|
|
| import pandas as pd |
| from fuzzywuzzy import process |
| from sklearn.feature_extraction.text import TfidfVectorizer |
| from sklearn.metrics.pairwise import cosine_similarity |
| import gradio as gr |
|
|
| |
| url = "https://raw.githubusercontent.com/devbernie/Medimatch/refs/heads/main/dataset.csv" |
| data = pd.read_csv(url) |
|
|
| |
| columns_to_process = ['Composition', 'Uses', 'Medicine Name'] |
| for column in columns_to_process: |
| data[column] = data[column].fillna('').str.lower() |
|
|
| |
| def fuzzy_search(query, data_column, threshold=80): |
| matches = process.extract(query.lower(), data_column, limit=5) |
| results = [match[0] for match in matches if match[1] >= threshold] |
| return results |
|
|
| |
| vectorizer_composition = TfidfVectorizer() |
| composition_matrix = vectorizer_composition.fit_transform(data['Composition']) |
|
|
| vectorizer_uses = TfidfVectorizer() |
| uses_matrix = vectorizer_uses.fit_transform(data['Uses']) |
|
|
| |
| composition_similarity = cosine_similarity(composition_matrix) |
| uses_similarity = cosine_similarity(uses_matrix) |
| overall_similarity = (composition_similarity + uses_similarity) / 2 |
|
|
| |
| def recommend_medicine(input_name, top_n=5): |
| matches = fuzzy_search(input_name, data['Medicine Name']) |
| if not matches: |
| return f"Không tìm thấy thuốc gần đúng với '{input_name}'. Vui lòng thử lại." |
| |
| selected_medicine = matches[0] |
| idx = data[data['Medicine Name'] == selected_medicine].index[0] |
| sim_scores = list(enumerate(overall_similarity[idx])) |
| sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True) |
| |
| recommendations = [] |
| for i in sim_scores[1:top_n+1]: |
| med_info = data.iloc[i[0]] |
| recommendations.append({ |
| "Medicine Name": med_info['Medicine Name'], |
| "Composition": med_info['Composition'], |
| "Uses": med_info['Uses'], |
| "Side Effects": med_info['Side_effects'], |
| "Manufacturer": med_info['Manufacturer'], |
| "Image URL": med_info['Image URL'] |
| }) |
| return recommendations |
|
|
| |
| def gradio_recommend(input_name): |
| results = recommend_medicine(input_name) |
| if isinstance(results, str): |
| return results |
| |
| output = "" |
| for med in results: |
| output += f"### Tên thuốc: {med['Medicine Name'].capitalize()}\n" |
| output += f"**Thành phần:** {med['Composition']}\n" |
| output += f"**Công dụng:** {med['Uses']}\n" |
| output += f"**Tác dụng phụ:** {med['Side Effects']}\n" |
| output += f"**Nhà sản xuất:** {med['Manufacturer']}\n" |
| if med['Image URL']: |
| output += f"\n" |
| output += "\n" |
| return output |
|
|
| |
| interface = gr.Interface( |
| fn=gradio_recommend, |
| inputs="text", |
| outputs="markdown", |
| title="Gợi ý Thuốc Tương Tự", |
| description="Nhập tên thuốc để nhận danh sách các thuốc tương tự dựa trên thành phần và công dụng." |
| ) |
|
|
| if __name__ == "__main__": |
| interface.launch() |
