Icon

L1-DS Final Assessment Workflow

This workflow contains the final assessment of the L1-DS self-paced course. Solve the workflow and complete the quiz at the end of the course!

URL: KNIME Self-Paced Courses https://www.knime.com/knime-self-paced-courses

Task 3. Make sense of the data The columns edu_mother and edu_father represent the education level of a student's parents. Map the indices to the following categories 0 - none 1 - primary 2 - middle 3 - secondary 4 - higher Group the data in order to obtain the percentage of students for each combination of mother and father education level.
Task 1. Read data The students.sqlite database stores student personal info in 2 tables - GP and MS - corresponding to two different schools. Read the content of the two tables into the workflow. The transcript.csv file contains failures, absences and grades for each student.
Question: What is the percentage of students with both parents having higher education?
Task 2. Bring things together Merge all the data in a single table containing students from both schools and the relative transcript data.
Question: What is the total number of students in both schools?
Fill the gaps: The feature with the highest coefficient is ____. Applied on the test data, the linear regression shows a mean absolute error of ___.
Task 4. Linear Regression Train a linear regresion model to fit the grade_final category. Partition 70-30 with random seed 1. Apply the model to the test data and evaluate its performance.
Question: Which of the following nodes can be used to replace the education index?
Question: For which of the following students there is no transcript available?
transcript.csv
CSV Reader
CSV Reader
DB Table Selector
DB Table Selector
DB Joiner
students.sqlite
SQLite Connector
DB Reader

Nodes

Extensions

Links