Return-Path: X-Original-To: archive-asf-public-internal@cust-asf2.ponee.io Delivered-To: archive-asf-public-internal@cust-asf2.ponee.io Received: from cust-asf.ponee.io (cust-asf.ponee.io [163.172.22.183]) by cust-asf2.ponee.io (Postfix) with ESMTP id 1CB5F200B73 for ; Mon, 29 Aug 2016 21:36:52 +0200 (CEST) Received: by cust-asf.ponee.io (Postfix) id 1AF1F160AB8; Mon, 29 Aug 2016 19:36:52 +0000 (UTC) Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by cust-asf.ponee.io (Postfix) with SMTP id 8A840160A89 for ; Mon, 29 Aug 2016 21:36:50 +0200 (CEST) Received: (qmail 9625 invoked by uid 500); 29 Aug 2016 19:36:49 -0000 Mailing-List: contact commits-help@predictionio.incubator.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@predictionio.incubator.apache.org Delivered-To: mailing list commits@predictionio.incubator.apache.org Received: (qmail 9616 invoked by uid 99); 29 Aug 2016 19:36:49 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd1-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 29 Aug 2016 19:36:49 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd1-us-west.apache.org (ASF Mail Server at spamd1-us-west.apache.org) with ESMTP id 5231FCDA89 for ; Mon, 29 Aug 2016 19:36:49 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd1-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: -3.739 X-Spam-Level: X-Spam-Status: No, score=-3.739 tagged_above=-999 required=6.31 tests=[KAM_ASCII_DIVIDERS=0.8, KAM_LAZY_DOMAIN_SECURITY=1, RCVD_IN_DNSWL_HI=-5, RCVD_IN_MSPIKE_H3=-0.01, RCVD_IN_MSPIKE_WL=-0.01, RP_MATCHES_RCVD=-0.519] autolearn=disabled Received: from mx1-lw-eu.apache.org ([10.40.0.8]) by localhost (spamd1-us-west.apache.org [10.40.0.7]) (amavisd-new, port 10024) with ESMTP id 3CGe2gXFOjP9 for ; Mon, 29 Aug 2016 19:36:45 +0000 (UTC) Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx1-lw-eu.apache.org (ASF Mail Server at mx1-lw-eu.apache.org) with SMTP id 62A9F60CDA for ; Mon, 29 Aug 2016 19:36:44 +0000 (UTC) Received: (qmail 9495 invoked by uid 99); 29 Aug 2016 19:36:43 -0000 Received: from git1-us-west.apache.org (HELO git1-us-west.apache.org) (140.211.11.23) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 29 Aug 2016 19:36:43 +0000 Received: by git1-us-west.apache.org (ASF Mail Server at git1-us-west.apache.org, from userid 33) id 638D8E08AF; Mon, 29 Aug 2016 19:36:43 +0000 (UTC) Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: donald@apache.org To: commits@predictionio.incubator.apache.org Date: Mon, 29 Aug 2016 19:36:45 -0000 Message-Id: In-Reply-To: References: X-Mailer: ASF-Git Admin Mailer Subject: [4/6] incubator-predictionio-site git commit: Based on apache/incubator-predictionio#8fa95bf5a76f2c345a1b6ede3cb2ae5a3cf2c528 archived-at: Mon, 29 Aug 2016 19:36:52 -0000 http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/18d9d1a4/templates/ecommercerecommendation/quickstart/index.html ---------------------------------------------------------------------- diff --git a/templates/ecommercerecommendation/quickstart/index.html b/templates/ecommercerecommendation/quickstart/index.html index 440f3ea..f06150d 100644 --- a/templates/ecommercerecommendation/quickstart/index.html +++ b/templates/ecommercerecommendation/quickstart/index.html @@ -32,7 +32,7 @@ Your system is all ready to go. [INFO] [App$] MyApp1 | 1 | 3mZWDzci2D5YsqAnqNnXH9SB6Rg3dsTBs8iHkK6X2i54IQsIZI1eEeQQyMfs7b3F | (all) [INFO] [App$] MyApp2 | 2 | io5lz6Eg4m3Xe4JZTBFE13GMAf1dhFl6ZteuJfrO84XpdOz9wRCrDU44EUaYuXq5 | (all) [INFO] [App$] Finished listing 2 app(s). -

4. Collecting Data

Next, let's collect training data for this Engine. By default, the E-Commerce Recommendation Engine Template supports 2 types of entities and 2 events: user and item; events view and buy. An item has the categories property, which is a list of category names (String). A user can view and buy an item. The specical constraint entiy with entityId unavailableItems defines a list of unavailable items and is taken into account in realtime during serving.

