Delete src

src/label_encoder.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:71f60109d277dd7a7214745370e35402d31c5abdec368c7a7a259ee5bcc180be
-size 351

src/lung_cancer_classifier.h5

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7444437d2b7d73ef8de823a92a9dc2de6c7353ed30a71539c0352489869d0a74
-size 64032

src/requirements.txt

@@ -1,6 +0,0 @@
-streamlit
-tensorflow
-numpy
-pandas
-scikit-learn
-joblib

src/streamlit_app.py

@@ -1,76 +0,0 @@
-import streamlit as st
-import numpy as np
-import tensorflow as tf
-import joblib
-
-# --- Load model and label encoder ---
-model = tf.keras.models.load_model("lung_cancer_classifier.h5")  # Load H5 model
-le_target = joblib.load("label_encoder.pkl")
-
-# --- Page configuration ---
-st.set_page_config(page_title="Lung Cancer Risk Classifier", layout="centered")
-
-# --- Title and description ---
-st.title("Lung Cancer Risk Prediction")
-st.write("""
-This application predicts the **level of lung cancer risk** for a patient.  
-**Note:** The data used to train this model consists of patients already diagnosed with lung cancer.  
-The target of this classification is the **Lung Cancer Level**.
-""")
-
-# --- Input fields ---
-Age = st.number_input("Age", min_value=1, max_value=100, value=37)
-
-# Gender dropdown fixed to show Male/Female but return encoded value
-Gender = st.selectbox(
-    "Gender",
-    options=[("Male", 1), ("Female", 2)],
-    format_func=lambda x: x[0]  # show only label
-)[1]  # get encoded value
-
-Air_Pollution = st.slider("Air Pollution Exposure", 1, 8, 4)
-Alcohol_use = st.slider("Alcohol Use", 1, 8, 5)
-Dust_Allergy = st.slider("Dust Allergy", 1, 8, 5)
-Occupational_Hazards = st.slider("Occupational Hazards", 1, 8, 5)
-Genetic_Risk = st.slider("Genetic Risk", 1, 7, 5)
-Chronic_Lung_Disease = st.slider("Chronic Lung Disease", 1, 7, 4)
-Balanced_Diet = st.slider("Balanced Diet", 1, 7, 4)
-Obesity = st.slider("Obesity", 1, 7, 4)
-Smoking = st.slider("Smoking", 1, 8, 4)
-Passive_Smoker = st.slider("Passive Smoker", 1, 8, 4)
-Chest_Pain = st.slider("Chest Pain", 1, 9, 4)
-Coughing_of_Blood = st.slider("Coughing of Blood", 1, 9, 4)
-Fatigue = st.slider("Fatigue", 1, 9, 4)
-Weight_Loss = st.slider("Weight Loss", 1, 8, 4)
-Shortness_of_Breath = st.slider("Shortness of Breath", 1, 9, 4)
-Wheezing = st.slider("Wheezing", 1, 8, 4)
-Swallowing_Difficulty = st.slider("Swallowing Difficulty", 1, 8, 4)
-Clubbing_of_Finger_Nails = st.slider("Clubbing of Finger Nails", 1, 9, 4)
-Frequent_Cold = st.slider("Frequent Cold", 1, 7, 4)
-Dry_Cough = st.slider("Dry Cough", 1, 7, 4)
-Snoring = st.slider("Snoring", 1, 7, 3)
-
-# --- Combine inputs ---
-input_data = np.array([[
-    Age, Gender, Air_Pollution, Alcohol_use, Dust_Allergy,
-    Occupational_Hazards, Genetic_Risk, Chronic_Lung_Disease,
-    Balanced_Diet, Obesity, Smoking, Passive_Smoker,
-    Chest_Pain, Coughing_of_Blood, Fatigue, Weight_Loss,
-    Shortness_of_Breath, Wheezing, Swallowing_Difficulty,
-    Clubbing_of_Finger_Nails, Frequent_Cold, Dry_Cough, Snoring
-]])
-
-# --- Prediction ---
-if st.button("Predict"):
-    prediction = model.predict(input_data)
-    predicted_class = prediction.argmax(axis=1)[0]
-    confidence = prediction.max(axis=1)[0]
-
-    label = le_target.inverse_transform([predicted_class])[0]
-
-    st.success(f"Predicted Lung Cancer Level: {label}")
-    st.info(f"Prediction Confidence: {confidence:.2%}")
-
-# --- Footer ---
-st.markdown("---")
-st.markdown("**Train By:** Edcel Bogay")