{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Set up Preview SDK" ] }, { "cell_type": "code", "execution_count": 85, "metadata": {}, "outputs": [], "source": [ "# Configures your AWS CLI to now understand our up and coming service Amazon Forecast\n", "!aws configure add-model --service-model file://../sdk/forecastquery-2018-06-26.normal.json --service-name forecastquery\n", "!aws configure add-model --service-model file://../sdk/forecast-2018-06-26.normal.json --service-name forecast" ] }, { "cell_type": "code", "execution_count": 86, "metadata": {}, "outputs": [], "source": [ "# Prerequisites : 1 time install only, remove the comments to execute the lines.\n", "#!pip install boto3\n", "#!pip install pandas" ] }, { "cell_type": "code", "execution_count": 87, "metadata": {}, "outputs": [], "source": [ "import boto3\n", "from time import sleep\n", "import subprocess" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [], "source": [ "session = boto3.Session(region_name='us-west-2') #us-east-1 is also supported\n", "\n", "forecast = session.client(service_name='forecast')\n", "forecastquery = session.client(service_name='forecastquery')\n", "s3 = session.client('s3')\n", "accountId = boto3.client('sts').get_caller_identity().get('Account')\n", "\n", "bucketName = 'amazon-forecast-ttsang-data'\n", "key=\"accounting_data/accounting_bar.csv\"\n" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "amazon-forecast-ttsang-data/accounting_data/accounting_bar.csv\n" ] } ], "source": [ "print('{}/{}'.format(bucketName,key))" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [], "source": [ "# One time setup only, uncomment the following command to create the role to provide to Amazon Forecast. \n", "# Save the generated role for all future calls to use for importing or exporting data. \n", "\n", "cmd = 'python ../setup_forecast_permissions.py '+bucketName\n", "p = subprocess.Popen(cmd.split(' '), stdout=subprocess.PIPE, stderr=subprocess.PIPE)\n", "roleArn = 'arn:aws:iam::%s:role/amazonforecast'%accountId" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### CreateDataset" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "More details about `Domain` and dataset type can be found on the [documentation](https://docs.aws.amazon.com/forecast/latest/dg/howitworks-domains-ds-types.html) . For this example, we are using [CUSTOM](https://docs.aws.amazon.com/forecast/latest/dg/custom-domain.html) domain with 3 required attributes `timestamp`, `target_value` and `item_id`. Also for your project name, update it to reflect your name in a lowercase format." ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [], "source": [ "DATASET_FREQUENCY = \"1M\" \n", "TIMESTAMP_FORMAT = \"yyyy-MM-dd hh:mm:ss\"\n", "project = 'accounting_forecast_v5' # Replace this with a unique name here, make sure the entire name is < 30 characters.\n", "datasetName= project+'_ds'\n", "datasetGroupName= project +'_gp'\n", "s3DataPath = \"s3://\"+bucketName+\"/\"+key" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'accounting_forecast_v5_ds'" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "datasetName" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [], "source": [ "# Specify the schema of your dataset here. Make sure the order of columns matches the raw data files.\n", "schema ={\n", " \"Attributes\":[\n", " {\n", " \"AttributeName\":\"timestamp\",\n", " \"AttributeType\":\"timestamp\"\n", " },\n", " {\n", " \"AttributeName\":\"item_id\",\n", " \"AttributeType\":\"string\"\n", " },\n", " {\n", " \"AttributeName\":\"store_id\",\n", " \"AttributeType\":\"integer\"\n", " },\n", " {\n", " \"AttributeName\":\"sales\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"target_value\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Upgraded_Download_Tracks\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Ad_Supported_Audio_Streams\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Subscription_Video_Streams\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Download_Albums\