File size: 7,022 Bytes
66b87c2 c21184b 3697a18 c21184b e1cd956 c21184b 3697a18 c21184b 66b87c2 c21184b 90a2c92 |
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 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from gliner import GLiNER
import plotly.express as px
import time
with st.sidebar:
st.button("DEMO APP", type="primary")
expander = st.expander("**Important notes on the AI-powered Resume Analysis based on Keywords App**")
expander.write('''
**Supported File Formats**
This app accepts files in .pdf formats.
**How to Use**
Paste the job description first. Then, upload the resume of each applicant to retrieve the results.
**Usage Limits**
For each applicant you can upload their resume and request results once (1 request per applicant's resume).
At the bottom of the app, you can also upload an applicant's resume once (1 request) to visualize their profile as a treemap chart as well as the results in a matrix heatmap. If you hover over the interactive graphs, an icon will appear to download them.
**Subscription Management**
This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own AI-powered Resume Analysis based on Keywords Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app within five business days. If you wish to delete your Account with us, please contact us at [email protected]
**File Handling and Errors**
The app may display an error message if your file is corrupt, or has other errors.
For any errors or inquiries, please contact us at [email protected]
''')
st.title("AI-powered Resume Analysis based on Keywords App")
st.divider()
job = pd.Series(st.text_area("Paste the job description and then press Ctrl + Enter", key="job_desc"), name="Text")
if 'applicant_data' not in st.session_state:
st.session_state['applicant_data'] = {}
max_attempts = 1
for i in range(1, 51):
st.subheader(f"Applicant {i} Resume", divider="green")
applicant_key = f"applicant_{i}"
upload_key = f"candidate_{i}"
if applicant_key not in st.session_state['applicant_data']:
st.session_state['applicant_data'][applicant_key] = {'upload_count': 0, 'uploaded_file': None, 'analysis_done': False}
if st.session_state['applicant_data'][applicant_key]['upload_count'] < max_attempts:
uploaded_file = st.file_uploader(f"Upload Applicant's {i} resume", type="pdf", key=upload_key)
if uploaded_file:
st.session_state['applicant_data'][applicant_key]['uploaded_file'] = uploaded_file
st.session_state['applicant_data'][applicant_key]['upload_count'] += 1
st.session_state['applicant_data'][applicant_key]['analysis_done'] = False
if st.session_state['applicant_data'][applicant_key]['uploaded_file'] and not st.session_state['applicant_data'][applicant_key]['analysis_done']:
pdf_reader = PdfReader(st.session_state['applicant_data'][applicant_key]['uploaded_file'])
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
with st.expander(f"See Applicant's {i} resume"):
st.write(text_data)
data = pd.Series(text_data, name='Text')
result = pd.concat([job, data])
vectorizer = TfidfVectorizer(stop_words = 'english')
tfidf_matrix = vectorizer.fit_transform(result)
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
for j, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
with st.popover(f"See Result for Applicant {i}"):
st.write(f"Similarity between Applicant's resume and job description based on keywords: {similarity_score:.2f}")
st.info(
f"A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's {i} resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's {i} resume and job description.")
st.session_state['applicant_data'][applicant_key]['analysis_done'] = True
else:
st.warning(f"Maximum upload attempts has been reached ({max_attempts}).")
if st.session_state['applicant_data'][applicant_key]['upload_count'] > 0:
st.info(f"Files uploaded for Applicant {i}: {st.session_state['applicant_data'][applicant_key]['upload_count']} time(s).")
st.divider()
st.subheader("Visualise Applicant's Profile", divider="blue")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 1
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader("Upload Applicant's resume", type="pdf", key="applicant 1")
if uploaded_files:
st.session_state['upload_count'] += 1
with st.spinner("Wait for it...", show_time=True):
time.sleep(2)
pdf_reader = PdfReader(uploaded_files)
text_data = ""
for page in pdf_reader.pages:
text_data += page.extract_text()
data = pd.Series(text_data, name='Text')
frames = [job, data]
result = pd.concat(frames)
model = GLiNER.from_pretrained("urchade/gliner_base")
labels = ["person", "country", "organization", "role", "skills"]
entities = model.predict_entities(text_data, labels)
df = pd.DataFrame(entities)
st.subheader("Applicant's Profile", divider = "orange")
fig = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig, key="figure 1")
vectorizer = TfidfVectorizer(stop_words = 'english')
tfidf_matrix = vectorizer.fit_transform(result)
tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
cosine_sim_matrix = cosine_similarity(tfidf_matrix)
cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
st.subheader("Similarity between Applicant's Profile and Job Description", divider = "orange")
fig = px.imshow(cosine_sim_df, text_auto=True,
labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume', 'Jon Description'],
y=['Resume', 'Job Description'])
st.plotly_chart(fig, key="figure 2")
else:
st.warning(f"Maximum upload attempts has been reached ({max_attempts}).")
if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")
|