Spaces:
Sleeping
Sleeping
File size: 2,757 Bytes
4736ae1 4e8b885 4736ae1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import streamlit as st
from huggingface_hub import hf_hub_download
from model import JobFakeModel
import torch
import torch.nn.functional as F
from data_processing import get_tokens
import numpy as np
import time
def get_model_list():
model_name = "sebastiansarasti/fakeJobs"
filename = "best_model.pth"
file_path = hf_hub_download(repo_id=model_name, filename=filename)
return file_path
def load_model(path):
model = JobFakeModel(base_model="distilbert", freeze_base=True)
model.load_state_dict(torch.load(path, device="cpu"))
return model
st.title('Fake Jobs Streamlit App')
st.write('This is a fake jobs streamlit app')
# download the model
path = get_model_list()
model = load_model(path)
with st.sidebar:
st.subheader('About the App')
st.markdown('Data used for the training come from the following source: https://www.kaggle.com/datasets/shivamb/real-or-fake-fake-jobposting-prediction')
st.empty()
st.subheader('Author')
st.markdown('Sebastián Sarasti Zambonino')
st.markdown('Data Scientist - Machine Learning Engineer')
st.markdown('https://www.linkedin.com/in/sebastiansarasti/')
st.markdown('https://github.com/sebassaras02')
# Create columns for the inputs
col1, col2, col3 = st.columns(3)
with col1:
# Create an input text box for the description
description = st.text_area('Description', 'Enter the job description here')
with col2:
# Create an input text box for the requirements
requirements = st.text_area('Requirements', 'Enter the job requirements here')
with col3:
# Create an input text box for the benefits
benefits = st.text_area('Benefits', 'Enter the job benefits here')
# if benefits is none, set it to an empty nothing
if benefits is None:
benefits = 'Nothing'
elif requirements is None:
requirements = 'Nothing'
elif description is None:
raise ValueError('Description cannot be empty')
# Create a button to submit the job
with st.spinner('Wait for it...'):
time.sleep(2)
if st.button('Submit Job'):
tokens_des = get_tokens(description)
tokens_req = get_tokens(requirements)
tokens_ben = get_tokens(benefits)
model.eval()
with torch.no_grad():
output = model(tokens_des, tokens_req, tokens_ben)
# calculate the probability
output = F.sigmoid(output).item()*100
# Create a box to show the result
st.metric('Fake Job Probability', f"{np.round(output, 5)}%")
if output > 75:
st.error('⚠️ High probability of being a fake job!')
elif output > 50:
st.warning('⚠️ Medium probability of being a fake job')
else:
st.success('✅ Low probability of being a fake job') |