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Video_Download_Purchases\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Download_Tracks\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Subscription_Audio_Streams\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Cloud_Match_Units\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Non_interactive_Radio\",\n", " \"AttributeType\":\"float\"\n", " },\n", " {\n", " \"AttributeName\":\"Streaming_Bonus\",\n", " \"AttributeType\":\"float\"\n", " }\n", " ]\n", "}\n", "\n", "response=forecast.create_dataset(\n", " Domain=\"CUSTOM\",\n", " DatasetType='TARGET_TIME_SERIES',\n", " DataFormat='CSV',\n", " DatasetName=datasetName,\n", " DataFrequency=DATASET_FREQUENCY, \n", " TimeStampFormat=TIMESTAMP_FORMAT,\n", " Schema = schema\n", " )" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'DatasetName': 'accounting_forecast_v5_ds',\n", " 'DatasetType': 'TARGET_TIME_SERIES',\n", " 'DataFormat': 'CSV',\n", " 'Domain': 'CUSTOM',\n", " 'ScheduleExpression': 'none',\n", " 'DatasetArn': 'arn:aws:forecast:us-west-2:073138737237:ds/accounting_forecast_v5_ds',\n", " 'Status': 'ACTIVE',\n", " 'ResponseMetadata': {'RequestId': 'e0826bdd-502d-45a0-ba33-f8c8a0a38a06',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:34:14 GMT',\n", " 'x-amzn-requestid': 'e0826bdd-502d-45a0-ba33-f8c8a0a38a06',\n", " 'content-length': '245',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 69, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.describe_dataset(DatasetName=datasetName)" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'DatasetGroupName': 'accounting_forecast_v5_gp',\n", " 'DatasetGroupArn': 'arn:aws:forecast:us-west-2:073138737237:dsgroup/accounting_forecast_v5_gp',\n", " 'ResponseMetadata': {'RequestId': 'e69c51df-7826-4142-90a4-20d882724795',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:34:17 GMT',\n", " 'x-amzn-requestid': 'e69c51df-7826-4142-90a4-20d882724795',\n", " 'content-length': '142',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.create_dataset_group(DatasetGroupName=datasetGroupName,RoleArn=roleArn,DatasetNames=[datasetName])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "If you have an existing datasetgroup, you can update it" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'DatasetGroupName': 'accounting_forecast_v5_gp',\n", " 'DatasetGroupArn': 'arn:aws:forecast:us-west-2:073138737237:dsgroup/accounting_forecast_v5_gp',\n", " 'Datasets': ['accounting_forecast_v5_ds'],\n", " 'RoleArn': 'arn:aws:iam::073138737237:role/amazonforecast',\n", " 'ResponseMetadata': {'RequestId': 'bbba8521-ec6b-4dfe-87c6-9a2380dedb76',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:34:22 GMT',\n", " 'x-amzn-requestid': 'bbba8521-ec6b-4dfe-87c6-9a2380dedb76',\n", " 'content-length': '241',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.describe_dataset_group(DatasetGroupName=datasetGroupName)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Create Data Import Job\n", "Brings the data into Amazon Forecast system ready to forecast from raw data. " ] }, { "cell_type": "code", "execution_count": 72, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1be23fa8\n" ] } ], "source": [ "ds_import_job_response=forecast.create_dataset_import_job(DatasetName=datasetName,Delimiter=',', DatasetGroupName =datasetGroupName ,S3Uri= s3DataPath)\n", "ds_versionId=ds_import_job_response['VersionId']\n", "print(ds_versionId)" ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "QUEUED\n", "0\n", "CREATING\n", "10\n", "CREATING\n", "20\n", "CREATING\n", "30\n", "CREATING\n", "40\n", "CREATING\n", "50\n", "CREATING\n", "60\n", "CREATING\n", "70\n", "CREATING\n", "80\n", "CREATING\n", "90\n", "CREATING\n", "100\n", "CREATING\n", "110\n", "CREATING\n", "120\n", "CREATING\n", "130\n", "CREATING\n", "140\n", "CREATING\n", "150\n", "CREATING\n", "160\n", "CREATING\n", "170\n", "CREATING\n", "180\n", "CREATING\n", "190\n", "CREATING\n", "200\n", "CREATING\n", "210\n", "CREATING\n", "220\n", "CREATING\n", "230\n", "CREATING\n", "240\n", "CREATING\n", "250\n", "CREATING\n", "260\n", "CREATING\n", "270\n", "CREATING\n", "280\n", "CREATING\n", "290\n", "CREATING\n", "300\n", "CREATING\n", "310\n", "CREATING\n", "320\n", "CREATING\n", "330\n", "CREATING\n", "340\n", "CREATING\n", "350\n", "CREATING\n", "360\n", "CREATING\n", "370\n", "CREATING\n", "380\n", "CREATING\n", "390\n", "CREATING\n", "400\n", "CREATING\n", "410\n", "CREATING\n", "420\n", "CREATING\n", "430\n", "CREATING\n", "440\n", "CREATING\n", "450\n", "CREATING\n", "460\n", "CREATING\n", "470\n", "CREATING\n", "480\n", "CREATING\n", "490\n", "CREATING\n", "500\n", "CREATING\n", "510\n", "CREATING\n", "520\n", "CREATING\n", "530\n", "CREATING\n", "540\n", "CREATING\n", "550\n", "CREATING\n", "560\n", "CREATING\n", "570\n", "CREATING\n", "580\n", "CREATING\n", "590\n", "CREATING\n", "600\n", "CREATING\n", "610\n", "CREATING\n", "620\n", "CREATING\n", "630\n", "CREATING\n", "640\n", "CREATING\n", "650\n", "CREATING\n", "660\n", "CREATING\n", "670\n", "CREATING\n", "680\n", "CREATING\n", "690\n", "CREATING\n", "700\n", "CREATING\n", "710\n", "CREATING\n", "720\n", "CREATING\n", "730\n", "CREATING\n", "740\n", "CREATING\n", "750\n", "CREATING\n", "760\n", "CREATING\n", "770\n", "CREATING\n", "780\n", "CREATING\n", "790\n", "CREATING\n", "800\n", "CREATING\n", "810\n", "CREATING\n", "820\n", "CREATING\n", "830\n", "CREATING\n", "840\n", "CREATING\n", "850\n", "CREATING\n", "860\n", "CREATING\n", "870\n", "CREATING\n", "880\n", "CREATING\n", "890\n", "CREATING\n", "900\n", "CREATING\n", "910\n", "CREATING\n", "920\n", "CREATING\n", "930\n", "CREATING\n", "940\n", "CREATING\n", "950\n", "CREATING\n", "960\n", "CREATING\n", "970\n", "CREATING\n", "980\n", "CREATING\n", "990\n", "CREATING\n", "1000\n", "CREATING\n", "1010\n", "CREATING\n", "1020\n", "CREATING\n", "1030\n", "CREATING\n", "1040\n", "CREATING\n", "1050\n", "CREATING\n", "1060\n", "CREATING\n", "1070\n", "CREATING\n", "1080\n", "CREATING\n", "1090\n", "CREATING\n", "1100\n", "CREATING\n", "1110\n", "CREATING\n", "1120\n", "CREATING\n", "1130\n", "CREATING\n", "1140\n", "CREATING\n", "1150\n", "CREATING\n", "1160\n", "CREATING\n", "1170\n", "ACTIVE\n", "1180\n" ] } ], "source": [ "i=0\n", "while True:\n", " dataImportStatus = forecast.describe_dataset_import_job(DatasetName=datasetName,VersionId=ds_versionId)['Status']\n", " print(dataImportStatus)\n", " print(i*10)\n", " i=i+1\n", " if dataImportStatus != 'ACTIVE' and dataImportStatus != 'FAILED':\n", " sleep(10)\n", " else:\n", " break\n" ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'DatasetArn': 'arn:aws:forecast:us-west-2:073138737237:ds/accounting_forecast_v5_ds',\n", " 'DatasetName': 'accounting_forecast_v5_ds',\n", " 'VersionId': '1be23fa8',\n", " 'Status': 'ACTIVE',\n", " 'FieldStatistics': {'Ad_Supported_Audio_Streams': {'Count': 312,\n", " 'CountDistinct': 172,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '1942.272323',\n", " 'Avg': 334.7521734839743,\n", " 'Stddev': 591.004853991729},\n", " 'Cloud_Match_Units': {'Count': 312,\n", " 'CountDistinct': 39,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '22483.502715',\n", " 'Avg': 119.56898417628206,\n", " 'Stddev': 1281.5244932753742},\n", " 'Download_Albums': {'Count': 312,\n", " 'CountDistinct': 133,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '112708.799995',\n", " 'Avg': 5212.891631464743,\n", " 'Stddev': 10614.360376791536},\n", " 'Download_Tracks': {'Count': 312,\n", " 'CountDistinct': 140,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '43508.244579',\n", " 'Avg': 2869.129437939103,\n", " 'Stddev': 5566.332855863449},\n", " 'Non_interactive_Radio': {'Count': 312,\n", " 'CountDistinct': 28,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '512.163509',\n", " 'Avg': 16.662813272435894,\n", " 'Stddev': 66.676748316807},\n", " 'Streaming_Bonus': {'Count': 312,\n", " 'CountDistinct': 2,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '373.100929',\n", " 'Avg': 1.195836310897436,\n", " 'Stddev': 21.12268066623567},\n", " 'Subscription_Audio_Streams': {'Count': 