Scribd Logo
Upload

Welcome to Scribd!

  • 47 views

    4063 Final复习资料

    Uploaded by

    Xie Tia
    1. Frank originally had 10 ounces of gold in each of his 3 bags. Sally added gold to each bag: 5 ounces to the first bag, 3 ounces to the second bag, and 12 ounces to the third bag. So now Frank has 15, 13, and 22 ounces of gold in each respective bag. 2. The document shows how to create data frames and manipulate data within them. Various plotting and summary functions are applied to the data frames as demonstrations. 3. The document demonstrates various statistical and data visualization techniques including describing data through measures like mean, median, range, standard deviation, histograms, boxplots, scatterplots and barplots. It also shows how to handle outliers and missing data.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    4063 Final复习资料

    Uploaded by

    Xie Tia
    47 views6 pages
    1. Frank originally had 10 ounces of gold in each of his 3 bags. Sally added gold to each bag: 5 ounces to the first bag, 3 ounces to the second bag, and 12 ounces to the third bag. So now Frank has 15, 13, and 22 ounces of gold in each respective bag. 2. The document shows how to create data frames and manipulate data within them. Various plotting and summary functions are applied to the data frames as demonstrations. 3. The document demonstrates various statistical and data visualization techniques including describing data through measures like mean, median, range, standard deviation, histograms, boxplots, scatterplots and barplots. It also shows how to handle outliers and missing data.

    Original Description:

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    1. Frank originally had 10 ounces of gold in each of his 3 bags. Sally added gold to each bag: 5 ounces to the first bag, 3 ounces to the second bag, and 12 ounces to the third bag. So now Frank has 15, 13, and 22 ounces of gold in each respective bag. 2. The document shows how to create data frames and manipulate data within them. Various plotting and summary functions are applied to the data frames as demonstrations. 3. The document demonstrates various statistical and data visualization techniques including describing data through measures like mean, median, range, standard deviation, histograms, boxplots, scatterplots and barplots. It also shows how to handle outliers and missing data.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    47 views6 pages

    4063 Final复习资料

    Uploaded by

    Xie Tia
    1. Frank originally had 10 ounces of gold in each of his 3 bags. Sally added gold to each bag: 5 ounces to the first bag, 3 ounces to the second bag, and 12 ounces to the third bag. So now Frank has 15, 13, and 22 ounces of gold in each respective bag. 2. The document shows how to create data frames and manipulate data within them. Various plotting and summary functions are applied to the data frames as demonstrations. 3. The document demonstrates various statistical and data visualization techniques including describing data through measures like mean, median, range, standard deviation, histograms, boxplots, scatterplots and barplots. It also shows how to handle outliers and missing data.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 6

    1.

    Frank has 3 bags of gold, containing 10 ounces each.


    Sally adds five ounces to one of his bags, 3 ounces to another, and 12 to the last.
    Use Vectors to show how much gold Frank has in each bag.
    Upload R code to Assignment 1 using R Markdown in a Word (docx) format
    Frank <-c(10,10,10)
    Sally <-c(5,3,12)
    Total <-Frank+Sally
    Total
    2.
    #Print out one cell from the dataframe.
    Sale[2,1]
    View(Sale)
    #Split the dataframe into two pieces
    split(Sale, Sale$Cost)
    split(Sale, Sale$Profit)
    #Add up all the values in one column of the dataframe
    sum(Sale$Cost)
    3.
    #Create a dataframe with 5 columns.
    C1<-c(1,2,3,4,5,6,7,8,9)
    C2<-c(2,3,4,5,6,7,8,9,10)
    C3<-c(3,4,5,6,7,8,9,10,11)
    C4<-c(4,5,6,7,8,9,10,11,12)
    C5<-c(5,6,7,8,9,10,11,12,13)
    dataframe<-data.frame(C1,C2,C3,C4,C5)
    View(dataframe)
    #Boxplot
    boxplot(dataframe)
    #Scatterplot
    plot(dataframe)
    #Histogram
    hist(dataframe)
    #Calculate the standard deviation of the data in one column.
    standard_deviation_C1<-sd(C1)
    standard_deviation_C1
    #Replace one of the datapoints with an outlier
    dataframe[5,2]<-50
    #Generate a new boxplot showing the outlier.
    boxplot(dataframe)
    4.
    #Describing data
    some_numbers<-c(13,15,16,20,30,4,5,6,7,8,90)
    some_numbers<-some_numbers + some_numbers
    some_numbers
    #mean, median, range qiantile
    mean_some_numbers<-mean(some_numbers)
    mean_some_numbers

