Drug Review - Data Mining

It has been used for final project of Data Mining course in UNIGE.

AdaBoost, LightGBM, XGBoost, Naive Bayes and Logistic Regression machine learning models have been applied.

AdaBoost

The Accuracy of the model is : 0.7558573284714364
The confusion Matrix is
[[ 5534 8651]
[ 2999 30534]]
The classification results are

target	precision	recall	f1-score	support
0	0.65	0.39	0.49	14185
1	0.78	0.91	0.84	33533
avg / total	0.74	0.76	0.73	47718

LightGBM

The Accuracy of the model is : 0.8331237688084161
The confusion Matrix is
[[ 9109 5076]
[ 2887 30646]]
The classification results are

target	precision	recall	f1-score	support
0	0.76	0.64	0.70	14185
1	0.86	0.91	0.89	33533
avg / total	0.83	0.83	0.83	47718

XGBoost

The Accuracy of the model is : 0.7810888972714699
The confusion Matrix is
[[ 6703 7482]
[ 2964 30569]]
The classification results are

target	precision	recall	f1-score	support
0	0.69	0.47	0.56	14185
1	0.80	0.91	0.85	33533
avg / total	0.77	0.78	0.77	47718

Naive Bayes

The Accuracy of the model is : 0.7220964835072718
The confusion Matrix is
[[ 6218 7967]
[ 5294 28239]]
The classification results are

target	precision	recall	f1-score	support
0	0.54	0.44	0.48	14185
1	0.78	0.84	0.81	33533
avg / total	0.71	0.72	0.71	47718

Logistic Regression

The Accuracy of the model is : 0.7448342344607904
The confusion Matrix is
[[ 4133 10052]
[ 2124 31409]]
The classification results are

target	precision	recall	f1-score	support
0	0.66	0.29	0.40	14185
1	0.76	0.94	0.84	33533
avg / total	0.73	0.74	0.71	47718