Trjtdtk

What *exactly* is electrical current, voltage, and resistance?

How to have a sharp product image?

Suing a Police Officer Instead of the Police Department

Is Electric Central Heating worth it if using Solar Panels?

Protagonist's race is hidden - should I reveal it?

How long after the last departure shall the airport stay open for an emergency return?

Implementing 3DES algorithm in Java: is my code secure?

Mistake in years of experience in resume?

Does Mathematica have an implementation of the Poisson binomial distribution?

Double-nominative constructions and “von”

Why didn't the Space Shuttle bounce back into space as many times as possible so as to lose a lot of kinetic energy up there?

Check if a string is entirely made of the same substring

Is accepting an invalid credit card number a security issue?

"Rubric" as meaning "signature" or "personal mark" -- is this accepted usage?

How to avoid introduction cliches

Contradiction proof for inequality of P and NP?

Are there moral objections to a life motivated purely by money? How to sway a person from this lifestyle?

How to keep bees out of canned beverages?

Air bladders in bat-like skin wings for better lift?

What is the ongoing value of the Kanban board to the developers as opposed to management

Approximating integral with small parameter

Multiple options vs single option UI

What is this word supposed to be?

How do I prove this combinatorial identity

Why am I getting accuracy of Xgboost model 0.00%?

1

$begingroup$

I am trying to build Job Recommender System using Deep Learning.

dataset used
From this dataset i have taken only users.tsv, user_history.tsv, apps.tsv and jobs.tsv to build a hybrid recommender system.

The steps i have performed till now are:

1. One hot encoding on this dataset


2. Embedding on one hot encoded features to reduce dimension and sparsity


3. Concatenated all the 4 datasets(Embedded matrix and non-categorical features of dataset)


4. Created Xgboost model for feature regularization

But I am getting accuracy of xgboost model equal to 0.00%. After this i also need to perform CNN to get the top-k recommendations, but since i am getting accuracy of xgboost model zero i cannot proceed further. So, please help me.

Google drive URL to my code:
code URL

deep-learning xgboost

share|improve this question

edited Apr 6 at 14:59

Aishwarya patil

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  Without the code, we will never know what you did? And one hot encoding and then Embedding??
  $endgroup$
  – Aditya
  Apr 6 at 7:15
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Obviously, we cannot say anything without looking at the code... Apart from that, please read this article about why you do not want to use one hot encoding with tree-based algorithms.
  $endgroup$
  – georg_un
  Apr 6 at 8:46
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Sorry, but now i have shared google drive link to my code in the description above. Please have a look at it. Reason for doing one hot encoding and embedding is i am trying to implement one Research Paper (which is also available on my drive) and i am completely new to this field so, Thank you
  $endgroup$
  – Aishwarya patil
  Apr 6 at 15:07
  

  
  
  
  

add a comment | 

1

$begingroup$

I am trying to build Job Recommender System using Deep Learning.

dataset used
From this dataset i have taken only users.tsv, user_history.tsv, apps.tsv and jobs.tsv to build a hybrid recommender system.

The steps i have performed till now are:

1. One hot encoding on this dataset


2. Embedding on one hot encoded features to reduce dimension and sparsity


3. Concatenated all the 4 datasets(Embedded matrix and non-categorical features of dataset)


4. Created Xgboost model for feature regularization

But I am getting accuracy of xgboost model equal to 0.00%. After this i also need to perform CNN to get the top-k recommendations, but since i am getting accuracy of xgboost model zero i cannot proceed further. So, please help me.

Google drive URL to my code:
code URL

deep-learning xgboost

share|improve this question

edited Apr 6 at 14:59

Aishwarya patil

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62

$endgroup$

• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  Without the code, we will never know what you did? And one hot encoding and then Embedding??
  $endgroup$
  – Aditya
  Apr 6 at 7:15
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Obviously, we cannot say anything without looking at the code... Apart from that, please read this article about why you do not want to use one hot encoding with tree-based algorithms.
  $endgroup$
  – georg_un
  Apr 6 at 8:46
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  Sorry, but now i have shared google drive link to my code in the description above. Please have a look at it. Reason for doing one hot encoding and embedding is i am trying to implement one Research Paper (which is also available on my drive) and i am completely new to this field so, Thank you
  $endgroup$
  – Aishwarya patil
  Apr 6 at 15:07
  

  
  
  
  

add a comment | 

$begingroup$

I am trying to build Job Recommender System using Deep Learning.

dataset used
From this dataset i have taken only users.tsv, user_history.tsv, apps.tsv and jobs.tsv to build a hybrid recommender system.

The steps i have performed till now are:

1. One hot encoding on this dataset


2. Embedding on one hot encoded features to reduce dimension and sparsity


3. Concatenated all the 4 datasets(Embedded matrix and non-categorical features of dataset)


4. Created Xgboost model for feature regularization

But I am getting accuracy of xgboost model equal to 0.00%. After this i also need to perform CNN to get the top-k recommendations, but since i am getting accuracy of xgboost model zero i cannot proceed further. So, please help me.

Google drive URL to my code:
code URL

deep-learning xgboost

share|improve this question

edited Apr 6 at 14:59

Aishwarya patil

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62

$endgroup$

share|improve this question

edited Apr 6 at 14:59

Aishwarya patil

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62

share|improve this question

edited Apr 6 at 14:59

Aishwarya patil

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62

asked Apr 6 at 5:32

Aishwarya patilAishwarya patil

62