Spaces:
Build error
Build error
File size: 4,100 Bytes
88a18a5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | import streamlit as st
import pandas as pd
import joblib
import tempfile
import os
from train_models import run_automl
import plotly.express as px
st.set_page_config(page_title="🔮 AutoML Explorer", layout="wide")
st.title("🔮 AutoML Explorer - Predict Anything From Any CSV")
st.markdown("""
Welcome to **AutoML Explorer** — your no-code ML assistant:
- 📂 Upload any CSV
- 🧠 Let the app clean, preprocess & analyze your data
- 🤖 Tries many ML models including XGBoost & LightGBM
- 🎯 Shows the best with full explanation & visuals
- 🔮 Make live predictions & download result CSV
""")
file = st.file_uploader("📁 Upload your CSV file", type=["csv"])
if file:
df = pd.read_csv(file)
st.subheader("📊 Dataset Preview")
st.dataframe(df.head())
st.subheader("🎯 Choose Your Target Column")
target = st.selectbox("Select what you want to predict:", df.columns)
if st.button("🚀 Run AutoML"):
with st.spinner("🤖 Running smart ML analysis..."):
result = run_automl(df, target)
if "error" in result:
st.error(result["error"])
else:
st.success("✨ AutoML Complete! Here's your custom ML report:")
st.markdown("### 🔍 What We Did With Your Data")
st.json(result["preprocessing"])
st.markdown("### 🤖 Model Scores")
model_df = pd.DataFrame(result["model_scores"], index=["Score (%)"]).T
st.dataframe(model_df)
# Bar Chart
st.markdown("### 📊 Visual Model Comparison")
chart = px.bar(model_df, x=model_df.index, y="Score (%)", title="Model Performance Comparison", color_discrete_sequence=["#636EFA"])
st.plotly_chart(chart, use_container_width=True)
st.markdown("### ✅ Best Model Chosen")
st.markdown(f"🏆 **{result['best_model']}** with **{result['best_accuracy']:.2f}% accuracy/performance**")
if result["type"] == "classification":
st.markdown("### 📈 Confusion Matrix")
st.dataframe(pd.DataFrame(result["confusion_matrix"]))
st.markdown("### 🧾 Classification Report")
st.json(result["classification_report"])
else:
st.markdown("### 📏 Regression Metrics")
st.json(result["regression_report"])
# Save model & create download button
with tempfile.NamedTemporaryFile(delete=False, suffix=".pkl") as tmp_file:
joblib.dump(result["model_object"], tmp_file.name)
st.download_button("📥 Download Best Model (.pkl)", data=open(tmp_file.name, "rb"), file_name="best_model.pkl")
# Predictions CSV
st.markdown("### 📄 Prediction Results (Test Set)")
st.dataframe(result["predictions"])
csv = result["predictions"].to_csv(index=False).encode('utf-8')
st.download_button("📥 Download Predictions CSV", csv, "predictions.csv", "text/csv")
# Live prediction input
st.markdown("### 🔮 Live Prediction Input")
input_data = {}
for col in df.drop(columns=[target]).columns:
dtype = df[col].dtype
if dtype == 'object':
input_data[col] = st.selectbox(f"{col}", options=sorted(df[col].dropna().unique()))
else:
input_data[col] = st.number_input(f"{col}", value=float(df[col].mean()))
if st.button("🎯 Predict with Best Model"):
user_df = pd.DataFrame([input_data])
from utils import preprocess_data
try:
X_temp, _, _, _ = preprocess_data(pd.concat([df, user_df], ignore_index=True), target)
user_input = X_temp.iloc[-1:]
prediction = result["model_object"].predict(user_input)[0]
st.success(f"🧠 Predicted Output: {prediction}")
except Exception as e:
st.error(f"Prediction failed: {e}")
|