Spaces:
Running
Running
| import torch | |
| try: | |
| print(f"Is CUDA available: {torch.cuda.is_available()}") | |
| if torch.cuda.is_available(): | |
| try: | |
| print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}") | |
| except Exception as e: | |
| print(f"Error getting CUDA device name: {str(e)}") | |
| else: | |
| print("No CUDA device available - using CPU") | |
| except Exception as e: | |
| print(f"Error checking CUDA availability: {str(e)}") | |
| print("Continuing with CPU...") | |
| import streamlit as st | |
| import os | |
| from huggingface_hub import login | |
| from datetime import datetime | |
| from modules.auth import validate_login, check_password | |
| from modules.utils import create_excel, clean_text, extract_predicted_labels, predict_category, process_data | |
| # Local | |
| # from dotenv import load_dotenv | |
| # load_dotenv() | |
| # Main app logic | |
| def main(): | |
| # Temporarily set authentication to True for testing | |
| if 'authenticated' not in st.session_state: | |
| st.session_state['authenticated'] = True | |
| if st.session_state['authenticated']: | |
| # Remove login success message for testing | |
| hf_token = os.environ["HF_TOKEN"] | |
| login(token=hf_token, add_to_git_credential=True) | |
| # Initialize session state variables | |
| if 'data_processed' not in st.session_state: | |
| st.session_state['data_processed'] = False | |
| st.session_state['df'] = None | |
| # Main Streamlit app | |
| st.title('MAF Application Pre-Filtering Tool') | |
| # Sidebar (filters) | |
| with st.sidebar: | |
| with st.expander("ℹ️ - Instructions", expanded=False): | |
| st.markdown( | |
| """ | |
| 1. **Download the Excel Template file (below).** | |
| 2. **[OPTIONAL]: Select the desired filtering sensitivity level (below).** | |
| 3. **Copy/paste the requisite application data in the template file. Best practice is to 'paste as values'.** | |
| 4. **Upload the template file in the area to the right (or click browse files).** | |
| The tool will immediately start processing the uploaded application data. This can take considerable time | |
| depending on the number of applications and the length of text in each. For example, a file with 500 applications | |
| could be expected to take approximately 20 minutes. | |
| ***NOTE (1)** - you can also simply rename the column headers in your own file. The headers must match the column names in the template for the tool to run properly.* | |
| ***NOTE (2)** - as of April 2024 this app running as a **test version**, NOT on a GPU. So the process can take up to 30 minutes for 20 applications.* | |
| """ | |
| ) | |
| # Excel file download | |
| st.download_button( | |
| label="Download Excel Template", | |
| data=create_excel(), | |
| file_name="MAF_upload_template.xlsx", | |
| mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" | |
| ) | |
| # get sensitivity level for use in review / reject (ref. process_data function) | |
| sens_options = { | |
| "Low": 4, | |
| "Medium": 5, | |
| "High": 7, | |
| } | |
| sens_input = st.sidebar.radio(label = 'Select the Sensitivity Level [OPTIONAL]', | |
| help = 'Increasing the level of sensitivity results in more \ | |
| applications being filtered out. At the same time, this also \ | |
| increases the probability of false negatives (FNs). The rate of \ | |
| FNs at the lowest setting is approximately 6 percent, and \ | |
| approaches 13 percent at the highest setting. ', | |
| options = list(sens_options.keys()), | |
| horizontal = False) | |
| sens_level = sens_options[sens_input] | |
| with st.expander("ℹ️ - About this app", expanded=False): | |
| st.write( | |
| """ | |
| This tool provides an interface for running an automated preliminary assessment of applications to the MAF call for applications. | |
| The tool functions by running selected text fields from the application through a series of 8 LLMs fine-tuned for text classification (ref. diagram below). | |
| The resulting output classifications are used to compute a score and a suggested pre-filtering action. The tool has been tested against | |
| human assessors and exhibits an extremely low false negative rate (<6%) at a Sensitivity Level of 'Low' (i.e. rejection threshold for predicted score < 4). | |
| """) | |
| st.image('images/pipeline.png') | |
| uploaded_file = st.file_uploader("Select a file containing MAF application pre-filtering data (see instructions in the sidebar)") | |
| if uploaded_file is not None: | |
| try: | |
| if not st.session_state['data_processed']: | |
| st.session_state['df'] = process_data(uploaded_file, sens_level) | |
| st.session_state['data_processed'] = True | |
| df = st.session_state['df'] | |
| # Get the current date | |
| current_datetime = datetime.now().strftime('%d-%m-%Y_%H-%M-%S') | |
| output_filename = 'processed_applications_'+current_datetime+'.csv' | |
| output_file = 'processed_applications.csv' | |
| df.to_csv(output_file, index=False) | |
| st.download_button( | |
| label="Download data as CSV", | |
| data=open(output_file, 'rb'), | |
| file_name=output_filename, | |
| mime='text/csv', | |
| ) | |
| except: | |
| st.error("Failed to process the file. Please ensure your column names match the template file.") | |
| # Comment out or remove the else block containing login form | |
| # else: | |
| # username = st.text_input("Username") | |
| # password = st.text_input("Password", type="password") | |
| # if st.button("Login"): | |
| # if validate_login(username, password): | |
| # st.session_state['authenticated'] = True | |
| # st.experimental_rerun() | |
| # else: | |
| # st.error("Incorrect username or password") | |
| # Run the main function | |
| main() | |