Machine Learning Assignment:

Using Supervised Machine Learning to Predict In-Hospital Mortality Aim. To apply learned data exploration and machine learning skills to design. Also implement an end-to-end machine learning pipeline for predicting a binary outcomes from a highly dimensional real-world dataset. Indicative Timetable. The following table shows a breakdown of the activities for this week to help you in prioritizing your time schedule. The actual time needed to complete each task is dependent on your implementation/analysis speed and personal circumstances. The timetable available below is merely representative of the average time you need to complete each task and the time you need for each relative to other tasks.

The timetable is also available to ensure that you know that the assignment is time-consuming and requires thoughtful planning to complete all necessary tasks. Activity Tentative Duration Data Cleaning 2 Days Data Aggregation 3-4 Days Data Exploration & Visualization 2 Day Classifier Implementation &Hyper parameter Tuning4-5 Days Model Evaluation 2 Days Analysis and Reflection 2 Days Writing 3 Days Assignment Details Now that you have been equipped with the skills to use different Machine Learning algorithms, you will have the opportunity to practice and apply it to a practical problem using real-world hospital data extracted from the MIMIC-III database. The dataset consists of measurements of 25 laboratory test results and vital signs for 2670patients recorded over 48 hours.

Further Description

In this assignment, you will complete and submit a Jupiter notebook. Containing an end-to-end supervised learning pipeline using the XG Boost algorithm. To predict 30-day in-hospital mortality from aggregates of patient vital signs and laboratory test results given in the Pneumonia TimeSeries.csv dataset. Recap of Supervised Learning The majority of practical machine learning uses supervised learning. In supervised learning, an algorithm learns a function that maps input variables (X) to an output variable (y). I.e. y = f(X). The goal is to approximate the real underlying mapping so that you supply  the algorithm with unseen data. It can predict the output variables (y) for the new samples.

Supervised learning is called so because the process of an algorithm learning from the training dataset can be thought of as a teacher supervising the learning process. During supervised training, we know the correct answers; the algorithm iteratively makes predictions on the training data and one can correct it  by making updates. Learning stops when the algorithm achieves an acceptable level of performance. Supervision learning problems can be further group into regression and classification. Classification: A classification problem is when the output variable is a category, such as “red” and “blue” or “disease” and “no disease. Regression: A regression problem is when the output variable is a real value, such as “dollars” or “weight.”

Attached Files

Download  |