Upload 3 files

Heart_ResNet.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ef3302e466550066f7941f280856761c006505cadb69ae3ea2a55713056495
+size 12056984

app (16).py

@@ -0,0 +1,172 @@
+import streamlit as st
+import librosa
+import numpy as np
+import tensorflow as tf
+import matplotlib.pyplot as plt
+from datetime import datetime
+
+# Load the pre-trained ResNet model
+@st.cache_resource
+def load_model():
+    model = tf.keras.models.load_model('Heart_ResNet.h5')
+    return model
+
+model = load_model()
+
+# Initialize session state
+if 'page' not in st.session_state:
+    st.session_state.page = '🏠 Home'
+if 'theme' not in st.session_state:
+    st.session_state.theme = 'Light Green'
+if 'history' not in st.session_state:
+    st.session_state.history = []
+
+# Custom CSS for theme
+def apply_theme():
+    if st.session_state.theme == "Light Green":
+        st.markdown("""
+        <style>
+        body, .stApp { background-color: #e8f5e9; }
+        .stApp { color: #004d40; }
+        .stButton > button, .stFileUpload > div { 
+            background-color: #004d40; 
+            color: white; 
+        }
+        .stButton > button:hover, .stFileUpload > div:hover {
+            background-color: #00332c;
+        }
+        </style>
+        """, unsafe_allow_html=True)
+    else:
+        st.markdown("""
+        <style>
+        body, .stApp { background-color: #e0f7fa; }
+        .stApp { color: #006064; }
+        .stButton > button, .stFileUpload > div { 
+            background-color: #006064; 
+            color: white; 
+        }
+        .stButton > button:hover, .stFileUpload > div:hover {
+            background-color: #004d40;
+        }
+        </style>
+        """, unsafe_allow_html=True)
+
+# Sidebar navigation
+with st.sidebar:
+    st.title("Heartbeat Analysis 🩺")
+    st.session_state.page = st.radio(
+        "Navigation",
+        ["🏠 Home", "⚙️ Settings", "👤 Profile"],
+        index=["🏠 Home", "⚙️ Settings", "👤 Profile"].index(st.session_state.page)
+    )
+
+# Audio processing function
+def process_audio(file_path):
+    SAMPLE_RATE = 22050
+    DURATION = 10
+    input_length = int(SAMPLE_RATE * DURATION)
+    
+    X, sr = librosa.load(file_path, sr=SAMPLE_RATE, duration=DURATION)
+    
+    if len(X) < input_length:
+        pad_width = input_length - len(X)
+        X = np.pad(X, (0, pad_width), mode='constant')
+    
+    mfccs = np.mean(librosa.feature.mfcc(y=X, sr=sr, n_mfcc=52,
+                                        n_fft=512, hop_length=256).T, axis=0)
+    return mfccs, X, sr
+
+def classify_audio(filepath):
+    mfccs, waveform, sr = process_audio(filepath)
+    features = mfccs.reshape(1, 52, 1)
+    preds = model.predict(features)
+    class_names = ["artifact", "murmur", "normal"]
+    result = {name: float(preds[0][i]) for i, name in enumerate(class_names)}
+    
+    # Store in history
+    st.session_state.history.append({
+        'date': datetime.now().strftime("%Y-%m-%d %H:%M"),
+        'file': filepath,
+        'result': result
+    })
+    
+    return result, waveform, sr
+
+# Page rendering functions
+def home_page():
+    st.title("Heartbeat Analysis")
+    uploaded_file = st.file_uploader("Upload your heartbeat audio", type=["wav", "mp3"])
+    
+    if uploaded_file is not None:
+        st.audio(uploaded_file.read(), format='audio/wav')
+        uploaded_file.seek(0)
+        
+        if st.button("Analyze Now"):
+            with st.spinner('Analyzing...'):
+                with open("temp.wav", "wb") as f:
+                    f.write(uploaded_file.getbuffer())
+                
+                results, waveform, sr = classify_audio("temp.wav")
+                
+                st.subheader("Analysis Results")
+                cols = st.columns(3)
+                labels = {
+                    'artifact': "🚨 Artifact",
+                    'murmur': "💔 Murmur",
+                    'normal': "❤️ Normal"
+                }
+                
+                for (label, value), col in zip(results.items(), cols):
+                    with col:
+                        st.metric(labels[label], f"{value*100:.2f}%")
+                
+                st.subheader("Heartbeat Waveform")
+                fig, ax = plt.subplots(figsize=(10, 3))
+                librosa.display.waveshow(waveform, sr=sr, ax=ax)
+                ax.set_title("Audio Waveform Analysis")
+                st.pyplot(fig)
+
+def settings_page():
+    st.title("Settings")
+    new_theme = st.selectbox(
+        "Select Theme",
+        ["Light Green", "Light Blue"],
+        index=0 if st.session_state.theme == "Light Green" else 1
+    )
+    
+    if new_theme != st.session_state.theme:
+        st.session_state.theme = new_theme
+        st.experimental_rerun()
+
+def profile_page():
+    st.title("Medical Profile")
+    with st.expander("Personal Information", expanded=True):
+        col1, col2 = st.columns(2)
+        with col1:
+            st.write("**Name:** Kpetaa Patrick")
+            st.write("**Age:** 35")
+        with col2:
+            st.write("**Blood Type:** O+")
+            st.write("**Last Checkup:** 2025-06-17")
+    
+    st.subheader("Analysis History")
+    if not st.session_state.history:
+        st.write("No previous analyses found")
+    else:
+        for analysis in reversed(st.session_state.history):
+            with st.expander(f"Analysis from {analysis['date']}"):
+                st.write(f"File: {analysis['file']}")
+                st.write("Results:")
+                for label, value in analysis['result'].items():
+                    st.progress(value, text=f"{label.capitalize()}: {value*100:.2f}%")
+
+# Main app logic
+apply_theme()
+
+if st.session_state.page == "🏠 Home":
+    home_page()
+elif st.session_state.page == "⚙️ Settings":
+    settings_page()
+elif st.session_state.page == "👤 Profile":
+    profile_page()

requirements (8).txt

@@ -0,0 +1,6 @@
+streamlit
+librosa
+numpy
+tensorflow
+matplotlib
+datetime