Blood-Transfusion-Service-Centre

To use the Data Science algorithms finding out the best prediction algorithm for the Blood Transfusion Service Centre UCI data set.

Blood transfusion saves lives - from replacing lost blood during major surgery or a serious injury to treating various illnesses and blood disorders. Ensuring that there's enough blood in supply whenever needed is a serious challenge for the health professionals. According to WebMD, "about 5 million Americans need a blood transfusion every year".

AIM: To use multinomial data set to visualise the best used method or model

1 Import

2 Feature Selection Technique

3 Data visualisation

4 Resampling

5 Spliting transufition data into train and test

6 Graphical Representation

6.1 Heatmaps

6.2 Histogram

6.2.1 BOXCOX

6.2.2 SQUARE ROOT

6.2.3 LOG

6.3 Violin plot

7 Models:

7.1 Logistic Regression -- 1

7.2 Random Forest -- 2

7.3 Decision Tree -- 3

7.4 Gaussian Naive Base -- 4

7.5 KNeighbors -- 5

7.6 SVM -- 6

7.7 ADaBoost -- 7

7.8 Gradient Boosting -- 8

7.9 Bagging -- 9

8 Model analysis

9 Model Graphical Representation

10 MAX Voting

10.1 Method 1

10.2 Method 2

11 Pickling