File size: 7,513 Bytes
9ac410d 88d066d b65c592 2955054 b1ed479 2955054 b1ed479 2955054 b1ed479 2955054 b1ed479 2955054 b1ed479 0274b27 7b3f010 a1c7830 5196b87 caf704e ebf4966 0274b27 ebf4966 caf704e 0274b27 caf704e a1c7830 1e10cc9 a1c7830 6ae6756 a1c7830 0274b27 a1c7830 99f18bc a1c7830 2e1adec 924c1f2 5b290a2 924c1f2 a1c7830 924c1f2 a518d34 924c1f2 a1c7830 1e10cc9 a1c7830 924c1f2 a1c7830 eea17f0 446b3f9 eea17f0 99f18bc |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 |
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
with st.sidebar:
st.button("DEMO APP", type="primary")
expander = st.expander("**Important notes on the AI 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 your resume to retrieve the results. You can upload up to 10 resumes in total.
**Usage Limits**
You can request results up to 10 times in total.
**Subscription Management**
This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own AI 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]
**Customization**
To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
**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.subheader("Candidate Profile 1", divider="red")
txt = st.text_area("Paste the job description and then press Ctrl + Enter", key="text 1")
job = pd.Series(txt, name="Text")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 3
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume", accept_multiple_files=True, type="pdf", key="candidate 1"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
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", "date", "time", "role", "skills", "year"]
entities = model(text_data, labels=labels)
df = pd.DataFrame(entities)
st.subheader("Profile of candidate 1", divider="green")
fig1 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig1.update_layout(margin=dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig1, key = "Figure 1")
vectorizer = TfidfVectorizer()
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("Measuring similarity between keywords of candidate profile 1 and job description", divider="green")
fig2 = px.imshow(cosine_sim_df, text_auto=True,
labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Job Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig2, key = "Figure 2")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity of job description with candidate profile 1. {i + 1}: {similarity_score:.4f}")
st.info("A score closer to 1 (0.80, 0.90) means higher similarity between candidate profile 1 and job description. A score closer to 0 (0.20, 0.30) means lower similarity between candidate profile 1 and job description.")
else:
st.warning(f"You have reached the maximum upload attempts ({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).")
st.subheader("Candidate Profile 2", divider="red")
if 'upload_count' not in st.session_state:
st.session_state['upload_count'] = 0
max_attempts = 3
if st.session_state['upload_count'] < max_attempts:
uploaded_files = st.file_uploader(
"Upload your resume", accept_multiple_files=True, type="pdf", key="candidate 2"
)
if uploaded_files:
st.session_state['upload_count'] += 1
for uploaded_file in uploaded_files:
pdf_reader = PdfReader(uploaded_file)
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", "date", "time", "role", "skills", "year"]
entities = model(text_data, labels=labels)
df = pd.DataFrame(entities)
st.subheader("Profile of candidate 1", divider="green")
fig3 = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
values='score', color='label')
fig3.update_layout(margin=dict(t=50, l=25, r=25, b=25))
st.plotly_chart(fig3, key = "Figure 3")
vectorizer = TfidfVectorizer()
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("Measuring similarity between keywords of candidate profile 1 and job description", divider="green")
fig4 = px.imshow(cosine_sim_df, text_auto=True,
labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"),
x=['Resume 1', 'Job Description'],
y=['Resume 1', 'Job Description'])
st.plotly_chart(fig4, key = "Figure 4")
for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
st.write(f"Similarity of job description with candidate profile 1. {i + 1}: {similarity_score:.4f}")
st.info("A score closer to 1 (0.80, 0.90) means higher similarity between candidate profile 1 and job description. A score closer to 0 (0.20, 0.30) means lower similarity between candidate profile 1 and job description.")
else:
st.warning(f"You have reached the maximum upload attempts ({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).")
|