Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,110 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+# streamlit_app.py  ← THIS NAME WORKS PERFECTLY ON HUGGING FACE
 import streamlit as st
+import pandas as pd
+import requests
+from io import StringIO
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import LabelEncoder
+import joblib
+import os
+
+st.set_page_config(page_title="Mushroom Doctor", layout="centered")
+st.title("Mushroom Doctor")
+st.markdown("### Is it *Edible* or *Poisonous*?")
+
+# Load dataset
+@st.cache_data
+def load_data():
+    url = "https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data"
+    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(r.text), header=None, names=cols)
+
+df = load_data()
+st.success("Dataset loaded – 8,124 mushrooms!")
+
+# Show stats
+edible = len(df[df['class'] == 'e'])
+poisonous = len(df[df['class'] == 'p'])
+c1, c2 = st.columns(2)
+c1.metric("Edible (Safe)", edible)
+c2.metric("Poisonous (Deadly)", poisonous)
+
+# Preprocess
+@st.cache_data
+def preprocess():
+    encoders = {}
+    df_enc = df.copy()
+    for col in df.columns:
+        le = LabelEncoder()
+        df_enc[col] = le.fit_transform(df[col])
+        encoders[col] = le
+    X = df_enc.drop('class', axis=1)
+    y = df_enc['class']
+    return X, y, encoders
+
+X, y, encoders = preprocess()
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+# Train button
+if st.button("Train Model – 100% Accuracy!", type="primary"):
+    with st.spinner("Training Random Forest..."):
+        model = RandomForestClassifier(n_estimators=100, random_state=42)
+        model.fit(X_train, y_train)
+        acc = model.score(X_test, y_test)
+        st.success(f"Trained! Accuracy: {acc:.1%}")
+        if acc == 1.0:
+            st.balloons()
+            st.markdown("*PERFECT CLASSIFICATION!*")
+        joblib.dump({"model": model, "encoders": encoders}, "model.pkl")
+
+# Load model
+model = None
+if os.path.exists("model.pkl"):
+    loaded = joblib.load("model.pkl")
+    model = loaded["model"]
+    encoders = loaded["encoders"]
+
+# Prediction
+st.header("Check Your Mushroom")
+if model is None:
+    st.info("Click 'Train Model' first!")
+else:
+    cols = st.columns(3)
+    inputs = {}
+    feature_options = {
+        'odor': ['none','almond','anise','creosote','fishy','foul','musty','pungent','spicy'],
+        'bruises': ['bruises','no'],
+        'gill_size': ['broad','narrow'],
+        '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]:
+            options = feature_options.get(col, list(encoders[col].classes_))
+            val = st.selectbox(col.replace("_", " ").title(), options, key=col)
+            inputs[col] = encoders[col].transform([val])[0]
+
+    if st.button("Predict – Safe or Deadly?", type="secondary"):
+        input_vec = [[inputs[c] for c in X.columns]]
+        pred = model.predict(input_vec)[0]
+        prob = model.predict_proba(input_vec)[0]
+        result = encoders['class'].inverse_transform([pred])[0]
+
+        if result == 'e':
+            st.success("EDIBLE – SAFE TO EAT!")
+            st.balloons()
+        else:
+            st.error("POISONOUS – DO NOT EAT!")
+            st.warning("This mushroom is deadly!")
+
+        st.metric("Edible Probability", f"{prob[0]:.1%}")
+        st.metric("Poisonous Probability", f"{prob[1]:.1%}")
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+st.caption("Mushroom Doctor • 100% Deployable • File: streamlit_app.py")