Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Extract Info #34

Open
mady143 opened this issue Mar 12, 2020 · 11 comments
Open

Extract Info #34

mady143 opened this issue Mar 12, 2020 · 11 comments

Comments

@mady143
Copy link

mady143 commented Mar 12, 2020

Hi @OmkarPathak @dazzag24 ,
I had clone your data and started parsing the resume but i found some difficulty in extracting the experience and company names can you tell how it works from utils.py file from the functions extract_experience and extract_competencies
and actually for parsing i had given my resume in that i mentioned as experience and company as side headings but also i was unable to get it

Thanks and Regards,
Manikantha Sekhar

@OmkarPathak
Copy link
Owner

@mady143 yes it is very difficult to parse experience and company names. The model that we have trained is not yet accurate in extracting these entities. If you want, you can train your model and then try the same

@mady143
Copy link
Author

mady143 commented Mar 12, 2020

@OmkarPathak okay how to train the model is their any training process in existing code
and
also i was unable to print the data from the some other functions which are in different files only getting the prints from views.py can you explain me y?

Thanks and Regards,
Manikantha Sekhar

@OmkarPathak
Copy link
Owner

OmkarPathak commented Mar 12, 2020

@mady143

okay how to train the model

There are these two files: train and test.
Your training data should be in the format like this

also i was unable to print the data from the some other functions which are in different files only getting the prints from views.py can you explain me y?

can you elaborate this issue?

@mady143
Copy link
Author

mady143 commented Mar 16, 2020

Hi @OmkarPathak ,
I had done training process like ,
(my_resume_pyresparser) manikantha@Manikantha-PC:~/Downloads/pyresparser/pyresparser$ python custom_train.py
Created blank 'en' model
Creating new pipe
Starting iteration 0
Losses {'ner': 83948.83401187272}
Starting iteration 1
Losses {'ner': 50266.19444030836}
Starting iteration 2
Losses {'ner': 43155.15530648954}
Starting iteration 3
Losses {'ner': 40022.855776749966}
Starting iteration 4
Losses {'ner': 34466.00632723602}
Starting iteration 5
Losses {'ner': 34260.82662641417}
Starting iteration 6
Losses {'ner': 32415.686345038288}
Starting iteration 7
Losses {'ner': 30070.207913930943}
Starting iteration 8
Losses {'ner': 28438.445806700598}
Starting iteration 9
Losses {'ner': 28697.96626680234}
Starting iteration 10
Losses {'ner': 24849.52654336362}
Starting iteration 11
Losses {'ner': 25142.6057196642}
Starting iteration 12
Losses {'ner': 24079.14422368379}
Starting iteration 13
Losses {'ner': 24257.180968177847}
Starting iteration 14
Losses {'ner': 23090.409918362162}
Starting iteration 15
Losses {'ner': 23996.485883846104}
Starting iteration 16
Losses {'ner': 23423.123708186868}
Starting iteration 17
Losses {'ner': 20781.21235375348}
Starting iteration 18
Losses {'ner': 20025.49499945144}
Starting iteration 19
Losses {'ner': 19859.159115096158}
Starting iteration 20
Losses {'ner': 19835.303925276472}
Starting iteration 21
Losses {'ner': 17874.102371228983}
Starting iteration 22
Losses {'ner': 18699.1655548761}
Starting iteration 23
Losses {'ner': 18402.408249338278}
Starting iteration 24
Losses {'ner': 17600.381271163213}
Starting iteration 25
Losses {'ner': 17745.068060417587}
Starting iteration 26
Losses {'ner': 17847.67826112547}
Starting iteration 27
Losses {'ner': 16500.602022483115}
Starting iteration 28
Losses {'ner': 17123.114352572746}
Starting iteration 29
Losses {'ner': 17659.68112649223}
Entities in 'Marathwada Mitra Mandals College of Engineering'
Name Marathwada Mitra Mandals College of Engineering
Saved model to /home/manikantha/Downloads/pyresparser/pyresparser
Loading from /home/manikantha/Downloads/pyresparser/pyresparser
Name Marathwada Mitra Mandals College of Engineering
and later i run custom_t.py
as
(my_resume_pyresparser) manikantha@Manikantha-PC:~/Downloads/pyresparser/pyresparser$ python custom_t.py
i am getting {} empty dict
so can you tell me how to resolve the issue...

Thanks and Regards,
Manikantha Sekhar..

@mady143
Copy link
Author

mady143 commented Mar 16, 2020

Hi @OmkarPathak
actually i used pyresparser to extract the Resume and get the data from that though i am getting the all required data like
name,
email,
mobile_number,
education(degree)
designation,
and skills
but in this also missing the experience so how can i get the experience can you explain me

Thanks and Regrads,
Manikantha Sekhar...

