#########################################################################################
#########################################################################################
Presenting 2 projects from totally different domains in order to showcase that the same underlying principles of Supervised ML can be applied for diverse problems!
This repository is comprised of 5 different Supervised ML algorithms applied on 2 datasets, namely:
- ExoPlanet Identification Original Dataset URL: https://exoplanetarchive.ipac.caltech.edu/cgi-bin/TblView/nph-tblView?app=ExoTbls&config=cumulative Website: https://www.nasa.gov/mission_pages/kepler/overview/index.html https://exoplanets.nasa.gov/
Problem Statement 1: Identify if the data recieved for a given celestial object does represent characterstics of being an ExoPlanet.
- Wine Quality Prediction Original Dataset URL: https://archive.ics.uci.edu/ml/datasets/wine+quality
Problem Statement 2: Predict the quality rating for a given wine (& associated characterstics) on a scale of 1 to 10.
I have done data pre-processing (Changing names, handling missing values etc.) on the original dataset above and saved the .csv files in this repository.
These are the five Python 3.x files for each dataset (I have used Microsoft Visual Studio Python IDE to build and execute my code):
- DecisionTreeWithCurves1, DecisionTreeWithCurves2
- BoostingWithCurves1, BoostingWithCurves2
- KNNWithCurves1, KNNWithCurves2
- SVMWithCurves1, SVMWithCurves2
- NeuralNetworkWithCurve1, NeuralNetworkWithCurve2
Note: Please update the code to get the address of the saved .csv data files in your personal computer that I have attached in my repository and then run the code.
Dependencies: Install the following python libraries: Numpy, Pandas, Matplotlib, Scikitlearn
Supervised ML Algorithms used:
-Decision Trees
-Boosting Mechanism
-K-Nearest Neghebours
-Support Vector Machines
-Neural Networks