Supervised ML of Adorable Fuzzy Possums from Australia
Challenge description:
You are a biologist researching possums from Australia and, after months of observations in the wild, you have finished collecting data that describes this animal mostly by its body dimensions (e.g., tail length, skull width, chest width, etc). Your initial task is to create a dashboard that visually explores the collected data. Next, define a supervised machine learning pipeline to pre-process the data, and train and score:
A regression algorithm of your choice to predict the total length of a possum using the different body dimensions. Target column: totlngth.
A classification algorithm of your choice to classify the location (Victoria or other) where the possum population was observed. Include only the possum's body dimensions with the exception of totlngth. Target column: Pop.
Clearly, after so many months of work in the field, you want to obtain predictions that are as accurate as possible.
Key requirement: you must score your models both visually and using numeric metrics.
Outcome:
A dashboard for data exploration and a supervised machine learning pipeline for data preprocessing, training and scoring of a regression and a classification algorithm.
Deliver your solution as a separate workflow and name it: Solution_Round_16_<your_team_name>. Place your solution workflow in the same folder of this challenge workflow.
Teams are strongly encouraged to submit high-quality work in order to improve their chances of getting maximum points. Don't be afraid to go the extra mile! :)
Dataset:
Provided in challenge folder.
Deadline:
March 10, 2024 (submission by 11:59 PM CET) **. Check the calendar of the tournament: https://info.knime.com/game-of-nodes
** We will verify the date and time of the latest edits.
KNIME Game of Nodes:
Rules, Assessment Criteria & FAQs: https://info.knime.com/game-of-nodes
Challenge description:
You are a biologist researching possums from Australia and, after months of observations in the wild, you have finished collecting data that describes this animal mostly by its body dimensions (e.g., tail length, skull width, chest width, etc). Your initial task is to create a dashboard that visually explores the collected data. Next, define a supervised machine learning pipeline to pre-process the data, and train and score:
A regression algorithm of your choice to predict the total length of a possum using the different body dimensions. Target column: totlngth.
A classification algorithm of your choice to classify the location (Victoria or other) where the possum population was observed. Include only the possum's body dimensions with the exception of totlngth. Target column: Pop.
Clearly, after so many months of work in the field, you want to obtain predictions that are as accurate as possible.
Key requirement: you must score your models both visually and using numeric metrics.
Outcome:
A dashboard for data exploration and a supervised machine learning pipeline for data preprocessing, training and scoring of a regression and a classification algorithm.
Deliver your solution as a separate workflow and name it: Solution_Round_16_<your_team_name>. Place your solution workflow in the same folder of this challenge workflow.
Teams are strongly encouraged to submit high-quality work in order to improve their chances of getting maximum points. Don't be afraid to go the extra mile! :)
Dataset:
Provided in challenge folder.
Deadline:
March 10, 2024 (submission by 11:59 PM CET) **. Check the calendar of the tournament: https://info.knime.com/game-of-nodes
** We will verify the date and time of the latest edits.
KNIME Game of Nodes:
Rules, Assessment Criteria & FAQs: https://info.knime.com/game-of-nodes