In summary, this template requires '$set' user event, '$set' item event, user-view-item events, user-buy-item event and '$set' constraint event.

This template can easily be customized to consider other user-to-it em events.

You can send these events to PredictionIO Event Server in real-time easily by making a HTTP request or through the provided SDK. Please see App Integration Overview for more details how to integrate your app with SDK.

Let's try sending events to EventServer with the following curl commands (The corresponding SDK code is showed in other tabs).

Replace <ACCCESS_KEY> by the Access Key generated in above steps. Note that localhost:7070 is the default URL of the Event Server.

For convenience, set your access key to the shell variable, run:

$ ACCESS_KEY=<ACCESS_KEY>

For example, when a new user with id "u0" is created in your app on time 2014-11-02T09:39:45.618-08:00 (current time will be used if eventTime is not specified), you can send a $set event for this user. To send this e vent, run the following curl command:

1
+

4. Collecting Data

Next, let's collect training data for this Engine. By default, the E-Commerce Recommendation Engine Template supports 2 types of entities and 2 events: user and item; events view and buy. An item has the categories property, which is a list of category names (String). A user can view and buy an item. The specical constraint entiy with entityId unavailableItems defines a list of unavailable items and is taken into account in realtime during serving.

In summary, this template requires '$set' user event, '$set' item event, user-view-item events, user-buy-item event and '$set' constraint event.

This template can easily be customized to consider other user-to-it em events.

You can send these events to PredictionIO Event Server in real-time easily by making a HTTP request or through the provided SDK. Please see App Integration Overview for more details how to integrate your app with SDK.

Let's try sending events to EventServer with the following curl commands (The corresponding SDK code is showed in other tabs).

Replace <ACCCESS_KEY> by the Access Key generated in above steps. Note that localhost:7070 is the default URL of the Event Server.

For convenience, set your access key to the shell variable, run:

$ ACCESS_KEY=<ACCESS_KEY>

For example, when a new user with id "u0" is created in your app on time 2014-11-02T09:39:45.618-08:00 (current time will be used if eventTime is not specified), you can send a $set event for this user. To send this e vent, run the following curl command:

1
 2
 3
 4
@@ -47,7 +47,7 @@ Your system is all ready to go.
   "entityId" : "u0",
   "eventTime" : "2014-11-02T09:39:45.618-08:00"
 }'
-
 
1
+
 
1
 2
 3
 4
@@ -78,7 +78,7 @@ Your system is all ready to go.
   entity_type="user",
   entity_id=<USER_ID>
 )
-
 
1
+
 
1
 2
 3
 4
@@ -119,7 +119,7 @@ Your system is all ready to go.
   'properties' => array('categories' => array('<CATEGORY_1>', '<CATEGORY_2>'))
 ));
 ?>
-
 
1
+
 
1
 2
 3
 4
@@ -136,7 +136,7 @@ Your system is all ready to go.
   'user',
   <USER ID>
 )
-
 
1
+
 
1
 2
 3
 4
@@ -161,7 +161,7 @@ Your system is all ready to go.
   .entityType("user")
   .entityId(<USER_ID>);
 client.createEvent(userEvent);
-

When a new item "i0" is created in your app on time 2014-11-02T09:39:45.618-08:00 (current time will be used if eventTime is not specified), you can send a $set event for the item. Note that the item is set with categories properties: "c1" and "c2". Run the following curl command:

1
+

When a new item "i0" is created in your app on time 2014-11-02T09:39:45.618-08:00 (current time will be used if eventTime is not specified), you can send a $set event for the item. Note that the item is set with categories properties: "c1" and "c2". Run the following curl command:

1
 2
 3
 4
@@ -182,7 +182,7 @@ Your system is all ready to go.
   }
   "eventTime" : "2014-11-02T09:39:45.618-08:00"
 }'
-
 
1
+
 
1
 2
 3
 4
@@ -201,7 +201,7 @@ Your system is all ready to go.
     "categories" : ["<CATEGORY_1>", "<CATEGORY_2>"]
   }
 )
-
 
1
+
 
1
 2
 3
 4
@@ -218,7 +218,7 @@ Your system is all ready to go.
   'properties' => array('categories' => array('<CATEGORY_1>', '<CATEGORY_2>'))
 ));
 ?>
-
 
1
+
 
1
 2
 3
 4
@@ -235,7 +235,7 @@ Your system is all ready to go.
   }
 )
 
-
 
1
+
 
1
 2
 3
 4
@@ -248,7 +248,7 @@ Your system is all ready to go.
   .entityId(<ITEM_ID>)
   .property("categories", ImmutableList.of("<CATEGORY_1>", "<CATEGORY_2>"));
 client.createEvent(itemEvent)
-

The properties of the user and item can be set, unset, or delete by special events $set, $unset and $delete. Please refer to Event API for more details of using these events.

