Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import pandas as pd | |
| from transformers import pipeline | |
| # Initialize the zero-shot classifier | |
| classifier = pipeline('zero-shot-classification', model='distilbert-base-uncased') | |
| # Define the possible categories (more granular categories) | |
| candidate_labels = ["ACL Tear", "Meniscus Tear", "Achilles Tear", "Fracture", "Hamstring", "Foot", "Shoulder", "Hip", "Calf", "Hand", "Wrist"] | |
| def classify_injuries(file): | |
| # Load the uploaded CSV file | |
| df = pd.read_csv(file.name) | |
| # Limit to a sample (e.g., first 100 rows) if necessary for performance | |
| new_df = df.head(100).copy() | |
| # Apply zero-shot classification to each note in the 'Notes' column | |
| classifications = classifier(new_df['Notes'].tolist(), candidate_labels) | |
| # Add the classification results to the DataFrame | |
| new_df['Classifications'] = classifications | |
| new_df['Top Classification'] = new_df['Classifications'].apply(lambda x: x['labels'][0] if isinstance(x, dict) else None) | |
| new_df['Top Score'] = new_df['Classifications'].apply(lambda x: x['scores'][0] if isinstance(x, dict) else None) | |
| # Initialize the 'Specific Injury' column with default value | |
| new_df['Specific Injury'] = None | |
| # Define a function to determine the specific injury based on keywords | |
| def extract_specific_injury(note, injury): | |
| note = note.lower() | |
| if "left" in note: | |
| return f"left {injury.lower()} injury" | |
| elif "right" in note: | |
| return f"right {injury.lower()} injury" | |
| else: | |
| return f"{injury.lower()} injury" | |
| # Apply specific injury classification based on keywords | |
| for injury in candidate_labels: | |
| new_df.loc[new_df['Top Classification'].str.contains(injury, case=False, na=False), 'Specific Injury'] = \ | |
| new_df['Notes'].apply(lambda x: extract_specific_injury(x, injury) if injury.lower() in x.lower() else None) | |
| # Sort by 'Top Score' in descending order | |
| new_df_sorted = new_df.sort_values(by='Top Score', ascending=False) | |
| # Return a subset of columns for clarity | |
| return new_df_sorted[['Notes', 'Top Classification', 'Top Score', 'Specific Injury']] | |
| # Set up the Gradio interface | |
| iface = gr.Interface( | |
| fn=classify_injuries, | |
| inputs=gr.File(label="Upload CSV File (must have a 'Notes' column)"), | |
| outputs="dataframe", | |
| title="Injury Classification App", | |
| description="Upload a CSV file with injury notes. The app classifies each note based on specified injury types and provides specific classifications where possible." | |
| ) | |
| # Launch the Gradio app | |
| iface.launch() | |