For titanic

1-for titanic

•Create a repository in RapidMiner called Homework and create two subfolders Data and Processes under the Homework repository

•Import the data from the file Titanic.xls provided to you (attached) and store it in a repository called Titanic in the Data subfolder you created above by doing the following

•In Design View Manually add the Read Excel Operator

•Manually add the Store operator and specify the repository

•Run the process to import and save the data to your local repository

•Filter the data for just the ones that survived the Titanic disaster

•In the design view add the Filter Examples Operator and specify the filter on the column “Survived” by clicking on the Add Filters button in the Parameters section

•You can also use Turbo Prep to filter the data, if you would like and add the process

•Run the process to check if the filtering worked

•Replace “Male” with “Man” in the Sex column

•In the design view add the Replace Operator and specify the attribute filter type as single and fill in the additional details to replace “Male” with “Man”

•Run the process to check if the replacement worked

•Go to File > Export Process and save the process you created above as a .rmp file and turn it in via the blackboard HW dropbox

2-for Bats-data , Geo-data

Download bats_data.csv and Geo_data.csv that are attached to the HW on blackboard and save it on your

computer

In RapidMiner do the following

Step 1 – Open a new process file and Read the two data files and store them as RapidMiner repositories

(you can call them Bats Data and Geo Data). Hint: Use the Read csv and store operator.

Step 2 – Now that you have read and stored the data in a local RapidMIner repository you can retrieve i

from the repository. Now, open another new process file and retrieve the two datasets from the RapidMiner

repositories created above. Hint: Use the Retrieve operator. You can use two Retrieve operators, one to

retrieve Bats Data and the other to retrieve Geo Data.

Step 3 – Replace the missing values in the Foraging column in the Bats Data dataset with 0 (zero). Hint:

Use the Replace Missing Values operator as shown in slide 3.

Step 4 – Merge the Bats Data dataset and the Geo Data dataset such that all the records in the Bats Data

dataset are retained and merged with the Latitude and Longitude columns in the Geo Data dataset. Hint:

Choose a left or right join depending on whether you have chosen the Bats Data dataset to be the left or

right dataset.

Step 5 – Now find the aggregate sum of Foraging by Site. Hint: Use the Aggregate operator. Click on the

group by attributes button and choose Site as the groupby column and click on aggregation attributes and

choose Foraging as the column and sum as the function.

Step 6 – Go to File > Export Process and save the process you created above as a .rmp file and turn it in

via the blackboard HW dropbox

3-ata dataset to be the left or

right dataset.

Step 5 – Now find the aggregate sum of Foraging by Site. Hint: Use the Aggregate operator. Click on the

group by attributes button and choose Site as the groupby column and click on aggregation attributes and

choose Foraging as the column and sum as the function.

Step 6 – Go to File > Export Process and save the process you created above as a .rmp file and turn it in

via the blackboard HW dropbox

3-

1. Retrieve the Titanic data that you already loaded into a RapidMiner repository in HW 1, using the

Retrieve operator. If you have not done HW 1 yet, then read the attached Titanic Excel file as per

instructions in HW 1 and proceed.

2. Search for the Statistics operator in RapidMiner and drag it into the process area. Connect it as shown

in slide 11.

3. Run the process and view the results. They should look like what is shown in slide 12.

4. Go to File > Export Process and save the process you created above as a .rmp file and turn it in via the

blackboard HW dropbox