Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/pradipece/insurance_data_analysis_ml

This project approach defines the terms machine learning and linear regression ML algorithm in the context of real-time problem-solving.
https://github.com/pradipece/insurance_data_analysis_ml

data-science data-visualization database machine-learning matplotlib numpy pandas python python3

Last synced: 12 days ago
JSON representation

This project approach defines the terms machine learning and linear regression ML algorithm in the context of real-time problem-solving.

Awesome Lists containing this project

README 

        
### Overview



This project consists of the following topics:



- Understanding the machine learning algorithms exploring the dataset

- Linear regression using Scikit-learn and adding some of the multiple features

- Using categorical features for machine learning and analysis of the data

- Regression coefficients and feature importance

- Other models and techniques for regression model using Scikit-learn

- Applying linear regression to other datasets



### Problem Statement



This approach defines the terms _machine learning_ and _linear regression_ in the context of a problem, and later generalizes their definitions:



> **QUESTION**: ACME Insurance Inc. offers affordable health insurance to thousands of customers in the United States. As the lead data scientist at ACME, **This tasked with creating an automated system to estimate the annual medical expenditure for new customers**, using information such as their age, sex, BMI, children, smoking habits, and region of residence.

>

> Estimates from the system regulatory requirements will determine the annual insurance premium (per month amount paid) offered to the customer.

>

> You're given a [CSV file](https://raw.githubusercontent.com/JovianML/opendatasets/master/data/medical-charges.csv) containing verified historical data, consisting of the aforementioned information and the actual medical charges incurred by over 1300 customers.

> 

>

> Dataset source: https://github.com/stedy/Machine-Learning-with-R-datasets



### Machine Learning



Congratulations, you've just trained your first _machine learning model!_ Machine learning is simply the process of computing the best parameters to model the relationship between some feature and targets.



Machine learning problem has three components:



1. **Model**



2. **Cost Function**



3. **Optimizer**



We'll look at several examples of each of the above in future tutorials. Here's how the relationship between these three components can be visualized:






### Categorical Features ML



Using only numeric columns, and perform computations with numbers. The categorical columns such as "smoker", train a single model for the entire dataset.

For the conversion three common techniques are:



1. If a categorical column has just two categories (it's called a binary category), then we can replace their values with 0 and 1.

2. If a categorical column has more than 2 categories, we can perform one-hot encoding i.e. create a new column for each category with 1s and 0s.

3. If the categories have a natural order (e.g. cold, neutral, warm, hot), then they can be converted to numbers (e.g. 1, 2, 3, 4) preserving the order is called ordinals



### One-hot Encoding



The "region" column contains 4 values, so we'll need to use hot encoding and create a new column for each region.



![](https://i.imgur.com/n8GuiOO.png)



### How to Approach a Machine Learning Problem



Here's a strategy you can apply to approach any machine learning problem:



1. Explore the data and find correlations between inputs and targets

2. Pick the right model, loss functions and optimizer for the problem at hand

3. Scale numeric variables and one-hot encode categorical data

4. Set aside a test set (using a fraction of the training set)

5. Train the model

6. Make predictions on the test set and compute the loss



Finally, Apply this process to several problems for ML.



## Conclusions



Covered the following topics in this project



- A typical problem statement for machine learning

- Downloading and exploring a dataset for machine learning

- Linear regression with one variable using Scikit-learn

- Linear regression with multiple variables

- Using categorical features for machine learning

- Regression coefficients and feature importance

- Creating a training and test set for reporting results



### Reference



Apply the techniques of ML



- https://www.kaggle.com/vikrishnan/boston-house-prices

- https://www.kaggle.com/sohier/calcofi

- https://www.kaggle.com/budincsevity/szeged-weather



Check out the following links to learn more about linear regression:



- https://jovian.ai/aakashns/02-linear-regression

- https://www.kaggle.com/hely333/eda-regression