Delete medic_bot.py

medic_bot.py

@@ -1,359 +0,0 @@
-# -*- coding: utf-8 -*-
-"""Medic_bot.ipynb
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/#fileId=https%3A//huggingface.co/spaces/QueenS5Ella/Royalty/blob/main/Medic_bot.ipynb
-"""
-
-# IMPORT THE NECESSARY LIBARIES 1
-#Import Python libraries: Numpy and Pandas
-import pandas as pd
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
-import openai
-import faiss
-import numpy as np
-
-#import libraries &modules for data visualization
-from pandas.plotting import scatter_matrix
-from matplotlib import pyplot
-
-#import scikit-learn module for algoruthm/model: Linear Regression
-from sklearn.neighbors import KNeighborsRegressor
-
-#import scikit learn module to split the dataset into train/test sub-datasets
-from sklearn.model_selection import train_test_split
-
-#Import scikit-learn module for K-fold cross validation - algorithm/model evluation & vallidation
-from sklearn.model_selection import KFold
-from sklearn.model_selection import cross_val_score
-
-#Import sckit-learn module for classification report
-from sklearn.metrics import classification_report
-
-from sklearn.preprocessing import LabelEncoder
-from sklearn.preprocessing import OrdinalEncoder
-
-# IMPORTATION OF NECESSARY LIBRARIES 2
-import os # for handling data
-import re # for text preprocessing
-
-# For Natural Language Processing tasks
-import nltk
-from sklearn.model_selection import train_test_split
-
-nltk.download("punkt")
-nltk.download("stopwords")
-
-# Optional: for vectorization and building of the models
-from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
-
-#IMPORTATION OF THE DIFFERENT MODELS FOR THE CHATBOT
-from sklearn.linear_model import LogisticRegression
-from sklearn.ensemble import RandomForestRegressor
-import xgboost as xgb
-from sklearn.linear_model import Ridge
-from sklearn.neural_network import MLPRegressor
-
-import scipy
-print(scipy.__version__)
-
-import gradio as gr
-
-# 🔑 Replace with your real OpenAI API key
-client = OpenAI(api_key = "sk-...")  # <- Replace this with your actual API key
-
-# 📄 Load dataset
-d1 = pd.read_csv("ai-medical-chatbot.csv")
-d1.dropna(subset=["Description", "Doctor"], inplace=True)
-
-vector1 = TfidfVectorizer()
-# Keep the sparse matrix — don't convert to dense
-qvs = vector1.fit_transform(d1["Description"])  # No .toarray()
-
-d1.head()
-
-def find_best_match(user_input):
-    user_vec = vector1.transform([user_input])  # Still a sparse matrix
-    similarities = cosine_similarity(user_vec, qvs)
-    best_idx = np.argmax(similarities[0])
-    best_score = float(similarities[0][best_idx])
-    return d1.iloc[best_idx]["Description"], d1.iloc[best_idx]["Doctor"], best_score
-
-# 🔍 Vectorize questions
-#vectorizer = TfidfVectorizer()
-#question_vectors = vectorizer.fit_transform(df["Question"]).toarray()
-
-# 🔎 Find the most similar FAQ match
-#def find_best_match(user_input):
-    #user_vec = vectorizer.transform([user_input]).toarray()
-    #similarities = cosine_similarity(user_vec, question_vectors)
-    #best_idx = np.argmax(similarities[0])
-   # best_score = float(similarities[0][best_idx])
-  #  return df.iloc[best_idx]["Question"], df.iloc[best_idx]["Answer"], best_score
-
-# 🤖 Query OpenAI if no good FAQ match
-def query_gpt(user_input):
-    try:
-        response = client.chat.completions.create(
-            model="gpt-4",  # or use "gpt-3.5-turbo"
-            messages=[
-                {"role": "system", "content": "You are a pediatric pulmonology expert."},
-                {"role": "user", "content": user_input},
-                {"role": "assistant", "content": "Hello"}
-            ]
-        )
-        return response.choices[0].message["content"]
-    except Exception as e:
-        return f"⚠️ GPT Error: {str(e)}"
-
-# 💬 Chatbot response logic
-def chatbot_response(user_input):
-    if not user_input.strip():
-        return "Please enter a question."
