Home » Kaggle Solution: What’s Cooking ? (Text Mining Competition)

# Kaggle Solution: What’s Cooking ? (Text Mining Competition)

• Gokul says:

Hi Manish,

Good Work.
Very Nice step by step narration on “Cooking” Competition.
How you obtained “Score – 0.798″? have you tried with Confusion matrix?.
Because I slightly altered the code & getting Score > 0.798”.

• Analytics Vidhya Content Team says:

As you could see from my approach, I simply used feature engineering and ml algorithm. I am sure there is huge scope of improvement in this score. I appreciate that you are getting a better score. What changes did you make?

• Uday Singh says:

Hi Manish,

Thanks for the tutorial, I would like listen more on Neural Network and Deep Learning by your way to describe each part step by step.

Thanks and Regards

Uday Singh

• Analytics Vidhya Content Team says:

• Swaty says:

Dear Manish,

New to Data Analytics. Really nice explanation.

• Analytics Vidhya Content Team says:

Thank You !

• Jatin Sharma says:

Hi Manish,
Thanks for this great piece of work.I am having some problems,and I would be grateful if you could have a look at them.

We used removeSparseTerms and removed all those ingredients occurring 3 or less than 3 times.Looking at the table,there are 567 ingredients repeating once,295 twice and 168 thrice.So only these ingredients should be getting removed and stored in the variable “sparse”.But the dimensions of sparse shows there are 1967 columns(ingredients).But shouldnt 567+295+168=1033 elements be deleted?

• Vedant Gupta says:

Hi Manish,
I have trying out the What’s Cooking competition and your tutorial is being of great help.
But I can’t figure out what is the command below attemting?
I would be really grateful if you can help me.

newsparse\$cuisine <- as.factor(c(train\$cuisine, rep('italian', nrow(test))))

• Siva says:

Hi I have a doubt..While attempting this kaggle competition now..Is it possible to get the cuisine of test set..How to validate the accuracy of the model that we develop?