0dust / resumefilter

Extracting relevant information from resume using deep learning.

Hi there 👋

• 💼 Works at Microsoft
• 💬 Ask me anything!

resumefilter's Issues

Use transformers

LSTM's are pretty old now, let's try to use transformer models for extracting information.

Tkinter issue

Hello ,

I am getting the issue with Tkinter , when we run python create_training.py in the console.
I am running in amazon ec2 linux instance and it don't have GUI.
Any alternative way we can do it?

Thanks,
Suhas

Add support for Gitpod

Having Gitpod will make it easier to checkout the project rather than first having to mess up with installation.

Process of Training

Hi @0dust ,
I had clone your repository and tried to execute the problem i didn't find any issues or dependency related to the code but i just made some changes in training data added 1000 sample resumes and did training and i changed to 150 epochs i got an accuracy of 0.5 and then i did the prediction of some sample resumes but i haven't the related info like name,email,mobile no,skills ,experience like may i know the issue what i am facing..

Note: while training process its showing like Train on 51 samples, validate on 22 samples
may i know the reason and can you help me in this to get the related info like experience from thge resume ...

Thanks and Regards,
Manikantha Sekhar...

H5Py error

Hi my name is Priya.
I am new to Python. When I try to run this program,
after running the Create_training where is the file stored? cant find Trained_Model folder.
My CVs are getting extracted and after running Create_training and the new window opens for every CV. Do i need to close all windows?

And i am getting a H5py warning when i run Start_training.py. below is the error . Please help

2020-08-12 12:54:18.552284: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
C:\Users\priya\anaconda3\envs\resumefilter\lib\site-packages\h5py_init_.py:40: UserWarning: h5py is running against HDF5 1.10.5 when it was built against 1.10.4, this may cause problems
'{0}.{1}.{2}'.format(*version.hdf5_built_version_tuple)
Warning! HDF5 library version mismatched error
The HDF5 header files used to compile this application do not match
the version used by the HDF5 library to which this application is linked.
Data corruption or segmentation faults may occur if the application continues.
This can happen when an application was compiled by one version of HDF5 but
linked with a different version of static or shared HDF5 library.
You should recompile the application or check your shared library related
settings such as 'LD_LIBRARY_PATH'.
You can, at your own risk, disable this warning by setting the environment
variable 'HDF5_DISABLE_VERSION_CHECK' to a value of '1'.
Setting it to 2 or higher will suppress the warning messages totally.
Headers are 1.10.4, library is 1.10.5
SUMMARY OF THE HDF5 CONFIGURATION
=================================

General Information:

               HDF5 Version: 1.10.5
              Configured on: 2019-03-04
              Configured by: Visual Studio 15 2017 Win64
                Host system: Windows-10.0.17763
          Uname information: Windows
                   Byte sex: little-endian
         Installation point: C:/Program Files/HDF5

Storing the output of predict.py to a textfile

Is there any way to store the output obtained from predict.py. At present we can see the output in the console. Please help me in doing this

docx PackageNotFoundError

@0dust When I want to run create_training_data I get a ModuleNotFound Error that says that docx doesn't exist. When I want to install:

PackagesNotFoundError: The following packages are not available from current channels:

• docx

Current channels:

• https://repo.anaconda.com/pkgs/main/win-64
• https://repo.anaconda.com/pkgs/main/noarch
• https://repo.anaconda.com/pkgs/r/win-64
• https://repo.anaconda.com/pkgs/r/noarch
• https://repo.anaconda.com/pkgs/msys2/win-64
• https://repo.anaconda.com/pkgs/msys2/noarch
  `
  Where is the problem?

Unable to move down the pop-up to tag each resume

Hi,
I am unable to go down to the resume to tag them since i am unable to drill down. I am only able to see till line 22 of each resume since upto line 22 is only be adjusted into my monitor screen.

Please suggest me the solution.

NameError: name '__file__' is not defined

import os
import sys
from tkinter import *
import tkinter.font as tkFont
import pandas as pd
sys.path.append(os.path.dirname(file))
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(file), '..')))
from read_input import read_docx_and_pdf
.
.
.
.
And then last is
if name == 'main':
main()

Issue in start_training

python3 start_training.py
2024-04-24 18:27:39.079680: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2024-04-24 18:27:39.079914: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-04-24 18:27:39.082191: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-04-24 18:27:39.110750: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-04-24 18:27:39.578656: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
###################### Training for line label ###########################
ready to fit training data..
shape of x_train,x_test,y_train,y_test>> (51, 11) (22, 11) (51, 5) (22, 5)
loading embeddings...
/home/lenovo3/resume-parsing/ResumeFilter-master/data/glove.6B/glove.6B.50d.txt
Glove.6B.zip is being downloaded>>>>

it stuck here