Update app.py

app.py

@@ -1,166 +1,10 @@
-# -*- coding: utf-8 -*-
-"""2_preprocessing_test.ipynb
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/10c3x9G9z70J73l0LJDA8_VDZphQmHEZB
-"""
-
-
 import pandas as pd
 import numpy as np
-import matplotlib.pyplot as plt
-from sklearn.preprocessing import LabelEncoder
-import os
-from sklearn.model_selection import train_test_split
 import pickle
-import warnings
-warnings.filterwarnings('ignore')
-
-df1 = pd.read_csv("/content/drive/MyDrive/Google Colab/disease-symptom-prediction/data/dataset.csv")
-
-print(df1.shape)
-df1.head()
-
-df1.sort_values(by='Disease', inplace=True)
-df1.head()
-
-df1.drop_duplicates(inplace=True)
-df1.shape
-
-df1['Disease'].value_counts()
-
-df1[df1['Disease']=="Fungal infection"]
-
-df1.fillna("none", inplace=True)
-df1[df1['Disease']=="Fungal infection"]
-
-df1.columns = df1.columns.str.strip().str.lower()
-for col in df1.columns:
-    df1[col] = df1[col].astype(str).str.strip().str.lower()
-
-
-symptom_cols = [col for col in df1.columns if col.startswith('symptom')]
-print(symptom_cols)
-
-all_symptoms = set()
-for col in symptom_cols:
-    for val in df1[col].unique():
-        if val != 'none':
-            all_symptoms.add(val)
-print(f"Unique symptoms: {len(all_symptoms)}")
-
-print(all_symptoms)
-
-df1.head()
-
-df1_num = pd.DataFrame(df1['disease'])
-
-for symptom in all_symptoms:
-    df1_num[symptom] = df1[symptom_cols].apply(lambda row: int(symptom in row.values), axis=1)
-
-df1_num
-
-X = df1_num.drop('disease', axis=1)
-y = df1_num['disease']
-X.shape, y.shape
-
-X.sum(axis=1)
-
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, stratify=y)
-
-print(np.unique(y_train, return_counts=True))
-print(np.unique(y_test, return_counts=True))
-
-from sklearn.ensemble import  RandomForestClassifier
-
-model = RandomForestClassifier(n_estimators=100,random_state=42)
-model.fit(X_train, y_train)
-model.fit(X_train, y_train)
-
-import pickle
-
-# Save model
-with open("disease_model.pkl", "wb") as f:
-    pickle.dump(model, f)
-
-# Save symptom list (to use in the app later)
-with open("symptoms.pkl", "wb") as f:
-    pickle.dump(list(all_symptoms), f)
-
-# Original symptoms (keys)
-all_symptoms = sorted(all_symptoms)
-
-# Create display labels by replacing '_' with ' ' and capitalizing each word
-display_symptoms = [symptom.replace('_', ' ').title() for symptom in all_symptoms]
-
-# Create a mapping from display label back to original symptom key
-label_to_symptom = dict(zip(display_symptoms, all_symptoms))
-
-from sklearn.metrics import accuracy_score, f1_score
-
-y_train_pred = model.predict(X_train)
-
-train_accuracy = accuracy_score(y_train, y_train_pred)
-train_f1_score = f1_score(y_train, y_train_pred,average="weighted")
-
-print("Train Accuracy:", train_accuracy)
-print("Train f1 score:", train_f1_score)
-
-y_test_pred = model.predict(X_test)
-test_accuracy = accuracy_score(y_test, y_test_pred)
-test_f1_score = f1_score(y_test, y_test_pred, average="weighted")
-print("Train Accuracy:", test_accuracy)
-print("Train f1 score:", test_f1_score)
-
-import numpy as np
-
-# Example user symptoms
-user_symptoms = ['nausea', 'vomiting', 'abdominal_pain', 'diarrhoea']
-
-# Tip for the user
-if len(user_symptoms) < 4:
-    print("Tip: The model performs better if you enter at least 4 symptoms.\n")
-
-# Convert symptoms to input vector
-input_vector = [1 if symptom in user_symptoms else 0 for symptom in all_symptoms]
-input_vector = np.array([input_vector])
-
-# Make prediction and get probabilities
-probas = model.predict_proba(input_vector)[0]
-max_proba = np.max(probas)
-predicted = model.classes_[np.argmax(probas)]
-
-# Confidence threshold
-threshold = 0.5
-
-# Print predicted disease and confidence
-if max_proba < threshold:
-    print("Warning: The model is not confident about this prediction.")
-    print(f"Predicted disease: {predicted} (Confidence: {max_proba * 100:.1f}%)")
-else:
-    print(f"Predicted disease: {predicted} (Confidence: {max_proba * 100:.1f}%)")
-
-# Function to print top N diseases
-def print_top_diseases(probas, model, top_n=5):
-    classes = model.classes_
-    sorted_indices = np.argsort(probas)[::-1]
-    print(f"\nTop {top_n} possible diseases:")
-    for i in range(min(top_n, len(classes))):
-        disease = classes[sorted_indices[i]]
-        probability = probas[sorted_indices[i]]
-        print(f"{i+1}. {disease}: {probability:.4f}")
-
-# Show top 5 possible diseases
-print_top_diseases(probas, model, top_n=5)
-
-
 import gradio as gr
-import pickle
-import numpy as np
 
