update partition and sample, create python model

Author: likebupt

articles/machine-learning/algorithm-module-reference/create-python-model.md

@@ -30,7 +30,7 @@ Use of this module requires intermediate or expert knowledge of Python. The modu
 
 This article will show how to use the **Create Python Model** with a simple pipeline. Below is the graph of the pipeline.
 
-![create-python-model](./media/module/aml-create-python-model.png)
+![create-python-model](./media/module/create-python-model.png)
 
 1.  Click **Create Python Model**, edit the script to implement your modeling or data management process. You can base the model on any learner that is included in a Python package in the Azure Machine Learning environment.
 

articles/machine-learning/algorithm-module-reference/media/module/create-python-model.png

@@ -149,9 +149,9 @@ This option is used when you have divided a dataset into multiple partitions and
 
 5. If you are working with multiple partitions, you must add additional instances of the **Partition and Sample** module to handle each partition.
 
-    For example, let's say previously partitioned patients into four folds using age. To work with each individual fold, you need four copies of the **Partition and Sample** module, and in each, you select a different fold, as shown below. It's not correct to use the **Assign to Folds** output directly.  
+    For example, the **Partition and Sample** module in the second row is set to **Assign to Folds**, and the modules in the third row is set to **Pick Fold**.   
 
-    [![Partition and sample](./media/partition-and-sample/partition-and-sample.png)](./media/partition-and-sample/partition-and-sample-lg.png#lightbox)
+    ![Partition and sample](./media/module/partition-and-sample.png)
 
 5. Run the pipeline.