Data Explorer Component

Component displays three tables (one for each data type column group Nominal-Numeric-Date&Time) with all statistics and histogram.

For nominal valued columns (String and Boolean) Unique Count, Missing Value Count, Minimum, Mode, Maximum, Top N value with count and percentage, Bottom N value with count and percentage are displayed. For each column the distribution of nominal values is displayed too.

For numeric valued columns (Double, Long, Integer) Minimum, Mode, Mean, Median, Maximum, Lower Bound, Range, Upper Bound, Standard Deviation, Variance, Q1, Q3, IQR, Bottom Whisker, Top Whisker, Overal Sum, Kurtosis, Skewness, Num of Missing Values, Number of Zeros, Number of Non Outlier, Number of Bottom Outliers, Number of Top Outliers, Top N outlier values, Bottom N Outlier Values are displayed. For each column the histogram is displayed too.

For date & time valued columns (Date, Time, Date & Time etc) Minimum, Mean Date, Median Date, Mode, Maximum, Lower Bound, Upper Bound, Date Range in Days, Unique Count, Number of Missing Values are displayed.

The component configuration dialog offers column selection, Top-Bottom nominal value display limit, Top-Bottom Outlier value display limit and K coefficient for IQR outlier analysis.

Displays statistics and histogram can be read from the out ports 1,2,3 respectively for Nominal, Numeric, Data&Time column group.

The excluded columns can be read from 4th out port.

Input ports

1. Type: Table
   Port 1
   A table from which to compute statistics.

Output ports

1. Type: Table
   Port 1
   Nominal valued column statistics and histogram output
2. Type: Table
   Port 2
   Numerical valued column statistics and histogram output
3. Type: Table
   Port 3
   Date & Time valued column statistics and histogram output
4. Type: Table
   Port 4
   The filtered input date after selected columns excluded