Update app.py

Update requirements.txt

Update app.py

Update app.py

Update requirements.txt

Update app.py

Update requirements.txt

Update app.py

Update requirements.txt

Update requirements.txt

Update requirements.txt

Rename .streamlit to .streamlit/config.toml:

Create .streamlit

Update students.csv

Update app.py

Update requirements.txt

math_grade,programming_grade,gpa,interest,recommended_course 85,80,3.8,Data Science,Machine Learning 78,70,3.5,Data Science,Data Mining 60,65,2.8,Networking,Computer Networks 55,50,2.5,Programming,Introduction to Programming 90,88,3.9,AI,Artificial Intelligence 72,75,3.2,Security,Cyber Security 68,60,3.0,Statistics,Applied Statistics 40,45,2.0,Programming,Basic Computing

Create requirements.txt

import streamlit as st import pandas as pd from sklearn.preprocessing import LabelEncoder from sklearn.tree import DecisionTreeClassifier import matplotlib.pyplot as plt import seaborn as sns # ----------------------- # Load Dataset # ----------------------- data = pd.read_csv("students.csv") # Encode categorical data le_interest = LabelEncoder() le_course = LabelEncoder() data["interest"] = le_interest.fit_transform(data["interest"]) data["recommended_course"] = le_course.fit_transform(data["recommended_course"]) # Features and target X = data[["math_grade", "programming_grade", "gpa", "interest"]] y = data["recommended_course"] # Train model model = DecisionTreeClassifier() model.fit(X, y) # ----------------------- # Streamlit UI # ----------------------- st.set_page_config(page_title="Course Recommendation System", layout="wide") st.title("🎓 University Course Recommendation System") st.markdown(""" This interactive system recommends the most suitable university courses for students based on their grades and interests. """) # Sidebar for input st.sidebar.header("Input Student Data") math = st.sidebar.slider("Math Grade", 0, 100, 70) programming = st.sidebar.slider("Programming Grade", 0, 100, 70) gpa = st.sidebar.slider("GPA", 0.0, 4.0, 3.0, 0.1) interest = st.sidebar.selectbox("Interest", le_interest.classes_) # Recommendation if st.button("Recommend Course"): interest_encoded = le_interest.transform([interest])[0] pred = model.predict([[math, programming, gpa, interest_encoded]]) course_name = le_course.inverse_transform(pred) st.success(f"✅ Recommended Course: {course_name[0]}") # Display student data in table st.subheader("📊 Your Input Data") input_df = pd.DataFrame({ "Math Grade": [math], "Programming Grade": [programming], "GPA": [gpa], "Interest": [interest] }) st.table(input_df) # Graph: Compare with dataset st.subheader("📈 Comparison with Dataset") fig, ax = plt.subplots(figsize=(8,4)) sns.scatterplot(data=data, x="math_grade", y="programming_grade", hue="recommended_course", palette="tab10", s=100, ax=ax) ax.scatter(math, programming, color='red', s=200, label="You") ax.set_title("Math vs Programming Grades") ax.legend() st.pyplot(fig) # Show dataset with st.expander("View Dataset"): st.dataframe(data)

initial commit