    median_some_numbers<-median(some_numbers)
    median_some_numbers

    range_some_numbers<-range(some_numbers)
    range_some_numbers

    quantile_some_numbers<-quantile(some_numbers)
    quantile_some_numbers

    #standard deviation
    standard_deviation_some_numbers<-sd(some_numbers)
    standard_deviation_some_numbers

    different_numbers<- c(1,3,4,5,6,7,7,7,3,8,10)
    summary(some_numbers)
    summary(different_numbers)
    View(some_numbers)

    #visualizing
    plot(some_numbers)
    some_numbers
    plot(some_numbers, type = "h", col="pink", main="statistics", xlab="Value",ylab="number")
    hist(some_numbers)
    barplot(some_numbers)
    boxplot(some_numbers)
    some_dataframe<-data.frame(some_numbers,different_numbers)
    some_dataframe
    plot(some_dataframe, type = "h", col="pink", main="statistics", xlab="Value",ylab="number")
    some_dataframe[10,2]<-50
    some_dataframe
    5.
    mydata<-Stocks
    str(mydata)
    head(mydata)
    View(mydata)

    names(mydata) [1:12]<-c("day", "Stock1","Stock2","Stock3","Stock4", "Stock5",


    "Stock6","Stock7", "Stock8", "Stock9","Stock10", "Rating")
    names(mydata)[1:12]
    str(mydata)

    mydata$Stock1<-as.numeric(as.character(mydata$Stock1))
    mydata$Stock2<-as.numeric(as.character(mydata$Stock2))
    mydata$Stock3<-as.numeric(as.character(mydata$Stock3))
    mydata$Stock4<-as.numeric(as.character(mydata$Stock4))
    mydata$Stock5<-as.numeric(as.character(mydata$Stock5))
    mydata$Stock6<-as.numeric(as.character(mydata$Stock6))
    mydata$Stock7<-as.numeric(as.character(mydata$Stock7))
    mydata$Stock8<-as.numeric(as.character(mydata$Stock8))
    mydata$Stock9<-as.numeric(as.character(mydata$Stock9))
    mydata$Stock10<-as.numeric(as.character(mydata$Stock10))
    mydata$Rating<-as.factor(as.character(mydata$Rating))
    str(mydata)
    #check for null"NA"values
    table(is.na(mydata))
    complete.cases(mydata)
    #remove NA's by overwriting with the mean of that column
    mydata$Stock1[is.na(mydata$Stock1)]=mean(mydata$Stock1,na.rm = TRUE)
    6.
    #Use three columns of data
    weather<-c("rainy","snow","sunny")
    time<-c("urgent","adequate","adequate")
    health<-c("bad","good","good")
    lawn<-c("no","yes","yes")
    dataset<-data.frame(weather,time,health,lawn)
    View(dataset)
    str(dataset)
    dataset$weather<-as.factor(as.character(dataset$weather))
    dataset$time<-as.factor(as.character(dataset$time))
    dataset$health<-as.factor(as.character(dataset$health))
    dataset$lawn<-as.factor(as.character(dataset$lawn))
    str(dataset)
    #Predicted
    set.seed(999)
    train=dataset[trainIndex, ]
    test=dataset[-trainIndex, ]
    print(table(dataset$lawn))
    print(train(dataset$lawn))
    NBclassfier=naiveBayes(lawn~weather+time+health, dataset=train)
    print(NBclassfier)
    7.Naive bayer
    str(CreditRating)
    CreditRating$PurchaseFrequency<-as.factor(as.character(CreditRating$PurchaseFrequency))
    CreditRating$CreditRating<-as.factor(as.character(CreditRating$CreditRating))
    CreditRating$Age<-as.factor(as.character(CreditRating$Age))
    CreditRating$Approval<-as.factor(as.character(CreditRating$Approval))
    str(CreditRating)

