AWS/Machine Learning - Revision history

Christoph: /* Multi-Class Model */

2017-03-20T16:50:49Z

‎Multi-Class Model

Christoph: /* External links */

2017-03-17T19:26:20Z

‎External links

Christoph: /* Binary Model */

2017-03-17T18:08:04Z

‎Binary Model

Christoph: /* Binary Model */

2017-03-17T18:07:38Z

‎Binary Model

Christoph at 18:05, 17 March 2017

2017-03-17T18:05:14Z

Christoph: /* Binary Model */

2017-03-17T18:02:24Z

‎Binary Model

Show changes

Christoph: /* Binary Model */

2017-03-17T16:59:02Z

‎Binary Model

Christoph: /* Binary Model */

2017-03-16T00:16:42Z

‎Binary Model

Christoph: /* Binary Model */

2017-03-15T22:58:03Z

‎Binary Model

Christoph: /* Binary Model */

2017-03-15T22:42:52Z

‎Binary Model

@@ Line 153: / Line 153: @@
 ** These patterns are the Amazon ML model.
 * Evaluate:
-** Using the remaining data, which already has a ''''target''', predict the target using the Amazon ML model and compare that to the target already on record.
+** Using the remaining data, which already has a '''target''', predict the target using the Amazon ML model and compare that to the target already on record.
 * Amazon ML model settings:
 *# Default (recommended setting, if you are not a data-scientist)

@@ Line 579: / Line 579: @@
 ==External links==
 * [https://aws.amazon.com/machine-learning/ AWS Machine Learning]
 * [http://archive.ics.uci.edu/ml/datasets.html University of California at Irvine (UCI) Machine Learning Repository]
 [[Category:AWS]]

@@ Line 556: / Line 556: @@
   $ aws machinelearning predict --ml-model-id "salary-model-v1" --record \
         "age=64,workclass=Private,education=Doctorate,marital-status=Married-civ-spouse,sex=Male,native-country=United-States" \
-         --predict-endpoint "https://realtime.machinelearning.us-east-1.amazonaws.com"
+         --predict-endpoint "<nowiki>https://realtime.machinelearning.us-east-1.amazonaws.com</nowiki>"
 <pre>
+{

@@ Line 513: / Line 513: @@
 The evaluation of my Amazon ML model produced an AUC (model's quality score) of ~0.919, which is considered extremely good for most machine learning applications.
-* Adjust score threshold:
+* If you want, you can adjust score threshold:
   $ aws machinelearning update-ml-model --ml-model-id "salary-model-v1" --score-threshold 0.51
 * Create a real-time endpoint for making predictions:
@@ Line 525: / Line 527: @@
          "PeakRequestsPerSecond": 0,
          "CreatedAt": 1489772906.293,
-         "EndpointUrl": "https://realtime.machinelearning.us-east-1.amazonaws.com"
+         "EndpointUrl": "<nowiki>https://realtime.machinelearning.us-east-1.amazonaws.com</nowiki>"
+     }
+}
@@ Line 533: / Line 535: @@
   $ aws machinelearning predict --ml-model-id "salary-model-v1" --record \
         "age=34,workclass=Private,fnlwgt=338955,education=Bachelors,education-num=13,marital-status=Never-married,occupation=Armed-Forces,relationship=Unmarried,race=Asian-Pacific-Islander,sex=Male,hours-per-week=40,native-country=United-States" \
-        --predict-endpoint "https://realtime.machinelearning.us-east-1.amazonaws.com"
+        --predict-endpoint "<nowiki>https://realtime.machinelearning.us-east-1.amazonaws.com</nowiki>"
 <pre>
+{

