/Student\/Desktop\/iris.csv”)<\/span><\/p>\n

For MAC<\/span><\/p>\n

iris <- read.csv(“\/Users\/UserName\/Downloads\/iris.csv”)<\/span><\/p>\n

\"\"<\/p>\n

First read in the data and then display first 6 elements of the iris data frame. We will take petallength<\/span><\/code> and petalwidth <\/span><\/code>as variables for k-means clustering. Why? Because after much exploration it has been found that these two variables have significant differences among species.<\/p>\n

This will load the proper package to make sure the rest of the lab will work correctly<\/p>\n

library(cluster)<\/p>\n

We will create a new data frame corresponding to these two variables.<\/p>\n

    \n
  1. kmeans_variables =<\/span> data<\/span>.<\/span>frame<\/span>(<\/span>iris$petallength<\/span>,<\/span> iris$petalwidth<\/span>)<\/span><\/span><\/li>\n<\/ol>\n

    Convert vector of characters to factors to avoid invalid color name error<\/p>\n

    2. pClass <- as.factor(iris$class)<\/p>\n

    Let\u00e2\u20ac\u2122s display the data.<\/p>\n

    3. plot<\/span>(<\/span>kmeans_variables<\/span>,<\/span>col<\/span>=pClass<\/span>)<\/span><\/p>\n

    \"\"<\/p>\n

    Applying K-means<\/p>\n

    4. KMC =<\/span> kmeans<\/span>(<\/span>kmeans_variables<\/span>,<\/span> centers =<\/span> 3<\/span>,<\/span> iter<\/span>.<\/span>max<\/span>=<\/span>50<\/span>,<\/span> nstart<\/span>=<\/span>20<\/span>)<\/span><\/span><\/span><\/p>\n

    centers<\/strong><\/p>\n

    number of clusters, k In our case we take it as 3 as number of different species are 3.<\/p>\n

    iter.max<\/strong><\/p>\n

    maximum number of iterations to be performed.<\/p>\n

    nstart<\/strong><\/p>\n

    R will try 20 different random starting assignments and then select the one with the lowest within cluster variation.<\/p>\n

    Output –<\/p>\n

    K<\/span>–<\/span>means clustering with<\/span> 3<\/span> clusters of sizes 49<\/span>,<\/span> 48<\/span>,<\/span> 52<\/span> <\/span><\/span><\/p>\n

    Cluster<\/span> means<\/span>:<\/span><\/p>\n

    iris<\/span>.<\/span>petallength iris<\/span>.<\/span>petalwidth<\/span><\/p>\n

    1 1.465306 0.244898<\/span><\/span><\/p>\n

    2 5.595833<\/span>2.037500<\/span><\/span><\/p>\n

    3 4.269231 1.342308<\/span><\/span><\/p>\n

    Clustering<\/span> vector<\/span>:<\/span><\/p>\n

    [<\/span>1<\/span>]<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span><\/p>\n

    [<\/span>38<\/span>]<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 1<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3 <\/span><\/p>\n

    [<\/span>75<\/span>]<\/span> 3<\/span> 3<\/span> 2<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 2<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 3<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 3<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span><\/p>\n

    [<\/span>112<\/span>]<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 3<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 3<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 3<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span> 2<\/span><\/p>\n

    [<\/span>149<\/span>]<\/span> 2<\/span><\/p>\n

    Within<\/span> cluster sum of squares by<\/span> cluster<\/span>:<\/span><\/span><\/p>\n

    [<\/span>1<\/span>]<\/span> 2.032245<\/span> 16.291667<\/span> 13.057692<\/span><\/p>\n

    (<\/span>between_SS \/<\/span> total_SS =<\/span> 94.2<\/span> %)<\/span><\/span><\/span><\/p>\n

    Available<\/span> components<\/span>:<\/span><\/p>\n

    [<\/span>1<\/span>]<\/span> “cluster”<\/span> “centers”<\/span> “totss”<\/span> “withinss”<\/span> “tot.withinss”<\/span><\/p>\n

    [<\/span>6<\/span>]<\/span> “betweenss”<\/span> “size”<\/span> “iter”<\/span> “ifault”<\/span><\/p>\n

    KMC$cluster<\/span><\/code> will give the details of which data point is assigned which cluster.<\/p>\n

    KMC$centers<\/span><\/code> will give the details regarding cluster centroids of each cluster<\/p>\n

