Youth Alcohol and Study Impact

Columns

• school: Indicates the student's school, with options 'GP' (Gabriel Pereira) or 'MS' (Mousinho da Silveira). For Maths.csv, 88% attend GP.
• sex: The student's sex, binary 'F' (female) or 'M' (male). For Maths.csv, 53% are female.
• age: The student's age, a numeric value ranging from 15 to 22. For Maths.csv, the mean age is 16.7.
• address: Type of student's home address, binary 'U' (urban) or 'R' (rural). For Maths.csv, 78% reside in urban areas.
• famsize: Family size, binary 'LE3' (less or equal to 3) or 'GT3' (greater than 3). For Maths.csv, 71% have family sizes greater than 3.
• Pstatus: Parents' cohabitation status, binary 'T' (living together) or 'A' (apart). For Maths.csv, 90% of parents live together.
• Medu: Mother's education level, numeric from 0 (none) to 4 (higher education). For Maths.csv, the mean is 2.75.
• Fedu: Father's education level, numeric from 0 (none) to 4 (higher education). For Maths.csv, the mean is 2.52.
• Mjob: Mother's job, nominal ('teacher', 'health' care, 'services', 'at_home', 'other'). For Maths.csv, 'other' is the most common at 36%.
• Fjob: Father's job, nominal ('teacher', 'health' care, 'services', 'at_home', 'other'). For Maths.csv, 'other' is the most common at 55%.
• reason: Reason for choosing the school, nominal ('home', 'reputation', 'course' preference, 'other'). For Maths.csv, 'course' preference is the most common at 37%.
• guardian: Student's guardian, nominal ('mother', 'father', 'other'). For Maths.csv, 'mother' is the most common at 69%.
• traveltime: Home to school travel time, numeric from 1 (<15 min) to 4 (>1 hour). For Maths.csv, the mean is 1.45, with 257 students travelling less than 15 minutes.
• studytime: Weekly study time, numeric from 1 (<2 hours) to 4 (>10 hours). For Maths.csv, the mean is 2.04, with 198 students studying 2 to 5 hours.
• failures: Number of past class failures, numeric ('n' if 1<=n<3, else 4). For Maths.csv, the mean is 0.33, with 312 students having 0 failures.
• schoolsup: Extra educational support, binary 'yes' or 'no'. For Maths.csv, 13% receive extra support.
• famsup: Family educational support, binary 'yes' or 'no'. For Maths.csv, 61% receive family support.
• paid: Extra paid classes for the course subject, binary 'yes' or 'no'. For Maths.csv, 46% attend paid classes.
• activities: Extra-curricular activities, binary 'yes' or 'no'. For Maths.csv, 51% participate in activities.
• nursery: Attended nursery school, binary 'yes' or 'no'. For Maths.csv, 79% attended nursery.
• higher: Wants to take higher education, binary 'yes' or 'no'. For Maths.csv, 95% desire higher education.
• internet: Internet access at home, binary 'yes' or 'no'. For Maths.csv, 83% have internet access.
• romantic: In a romantic relationship, binary 'yes' or 'no'. For Maths.csv, 33% are in a relationship.
• famrel: Quality of family relationships, numeric from 1 (very bad) to 5 (excellent). For Maths.csv, the mean is 3.94, with most ratings being 4 or 5.
• freetime: Free time after school, numeric from 1 (very low) to 5 (very high). For Maths.csv, the mean is 3.24, with most ratings being 3 or 4.
• goout: Frequency of going out with friends, numeric from 1 (very low) to 5 (very high). For Maths.csv, the mean is 3.11, with most ratings being 2, 3 or 4.
• Dalc: Workday alcohol consumption, numeric from 1 (very low) to 5 (very high). For Maths.csv, the mean is 1.48, with most students having very low consumption.
• Walc: Weekend alcohol consumption, numeric from 1 (very low) to 5 (very high). For Maths.csv, the mean is 2.29, with common values being 1, 2, and 3.
• health: Current health status, numeric from 1 (very bad) to 5 (very good). For Maths.csv, the mean is 3.55, with most ratings being 5.
• absences: Number of school absences, numeric from 0 to 93. For Maths.csv, the mean is 5.71, with a median of 4.
• G1: First period grade, numeric from 0 to 20. For Maths.csv, the mean is 10.9.
• G2: Second period grade, numeric from 0 to 20. For Maths.csv, the mean is 10.7.
• G3: Final grade, numeric from 0 to 20 (output target attribute). For Maths.csv, the mean is 10.4.

Distribution

Usage

• Predicting student academic performance (final grades - G3) based on a wide array of personal, social, and school-related factors.
• Investigating the correlation between alcohol consumption habits (workday and weekend) and academic outcomes.
• Building classification models to identify students at risk of academic failure or those likely to pursue higher education.
• Performing regression analysis to understand the influence of different attributes on grades.
• Conducting educational research to understand socio-economic impacts on learning and inform school policies or support programmes.

Coverage

License

Who Can Use It

• Education Professionals: For insights into student behaviour and academic drivers.
• Machine Learning Engineers: To develop predictive models for student success or classification tasks.
• Social Scientists: For exploring the impact of social and family backgrounds on educational attainment.
• Public Health Researchers: To study the relationship between alcohol consumption and academic performance.
• Data Analysts: For exploratory data analysis and visualising educational trends.

Dataset Name Suggestions

• Portuguese Student Performance Factors
• Student Academic Achievement in Portugal
• Secondary Education Performance Study
• Youth Alcohol and Study Impact
• Portuguese School Grades Dataset

Attributes