FABRA documentation
2. Description of the aggregators
Language variables description
Description of the aggregators
Measures of range
1. sum: The sum of all observed values in the text.
2. min: The smallest observed value in the text.
3. max: The biggest observed value in the text.
4. len: The total number of observations in the text.
Measures of separation
5. median: The median value of all observations in the text.
6. Q1: The first quantile of all observations in the text.
7. Q3: The third quantile of all observations in the text.
8. 80P: The 80th percentile of all observations in the text.
9. 90P: The 90th percentile of all observations in the text..
Measures of central tendency
10. avg: The average value of all observations in the text.
11. mode: The mode value of all observations in the text.
Measures of dispersion
12. var: The variance of all observations in the text.
13. std: The standard deviation of all observations in the text.
14. RSD: The relative standard deviation of all observations in the text.
15. IQR: The interquartile range of all observations in the text.
16. Dolch: The 90th percentile subtracted from the median, to be applicable to other variables than just sentence length.
Measures of description of the curve
17. skewness: The skewness of the distributuion of all observations in the text.
18. kurtosis: The kurtosis of the distributuion of all observations in the text.