data analysis

missing values

1. visualizing missing values.

   
   

2. imputing data set selection.(the picture is very important.)

   
   

3. just few missing values by particular model

   
   
   

4. predicting values based on other variables

   
   

model testing

1. OOB error

The black line shows the overall error rate which falls below 20%. The red and green lines show the error rate for ‘died’ and ‘survived’ respectively.

2. RMSE

   
   
   LASSO MODEL
   THE MOST POPULAR ALGORITHM
   

   THEN WE COULD COMPARE THEM BY RMSE AS FOLLOWS

   
   

variable importance

variable selecting

1. Boruta Feature Importance Analysis
2. Plotting all data
3. Explore the correlation
   

4. Plot scatter plot for variables that have high correlation.(the same link as 3th)

   
   
   
5. some useful plot