@mady143
Copy link
Author

mady143 commented Mar 16, 2020

Hi @OmkarPathak ,
I had done training process like ,
(my_resume_pyresparser) manikantha@Manikantha-PC:~/Downloads/pyresparser/pyresparser$ python custom_train.py
Created blank 'en' model
Creating new pipe
Starting iteration 0
Losses {'ner': 83948.83401187272}
Starting iteration 1
Losses {'ner': 50266.19444030836}
Starting iteration 2
Losses {'ner': 43155.15530648954}
Starting iteration 3
Losses {'ner': 40022.855776749966}
Starting iteration 4
Losses {'ner': 34466.00632723602}
Starting iteration 5
Losses {'ner': 34260.82662641417}
Starting iteration 6
Losses {'ner': 32415.686345038288}
Starting iteration 7
Losses {'ner': 30070.207913930943}
Starting iteration 8
Losses {'ner': 28438.445806700598}
Starting iteration 9
Losses {'ner': 28697.96626680234}
Starting iteration 10
Losses {'ner': 24849.52654336362}
Starting iteration 11
Losses {'ner': 25142.6057196642}
Starting iteration 12
Losses {'ner': 24079.14422368379}
Starting iteration 13
Losses {'ner': 24257.180968177847}
Starting iteration 14
Losses {'ner': 23090.409918362162}
Starting iteration 15
Losses {'ner': 23996.485883846104}
Starting iteration 16
Losses {'ner': 23423.123708186868}
Starting iteration 17
Losses {'ner': 20781.21235375348}
Starting iteration 18
Losses {'ner': 20025.49499945144}
Starting iteration 19
Losses {'ner': 19859.159115096158}
Starting iteration 20
Losses {'ner': 19835.303925276472}
Starting iteration 21
Losses {'ner': 17874.102371228983}
Starting iteration 22
Losses {'ner': 18699.1655548761}
Starting iteration 23
Losses {'ner': 18402.408249338278}
Starting iteration 24
Losses {'ner': 17600.381271163213}
Starting iteration 25
Losses {'ner': 17745.068060417587}
Starting iteration 26
Losses {'ner': 17847.67826112547}
Starting iteration 27
Losses {'ner': 16500.602022483115}
Starting iteration 28
Losses {'ner': 17123.114352572746}
Starting iteration 29
Losses {'ner': 17659.68112649223}
Entities in 'Marathwada Mitra Mandals College of Engineering'
Name Marathwada Mitra Mandals College of Engineering
Saved model to /home/manikantha/Downloads/pyresparser/pyresparser
Loading from /home/manikantha/Downloads/pyresparser/pyresparser
Name Marathwada Mitra Mandals College of Engineering
and later i run custom_t.py
as
(my_resume_pyresparser) manikantha@Manikantha-PC:~/Downloads/pyresparser/pyresparser$ python custom_t.py
i am getting {} empty dict
so can you tell me how to resolve the issue...

Thanks and Regards,
Manikantha Sekhar..

I resolved this issue by increasing the iterations so at first i tried for 30 then empty dict as an output and later i was tried for 50 then i got the output a little bit so their is an issue to resolve is increase the iterations

@mady143
Copy link
Author

mady143 commented Mar 17, 2020

Hi @OmkarPathak ,
How can i link the train and test to this folder to get the accurate experience of the candidate in the resume and display in the browser

screen1001

in the above image i have to display the experience also before training and testing i was unable to get the experience so i remove the experience column
but now i am running the training and testing files from another github code Pyreparser (https://github.com/OmkarPathak/pyresparser) so i how could i put these files in https://github.com/OmkarPathak/ResumeParser/ in this project

please help me in this

Thanks & Regards,
Manikantha Sekhar..

@OmkarPathak
Copy link
Owner

OmkarPathak commented Mar 18, 2020

@mady143 you can do it using python setup.py install. This will install pyresparser using your pre-trained model. Make sure you uninstall previously installed version or else install your trained pyresparser into an entirely new environment

@mady143
Copy link
Author

mady143 commented Mar 18, 2020

@OmkarPathak ,
https://github.com/OmkarPathak/pyresparser how can i test these code through UI to get the result as like your previous code in https://github.com/OmkarPathak/ResumeParser/ to get the experience and company names....

@OmkarPathak
Copy link
Owner

@mady143 for that you need the knowledge of django. You can add you're fields in views.py and then render them in template

@mady143
Copy link
Author

mady143 commented Apr 1, 2020

Hi @OmkarPathak ,
Actually i am developing a module to match the job description we have to get the matched resume and also matches the experience though for that i had used pyresparser package for that in some cases or some resume i am getting the total_experience as 4.7 like that but missing the experience but giving the content with month year its unable to calculate the overall years
can you explain in a simple way either with training process or as in normal way can you help me in this or you can given any related links which matches for my requirement...

Thanks and Regards,
Manikantha Sekhar...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants