Differences

This shows you the differences between two versions of the page.

--- ease:machinelearning:classifier_evaluation [2020/06/22 10:10] – created s_fuyedc
+++ ease:machinelearning:classifier_evaluation [2020/06/22 11:49] (current) – s_fuyedc
@@ Line 3: / Line 3: @@
 In [[https://ease-crc.org/material/ease/machinelearning/classifier_training|the previous section]] we trained our decision tree model. With this last section this model is to be evaluated.
-Now it comes to evaluating what the tree model is capable of. The purpose of this model is to predict which action is the most likely to happen, depending on the previously performed action. Simply execute the code blocks to see the outcome.
+Now it comes to evaluating what the tree model is capable of. The purpose of this model is to predict which action is the most likely to happen, depending on the previously performed action and its context. Simply execute the code blocks to see the outcome.
-The first block shows a table that gives information about precision, recall, F1-Score, and support of the model. Read more about these terms further above in the lesson.
+The first block shows a table that gives information about precision, recall, F1-Score, and support of the model. Read more about these terms [[https://ease-crc.org/material/ease/machinelearning/machine_learning_theory|in the earlier sections]] of this lesson.
-The second code block is much more interesting. It generates a confusion matrix, showing for each action how often it was predicted successfully. In an optimal model, this matrix would only show entries on a diagonal line from top-left to bottom-right. If the confusion matrix is visualized without labels at the left and bottom side, check the code in the beginning and compare it with the solutions provided in this tutorial. Having the //NEXT// column removed is the most probable mistake.
+The second code block is much more interesting. It generates a confusion matrix, showing for each action how often it was predicted successfully. In an optimal model, this matrix would only show entries on a diagonal line from top-left to bottom-right. If the confusion matrix is visualized without labels at the left and bottom side, check the code [[https://ease-crc.org/material/ease/machinelearning/data_preparation|of your data preparation]] and compare it with the solutions provided in this tutorial. Having the //NEXT// column removed is the most probable mistake.
 {{ :ease:generated_cof_matrix.png |}}
@@ Line 13: / Line 13: @@
 Along the rows we see the true classes, or what is expected to be predicted. In the columns are the classes predicted from our decision-tree model. Notice, that the most prominent and also correct prediction is //NoNext//, whereas the other classes line up pretty well along the optimal diagonal line. Some predictions are either falsely classified, or defaulted to //NoNext//.
-There seems to be some confusion especially about the //AcquireGraspOfSomething// and the //MovingToLocation//. Print out the narratives for //MovingToLocation// and compare it with the other table.
+There seems to be some confusion, especially about the //AcquireGraspOfSomething// and the //MovingToLocation//. Print out the narratives for //MovingToLocation// and compare it with the other table.
 <code python>
 other_narratives = narratives[(narratives.next == 'MovingToLocation')]