Update app.py

app.py

@@ -63,15 +63,15 @@ def load_data():
     # Encode diseases in a dictionary
     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 (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
+        'Peptic ulcer disease': 5, 'AIDS': 6, 'Diabetes': 7, 'Gastroenteritis': 8, 'Bronchial Asthma': 9,
+        '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,
+        'Heart attack': 28, 'Varicose veins': 29, 'Hypothyroidism': 30, 'Hyperthyroidism': 31,
+        'Hypoglycemia': 32, 'Osteoarthritis': 33, 'Arthritis': 34,
+        '(vertigo) Paroxysmal Positional Vertigo': 35, 'Acne': 36, 'Urinary tract infection': 37,
+        'Psoriasis': 38, 'Impetigo': 39
     }
 
     # Replace prognosis values with numerical categories
@@ -84,16 +84,18 @@ def load_data():
     if df['prognosis'].dtype == 'object':  # Check for unmapped entries
         raise ValueError(f"The prognosis contains unmapped values: {df['prognosis'].unique()}")
 
-    df['prognosis'] = df['prognosis'].astype(int)  # Convert to integer if necessary
-    df = df.infer_objects()  # Remove 'copy' argument
+    df['prognosis'] = df['prognosis'].astype(int)  # Convert to integer
 
+    df = df.infer_objects()  # Remove 'copy' argument
+    
+    # Similar process for the testing data
     tr.replace({'prognosis': disease_dict}, inplace=True)
 
-    # Check unique values in testing data
+    # Ensure it is also numerical
     if tr['prognosis'].dtype == 'object':
         raise ValueError(f"Testing data prognosis contains unmapped values: {tr['prognosis'].unique()}")
     
-    tr['prognosis'] = tr['prognosis'].astype(int)  # Convert to integer if necessary
+    tr['prognosis'] = tr['prognosis'].astype(int)  # Convert to integer
     tr = tr.infer_objects()  # Remove 'copy' argument
 
     return df, tr, disease_dict
@@ -107,7 +109,7 @@ y_test = tr['prognosis']
 
 # Encode the target variable with LabelEncoder if still in string format
 le = LabelEncoder()
-y_encoded = le.fit_transform(y)  # Needs to be string labels, assuming df['prognosis'] has no numerical labels
+y_encoded = le.fit_transform(y)  # Needs to be string labels if they were mixed types
 
 def train_models():
     models = {