    ><\/span> KMC$centers<\/span><\/p>\n

    iris<\/span>.<\/span>petallength iris<\/span>.<\/span>petalwidth<\/span><\/p>\n

    1<\/span>1.465306<\/span> 0.244898<\/span><\/p>\n

    2<\/span>5.595833<\/span> 2.037500<\/span><\/p>\n

    3<\/span>4.269231<\/span> 1.342308<\/span><\/p>\n

    KMC$size<\/span><\/code> will give number of data points inside each cluster<\/p>\n

      \n
    1. ><\/span> KMC$size<\/span><\/li>\n
    2. [<\/span>1<\/span>]<\/span> 49<\/span> 48<\/span> 52<\/span><\/li>\n<\/ol>\n

      For other parameters look here – K-Means Clustering
      \n \n <\/path>\n <\/svg>Links to an external site.<\/span><\/span><\/a><\/span> . But for beginner I think this much is sufficient.<\/p>\n

      Let\u00e2\u20ac\u2122s see which species got which cluster<\/p>\n

        \n
      1. ><\/span> table<\/span>(<\/span>KMC$cluster<\/span>,<\/span> iris$class<\/span>)<\/span><\/li>\n
      2. <\/li>\n
      3. Iris<\/span>–<\/span>setosa Iris<\/span>–<\/span>versicolor Iris<\/span>–<\/span>virginica<\/span><\/span><\/span><\/li>\n
      4. 1<\/span>49<\/span>0 0<\/span><\/span><\/li>\n
      5. 2 0<\/span>2<\/span>46<\/span><\/span><\/li>\n
      6. 3 0 48 4<\/span><\/span><\/span><\/span><\/li>\n<\/ol>\n

        We can see setosa got cluster 1, versicolor got 3 and virginica got 2.<\/p>\n

        Plotting k-means<\/p>\n

          \n
        1. clusplot<\/span>(<\/span>iris<\/span>,<\/span> KMC$cluster<\/span>,<\/span> color<\/span>=<\/span>TRUE<\/span>,<\/span> shade<\/span>=<\/span>TRUE<\/span>,<\/span> lines<\/span>=<\/span>0<\/span>)<\/span><\/li>\n<\/ol>\n

          \"\"<\/p>\n

          What you are actually watching in the clusplot<\/span>()<\/span><\/code> is the plot of your observations in the principal plane. What this function is doing is calculating the principal component score for each of your observations, plotting those scores and coloring by cluster.<\/p>\n

          Principal component analysis (PCA) is a dimension reduction technique; it “summarizes” the information of all variables into a couple of “new” variables called components.<\/p>\n

          For simple plot use<\/p>\n

            \n
          1. plot<\/span>(<\/span>kmeans_variables<\/span>,<\/span>col<\/span>=<\/span>KMC$cluster<\/span>)<\/span><\/li>\n<\/ol>\n

            Sources –<\/p>\n

            NOTE:To install the cluster package in RStudio: install.packages(“cluster”)<\/p>\n

            K Means Clustering in R
            \n \n <\/path>\n <\/svg>Links to an external site.<\/span><\/span><\/a><\/span><\/p>\n

            Using the stats package in R for kmeans clustering
            \n \n <\/path>\n <\/svg>Links to an external site.<\/span><\/span><\/a><\/span><\/p>\n

            How to produce a pretty plot of the results of k-means cluster analysis?<\/a><\/span><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

            Learning Goal: I’m working on a databases question and need the explanation and answer to help me learn. At the end of this lab you will upload your RStudio script for points. For CIS 389 download this dataset: iris.csv Download iris.csv first, we will need data to perform the algorithm on. We will take the […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"closed","template":"","meta":[],"disciplines":[721],"paper_types":[],"tagged":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/questions\/5067"}],"collection":[{"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/questions"}],"about":[{"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/types\/questions"}],"author":[{"embeddable":true,"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/comments?post=5067"}],"version-history":[{"count":0,"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/questions\/5067\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/media?parent=5067"}],"wp:term":[{"taxonomy":"disciplines","embeddable":true,"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/disciplines?post=5067"},{"taxonomy":"paper_types","embeddable":true,"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/paper_types?post=5067"},{"taxonomy":"tagged","embeddable":true,"href":"https:\/\/www.goodacademic.com\/blog\/wp-json\/wp\/v2\/tagged?post=5067"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}