I have a set of data as below, where I am studying using Python (
sklearn) what are the 3 top features affecting a
Id,Cook_Temp_C,Cook_Time_Min,Ingredients_Count,Salt_Level_g,Meat_Freshness,Food_Taste(Bad:0,OK:1,Good:2) 0,40,15,5,3,0,1 1,28,5,7,3,1,2 2,43,15,4,2,0,0 3,48,20,5,3,1,0 4,22,7,8,3,1,2 5,25,8,6,3,1,2 6,34,13,6,1,1,0 7,30,8,8,1,1,2 8,11,11,5,2,0,1 9,15,16,6,1,1,0
After fitting e.g using
RandomForestClassifier(), the Feature Importance returns
Meat_Freshness as the 3 most important features.
Now, I am trying to answer the below research question,
What are the value ranges for
Meat_Freshness that statistically contributed for a good Food_Taste (Good:2) ?
Possible Expected Result:
Cook_Temp_C = [22,25,28,30] Cook_Time_Min = [5,7,8,8] Meat_Freshness = 
The above result basically concludes if a person like to have a good meal, he need to cook a fresh meat in anyway he likes between 5-8 minutes within 22-30ºC.
Would you be able to guide me on how to go about approaching this research question?
Is there any library in sklearn or otherwise that able to get this information? Any additional information such as confidence interval, outliers etc. is a bonus.