| 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 = "green") | |
| txt = st.text_area("Job description", 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 = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 2") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 = "green") | |
| txt = st.text_area("Job description", key = "text 2") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 4") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 3", divider = "green") | |
| txt = st.text_area("Job description", key = "text 3") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 3" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 5") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 6") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 4", divider = "green") | |
| txt = st.text_area("Job description", key = "text 4") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 4" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 7") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 8") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 5", divider = "green") | |
| txt = st.text_area("Job description", key = "text 5") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 5" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 9") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 10") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 6", divider = "green") | |
| txt = st.text_area("Job description", key = "text 6") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 6" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 11") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 12") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 7", divider = "green") | |
| txt = st.text_area("Job description", key = "text 7") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 7" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 13") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 14") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 8", divider = "green") | |
| txt = st.text_area("Job description", key = "text 8") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 8" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 16") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 18") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 9", divider = "green") | |
| txt = st.text_area("Job description", key = "text 9") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 9" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 17") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 18") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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 10", divider = "green") | |
| txt = st.text_area("Job description", key = "text 10") | |
| job = pd.Series(txt, name="Text") | |
| if 'upload_count' not in st.session_state: | |
| st.session_state['upload_count'] = 0 | |
| max_attempts = 2 | |
| if st.session_state['upload_count'] < max_attempts: | |
| uploaded_files = st.file_uploader( | |
| "Upload your resume in .pdf format", type="pdf", key="candidate 10" | |
| ) | |
| 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.predict_entities(text_data, labels) | |
| df = pd.DataFrame(entities) | |
| 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 19") | |
| 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) | |
| fig2 = px.imshow(cosine_sim_df, text_auto=True, labels=dict(x="Keyword similarity", y="Resumes", color="Productivity"), | |
| x=['Resume 1', 'Jon Description'], | |
| y=['Resume 1', 'Job Description']) | |
| st.plotly_chart(fig2, key = "figure 20") | |
| st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):") | |
| for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]): | |
| st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}") | |
| 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).") | |