-
-    try:
-        matched_q, matched_a, score = find_best_match(user_input)
-        if score > 0.75:
-            return f"📚 **Answer from FAQ**:\n\n**Q:** {matched_q}\n**A:** {matched_a}"
-        else:
-            gpt_answer = query_gpt(user_input)
-            return f"🤖 **Answer from GPT-4**:\n\n{gpt_answer}"
-    except Exception as e:
-        return f"❌ Error processing your question: {str(e)}"
-
-# 🌐 Launch Gradio interface
-gr.Interface(
-    fn=chatbot_response,
-    inputs=gr.Textbox(label="Ask any pediatric pulmonology related questions"),
-    outputs=gr.Textbox(label="Response", lines=10),
-    title="Pediatric Pulmonology Medicbot",
-    description="Answers common non-critical questions about pediatric pulmonology using a mix of FAQ and GPT-4."
-).launch(share=True)
-
-# Set your OpenAI key
-#openai.api_key = "sk-..."  # <- Replace this with your actual API key
-
-# Load CSV
-chat = pd.read_csv("PedMedQA_final.csv")
-
-chat.head()
-
-chat.describe()
-
-chat.isnull().sum()
-
-chat.shape
-
-chat.info()
-
-chat["answer"]. unique()
-
-chat["answer"].value_counts()
-
-chat["answer"] = chat["answer"].fillna("Reassurance")
-print(chat["answer"])
-
-chat["age_years"].unique
-
-chat["age_years"].value_counts
-
-chat.head()
-
-chat.dtypes
-
-chat.dropna(subset=["question", "answer"], inplace=True)
-chat.drop_duplicates(subset=["question"], inplace=True)
-
-chat.isnull().sum()
-
-#oe = OrdinalEncoder()
-
-#chat["index"] = oe.fit_transform(chat[["index"]])
-chat["index"].head(3)
-
-#chat["meta_info"] = oe.fit_transform(chat[["meta_info"]])
-chat["meta_info"].head(3)
-
-#chat["question"] = oe.fit_transform(chat[["question"]])
-chat["question"].head(3)
-
-#chat["answer_idx"] = oe.fit_transform(chat[["answer_idx"]])
-chat["answer_idx"].head(3)
-
-#chat["answer"] = oe.fit_transform(chat[["answer"]])
-chat["answer"].head(3)
-
-#chat["options"] = oe.fit_transform(chat[["options"]])
-chat["options"].head(3)
-
-chat.shape
-
-chat.columns
-
-from sklearn.linear_model import LassoCV
-from sklearn.feature_selection import SelectFromModel
-
-#clf = LassoCV.fit(X_train, Y_trarin)
-#importance = np.abs(clf.coef)
-#print(importance)
-
-while True:
-    user_input = input("You can ask me any pediatric pulmonology related question (or type 'exit'): ")
-
-    if user_input.lower() == "exit":
-        break
-
-    response = chatbot_response(user_input)
-    print(response)
-
-#response = chatbot_response(ui)
-#print(response)
-chat.dropna(subset=["question", "answer"], inplace=True)
-
-from sklearn.feature_extraction.text import TfidfVectorizer
-
-# Vectorize the questions using TF-IDF
-# ✅ 1. Fit and transform your dataset questions
-vector1 = TfidfVectorizer()
-qvs = vector1.fit_transform(chat["question"]).toarray()
-
-# ✅ 2. Later, transform user input using the same vectorizer
-user_vec = vector1.transform([user_input]).toarray()
-
-# 🔌 Connect to OpenAI
-#openai.api_key = "your-openai-api-key"  # Replace with your real key
-
-# 📄 Step 1: Load your dataset
-df.dropna(subset=["Question", "Answer"], inplace=True)
-
-# 🧠 Step 2: Vectorize dataset questions
-#vectorizer = TfidfVectorizer()
-#question_vectors = vectorizer.fit_transform(df["Question"]).toarray()
-
-# 🔍 Step 3: Find most similar question
-def find_best_match(user_input):
-    user_vec = vector1.transform([user_input]).toarray()
-    similarities = cosine_similarity(user_vec, qvs)
-    best_idx = np.argmax(similarities[0])
-    best_score = similarities[0][answer_idx]
-    return df.iloc[best_idx]["question"], chat.iloc[best_idx]["answer"], best_score
-
-# 🤖 Step 4: Fallback to GPT-4 if no good match
-def query_gpt(user_input):
-    response = client.chat.completions.create(
-        model="gpt-4",
-        messages=[
-            {"role": "system", "content": "You are a pediatric pulmonology expert."},
-            {"role": "user", "content": user_input}
-        ]
-    )
-try:
-    # some risky code
-    risky_function()
-except Exception as e:
-    print(f"An error occurred: {e}")
-
-# 💬 Step 5: Define chatbot logic
-def chatbot_response(user_input):
-    matched_q, matched_a, score = find_best_match(user_input)
-    if score > 0.75:
-        return f"📚 Answer from FAQ:\nQ: {matched_q}\nA: {matched_a}"
-    else:
-        return f"🤖 Answer from GPT-4:\n{query_gpt(user_input)}"
-
-# 🌐 Step 6: Launch Gradio interface
-gr.Interface(
-    fn=chatbot_response,
-    inputs=gr.Textbox(label="Ask any pediatric pulmonology related question"),
-    outputs=gr.Textbox(label="Response"),
-    title="Royalty Medic_bot",
-    description="Get non-crtical answers to common pediatric respiratory health questions."
