Update src/app.py

src/app.py

@@ -1,3 +1,4 @@
+# app.py
 import streamlit as st
 import pandas as pd
 import requests
@@ -8,109 +9,87 @@ from sklearn.preprocessing import LabelEncoder
 import joblib
 import os
 
-# Load Dataset
+st.set_page_config(page_title="Mushroom Doctor", layout="centered")
+st.title("Mushroom Doctor")
+st.markdown("### *Edible* or *Poisonous*? AI Knows!")
+
 @st.cache_data
 def load_data():
     url = "https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data"
-    res = requests.get(url)
-    res.raise_for_status()
+    r = requests.get(url)
     cols = ['class','cap_shape','cap_surface','cap_color','bruises','odor','gill_attachment',
             'gill_spacing','gill_size','gill_color','stalk_shape','stalk_root','stalk_surface_above_ring',
             'stalk_surface_below_ring','stalk_color_above_ring','stalk_color_below_ring','veil_type',
             'veil_color','ring_number','ring_type','spore_print_color','population','habitat']
-    return pd.read_csv(StringIO(res.text), header=None, names=cols)
+    return pd.read_csv(StringIO(r.text), header=None, names=cols)
 
 df = load_data()
-st.set_page_config(page_title="Mushroom Doctor", layout="centered")
-st.title("🍄 Mushroom Doctor")
-st.markdown("### *Edible* or *Poisonous*? AI Will Tell You!")
+st.success(f"Loaded {len(df):,} mushrooms")
 
-# Stats
-edible = len(df[df['class'] == 'e'])
-poison = len(df[df['class'] == 'p'])
-col1, col2 = st.columns(2)
-col1.metric("🍄 Edible", edible)
-col2.metric("☠ Poisonous", poison)
+edible = len(df[df['class']=='e'])
+poison = len(df[df['class']=='p'])
+c1, c2 = st.columns(2)
+c1.metric("Edible", edible)
+c2.metric("Poisonous", poison)
 
-# Preprocess
 @st.cache_data
-def encode_data(df):
+def prepare():
     encoders = {}
-    df_enc = df.copy()
+    df2 = df.copy()
     for col in df.columns:
         le = LabelEncoder()
-        df_enc[col] = le.fit_transform(df[col])
+        df2[col] = le.fit_transform(df[col])
         encoders[col] = le
-    X = df_enc.drop('class', axis=1)
-    y = df_enc['class']
+    X = df2.drop('class', axis=1)
+    y = df2['class']
     return X, y, encoders
 
-X, y, encoders = encode_data(df)
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+X, y, encoders = prepare()
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-# Train
-if st.button("🚀 Train Model (100% Accuracy!)", type="primary"):
-    with st.spinner("Training Random Forest..."):
+if st.button("Train Model (100% Accuracy)", type="primary"):
+    with st.spinner("Training..."):
         model = RandomForestClassifier(n_estimators=100, random_state=42)
         model.fit(X_train, y_train)
-        accuracy = model.score(X_test, y_test)
-        st.success(f"✅ Trained! Accuracy: {accuracy:.1%}")
-        if accuracy == 1.0:
-            st.balloons()
-            st.markdown("🎉 PERFECT – 100% Accurate!")
+        acc = model.score(X_test, y_test)
+        st.success(f"Trained! Accuracy: {acc:.1%}")
+        if acc == 1.0: st.balloons()
         joblib.dump({"model": model, "encoders": encoders}, "model.pkl")
-        st.session_state.model_trained = True
 
-# Load Model
 model = None
 if os.path.exists("model.pkl"):
-    data = joblib.load("model.pkl")
+    data = joblib.dump.load("model.pkl")
     model = data["model"]
     encoders = data["encoders"]
-    st.session_state.model_trained = True
 
-# Predict
-st.header("🧪 Test Your Mushroom")
-if not st.session_state.get("model_trained", False):
-    st.info("👆 Click 'Train Model' first!")
+st.header("Predict Mushroom")
+if model is None:
+    st.info("Train the model first!")
 else:
     cols = st.columns(3)
     inputs = {}
-    feature_options = {
-        'cap_shape': ['bell', 'conical', 'convex', 'flat', 'knobbed', 'sunken'],
-        'cap_surface': ['fibrous', 'grooves', 'scaly', 'smooth'],
-        'cap_color': ['brown', 'buff', 'cinnamon', 'gray', 'green', 'pink', 'purple', 'red', 'white', 'yellow'],
-        'bruises': ['bruises', 'no'],
-        'odor': ['almond', 'anise', 'creosote', 'fishy', 'foul', 'musty', 'none', 'pungent', 'spicy'],
-        'gill_color': ['black', 'brown', 'buff', 'chocolate', 'gray', 'green', 'orange', 'pink', 'purple', 'red', 'white', 'yellow'],
-        'stalk_shape': ['enlarging', 'tapering'],
-        'spore_print_color': ['black', 'brown', 'buff', 'chocolate', 'green', 'orange', 'purple', 'white', 'yellow'],
-        'population': ['abundant', 'clustered', 'numerous', 'scattered', 'several', 'solitary'],
-        'habitat': ['grasses', 'leaves', 'meadows', 'paths', 'urban', 'waste', 'woods']
+    options = {
+        'cap_shape': ['bell','conical','convex','flat','knobbed','sunken'],
+        'bruises': ['bruises','no'],
+        'odor': ['almond','anise','creosote','fishy','foul','musty','none','pungent','spicy'],
+        'spore_print_color': ['black','brown','buff','chocolate','green','orange','purple','white','yellow'],
+        'population': ['abundant','clustered','numerous','scattered','several','solitary'],
+        'habitat': ['grasses','leaves','meadows','paths','urban','waste','woods']
     }
-
     for i, col in enumerate(X.columns):
         with cols[i % 3]:
-            opts = feature_options.get(col, list(encoders[col].classes_))
-            val = st.selectbox(col.replace('_', ' ').title(), opts, key=f"{col}_sel")
+            val = st.selectbox(col.replace(""," ").title(), options.get(col, list(encoders[col].classes)))
             inputs[col] = encoders[col].transform([val])[0]
 
-    if st.button("🔮 Predict: Safe or Deadly?", type="secondary"):
-        input_data = [[inputs[col] for col in X.columns]]
-        prediction = model.predict(input_data)[0]
-        probs = model.predict_proba(input_data)[0]
-
-        result = encoders['class'].inverse_transform([prediction])[0]
+    if st.button("Is it Safe?", type="secondary"):
+        vec = [[inputs[c] for c in X.columns]]
+        pred = model.predict(vec)[0]
+        prob = model.predict_proba(vec)[0]
+        result = encoders['class'].inverse_transform([pred])[0]
         if result == 'e':
-            st.success("🍄 *EDIBLE – SAFE TO EAT!* 🎉")
+            st.success("EDIBLE – SAFE TO EAT!")
             st.balloons()
         else:
-            st.error("☠ *POISONOUS – DO NOT EAT!* ⚠")
-            st.warning("This could be fatal!")
-
-        col1, col2 = st.columns(2)
-        col1.metric("Safe to Eat", f"{probs[0]:.1%}")
-        col2.metric("Dangerous", f"{probs[1]:.1%}")
-
-st.markdown("---")
-st.caption("🍄 Mushroom Doctor | UCI Dataset | Powered by Streamlit & Hugging Face")
+            st.error("POISONOUS – DO NOT EAT!")
+        st.metric("Edible", f"{prob[0]:.1%}")
+        st.metric("Poisonous", f"{prob[1]:.1%}")