R Project $02$: Data Frame$/$Data Preparation$/$Data Mining

Please download the R file $$R Project $02.$R$.$

Please download the data files: $$Pokeman Data.csv$,$Pokemon Info.csv$,$ and $$Diabetes

Data.csv$$

Please write down your code in the file and submit the file in the submission box.

Section one: Pok$$mon

$1.$ Load two $.$csv files $$Pokeman Data.csv$$ and $$Pokemon Info.csv$$ as data frames.

The datasets record the basic information and key ratios of $721$ Pok$$mon$.$ The data attributions

are listed as follows:

Pok$$mon Info.csv Pok$$mon Data.csv

ID PokeID

Pok$$mon Pok$$mon

Height Attack

Weight Defense

Type HP

Speed

$2.$ Combine the two data frames into one data frame.

$($Hint: ID and PokeID are the primary keys for each table$)$

$3.$ Missing Values:

a$.$ Print all the rows including missing values.

b$.$ Pok$$mon names: If you can find the Pok$$mon names from another data frame, you

can replace the names. If you cannot find the names, you can remove the row.

c$.$ Ratios: Please replace the missing values of the ratios with the median of the same

type.

$4.$ Complete the following tasks:

a$.$ Check the first $10$ rows of the combined data frame.

b$.$ Check the structure of the data frame. Make sure Pok$$mon names and Type are

factors.

c$.$ Use the summary command to check how many Pok$$mon there are in each type.

$($Hint: summary $()$ can be used for a single column of a data frame$)$

$5.$ Calculate a comprehensive score for Pok$$mon $(=$ the sum of attack, defense, hp$,$ and

speed$).$

$6.$ Complete the following filtering tasks:

a$.$ Print all the Pok$$mon of the $$grass$$ type.

b$.$ Print all the Pok$$mon have an $$attack$$ score larger than or equal to $50$ and less than

or equal to $100.$

c$.$ Print all the Pok$$mon of the $$grass$$ type and have a height larger than or equal to $15.$

d$.$ Print the data for $$pichu$.$

R Project $02$: Data Frame$/$Data Preparation$/$Data Mining

Please download the $\backslash ($ R $\backslash )$ file $"$R Project $02.$R$".$

Please download the data files: "Pokeman Data.csv$",$ "Pokemon Info.csv$",$ and "Diabetes

Data.csv$"$

Please write down your code in the file and submit the file in the submission box.

Section one: Pok$$mon

$1.$ Load two $.$csv files "Pokeman Data.csv$"$ and "Pokemon Info.csv$"$ as data frames.

The datasets record the basic information and key ratios of $721$ Pok$$mon$\text{'}.$ The data attributions are listed as follows:

$2.$ Combine the two data frames into one data frame.

$($Hint: ID and PokeID are the primary keys for each table$)$

$3.$ Missing Values:

a$.$ Print all the rows including missing values.

b$.$ Pok$$mon names: If you can find the Pok$$mon names from another data frame, you can replace the names. If you cannot find the names, you can remove the row.

c$.$ Ratios: Please replace the missing values of the ratios with the median of the same type.

$4.$ Complete the following tasks:

a$.$ Check the first $10$ rows of the combined data frame.

b$.$ Check the structure of the data frame. Make sure Pok$$mon names and Type are factors.

c$.$ Use the summary command to check how many Pok$$mon there are in each type. $($Hint: summary $()$ can be used for a single column of a data frame$)$

$5.$ Calculate a comprehensive score for Pok$$mon $(=$ the sum of attack, defense, hp$,$ and speed$).$

$6.$ Complete the following filtering tasks:

a$.$ Print all the Pok$$mon of the "grass" type.

b$.$ Print all the Pok$$mon have an "attack" score larger than or equal to $50$ and less than or equal to $100.$

c$.$ Print all the Pok$$mon of the "grass" type and have a height larger than or equal to $15.$

d$.$ Print the data for "pichu".

Section Two: Diabetes Data

This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. The objective of the dataset is to diagnostically predict whether or not a patient has diabetes based on certain diagnostic measurements included in the dataset. In particular, all patients here are females at least $21$ years old of Pima Indian heritage. The attributions are listed as follows:

$1.$ Load the. csv file "Diabetes Data.csv$"$ as a data frame

$2.$ Data Preparation$/$Missing Values:

a$.$ Check the summary and structure of the data

b$.$ Encode the target variable as a factor

$3.$ Data Splitting:

a$.$ Split the dataset into the training set and testing set

b$.$ Pick the variable needed: "Age", "BMI", "Glucose", and "Outcome"

$4.$ Decision Tree Classification:

a$.$ Fitting Decision Tree Classification to the Training set

b$.$ Plotting the tree

$5.$ Assess the model:

a$.$ Predicting the Test set results

b$.$ Making the Confusion Matrix

c$.$ Calculate the accuracy ratios

$6.$ Pick the variable needed for clustering analysis: "Age" and "BMI"

$7.$ Using the Elbow Method to find the optimal number of cluster

$8.$ Run the clustering analysis

$9.$ Print the results in the plot $($color the clusters$)$