intial commit

app.py

@@ -0,0 +1,34 @@
+import streamlit as st
+import joblib
+import numpy as np
+import pandas as pd
+
+# Load the PyCaret model
+stress_model = joblib.load('base_model_nurse_stress_15min.pkl')
+
+# Set up the main title and subtitle
+st.title("Prediksi Tingkat Stres")
+st.markdown("Prediksi tingkat stres untuk perawat berdasarkan input **EDA**, **HR**, dan **TEMP**. Ideal untuk aplikasi pemantauan stres!")
+
+# Sidebar for input parameters with an expander
+with st.sidebar.expander("🩺 Parameter Input"):
+    st.write("Masukkan parameter untuk **EDA**, **HR**, dan **TEMP** untuk memprediksi tingkat stres.")
+    eda = st.number_input("🖐️ EDA (Aktivitas Elektrodermal)", min_value=0.0, max_value=100.0, value=5.0)
+    hr = st.number_input("❤️ HR (Denyut Jantung)", min_value=0, max_value=200, value=60)
+    temp = st.number_input("🌡️ TEMP (Temperatur)", min_value=30.0, max_value=45.0, value=36.5)
+
+# Create a "Predict" button
+if st.button("🚑 Prediksi"):
+    # Create feature array for prediction
+    features = pd.DataFrame([[eda, hr, temp]], columns=['EDA', 'HR', 'TEMP'])
+
+    # Predict stress level
+    stress_prediction = stress_model.predict(features)[0]
+
+    # Map prediction to stress level category
+    stress_level_map = {0: "Tidak Stres", 1: "Stres Rendah", 2: "Stres Tinggi"}
+    stress_level = stress_level_map.get(stress_prediction, "Tidak Diketahui")
+
+    # Display the prediction
+    st.markdown("### 🧾 Hasil Prediksi")
+    st.write(f"Tingkat Stres yang Diprediksi: **{stress_level}**")

base_model_nurse_stress_15min.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b13c38af23e81bf118c74240ddefeb02ce9344378e03e7821bbe396b519491a
+size 43278906

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+joblib
+numpy
+pandas
+pickle
+pycaret