java/com.sap.sailing.windestimation/src/com/sap/sailing/windestimation/model/regressor/twdtransition/DurationBasedTwdTransitionRegressorModelContext.java
... ...
@@ -43,8 +43,10 @@ public final class DurationBasedTwdTransitionRegressorModelContext
43 43
*
44 44
*/
45 45
public enum DurationValueRange {
46
- BEGINNING(0, 1, 1, false), MIDDLE1(1, 140, SupportedDimensionValueRange.SQUARE_ROOT_AS_POLYNOMIAL_DEGREE,
47
- true), MIDDLE2(140, 5394, 1, true), REMAINDER(5394, SupportedDimensionValueRange.MAX_VALUE, 1, true);
46
+ BEGINNING(0, 1, 1, false),
47
+ MIDDLE1(1, 140, SupportedDimensionValueRange.SQUARE_ROOT_AS_POLYNOMIAL_DEGREE, true),
48
+ MIDDLE2(140, 5394, 1, true),
49
+ REMAINDER(5394, SupportedDimensionValueRange.MAX_VALUE, 1, true);
48 50
49 51
private final SupportedDimensionValueRange supportedDimensionValueRange;
50 52
wiki/howto/windestimation.md
... ...
@@ -20,7 +20,7 @@ To complete the training process successfully, you need to make sure that you ha
20 20
![Screenshot of graphical info dialog requesting to perform data cleansing for duration dimension](../images/windestimation/dialogRequestingDataCleansingForDurationDimension.jpg "Screenshot of graphical info dialog requesting to perform data cleansing for duration dimension")
21 21
Press OK. Afterwards, a graphical window must open with two charts. The top chart is an XY-chart where the x-axis represents **seconds** and the y-axis represents various TWD delta-based measures (e.g. standard deviation or mean). Below the XY-chart, a histogram for the data points of the XY-chart is provided. You can zoom-in and zoom-out in each of the charts by mouse dragging. Be aware that currently the zoom level of both charts is not synchronizing.
22 22
![Screenshot of graphical wind data visualization tool for duration dimension](../images/windestimation/aggregatedDurationBasedTwdDeltaTransitionBeforeDataCleansing.jpg "Screenshot of duration-based TWD delta visualization tool before data cleansing")
23
-3. Open your graphical MongoDB client and connect to ``windEstimation`` database hosted within your local MongoDB. Open the collection with name ``aggregatedDurationTwdTransition``. Within the collection, you will see all the instances/data points visualized in the previous step. The attribute used for the x-axis is ``value``. Its corresponding metrics plotted in y-axis are the other attributes. ``std`` represents standard deviation (``Sigma`` curve in XY-chart) and ``std0`` represents standard deviation with zero as mean value (``Zero mean sigma`` curve in XY-chart).
23
+3. Open your graphical MongoDB client and connect to the ``windEstimation`` database hosted within your local MongoDB. Open the collection named ``aggregatedDurationTwdTransition``. Within the collection you will see all the instances/data points visualized in the previous step. The attribute used for the x-axis is ``value``. Its corresponding metrics plotted in y-axis are the other attributes. ``std`` represents standard deviation (``Sigma`` curve in XY-chart) and ``std0`` represents standard deviation with zero as mean value (``Zero mean sigma`` curve in XY-chart).
24 24
![Screenshot of MongoDB Compass with opened aggregatedDurationTwdTransition collection](../images/windestimation/mongoDbCompassWithOpenedAggregatedDurationTwdTransitionCollection.jpg "Screenshot of MongoDB Compass with opened aggregatedDurationTwdTransition collection")
25 25
4. Delete all the instances within the collection which do not make sense. For this, use the data visualization tool from step 2 to identify such instances. Some of the instances are not representative due to the small number of supporting instances which is visualized in the histogram. Such instances can produce unreasonable bumps in the XY-chart. The desired output of this step is that the curve ``Zero mean sigma`` looks smooth and always growing, e.g. as depicted below:
26 26
![Screenshot of graphical visualization tool of duration dimension after data cleansing](../images/windestimation/aggregatedDurationBasedTwdDeltaTransitionAfterDataCleansing.jpg "Screenshot of duration-based TWD delta visualization tool after data cleansing")