Table 7.
The Data Quality Plan in tabular form, giving a brief overview of the issues present and the handling strategies to be employed.
| Feature | Data Quality Issue(s) | Potential Handling Strategies |
|---|---|---|
| Week20_ONLY nGB | Skew data | Remove rows with 0 values. Remove Outliers. |
| total_GB | Skew data/Outliers/High Cardinality | Remove rows with 0 values. Remove Outliers. |
| GBoverTime (per hour) | Skew data/Outliers | Remove rows with 0 values. Remove Outliers. |
| accDuration | Outliers (Low) | Remove rows with 0 values. Remove Outliers. |
| totalDuration | Outliers (Low) | Remove rows with 0 values. Remove Outliers. |
| nLB | Skew data/Outliers | Remove rows with 0 values. Remove Outliers. |
| total_LB | Skew data/Outliers | Remove rows with 0 values. Remove Outliers. |
| nfGB | Outliers (Low) | Remove rows with 0 values. Remove Outliers. |
| total_fGB | Skew data/Outliers/High Cardinality | Remove rows with 0 values. Remove Outliers. |
| fGBoverTime(per hour) | Skew data/Outliers | Remove rows with 0 values. Remove Outliers. |
| fAccDuration | Outliers (Low) | Remove rows with 0 values. Remove Outliers. |
| fTotalDuration | Outliers (Low) | Remove rows with 0 values. Remove Outliers. |
| f_nLB | Skewed data | Remove rows with 0 values. Remove Outliers. |
| total_fLB | Skewed data/High Cardinality | Remove rows with 0 values. Remove Outliers. |
| F3 | ||
| f3_umbilical_artery_pi | Missing Data (76.7%) | Match metavalues (patID) to isolate relevant data |
| f3_avg_uterine_artery_PI | Missing Data (76.3%) | Match metavalues (patID) to isolate relevant data |
| f3_mca_pi | Missing Data (76.9%) | Match metavalues (patID) to isolate relevant data |
| f3_iugr3 | Missing Data (49.1%)/Irregular Cardinality | Drop from dataset |
| f3_iugr10 | Missing Data (49.1%)/Irregular Cardinality | Match metavalues (patID) to isolate relevant data |