The project is on Measuring the Productivity of Construction labour like who is doing productive work and who is doing non-productive or skipping the work
Real Challenge is that before splitting the data x=columns i have taken
X = Age, Gender, galvanic Skin Response Sensor , skin Temperature Sensor , blood Volume Pulse , Respiration Rate Sensor , Heart Rate Sensor, Motion Sensor
Y = Performance/Output
and Spliiting into train_test_split
in which train_size=0.80, and test_size=0.20
and Model Building to know the Test Accuracy
and those are the test accuracies
|Model|Score|
|3|Decision Tree|0.982143|
|4|Random Forest|0.946429|
|0|KNN|0.857143|
|2|Support Vector Machine|0.857143|
|6|ANN|0.857143|
|5|XgBoost|0.839286|
|1|logistic regression|0.821429|
|7|Naive Bayes Classifier|0.732143|
in which taking the decision tree Classifier model becoz it is giving the best accuracy and
Dumping it into joblib file
i Don’t know how to create the Streamlit_app.py
for deploying the app