Update app.py

app.py

@@ -64,7 +64,7 @@ def load_data():
     disease_dict = {
         'Fungal infection': 0, 'Allergy': 1, 'GERD': 2, 'Chronic cholestasis': 3, 'Drug Reaction': 4,
         'Peptic ulcer disease': 5, 'AIDS': 6, 'Diabetes': 7, 'Gastroenteritis': 8, 'Bronchial Asthma': 9,
-        'Hypertension': 10, 'Migraine': 11, 'Cervical spondylosis': 12, 'Paralysis': 13,
+        '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,
@@ -80,37 +80,36 @@ def load_data():
     # Unique values for debugging
     print("Unique values in prognosis after mapping:", df['prognosis'].unique())
 
-    # Before converting to integer, check if all entries are mapped correctly
-    if df['prognosis'].dtype == 'object':  # Check if any mapping error occurred
-        raise ValueError(f"Prognosis contains unmapped values: {df['prognosis'].unique()}")
+    # Ensure prognosis is purely numerical after mapping
+    if df['prognosis'].dtype == 'object':  # Check for unmapped entries
+        raise ValueError(f"The prognosis contains unmapped values: {df['prognosis'].unique()}")
 
-    # Convert to integer
-    df['prognosis'] = df['prognosis'].astype(int)
+    df['prognosis'] = df['prognosis'].astype(int)  # Convert to integer
 
     # Inference doesn't require fixing as copy=True defaults
     df = df.infer_objects()
 
     tr.replace({'prognosis': disease_dict}, inplace=True)
-    
+
     # 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 = tr.infer_objects()
+
+    tr['prognosis'] = tr['prognosis'].astype(int)  # Convert to integer
+    tr = tr.infer_objects()  # Remove 'copy' argument
 
     return df, tr, disease_dict
 
 df, tr, disease_dict = load_data()
-l1 = list(df.columns[:-1])
+l1 = list(df.columns[:-1])  # All columns except prognosis
 X = df[l1]
 y = df['prognosis']
 X_test = tr[l1]
 y_test = tr['prognosis']
 
-# Encode the target variable with LabelEncoder if not already numerical
+# Encode the target variable with LabelEncoder if still in string format
 le = LabelEncoder()
-y_encoded = le.fit_transform(y)  # Fits and transforms the labels
+y_encoded = le.fit_transform(y)  # Needs to be only string labels for the encoder
 
 def train_models():
     models = {