Spaces:
Runtime error
Runtime error
| from typing import List | |
| import numpy as np | |
| import pandas as pd | |
| import streamlit as st | |
| from sentence_transformers import SentenceTransformer, util | |
| from st_aggrid import AgGrid, GridOptionsBuilder, JsCode | |
| st.set_page_config(layout='wide') | |
| def load_model(): | |
| """Load pretrained model from SentenceTransformer""" | |
| return SentenceTransformer('minilm_sbert') | |
| def semantic_search(model: SentenceTransformer, | |
| query: str, | |
| corpus_embeddings: List) -> pd.DataFrame: | |
| """Perform semantic search on the corpus""" | |
| query_embeddings = model.encode(sentences=query, | |
| batch_size=128, | |
| show_progress_bar=False, | |
| convert_to_tensor=True, | |
| normalize_embeddings=True) | |
| hits = util.semantic_search(query_embeddings, | |
| corpus_embeddings, | |
| top_k=len(corpus_embeddings), | |
| score_function=util.dot_score) | |
| return pd.DataFrame(hits[0]) | |
| def get_similarity_score(model: SentenceTransformer, | |
| data: pd.DataFrame, | |
| query: str, | |
| corpus_embeddings: List) -> pd.DataFrame: | |
| """Get similarity score for each data point and sort by similarity score and last day""" | |
| hits = semantic_search(model, query, corpus_embeddings) | |
| result = pd.merge(data, hits, left_on='ID', right_on='corpus_id') | |
| result['Last Day'] = pd.to_datetime(result['Last Day'], format='%d/%m/%Y', errors='coerce').dt.date | |
| result.sort_values(by=['score', 'Last Day'], ascending=[False, True], inplace=True) | |
| return result | |
| def create_embedding(model: SentenceTransformer, | |
| data: pd.DataFrame, | |
| key: str) -> List: | |
| "Maps job title from the corpus to a 384 dimensional vector embeddings" | |
| corpus_sentences = data[key].astype(str).tolist() | |
| corpus_embeddings = model.encode(sentences=corpus_sentences, | |
| batch_size=128, | |
| show_progress_bar=False, | |
| convert_to_tensor=True, | |
| normalize_embeddings=True) | |
| return corpus_embeddings | |
| def load_dataset(columns: List[str]) -> pd.DataFrame: | |
| """Load real-time dataset from google sheets""" | |
| sheet_id = '1KeuPPVw9gueNmMrQXk1uGFlY9H1vvhErMLiX_ZVRv_Y' | |
| sheet_name = 'Form Response 3'.replace(' ', '%20') | |
| url = f'https://docs.google.com/spreadsheets/d/{sheet_id}/gviz/tq?tqx=out:csv&sheet={sheet_name}' | |
| data = pd.read_csv(url) | |
| data = data.iloc[: , :7] | |
| data.columns = columns | |
| data.insert(0, 'ID', range(len(data))) | |
| data['Full Name'] = data['Full Name'].str.title() | |
| data['LinkedIn Profile'] = data['LinkedIn Profile'].str.lower() | |
| data['LinkedIn Profile'] = np.where(data['LinkedIn Profile'].str.startswith('www.linkedin.com'), | |
| "https://" + data['LinkedIn Profile'], | |
| data['LinkedIn Profile']) | |
| data['LinkedIn Profile'] = np.where(data['LinkedIn Profile'].str.startswith('linkedin.com'), | |
| "https://www." + data['LinkedIn Profile'], | |
| data['LinkedIn Profile']) | |
| return data | |
| def show_aggrid_table(result: pd.DataFrame): | |
| """Show interactive table from similarity result""" | |
| gb = GridOptionsBuilder.from_dataframe(result) | |
| gb.configure_pagination(paginationAutoPageSize=True) | |
| gb.configure_side_bar() | |
| gb.configure_default_column(min_column_width=200) | |
| gb.configure_selection('multiple', use_checkbox=True, groupSelectsChildren="Group checkbox select children") | |
| gb.configure_column(field='LinkedIn Profile', | |
| headerName='LinkedIn Profile', | |
| cellRenderer=JsCode('''function(params) {return `<a href=${params.value} target="_blank">${params.value}</a>`}''')) | |
| grid_options = gb.build() | |