312,\n", " 'CountDistinct': 217,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '20274.749353',\n", " 'Avg': 3885.9500986250014,\n", " 'Stddev': 6044.261336145459},\n", " 'Subscription_Video_Streams': {'Count': 312,\n", " 'CountDistinct': 26,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '33.964542',\n", " 'Avg': 1.5041982179487179,\n", " 'Stddev': 5.228372027066128},\n", " 'Upgraded_Download_Tracks': {'Count': 312,\n", " 'CountDistinct': 32,\n", " 'CountNull': 0,\n", " 'Min': '-0.15',\n", " 'Max': '34.342685',\n", " 'Avg': 0.32573170192307693,\n", " 'Stddev': 2.2880563569632755},\n", " 'Video_Download_Purchases': {'Count': 312,\n", " 'CountDistinct': 95,\n", " 'CountNull': 0,\n", " 'Min': '0.0',\n", " 'Max': '309.055397',\n", " 'Avg': 8.601176131410256,\n", " 'Stddev': 26.880984105560252},\n", " 'date': {'Count': 312,\n", " 'CountDistinct': 132,\n", " 'CountNull': 0,\n", " 'Min': '2004-03-01T00:00:00Z',\n", " 'Max': '2018-08-01T00:00:00Z'},\n", " 'item': {'Count': 312, 'CountDistinct': 1, 'CountNull': 0},\n", " 'sales': {'Count': 312,\n", " 'CountDistinct': 312,\n", " 'CountNull': 0,\n", " 'Min': '29.0',\n", " 'Max': '1.2157463E7',\n", " 'Avg': 1180733.173076923,\n", " 'Stddev': 1810509.33123693},\n", " 'store_id': {'Count': 312,\n", " 'CountDistinct': 3,\n", " 'CountNull': 0,\n", " 'Min': '1',\n", " 'Max': '348',\n", " 'Avg': 180.92307692307693,\n", " 'Stddev': 156.0844251088596},\n", " 'target': {'Count': 312,\n", " 'CountDistinct': 312,\n", " 'CountNull': 0,\n", " 'Min': '0.2175',\n", " 'Max': '127327.130063',\n", " 'Avg': 12460.616849096154,\n", " 'Stddev': 14137.171761760064}},\n", " 'ResponseMetadata': {'RequestId': '3efba0c6-87ea-4049-b541-154945f527cc',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:55:11 GMT',\n", " 'x-amzn-requestid': '3efba0c6-87ea-4049-b541-154945f527cc',\n", " 'content-length': '2320',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 74, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.describe_dataset_import_job(DatasetName=datasetName,VersionId=ds_versionId)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Recipe" ] }, { "cell_type": "code", "execution_count": 75, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'RecipeNames': ['forecast_ARIMA',\n", " 'forecast_DEEP_AR',\n", " 'forecast_DEEP_AR_PLUS',\n", " 'forecast_ETS',\n", " 'forecast_MDN',\n", " 'forecast_MQRNN',\n", " 'forecast_NPTS',\n", " 'forecast_PROPHET',\n", " 'forecast_SQF'],\n", " 'ResponseMetadata': {'RequestId': '6ff68ce2-2ce2-4028-bcf5-972243bf0aa1',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:55:34 GMT',\n", " 'x-amzn-requestid': '6ff68ce2-2ce2-4028-bcf5-972243bf0aa1',\n", " 'content-length': '174',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 75, "metadata": {}, "output_type": "execute_result" } ], "source": [ "recipesResponse=forecast.list_recipes()\n", "recipesResponse" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Get details about each recipe." ] }, { "cell_type": "code", "execution_count": 76, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'Recipe': {'Name': 'forecast_MQRNN',\n", " 'Train': [{'TrainingInfo': {'TrainedModelName': 'algorithm_MQRNN',\n", " 'AlgorithmName': 'MQRNN',\n", " 'TrainingParameters': {'epochs': '60',\n", " 'learning_rate': '3E-3',\n", " 'mini_batch_size': '32',\n", " 'quantiles': '[0.1,0.5,0.9]'}},\n", " 'BackTestWindowCount': 1,\n", " 'MetricsBuckets': []}]},\n", " 'ResponseMetadata': {'RequestId': '089d72d0-ebae-430e-854f-029294010531',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:55:37 GMT',\n", " 'x-amzn-requestid': '089d72d0-ebae-430e-854f-029294010531',\n", " 'content-length': '281',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 76, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.describe_recipe(RecipeName='forecast_MQRNN')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Create Solution with customer forecast horizon" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Forecast horizon is how long in future the forecast should be predicting. For weekly