📈Students Performance in Exams: EDA and Visualization 📊

Students Performance in Exams dataset consists of the marks secured by the students in various subjects.

Why did I choose this dataset?

This was my first analysis and this dataset seemed easier to me than others

What was my aim and did I succeed?

I wanted to observe how some features in the dataset (gender, race/ethnicity, course scores, etc..) make a difference in exams.

As a result of the analyzes and visualizations I made on the data set, I answered some questions that I was curious about.

For example;

• What is the effect of gender and education level on average score?
• What is the effect of gender and preparation course on average score?
• Which group is the most successful? (on average_score)

What could I have done better ? (TO-DO)

• I will increase the variety of questions I want to know (i will ask a lot more questions to the dataset)
• Visualization techniques are poor. Should be improved.

What did I learn from this analysis?

• Practice in exploratory data analysis, data manipulation and data visualization
• My graphic interpretation skills have improved

Analysis Content

1. [First Step]

   • [Import The Required Libraries]
   • [Load Dataset]
   • [Copy Real Dataset]
   • [Data Frame Info And Missing Values]
   • [First look]
   • [Rename Columns]
   • [Create a new column ("average_score")]
   • [Describe Data Frame]
   • [Create a new column ("grade")]

2. [Visualization]

   • [Grade Pie Chart]
   • [Score Heatmap]
   • [Let's compare Grades and Gender]

3. [What I want to know]

   • [Q1: What is the effect of gender and education level on average score?]
   • [Q2: What is the effect of gender and preparation course on average score?]
   • [Q3: Which group is the most successful? (on average_score)]

---

Dataset Link: Students Performance in Exams (Kaggle)

My Analysis on Kaggle: Students Performance: 📈 EDA and 📊 Visualization

My Kaggle Profile: Samet Arda Erdogan