Student_Performance_Analysis_Project
Student_Performance_Analysis_Project
Objective
To analyze student performance based on various factors such as attendance, study habits,
parental involvement, and socioeconomic status, and visualize the findings through
interactive dashboards and detailed plots.
Dataset
Publicly available datasets like the Student Performance Dataset from the UCI Repository or
custom data can be used. Example fields include:
- Student ID
- Exam Scores (Math, Reading, Writing)
- Attendance (%)
- Hours Studied Weekly
- Parental Education Level
- Socioeconomic Status
Project Workflow
1. Data Preprocessing
Tools: Python (Pandas)
Steps:
- Load and clean the dataset (handle missing values, normalize data, etc.).
- Add calculated fields if necessary (e.g., total score, average study time).
- Export the processed dataset for visualization tools (CSV/Excel).
2. Visualization Plan
a) Power BI Dashboard
Create an interactive dashboard with filters like:
- Gender, parental education level, and socioeconomic status.
- Attendance range, study hours, or exam types.
Visualizations:
- Pie chart for gender distribution.
- Bar chart showing average performance across subjects.
- Line chart for trends in attendance vs. grades.
b) Matplotlib Visualizations
Visualizations:
- Line chart showing average grades over time (e.g., semester).
- Scatter Plot: Attendance vs. Exam Scores to show correlation.
- Bar Plot: Exam scores by parental education level.
Example Code:
```python
import matplotlib.pyplot as plt
plt.scatter(data['Attendance'], data['Math_Score'], alpha=0.7)
plt.title('Attendance vs Math Scores')
plt.xlabel('Attendance (%)')
plt.ylabel('Math Scores')
plt.show()
```
c) Seaborn Visualizations
Visualizations:
- Heatmap: Correlation between scores, attendance, study time, and parental involvement.
- Box Plot: Subject scores grouped by gender or parental education level.
- Pair Plot: Relationships between all numerical variables (scores, attendance, study hours).
Example Code:
```python
import seaborn as sns
sns.heatmap(data.corr(), annot=True, cmap='coolwarm')
plt.title('Correlation Heatmap')
plt.show()
```
d) Tableau Dashboard
Visualizations:
- Geographical Heatmap: Show regional performance trends if location data is available.
- Sunburst Chart: Break down performance by categories like gender → parental education
→ scores.
- Interactive Storyboard: Highlight key findings (e.g., how study hours improve scores).
Features:
- Clickable filters to explore specific demographics.
- Time-lapse to visualize performance changes over terms or semesters.