🤾‍♂️ Caloric Consumption

Problem Statement

Implement an AI/ML model to predict the caloric consumption of an activity given a training set train_data.csv and a test set test_data.csv (on which you only need to make predictions).

The dataset contains the following fields with their meanings:

• User_ID: ID of the user who performed the activity
• Gender: user's gender
• Age: user's age
• Height: user's height in cm
• Weight: user's weight in kg
• Duration: activity duration
• Heart_Rate: average heart rate during the activity
• Body_Temp: average temperature during the activity
• Calories: number of calories consumed during the activity (present only in the training dataset)

Notes about the dataset:

The target attribute is Calories. Given the other attributes, the goal is to predict Calories based on the test dataset. The evaluation metric used is MAE (mean absolute error between the value predicted by the algorithm and the correct value).

Requirements

Part 1 (20p). Based on the training dataset, calculate the following:

"Samples, No.Males, AverageDuration, SeniorUsers"

• Subtask 1: Samples: number of rows in the training dataset
• Subtask 2: No.Males: number of training examples that describe activities performed by men
• Subtask 3: AverageDuration: average duration of activities in the training set
• Subtask 4: SeniorUsers: number of users in the training set who are at least 75 years old

Each of the 4 subtasks is worth 5p.

Part 2 (80p)

• Subtask 5: (60p) Develop an AI/ML model and perform prediction for the Calories attribute for each example in the test data file, for which the Subtask column has the value 5.

• Subtask 6: (20p) A men's handball team needs to estimate caloric consumption to optimize the players' diet. Develop an AI/ML model and predict the number of calories for each example in the test data file for which the Subtask column has the value 6.

Output Format

A csv file output.csv that should include the following 3 columns:

• subtaskID - represents the subtask number (1, 2, 3, 4, 5 or 6)
• datapointID - which refers to the User_ID column from test_data.csv
• answer - the answer corresponding to the datapoint for the respective subtask

Note: For subtasks 1, 2, 3 and 4, which require a single answer for the entire dataset, display a single line whose datapointID should be 1.

Submit a single csv that contains the answers for all subtasks you have solved. To see an example, download the sample_output.csv file

👉 📦 Download Starter Kit OJIA 2025