Update app.py

app.py

@@ -60,23 +60,31 @@ def load_data():
     except FileNotFoundError:
         raise RuntimeError("Data files not found. Please ensure `Training.csv` and `Testing.csv` are uploaded correctly.")
 
+    # Encode diseases
     disease_dict = {
         'Fungal infection': 0, 'Allergy': 1, 'GERD': 2, 'Chronic cholestasis': 3, 'Drug Reaction': 4,
         'Peptic ulcer diseae': 5, 'AIDS': 6, 'Diabetes': 7, 'Gastroenteritis': 8, 'Bronchial Asthma': 9,
-        'Hypertension': 10, 'Migraine': 11, 'Cervical spondylosis': 12, 'Paralysis': 13,
-        'Jaundice': 14, 'Malaria': 15, 'Chicken pox': 16, 'Dengue': 17, 'Typhoid': 18,
-        'Hepatitis A': 19, 'Hepatitis B': 20, 'Hepatitis C': 21, 'Hepatitis D': 22, 'Hepatitis E': 23,
-        'Alcoholic hepatitis': 24, 'Tuberculosis': 25, 'Common Cold': 26, 'Pneumonia': 27,
-        'Heart attack': 28, 'Varicose veins': 29, 'Hypothyroidism': 30, 'Hyperthyroidism': 31,
-        'Hypoglycemia': 32, 'Osteoarthritis': 33, 'Arthritis': 34
+        'Hypertension': 10, 'Migraine': 11, 'Cervical spondylosis': 12, 'Paralysis (brain hemorrhage)': 13,
+        'Jaundice': 14, 'Malaria': 15, 'Chicken pox': 16, 'Dengue': 17, 'Typhoid': 18, 'Hepatitis A': 19,
+        'Hepatitis B': 20, 'Hepatitis C': 21, 'Hepatitis D': 22, 'Hepatitis E': 23, 'Alcoholic hepatitis': 24,
+        'Tuberculosis': 25, 'Common Cold': 26, 'Pneumonia': 27, 'Dimorphic hemorrhoids(piles)': 28,
+        'Heart attack': 29, 'Varicose veins': 30, 'Hypothyroidism': 31, 'Hyperthyroidism': 32,
+        'Hypoglycemia': 33, 'Osteoarthritis': 34, 'Arthritis': 35,
+        '(vertigo) Paroxysmal Positional Vertigo': 36, 'Acne': 37, 'Urinary tract infection': 38,
+        'Psoriasis': 39, 'Impetigo': 40
     }
 
     # Replace prognosis values with numerical categories
     df.replace({'prognosis': disease_dict}, inplace=True)
-    df = df.infer_objects()  # Removed 'copy=False' argument
+
+    # Ensure prognosis is purely numerical after mapping
+    df['prognosis'] = df['prognosis'].astype(int)  # Convert to integer if necessary
+    
+    df = df.infer_objects()  # Removed 'copy' argument
 
     tr.replace({'prognosis': disease_dict}, inplace=True)
-    tr = tr.infer_objects()  # Removed 'copy=False' argument
+    tr['prognosis'] = tr['prognosis'].astype(int)  # Ensure it is also numerical
+    tr = tr.infer_objects()  # Remove 'copy' argument
 
     return df, tr, disease_dict
 
@@ -87,9 +95,9 @@ y = df['prognosis']
 X_test = tr[l1]
 y_test = tr['prognosis']
 
-# Encode the target variable
+# Encode the target variable with LabelEncoder if not already numerical
 le = LabelEncoder()
-y_encoded = le.fit_transform(y)  # Encode string labels into integers
+y_encoded = le.fit_transform(y)  # Needs to be string labels, assuming df['prognosis'] has no numerical labels
 
 def train_models():
     models = {
@@ -186,7 +194,7 @@ def detect_emotion(user_input):
 def generate_suggestions(emotion):
     emotion_key = emotion.lower()
     suggestions = {
-        # Replace with appropriate suggestions for each emotion
+        # Define suggestions based on the emotion detected
     }
     
     formatted_suggestions = [