    #Get package to divide data into training & test data


    library(caret)
    set.seed(7267166) #random number generator
    trainIndex=createDataPartition(CreditRating$Approval, p=0.7)$Resample1
    train=CreditRating[trainIndex, ]
    test=CreditRating[-trainIndex, ]

    # check the balance y predicted


    print(table(CreditRating$Approval))

    print(table(train$Approval))
    NBclassfier=naiveBayes(Approval~CreditRating+Age+Approval, data=train)
    print(NBclassfier)
    8.
    #load dataset: iris
    data("iris")
    #view structure of dataset
    str(iris)
    #view summary of dataset
    summary(iris)
    #view top row
    head(iris)
    #creat new dataset
    iris.new<- iris[,c(1,2,3,4)]
    iris.class<- iris[,"Species"]
    #view top row
    head(iris.new)
    head(iris.class)
    normalize <- function(x){return ((x-min(x))/(max(x)-min(x)))}
    iris.new$Sepal.Length<- normalize(iris.new$Sepal.Length)
    iris.new$Sepal.Width<- normalize(iris.new$Sepal.Width)
    iris.new$Petal.Length<- normalize(iris.new$Petal.Length)
    iris.new$Petal.Width<- normalize(iris.new$Petal.Width)
    #view top row
    head(iris.new)
    #apply k-means clustering algorithm
    result<- kmeans(iris.new,3)
    #give number of each cluster
    result$size
    # gives value of cluster center datapoint value
    result$centers
    #gives cluster vector
    result$cluster
    #Verify results of clustering
    par(mfrow=c(2,2), mar=c(5,4,2,2))
    # Plot to see sepal length and sepal width been distributed in clusters
    plot(iris.new[c(1,2)], col=result$cluster)
    # Plot to see Sepal. length and Sepal. width been distributed originally as per "class"
    attribute in dataset
    plot(iris.new[c(1,2)], col=iris.class)
    # Plot to see how Petal.Length and Petal.Width data points have been distributed in clusters
    plot(iris.new[c(3,4)], col=result$cluster)
    plot(iris.new[c(3,4)], col=iris.class)
    #Result of table
    table(result$cluster,iris.class)
    9.
    #explore data
    View(grades)
    str(grades)
    table(grades$Level)
    #clean data
    grades$Level<-as.factor(as.character(grades$Level))
    str(grades)
    set.seed(2134)
    ind<-sample(2,nrow(grades),replace = TRUE, prob = c(0.7,0.3))
    train_set<-grades[ind==1,]
    test_set<-grades[ind==2,]
    nrow(train_set)
    nrow(test_set)
    #building desision tree
    mytree<-tree(Level~Quiz1+Quiz2+Quiz3+Quiz4+Quiz5, data = train_set)
    #summarize the model
    summary(mytree)
    #plot the tree
    plot(mytree)
    text(mytree,pretty=0, cex=0.6)
    10.
    #Import the data1.csv file into Rstudio.
    Summarize the data.
    Remove the last column and create a boxplot from the remaining columns.
    Create a scatterplot of column 1 and column 3.
    Calculate the correlation between column 1 and 3.
    data1<-read.csv("data1.csv")
    summary(data1)
    data2<-data1[,-6]
    boxplot(data2)
    pairs(data2[, 1:3])
    cor(data2[, 1:3])

    You might also like