When the user "u0" view item "i0" on time 2014-11-10T12:34:56.123-08:00 (current time will be used if eventTime is not specified), you can send a view event. Run the following curl command:

1
+

The properties of the user and item can be set, unset, or delete by special events $set, $unset and $delete. Please refer to Event API for more details of using these events.

When the user "u0" view item "i0" on time 2014-11-10T12:34:56.123-08:00 (current time will be used if eventTime is not specified), you can send a view event. Run the following curl command:

1
 2
 3
 4
@@ -267,7 +267,7 @@ Your system is all ready to go.
   "targetEntityId" : "i0",
   "eventTime" : "2014-11-10T12:34:56.123-08:00"
 }'
-
 
1
+
 
1
 2
 3
 4
@@ -284,7 +284,7 @@ Your system is all ready to go.
   target_entity_type="item",
   target_entity_id=<ITEM ID>
 )
-
 
1
+
 
1
 2
 3
 4
@@ -303,7 +303,7 @@ Your system is all ready to go.
    'targetEntityId' => <ITEM ID>
 ));
 ?>
-
 
1
+
 
1
 2
 3
 4
@@ -322,7 +322,7 @@ Your system is all ready to go.
   }
 )
 
-
 
1
+
 
1
 2
 3
 4
@@ -337,7 +337,7 @@ Your system is all ready to go.
     .targetEntityType("item")
     .targetEntityId(<ITEM_ID>);
 client.createEvent(viewEvent);
-

When the user "u0" buy item "i0" on time 2014-11-10T13:00:00.123-08:00 (current time will be used if eventTime is not specified), you can send a view event. Run the following curl command:

1
+

When the user "u0" buy item "i0" on time 2014-11-10T13:00:00.123-08:00 (current time will be used if eventTime is not specified), you can send a view event. Run the following curl command:

1
 2
 3
 4
@@ -356,7 +356,7 @@ Your system is all ready to go.
   "targetEntityId" : "i0",
   "eventTime" : "2014-11-10T13:00:00.123-08:00"
 }'
-
 
1
+
 
1
 2
 3
 4
@@ -373,7 +373,7 @@ Your system is all ready to go.
   target_entity_type="item",
   target_entity_id=<ITEM ID>
 )
-
 
1
+
 
1
 2
 3
 4
@@ -392,7 +392,7 @@ Your system is all ready to go.
    'targetEntityId' => <ITEM ID>
 ));
 ?>
-
 
1
+
 
1
 2
 3
 4
@@ -409,7 +409,7 @@ Your system is all ready to go.
     'targetEntityId' => <ITEM ID>
   }
 )
-
 
1
+
 
1
 2
 3
 4
@@ -490,19 +490,19 @@ User u10 buys item i40

When the engine is deployed successfully and running, you should see a console message similar to the following:

1
 2
[INFO] [HttpListener] Bound to /0.0.0.0:8000
 [INFO] [MasterActor] Bind successful. Ready to serve.
-

Do not kill the deployed engine process.

By default, the deployed engine binds to http://localhost:8000. You can visit that page in your web browser to check its status.

Engine Status

6. Use the Engine

Now, You can retrieve predicted results. To recommend 4 items to user ID "u1". You send this JSON { "user": ["u1"], "num": 4 } to the deployed engine and it will return a JSON of the recommended items. Simply send a query by making a HTTP request or through the EngineClient of an SDK.

With the deployed engine running, open another temrinal and run the following curl command or use SDK to send the query:

1
+

Do not kill the deployed engine process.

By default, the deployed engine binds to http://localhost:8000. You can visit that page in your web browser to check its status.

Engine Status

6. Use the Engine

Now, You can retrieve predicted results. To recommend 4 items to user ID "u1". You send this JSON { "user": ["u1"], "num": 4 } to the deployed engine and it will return a JSON of the recommended items. Simply send a query by making a HTTP request or through the EngineClient of an SDK.

