Breast Cancer Identification from Patients’ Tweet Streaming Using Machine Learning Solution on Spark

Table 4

Results of models were applied on the selected features by RFECV.

Model	Accuracy of cross-validation (%)	Accuracy of unseen data (%)	Best value of parameters
LR	99.5	98.8	regPram: 0.1; maxIter: 20
DT	98.6	91.2	imprity: gini; maxDepth: 5; maxBins: 32
SVM	98.9	98.5	regParam: 0.02; maxIter: 50; Kernal type: Liner
RF	100	99.1	maxDepth: 7; maxBins: 32; numTrees: 20