A pandas DataFrame with 100000 rows and 14 columns. Nulls: 31875. Memory: 4.1 MB. Columns: age (category, 14976 nulls, cardinality: 42 categories including '33.0', '24.0', '22.0'), self_emp (category, 5883 nulls, cardinality: 2 categories including 'Salaried', 'Self Emp'), afqt (float32, 5542 nulls, stats: range 0 to 1e+02, mean 50, std 29). Sample row: {'id': '1.0', 'year': '1', 'sample_id': "'CROSS FEMALE WHITE'", 'race': "'NON-BLACK, NON-HISPANIC'", 'sex': "'FEMALE'", 'afqt': 'nan', 'self_emp': 'nan', 'income': "'0'", 'age': 'nan', 'hourswork': "'0'", 'hgc': 'nan', 'weight': '0.0', 'nlsy79': '1.0', 'nlsy97': '0.0'}. (profiled from a sample of the first 100,000 rows; pass full=True to read all)