How ranjeetchauhan0805/student-exam-score-predictor works
The product is a student exam-score prediction app: students enter study and academic details, and the app returns a score predicted by a saved linear-regression model. A separate training script builds and evaluates that model from the CSV; the Streamlit app also shows dataset summaries. The README documents exploratory analysis and visualization, and the tree includes a notebook, but its contents were not sampled, so its specific operations and connections are uncertain.
Main entry points: app.py Streamlit app · exam_score_predictor.pkl Regression model · predict.py CLI predictor · student_exam_scores.csv Student scores CSV
Components 10
Analysis & training
- Train & evaluate
src/train.py - EDA & visualization
notebooks/eda.ipynb
Prediction interfaces
- Streamlit app
app.py - Predicted score
- CLI predictor
src/predict.py - Printed score
Data & model artifacts
- Student scores CSV
data/student_exam_scores.csv - Regression model
models/exam_score_predictor.pkl
Other components
- Student
- Terminal user
Connections 12
- Student → Streamlit app: enters details
- Streamlit app → Regression model: loads model
- Streamlit app → Regression model: predicts with
- Streamlit app → Predicted score: displays
- Streamlit app → Student scores CSV: reads summaries
- Train & evaluate → Student scores CSV: reads
- Train & evaluate → Regression model: saves model
- EDA & visualization → Student scores CSV: analyzes
- Terminal user → CLI predictor: enters details
- CLI predictor → Regression model: loads model
- CLI predictor → Regression model: predicts with
- CLI predictor → Printed score: prints