data, a value of 12 means 1 weeks. Our example is hourly data, we try forecast the next day, so we can set to 24." ] }, { "cell_type": "code", "execution_count": 78, "metadata": {}, "outputs": [], "source": [ "predictorName= project+'_mqrnn'" ] }, { "cell_type": "code", "execution_count": 79, "metadata": {}, "outputs": [], "source": [ "forecastHorizon = 3" ] }, { "cell_type": "code", "execution_count": 80, "metadata": {}, "outputs": [], "source": [ "createPredictorResponse=forecast.create_predictor(RecipeName='forecast_MQRNN',DatasetGroupName= datasetGroupName ,PredictorName=predictorName, \n", " ForecastHorizon = forecastHorizon)" ] }, { "cell_type": "code", "execution_count": 81, "metadata": {}, "outputs": [], "source": [ "predictorVerionId=createPredictorResponse['VersionId']" ] }, { "cell_type": "code", "execution_count": 82, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PredictorVersions': [{'PredictorName': 'accounting_forecast_v5_mqrnn',\n", " 'VersionId': '2fe7438b'}],\n", " 'ResponseMetadata': {'RequestId': '96dd400e-ea33-4f66-b54f-a5c247a72e2d',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 15:56:04 GMT',\n", " 'x-amzn-requestid': '96dd400e-ea33-4f66-b54f-a5c247a72e2d',\n", " 'content-length': '95',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 82, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.list_predictor_versions(PredictorName=predictorName)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Check the status of solutions, when the status change from **CREATING** to **ACTIVE**, we can continue to next steps. Depending on data size, model selection and hyper parameters，it can take 10 mins to more than one hour to be **ACTIVE**." ] }, { "cell_type": "code", "execution_count": 83, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "CREATING\n", "0\n", "CREATING\n", "10\n", "CREATING\n", "20\n", "CREATING\n", "30\n", "CREATING\n", "40\n", "CREATING\n", "50\n", "CREATING\n", "60\n", "CREATING\n", "70\n", "CREATING\n", "80\n", "CREATING\n", "90\n", "CREATING\n", "100\n", "CREATING\n", "110\n", "CREATING\n", "120\n", "CREATING\n", "130\n", "CREATING\n", "140\n", "CREATING\n", "150\n", "CREATING\n", "160\n", "CREATING\n", "170\n", "CREATING\n", "180\n", "CREATING\n", "190\n", "CREATING\n", "200\n", "CREATING\n", "210\n", "FAILED\n", "220\n" ] } ], "source": [ "i=0\n", "while True:\n", " predictorStatus = forecast.describe_predictor(PredictorName=predictorName,VersionId=predictorVerionId)['Status']\n", " print(predictorStatus)\n", " print(i*10)\n", " i=i+1\n", " if predictorStatus != 'ACTIVE' and predictorStatus != 'FAILED':\n", " sleep(10)\n", " else:\n", " break" ] }, { "cell_type": "code", "execution_count": 84, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PredictorName': 'accounting_forecast_v5_mqrnn',\n", " 'VersionId': '2fe7438b',\n", " 'Status': 'FAILED',\n", " 'CreationStartTime': '2019-01-11T15:55:53.596Z',\n", " 'PredictorArn': 'arn:aws:forecast:us-west-2:073138737237:predictor/accounting_forecast_v5_mqrnn',\n", " 'RecipeName': 'forecast_MQRNN',\n", " 'DatasetGroup': 'accounting_forecast_v5_gp',\n", " 'RecipeParameters': {},\n", " 'ResponseMetadata': {'RequestId': '678003f0-5698-4e49-bb5a-fd2c7661a3b7',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 16:00:12 GMT',\n", " 'x-amzn-requestid': '678003f0-5698-4e49-bb5a-fd2c7661a3b7',\n", " 'content-length': '327',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 84, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecast.describe_predictor(PredictorName=predictorName,VersionId=predictorVerionId)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Get Error Metrics" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'ModelMetrics': {},\n", " 'ResponseMetadata': {'RequestId': '9060e831-df45-40f7-a6f7-12a396b20982',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 07:44:15 GMT',\n", " 'x-amzn-requestid': '9060e831-df45-40f7-a6f7-12a396b20982',\n", " 'content-length': '19',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "forecastquery.get_accuracy_metrics(PredictorName=predictorName)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Deploy Predictor" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "forecast.deploy_predictor(PredictorName=predictorName)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "deployedPredictorsResponse=forecast.list_deployed_predictors()\n", "print(deployedPredictorsResponse)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Please note that the following cell can also take 10 minutes or more to be fully operational. There's no output here, but that is fine as long as the * is there." