Student-Habits-vs-Academic-Performance
Data cleaning, and exploratory analysis using Python Pandas and scikit-learn.
Project Overview
The Challenge
Finding out which variables have a high correlation with test scores in the dataset in order to make a linear regression model.
My Solution
Since a lot of the columns had categorical non-numerical data, the best solution was to one-hot encode the values so that I could use them in the correlation heatmap.
Impact
- ✓Was able to see the relationships in data because I used a heatmap
- ✓Determined that the variable that impacted high test scores the most was the study hours per day
Technical Details
Data Visualizations
Data Structure Analysis
This visual shows the data columns with their types before and after one-hot encoding.
Feature Importance
The feature importance reveals which factors most significantly impact test scores.
Correlation Heatmap
Correlation heatmap showing relationships between different variables in the dataset.
Regression Analysis
Scatter plot with regression line showing how well the predicted scores are against the actual scores.