Classification:
	1. Classification_FynnWolf_XGBoost.txt: (Model: 327 kb)
	XGBoost tree for classification, no HP configuration 
	variables determined using Shap
	
	2.Classification_FynnWolf_LightGBM.txt: (Model: 348 kb)
	LightGBM tree for classification, HP optimization using Bayesian optimization, best value for max_depth=38 and min_sample_leafs=95
	variables determined using Shap

	3.Classification_FynnWolf_SKlearMLP.txt: (Model: 21 kb)
	Neural Network from SKlearn for classification, no HP optimization, early stopping
	variables from LightGBM were used

Regression:
	1.Regression_FynnWolf_LightGBM.txt: (Model: 292 kb)
	LightGBM tree for regression, HP optimization using Bayesian optimization, best value for max_depth=187 and min_sample_leafs=475
	variables determined using Shap

	2.Regression_FynnWolf_SKlearnRandomForrest.txt: (Model: 25 mb)
	Random forest from SKlearn, no HP optimization
	variables used from LightGBM 

	3.Regression_FynnWolf_TensorFlowKeras.txt: (Model: )
	Neural Network Keras on Tensorflow, no HP optimization, K-Fold test and early stopping,
	variables used from LightGBM 

Clustering:
	1.Clustering_FynnWolf_SKlearnKmean.txt: (Model: 651 kb)
	K-Means clustering from SKlearn, 3 cluster, result looks pretty bad, could not find a way to better it
	variables determined using permutation importance from SKlearn

	2.Clustering_FynnWolf_SKlearnBayesianGaussian.txt: (Model: 82 kb)
	Bayesian Gaussian mixture from SKlearn, 5 cluster, number of cluster determined by looking at weights, only took cluster over 1%,
	variables determined using permutation importance from SKlearn

	3.Clustering_FynnWolf_SKlearnGaussian.txt: (Model: 46 kb)
	Gaussian mixture from SKlearn, 3 cluster, tried BIC score to determine numbers of clusters, did not provide any useful information
	variables determined using permutation importance from SKlearn