 # --- 1. Load Disease Prediction Model ---
+# Load model and symptoms from files (upload these to your HF Space)
 with open("disease_model.pkl", "rb") as f:
     model = pickle.load(f)
 
@@ -174,12 +18,10 @@ label_to_symptom = dict(zip(display_symptoms, all_symptoms))
 
 # --- 2. Medical Knowledge Base ---
 MEDICAL_KNOWLEDGE = {
-
     "migraine": [
         "For migraines: (1) Rest in dark room (2) OTC pain relievers (ibuprofen/acetaminophen) (3) Apply cold compress (4) Consult neurologist if frequent",
         "Migraine treatment options include triptans (prescription) and caffeine. Avoid triggers like bright lights or strong smells."
     ],
-
     "allergy": [
         "Allergy management: (1) Antihistamines (cetirizine/loratadine) (2) Nasal sprays (3) Allergy shots (immunotherapy) for severe cases",
         "For food allergies: Strict avoidance, carry epinephrine auto-injector (EpiPen), read food labels carefully"
@@ -275,13 +117,31 @@ body, .gradio-container {
     color: var(--text) !important;
     font-family: 'Segoe UI', Roboto, sans-serif;
 }
-/* [Keep all your existing CSS styles] */
+.gr-button {
+    background: var(--primary) !important;
+    color: var(--secondary) !important;
+    border: none !important;
+}
+.gr-button:hover {
+    opacity: 0.9 !important;
+}
+.gr-checkbox {
+    background: var(--card-bg) !important;
+    border-color: var(--primary) !important;
+}
+.gr-checkbox label {
+    color: var(--text) !important;
+}
+.gr-interface {
+    max-width: 1200px !important;
+    margin: 0 auto !important;
+}
 """
 
-with gr.Blocks(css=custom_css) as demo:
+with gr.Blocks(css=custom_css, title="Medical Diagnosis Assistant") as demo:
     gr.Markdown("""
     <div style="text-align: center; margin-bottom: 20px;">
-        <h1 style="margin-bottom: 5px;">🧬 Medical Diagnosis Assistant</h1>
+        <h1 style="margin-bottom: 5px; color: #4fc3f7;">🧬 Medical Diagnosis Assistant</h1>
         <p style="color: #4fc3f7; font-size: 16px;">Select symptoms for diagnosis and get medical advice</p>
     </div>
     """)
@@ -295,9 +155,9 @@ with gr.Blocks(css=custom_css) as demo:
                 interactive=True
             )
             predict_btn = gr.Button("Analyze Symptoms", variant="primary")
-            prediction_output = gr.Markdown(
+            prediction_output = gr.HTML(
                 label="Diagnosis Results",
-                value="Your results will appear here..."
+                value="<div style='padding: 20px; background: #001a33; border-radius: 8px; color: white;'>Your results will appear here...</div>"
             )
 
         with gr.Column(scale=1, min_width=400):
@@ -305,7 +165,10 @@ with gr.Blocks(css=custom_css) as demo:
             chatbot = gr.Chatbot(
                 label="Chat with Medical Advisor",
                 show_label=False,
-                bubble_full_width=False
+                bubble_full_width=False,
+                avatar_images=(
+                    None, (None, "assets/doctor_avatar.png")
+                )
             )
             with gr.Row():
                 user_input = gr.Textbox(
@@ -334,4 +197,5 @@ with gr.Blocks(css=custom_css) as demo:
         outputs=[chatbot, user_input]
     )
 
+# For Hugging Face Spaces
 demo.launch()