Upload 3 files

Discover how many calories you burn with ease! Our Calories Burn Predictor is a simple yet powerful app designed to help you track your fitness progress.

Key Features:
➤Easy Input: Provide details like age, gender, height, weight, exercise duration, heart rate, and body temperature.
➤Instant Results: Get accurate calorie burn predictions in just one click.
➤User-Friendly Design: Enjoy a sleek, dark-themed interface for a smooth experience.
➤Fitness Tracking Made Simple: Perfect for both fitness enthusiasts and casual users.
➤Built with Care: Developed by M. Nabeel to bring precision and simplicity to your fitness journey.
Start your journey toward better health today!

app.py

@@ -0,0 +1,105 @@
+import pandas as pd
+import pickle
+import streamlit as st
+
+# Load the model at the start
+#@st.cache_resource
+def load_model(pkl_file):
+    """Load the prediction model from a file."""
+    with open(pkl_file, 'rb') as model_file:
+        return pickle.load(model_file)
+
+def main():
+    # Title and layout
+    st.markdown("<h1 style='text-align: center; margin-top: -30px;'>Calories Burn Predictor 🏋🏽</h1>", unsafe_allow_html=True)
+
+    # Input fields
+    st.subheader("Enter Your Details:")
+
+    gender = st.radio("Gender", options=["Male", "Female"])
+    age_input = st.text_input("Age (years):", placeholder="e.g., 25")
+    height_input = st.text_input("Height (cm):", placeholder="e.g., 170")
+    weight_input = st.text_input("Weight (kg):", placeholder="e.g., 70")
+    duration_input = st.text_input("Duration of Exercise (minutes):", placeholder="e.g., 30")
+    heart_rate_input = st.text_input("Heart Rate (bpm):", placeholder="e.g., 100")
+    body_temp_input = st.text_input("Body Temperature (°C):", placeholder="e.g., 36.5")
+
+    # Prediction button
+    if st.button("Predict"):
+        inputs_valid, validated_inputs = validate_inputs(
+            gender, age_input, height_input, weight_input, duration_input, heart_rate_input, body_temp_input
+        )
+
+        if inputs_valid:
+            predict_calories(validated_inputs)
+
+
+def validate_inputs(gender, age_input, height_input, weight_input, duration_input, heart_rate_input, body_temp_input):
+    """Validate user inputs and return a flag with validated inputs."""
+    errors = []
+
+    def validate_input(value, field_name, is_float=False, is_int=False):
+        if not value.strip():
+            errors.append(f"Please enter your {field_name}.")
+            return None
+        try:
+            if is_float:
+                return float(value)
+            elif is_int:
+                return int(float(value))
+            else:
+                return value
+        except ValueError:
+            errors.append(f"Please enter a valid numeric value for {field_name}.")
+            return None
+
+    # Validate each input
+    age = validate_input(age_input, "Age", is_int=True)
+    height = validate_input(height_input, "Height", is_float=True)
+    weight = validate_input(weight_input, "Weight", is_float=True)
+    duration = validate_input(duration_input, "Duration of Exercise", is_float=True)
+    heart_rate = validate_input(heart_rate_input, "Heart Rate", is_float=True)
+    body_temp = validate_input(body_temp_input, "Body Temperature", is_float=True)
+
+    if errors:
+        for error in errors:
+            st.error(error)
+        return False, None
+
+    return True, {
+        "Gender": gender,
+        "Age": age,
+        "Height": height,
+        "Weight": weight,
+        "Duration": duration,
+        "Heart_Rate": heart_rate,
+        "Body_Temp": body_temp
+    }
+
+def predict_calories(inputs):
+    """Perform the calorie prediction and display the result."""
+    try:
+        # Convert inputs to DataFrame
+        input_data = pd.DataFrame([
+            [
+                inputs["Gender"],
+                inputs["Age"],
+                inputs["Height"],
+                inputs["Weight"],
+                inputs["Duration"],
+                inputs["Heart_Rate"],
+                inputs["Body_Temp"]
+            ]
+        ], columns=['Gender', 'Age', 'Height', 'Weight', 'Duration', 'Heart_Rate', 'Body_Temp'])
+
+        # Predict and display the result
+        result = pipe.predict(input_data)[0]
+        st.success(f"Calories burned: {result:.2f} kcal")
+    except Exception as e:
+        st.error(f"An error occurred during prediction: {e}")
+
+if __name__ == "__main__":
+
+    pipe = load_model("final_pipe.pkl")
+    main()
+    st.markdown("<br><br><h5 style='text-align: center;'>Developed by M.Nabeel</h5>", unsafe_allow_html=True)

final_pipe.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d6a34c40c5225c77c8d64e675675f02511a81d6547c5f08b15cb9d33ca9f05
+size 439060

requirements.txt

@@ -0,0 +1,5 @@
+pandas==2.2.2
+numpy==1.26.4
+streamlit==1.37.1
+scikit-learn==1.5.1
+xgboost==2.1.2