Dark Mode
Educational Performance Survey Dataset
Education & Learning Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset provides detailed information on student performance in mathematics courses within secondary school settings. It offers a rich collection of 33 features, encompassing demographic, social, and academic factors that can influence a student's grades. This dataset is suitable for both regression tasks, particularly when predicting student grades, and a variety of analytical tasks, including exploratory data analysis and data visualisation to uncover insights into educational outcomes. It is noted that some categorical features within the dataset might exhibit imbalance.
Columns
- school: Type of school (e.g., GP, MS)
- sex: Gender of the student (F for Female, M for Male)
- age: Age of the student
- address: Address type of the student (U for Urban, R for Rural)
- famsize: Family size (GT3 for greater than 3, LE3 for less than or equal to 3)
- Pstatus: Parents' cohabitation status (T for Together, A for Apart)
- Medu: Mother's education level (ranked from 0 to 4, where 0 is none and 4 is university degree)
- Fedu: Father's education level (ranked from 0 to 4, where 0 is none and 4 is university degree)
- Mjob: Mother's occupation (e.g., other, services, at_home, teacher, health)
- Fjob: Father's occupation (e.g., other, services, at_home, teacher, health)
- reason: Reason for choosing the current school (e.g., course, home, reputation, other)
- guardian: Student's guardian (mother, father, other)
- traveltime: Travel time to school (ranked from 1 to 4, where 1 is <15 min and 4 is >1 hour)
- studytime: Weekly study time (ranked from 1 to 4, where 1 is <2 hours and 4 is >10 hours)
- failures: Number of past class failures (from 0 to 3)
- schoolsup: Extra educational support from school (Boolean: true/false)
- famsup: Family educational support (Boolean: true/false)
- paid: Extra paid classes within the course subject (Boolean: true/false)
- activities: Participation in extra-curricular activities (Boolean: true/false)
- nursery: Attended nursery school (Boolean: true/false)
- higher: Desire for higher education (Boolean: true/false)
- internet: Internet access at home (Boolean: true/false)
- romantic: In a romantic relationship (Boolean: true/false)
- famrel: Quality of family relationships (ranked from 1 to 5, where 1 is very bad and 5 is excellent)
- freetime: Free time after school (ranked from 1 to 5, where 1 is very low and 5 is very high)
- goout: Going out with friends (ranked from 1 to 5, where 1 is very low and 5 is very high)
- Dalc: Workday alcohol consumption (ranked from 1 to 5, where 1 is very low and 5 is very high)
- Walc: Weekend alcohol consumption (ranked from 1 to 5, where 1 is very low and 5 is very high)
- health: Current health status (ranked from 1 to 5, where 1 is very bad and 5 is very good)
- absences: Number of school absences
- G1: First period grade (numerical)
- G2: Second period grade (numerical)
- G3: Final grade (numerical)
Distribution
The dataset is provided as a CSV file, named 'student_data.csv', with a file size of 41.98 kB. It contains 395 records (rows) and consists of 33 distinct columns, each with complete data and no missing values.
Usage
This dataset is ideal for:
- Predictive Modelling: Utilising regression techniques to forecast student performance, with the final grade (G3) serving as a primary target variable.
- Data Analysis: Conducting in-depth analysis to understand the various factors influencing student success and well-being.
- Educational Research: Exploring correlations between social, family, and demographic attributes and academic achievement.
- Data Visualisation: Creating visual representations of student data to identify trends, patterns, and outliers.
- Exploratory Data Analysis (EDA): Gaining initial insights and understanding the underlying structure of the data before more complex modelling.
Coverage
The dataset covers students from secondary schools, surveyed regarding their mathematics course performance. It captures a diverse demographic of students based on age, gender, family background (size, parental education and occupation, relationship status), and lifestyle choices (travel time, study time, social activities, health). No specific geographic region or precise time range for the survey is detailed in the provided information.
License
CC0: Public Domain
Who Can Use It
This dataset is particularly useful for:
- Data Analysts: To perform various analytical tasks and extract meaningful insights.
- Data Scientists: For building and evaluating regression models predicting student grades.
- Educators and Researchers: To understand factors impacting student performance and inform educational strategies.
- Beginners in Data Science: As a beginner-friendly resource for learning data analysis, data visualisation, and machine learning concepts due to its clean structure and relevant features.
Dataset Name Suggestions
- Student Academic Performance Factors
- Secondary School Math Grades
- Student Success Predictor Dataset
- Educational Performance Survey
- Factors Affecting Student Achievement
Attributes
Original Data Source: Educational Performance Survey Dataset
QUALITY