@@ Line 381: / Line 381: @@
 * Create the datasource:
   $ aws machinelearning create-data-source-from-s3 \
         --data-source-id "salary-data-all" \
         --data-source-name "salary-data-all" \
@@ Line 395: / Line 394: @@
 * Poll the status of the datasource until complete (useful when creating a datasource via a script):
   $ aws machinelearning wait data-source-available \
         --filter-variable Name --eq "salary-data-all"
 * Create a training datasource using a random selection of 70% of the data:
   $ aws machinelearning create-data-source-from-s3 \
         --cli-input-json '{
         "DataSourceId": "salary-data-model-training",
@@ Line 413: / Line 410: @@
     }'
   $ time aws machinelearning wait data-source-available \
          --filter-variable Name \
          --eq "salary-data-model-training"
@@ Line 423: / Line 419: @@
 * Create an evaluation datasource using a random selection of 30% of the data:
   $ aws machinelearning create-data-source-from-s3 \
         --cli-input-json '{
         "DataSourceId": "salary-data-model-evaluation",
@@ Line 440: / Line 435: @@
 * Get details for a given datasource:
-  $ aws machinelearning get-data-source --data-source-id "salary-data-model-evaluation" --region us-east-1
+  $ aws machinelearning get-data-source --data-source-id "salary-data-model-evaluation"
 <pre>
+{
@@ Line 462: / Line 457: @@
 * Get even more details for a given datasource (output will include datasource schema):
-  $ aws machinelearning describe-data-sources --region us-east-1 --verbose
+  $ aws machinelearning describe-data-sources --verbose
 ;Create and train an Amazon ML model
@@ Line 468: / Line 463: @@
 * Create an Amazon ML model from the "salary-data-model-training" datasource:
   $ aws machinelearning create-ml-model \
         --ml-model-id "salary-model-v1" \
         --ml-model-name "salary-model-v1" \
@@ Line 476: / Line 470: @@
 * Get details on all Amazon ML models:
-  $ aws machinelearning describe-ml-models --region us-east-1
+  $ aws machinelearning describe-ml-models
 * Get details on a given Amazon ML model:
-  $ aws machinelearning describe-ml-models --region us-east-1 --filter-variable Name --eq "salary-model-v1"
+  $ aws machinelearning describe-ml-models --filter-variable Name --eq "salary-model-v1"
   #~OR~
-  $ aws machinelearning get-ml-model --ml-model-id "salary-model-v1" --region us-east-1
+  $ aws machinelearning get-ml-model --ml-model-id "salary-model-v1"
   #~OR~
-  $ aws machinelearning get-ml-model --ml-model-id "salary-model-v1" --region us-east-1 --verbose
+  $ aws machinelearning get-ml-model --ml-model-id "salary-model-v1" --verbose
 * Evaluate the performance of the Amazon ML model created above:
   $ aws machinelearning create-evaluation \
         --evaluation-id "salary-model-eval1" \
         --evaluation-name "salary-model-eval1" \
         --ml-model-id "salary-model-v1" \
         --evaluation-data-source-id "salary-data-model-evaluation"
-  $ aws machinelearning wait evaluation-available --filter-variable Name --eq "salary-model-eval1" --region us-east-1
+  $ aws machinelearning wait evaluation-available --filter-variable Name --eq "salary-model-eval1"
-  $ aws machinelearning get-evaluation --evaluation-id "salary-model-eval1" --region us-east-1
+  $ aws machinelearning get-evaluation --evaluation-id "salary-model-eval1"
 <pre>
+{
@@ Line 524: / Line 517: @@
 * Create a real-time endpoint for making predictions:
-aws machinelearning create-realtime-endpoint --ml-model-id "salary-model-v1"
+ $ aws machinelearning create-realtime-endpoint --ml-model-id "salary-model-v1"
+{
      "MLModelId": "salary-model-v1",
@@ Line 534: / Line 528: @@
+     }
+}
 * Create a prediction based on given characteristics:
@@ Line 553: / Line 548: @@
+}
 </pre>
 The prediction is that someone with the above characteristics will make less than $50k/year (i.e., "<code>predictedLabel</code>" = 0).
@@ Line 573: / Line 569: @@
+}
 </pre>
 The prediction is that someone with the above characteristics will make more than $50k/year (i.e., "<code>predictedLabel</code>" = 1).
 ==External links==

@@ Line 254: / Line 254: @@
 $ cat salary-schema.json
+{
-     "version": "1.0",
+     "version" : "1.0",
-     "targetAttributeName": "target",
+    "rowId" : null,
-     "dataFormat": "CSV",
+    "rowWeight" : null,
-     "dataFileContainsHeader": true,
+     "targetAttributeName" : "target",
      "attributes": [
+         {
@@ Line 319: / Line 321: @@
              "attributeType": "BINARY"
+         }
+     ],
+}
 </pre>
@@ Line 389: / Line 392: @@
       "DataSourceId": "salary-data-all"
+  }
 ==External links==

@@ Line 335: / Line 335: @@
   $ aws s3 cp salary-training.csv s3://${BUCKET_NAME}/
   $ aws s3 cp salary-schema.json s3://${BUCKET_NAME}/
 ==External links==

@@ Line 214: / Line 214: @@
 * Create an S3 bucket to store the data files in:
-  $ aws s3 mb s3://<name-of-your-bucket>
+  $ BUCKET_NAME=<name-of-your-bucket>
 * Download the datasets:
@@ Line 251: / Line 252: @@
 You should end up with a schema file that looks like the following:
 <pre>
-$ cat salary-training.schema
+$ cat salary-schema.json
+{
      "version": "1.0",
@@ Line 321: / Line 322: @@
+}
 </pre>
 ==External links==

@@ Line 238: / Line 238: @@
 ;Creating a schema for a datasource
 * We need to tell Amazon ML how to interpret our dataset by telling it the layout of our data. This is done via a schema.
-* A ''schema'' is composed of all attributes in the input data and their corresponding data types.
+* A ''schema'' is composed of all attributes in the input data and their corresponding data types. That is, the schema tells ML what type of data is in each of the columns in the CSV file.
 * Amazon ML uses the information in the schema to read and interpret the input data, compute statistics, apply the correct attribute transformations, and fine-tune its learning algorithms.
 * Amazon ML requires a schema or a record layout to be submitted with the data when using the AWS CLI.
 ==External links==