personal/nunosempere.github.io
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Create readme.md

Browse Source
This commit is contained in:
Nuño Sempere 2019-10-09 20:53:29 +02:00 committed by GitHub
parent 0ee3fb2c8e
commit 5e4041502c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
maths-prog/MachineLearningDemystified/readme.md Normal file
View File

@ -0,0 +1,14 @@
# Machine Learning Demystified
Several friends encouraged me to apply to a Data Scientist position at ID Insights, an organization I greatly admire, and for a position which I would be passionate about.
Unfortunately, they require Python, and I'm more of a R programmer. I decided to apply anyways, but before, I familiarized myself throrougly with numpy, pandas and sklearn, three of the most important libraries for machine learning in Python.
I used a dataset from Kaggle [Health Care Cost Analysis](https://www.kaggle.com/flagma/health-care-cost-analysys-prediction-python/data), referenced as insurance.csv thoughout the code. The reader will also have to change the variable directory to fit their needs.
Otherwise, the current files in this directory are:
- [CleaningUpData.py](https://nunosempere.github.io/maths-prog/MachineLearningDemystified/CleaningUpData.py). I couldn't work with the dataset directly, so I tweaked it somewhat.
- [AlgorithmsClassification.py](https://nunosempere.github.io/maths-prog/MachineLearningDemystified/AlgorithmsClassification.py). As a first exercise, I try to predict whether the medical bills of a particular individual are higher than the mean of the dataset. Some algorithms, like Naïve Bayes, are not really suitable for regression, but are great for predicting classes.
- [AlgorithmsRegression,py](https://nunosempere.github.io/maths-prog/MachineLearningDemystified/AlgorithmsRegression,py). I try to predict the healthcare costs of a particular individual, using all the features in the dataset.