With the deployed engine running, open another temrinal and run the following curl command or use SDK to send the query:

1
 2
 3
 4
 
$ curl -H "Content-Type: application/json" \
 -d '{ "user": "u1", "num": 4 }' \
 http://localhost:8000/queries.json
 
-
 
1
+
 
1
 2
 3
 
import predictionio
 engine_client = predictionio.EngineClient(url="http://localhost:8000")
 print engine_client.send_query({"user": "u1", "num": 4})
-
 
1
+
 
1
 2
 3
 4
@@ -521,7 +521,7 @@ http://localhost:8000/queries.json
 print_r($response);
 
 ?>
-
 
1
+
 
1
 2
 3
 4
@@ -534,7 +534,7 @@ http://localhost:8000/queries.json
 response = client.send_query('user' => 'i1', 'num' => 4)
 
 puts response
-
 
1
+
 
1
 2
 3
 4
@@ -578,7 +578,7 @@ http://localhost:8000/queries.json
     {"item":"i3","score":0.003007015026561692}
   ]
 }
-

MyECommerceRecommendation is now running.

To update the model periodically with new data, simply set up a cron job to call pio train and pio deploy. The engine will continue to serve prediction results during the re-train process. After the training is completed, pio deploy will automatically shutdown the existing engine server and bring up a new process on the same port.

Note that if you import a large data set and the training seems to be taking forever or getting stuck, it's likely that there is not enough executor memory. It's recommended to setup a Spark standalone cluster, you'll need to specify more driver and executor memory when training with a large data set. Please see FAQ here for instructions.

Setting constraint "unavailableItems"

Now let's send a item contraint "unavailableItems" (replace accessKey with your Access Key):

You can also use SDK to send this event as decribed in the SDK sample above.

1
+

MyECommerceRecommendation is now running.

To update the model periodically with new data, simply set up a cron job to call pio train and pio deploy. The engine will continue to serve prediction results during the re-train process. After the training is completed, pio deploy will automatically shutdown the existing engine server and bring up a new process on the same port.

Note that if you import a large data set and the training seems to be taking forever or getting stuck, it's likely that there is not enough executor memory. It's recommended to setup a Spark standalone cluster, you'll need to specify more driver and executor memory when training with a large data set. Please see FAQ here for instructions.

Setting constraint "unavailableItems"

Now let's send a item contraint "unavailableItems" (replace accessKey with your Access Key):

You can also use SDK to send this event as decribed in the SDK sample above.

1
 2
 3
 4
@@ -599,7 +599,7 @@ http://localhost:8000/queries.json
   }
   "eventTime" : "2015-02-17T02:11:21.934Z"
 }'
-
 
1
+
 
1
 2
 3
 4
@@ -618,7 +618,7 @@ http://localhost:8000/queries.json
     "items" : ["<ITEM ID1>", "<ITEM ID2>"]
   }
 )
-
 
1
+
 
1
 2
 3
 4
@@ -635,7 +635,7 @@ http://localhost:8000/queries.json
   'properties' => array('items' => array('<ITEM ID1>', '<ITEM ID2>'))
 ));
 ?>
-
 
1
+
 
1
 2
 3
 4
@@ -650,7 +650,7 @@ http://localhost:8000/queries.json
     'properties' => { 'items' => ['<ITEM ID1>', '<ITEM ID2>'] }
   }
 )
-
 
1
+
 
1
 2
 3
 4

http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/18d9d1a4/templates/ecommercerecommendation/quickstart/index.html.gz
----------------------------------------------------------------------
diff --git a/templates/ecommercerecommendation/quickstart/index.html.gz b/templates/ecommercerecommendation/quickstart/index.html.gz
index 5c0c776..97f038b 100644
Binary files a/templates/ecommercerecommendation/quickstart/index.html.gz and b/templates/ecommercerecommendation/quickstart/index.html.gz differ

http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/18d9d1a4/templates/ecommercerecommendation/train-with-rate-event/index.html.gz
----------------------------------------------------------------------
diff --git a/templates/ecommercerecommendation/train-with-rate-event/index.html.gz b/templates/ecommercerecommendation/train-with-rate-event/index.html.gz
index 1115532..da7e916 100644
Binary files a/templates/ecommercerecommendation/train-with-rate-event/index.html.gz and b/templates/ecommercerecommendation/train-with-rate-event/index.html.gz differ

http://git-wip-us.apache.org/repos/asf/incubator-predictionio-site/blob/18d9d1a4/templates/javaecommercerecommendation/dase/index.html.gz
----------------------------------------------------------------------
diff --git a/templates/javaecommercerecommendation/dase/index.html.gz b/templates/javaecommercerecommendation/dase/index.html.gz
index efb7191..a59f8e4 100644
Binary files a/templates/javaecommercerecommendation/dase/index.html.gz and b/templates/javaecommercerecommendation/dase/index.html.gz differ