|
59 | 59 | "syntheticData": { |
60 | 60 | "demo": { |
61 | 61 | "heading": "Information about demo dataset", |
62 | | - "description": "A subset of the [Law School Admission Bar](https://www.kaggle.com/datasets/danofer/law-school-admissions-bar-passage)* dataset is used as a demo. Synthetic data will be generated for the following columns:\n \n \n- sex: student gender, i.e. 1 (male), 2 (female);\n- race1: race of student, i.e., asian, black, hispanic, white, other;\n- ugpa: undergraduate GPA of student (average course grades), continous variable;\n- bar: Ground truth label indicating whether or not the student passed the bar, i.e., passed 1st time, passed 2nd time, failed, non-graduated.\n \n \n\nThe CART method is used to generate the synthetic data. CART generally produces higher quality synthetic datasets, but might not work well on datasets with categorical variables with 20+ categories. Use Gaussian Copula in those cases.\n \n \n\n*The original paper can be found [here](https://files.eric.ed.gov/fulltext/ED469370.pdf)\n \n \n" |
| 62 | + "description": "A subset of the [Law School Admission Bar](https://www.kaggle.com/datasets/danofer/law-school-admissions-bar-passage)* dataset is used as a demo. Synthetic data will be generated for the following columns:\n \n \n", |
| 63 | + "post.description": "The CART method is used to generate the synthetic data. CART generally produces higher quality synthetic datasets, but might not work well on datasets with categorical variables with 20+ categories. Use Gaussian Copula in those cases.\n \n \n\n*The original paper can be found [here](https://files.eric.ed.gov/fulltext/ED469370.pdf)\n \n \n", |
| 64 | + "data.column.Variable_name": "Variable name", |
| 65 | + "data.sex": "sex", |
| 66 | + "data.race1": "race1", |
| 67 | + "data.ugpa": "ugpa", |
| 68 | + "data.bar": "bar", |
| 69 | + |
| 70 | + "data.column.Description": "Description", |
| 71 | + |
| 72 | + "data.column.Description.gender_of_students": "gender of students", |
| 73 | + "data.column.Description.race_of_students": "race of students", |
| 74 | + "data.column.Description.undergraduate_GPA_student": "undergraduate GPA of student (average course grades)", |
| 75 | + "data.column.Description.Ground_truth_label": "Ground truth label indicating whether or not the student passed the bar", |
| 76 | + |
| 77 | + "data.column.Values": "Values", |
| 78 | + |
| 79 | + "data.column.Values.sex": "1 (male), 2 (female)", |
| 80 | + "data.column.Values.race": "asian, black, hispanic, white, other", |
| 81 | + "data.column.Values.ugpa": "1-4", |
| 82 | + "data.column.Values.bar": "passed 1st time, passed 2nd time, failed, non-graduated" |
63 | 83 | }, |
64 | 84 | "exportToPDF": "Download evaluation report as pdf", |
65 | 85 | "exportToJSON": "Download synthetic data as json", |
|
0 commit comments