| grid_response = AgGrid( | |
| dataframe=result, | |
| gridOptions=grid_options, | |
| height=1100, | |
| fit_columns_on_grid_load=True, | |
| data_return_mode='AS_INPUT', | |
| update_mode='VALUE_CHANGED', | |
| theme='light', | |
| enable_enterprise_modules=True, | |
| allow_unsafe_jscode=True, | |
| ) | |
| def show_heading(): | |
| """Show heading made using streamlit""" | |
| st.title('@ecommurz Talent Search Engine') | |
| st.markdown(''' | |
| <div align="left"> | |
| [](https://temandata.com/) | |
| [](https://github.com/teman-data/ecommurz-talent-search-engine) | |
|  | |
| </div> | |
| ''', unsafe_allow_html=True) | |
| st.write('This app lets you search and sort talent by job title or relevant job descriptions from ecommurz talent list in real-time.') | |
| def get_specific_category(model, data, category, corpus_embeddings): | |
| """Get specific category with confidence score > 0.45""" | |
| data = get_similarity_score(model, data, category, corpus_embeddings) | |
| return data[data['score'] > 0.45].shape[0] | |
| def main(): | |
| """Main Function""" | |
| show_heading() | |
| columns = ['Timestamp', 'Full Name', 'Company', 'Previous Role', | |
| 'Experience (months)', 'Last Day', 'LinkedIn Profile'] | |
| data = load_dataset(columns) | |
| model = load_model() | |
| corpus_embeddings = create_embedding(model, data, 'Previous Role') | |
| col1, col2, col3, col4, col5, col6, col7, _ = st.columns([1.1, 1.3, 1.6, 1.65, 1.7, 2.1, 2.25, 9]) | |
| with col1: | |
| data_count = get_specific_category(model, data, 'data', corpus_embeddings) | |
| data_bt = st.button(f'Data ({data_count})') | |
| with col2: | |
| finance_count = get_specific_category(model, data, 'finance', corpus_embeddings) | |
| finance_bt = st.button(f'Finance ({finance_count})') | |
| with col3: | |
| marketing_count = get_specific_category(model, data, 'marketing', corpus_embeddings) | |
| marketing_bt = st.button(f'Marketing ({marketing_count})') | |
| with col4: | |
| social_media_count = get_specific_category(model, data, 'social media', corpus_embeddings) | |
| social_media_bt = st.button(f'Social Media ({social_media_count})') | |
| with col5: | |
| arts_design_count = get_specific_category(model, data, 'design and creative', corpus_embeddings) | |
| arts_design_bt = st.button(f'Arts & Design ({arts_design_count})') | |
| with col6: | |
| computer_count = get_specific_category(model, data, 'engineer', corpus_embeddings) | |
| computer_bt = st.button(f'Computer Science ({computer_count})') | |
| with col7: | |
| business_count = get_specific_category(model, data, 'business and management', corpus_embeddings) | |
| business_bt = st.button(f'Business and Management ({business_count})') | |
| job_title = st.text_input('Insert the job title below:', '') | |
| submitted = st.button('Submit') | |
| if data_bt: | |
| job_title = 'data' | |
| if finance_bt: | |
| job_title = 'finance and accounting' | |
| if business_bt: | |
| job_title = 'business and management' | |
| if marketing_bt: | |
| job_title = 'marketing' | |
| if social_media_bt: | |
| job_title = 'social media' | |
| if arts_design_bt: | |
| job_title = 'design and creative' | |
| if computer_bt: | |
| job_title = 'engineer and developer' | |
| if submitted or data_bt or finance_bt or marketing_bt or social_media_bt or arts_design_bt or computer_bt or business_bt: | |
| print(job_title + ',' + str(pd.Timestamp.now())) | |
| st.info(f'Showing most similar results for {job_title}...') | |
| result = get_similarity_score(model, data, job_title, corpus_embeddings) | |
| result = result[columns] | |
| show_aggrid_table(result) | |
| if __name__ == '__main__': | |
| main() | |