-).launch(share=True)
-
-
-def find_best_match(user_input):
-    input_vec = vectorizer.transform([user_input]).toarray()
-    sims = cosine_similarity(input_vec, question_vectors)
-    idx = np.argmax(sims)
-    score = sims[0][answer_idx]
-    return chat.iloc[answer_idx]["Question"], chat.iloc[answer_idx]["Answer"], score
-
-while True:
-    user_input = input("🧒 Ask a pediatric pulmonology question (or type 'exit'): ")
-    if user_input.lower() == "exit":
-        print("👋 Goodbye!")
-        break
-    print(chatbot_response(user_input))
-
-
-def chatbot_gradio_interface(user_input):
-    return chatbot_response(user_input)
-
-gr.Interface(fn=chatbot_gradio_interface,
-             inputs="text",
-             outputs="text",
-             title="Pediatric Pulmonology Medicbot",
-             description="Ask any question related to pediatric lung health.").launch(share=True)
-
-
-
-
-
-# Build FAISS index for similarity search
-index = faiss.IndexFlatL2(question_vectors.shape[1])
-index.add(np.array(question_vectors))
-
-# Function to find the closest question
-def find_most_similar_question(user_question, top_k=1):
-    user_vec = vectorizer.transform([user_question]).toarray()
-    D, I = index.search(user_vec, top_k)
-    return df.iloc[I[0][0]]["Question"], df.iloc[I[0][0]]["Answer"]
-
-# Function to query a language model
-def ask_openai(question, model="gpt-4"):
-    try:
-        response = client.chat.completions.create(
-            model=model,
-            messages=[
-                {"role": "system", "content": "You are a pediatric pulmonology expert."},
-                {"role": "user", "content": question},
-            ],
-            temperature=0.3,
-        )
-        return response.choices[0].message["content"]
-    except Exception as e:
-        print(f"Error with {model}: {e}")
-        return None
-
-# Main chatbot function
-def pediatric_pulmonology_chatbot(user_input):
-    matched_question, matched_answer = find_most_similar_question(user_input)
-
-    similarity = cosine_similarity(
-        vectorizer.transform([user_input]), vectorizer.transform([matched_question])
-    )[0][0]
-
-    if similarity > 0.7:
-        return f"(From Knowledge Base)\nQ: {matched_question}\nA: {matched_answer}"
-    else:
-        # Try GPT-4 first
-        reply = ask_openai(user_input, model="gpt-4")
-        if reply:
-            return f"(From GPT-4)\n{reply}"
-        else:
-            # Fallback to GPT-3.5
-            reply = ask_openai(user_input, model="gpt-3.5-turbo")
-            if reply:
-                return f"(From GPT-3.5)\n{reply}"
-            else:
-                return "Sorry, I couldn't find an answer to that."
-
-# 🔁 Example interaction
-while True:
-    user_input = input("\n👶 Ask a pediatric pulmonology question (or type 'exit'): ")
-    if user_input.lower() == "exit":
-        break
-    print(pediatric_pulmonology_chatbot(user_input))