Skip to content

harshraj11584/Human-Activity-Recognition-0.97-Kaggle

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Human-Activity-Recognition-Kaggle-0.97

Human Activity Recognition UCI Dataset [link], final score 0.97196

[Competition Link]

d_nn.ipynb first finds features with high correlation, drops them, then uses Sequential DNN for prediction.
Accuracy = 0.95443

Predictor.ipynb uses xgboost for classification, for different values of number of estimators and max depth.
Accuracy = 0.97196