How samirshaikh2425/student-performance-prediction works
This repository is a student exam-score prediction and feature-engineering analysis project. Its main workflow loads the CSV, cleans and enriches student records, encodes categorical features, compares three Random Forest regression setups, and prints regression metrics. The README also documents feature importance and visualizations, but their implementation in the notebook was not sampled, so those relationships are not asserted. The Python source supports the modeling flow; no separate application or persistent model store is shown.
Main entry points: model.py Run Analysis · student_performance.csv Student Records
Components 12
Student Data
- Student Records
data/student_performance.csv
Data Preparation
- Clean Data
src/model.py - Engineer Features
src/model.py - Encode Categories
src/model.py
Model Analysis
- Run Analysis
src/model.py - Baseline Model
src/model.py - Engineered Model
src/model.py - Select Features
src/model.py - Selected Model
src/model.py - Regression Metrics
src/model.py - Model Comparison
src/model.py
Other components
- Analyst
Connections 13
- Analyst → Run Analysis: runs
src/model.py - Run Analysis → Clean Data: loads and cleans
src/model.py - Clean Data → Student Records: reads
src/model.py - Run Analysis → Engineer Features: engineers
src/model.py - Run Analysis → Encode Categories: encodes
src/model.py - Run Analysis → Baseline Model: trains and predicts
src/model.py - Baseline Model → Regression Metrics: evaluates predictions
src/model.py - Run Analysis → Engineered Model: trains and predicts
src/model.py - Engineered Model → Regression Metrics: evaluates predictions
src/model.py - Run Analysis → Select Features: selects features
src/model.py - Run Analysis → Selected Model: trains and predicts
src/model.py - Selected Model → Regression Metrics: evaluates predictions
src/model.py - Run Analysis → Model Comparison: prints summary
src/model.py