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "while True:\n", " deployedPredictorStatus = forecast.describe_deployed_predictor(PredictorName=predictorName)['Status']\n", " print(deployedPredictorStatus)\n", " if deployedPredictorStatus != 'ACTIVE' and deployedPredictorStatus != 'FAILED':\n", " sleep(30)\n", " else:\n", " break\n", "print(deployedPredictorStatus)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Get Forecast" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "When the solution is deployed and forecast results are ready, you can view them. " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "forecastResponse = forecastquery.get_forecast(\n", " PredictorName=predictorName,\n", " Interval=\"hour\",\n", " Filters={\"item_id\":\"client_12\"}\n", ")\n", "print(forecastResponse)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Export Forecast" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "###### You can batch export forecast to s3 bucket. To do so an role with s3 put access is needed, but this has already been created." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "forecastInfoList= forecast.list_forecasts(PredictorName=predictorName)['ForecastInfoList']\n", "forecastId= forecastInfoList[0]['ForecastId']" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "outputPath=\"s3://\"+bucketName+\"/output\"" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "forecastExportResponse = forecast.create_forecast_export_job(ForecastId=forecastId, OutputPath={\"S3Uri\": outputPath,\"RoleArn\":roleArn})" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "forecastExportJobId = forecastExportResponse['ForecastExportJobId']" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "while True:\n", " forecastExportStatus = forecast.describe_forecast_export_job(ForecastExportJobId=forecastExportJobId)['Status']\n", " print(forecastExportStatus)\n", " if forecastExportStatus != 'ACTIVE' and forecastExportStatus != 'FAILED':\n", " sleep(30)\n", " else:\n", " break" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Check s3 bucket for results" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "s3.list_objects(Bucket=bucketName,Prefix=\"output\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Cleanup\n", "\n", "While Forecast is in preview there are no charges for using it, but to future proof this work below are the instructions to cleanup your work space." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Delete Deployed Predictor \n", "forecast.delete_deployed_predictor(PredictorName=predictorName)" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'PredictorName': 'accounting_forecast_V3_mqrnn',\n", " 'ResponseMetadata': {'RequestId': 'aa05047b-e14c-4e0b-9be6-42c90f4b0194',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 14:51:32 GMT',\n", " 'x-amzn-requestid': 'aa05047b-e14c-4e0b-9be6-42c90f4b0194',\n", " 'content-length': '48',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Delete the Predictor: \n", "forecast.delete_predictor(PredictorName=predictorName)" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'DatasetName': 'accounting_forecast_V3_ds',\n", " 'ResponseMetadata': {'RequestId': '64dd406d-1529-49b7-8d52-a83239bcc01a',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 14:51:27 GMT',\n", " 'x-amzn-requestid': '64dd406d-1529-49b7-8d52-a83239bcc01a',\n", " 'content-length': '43',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Delete Import\n", "forecast.delete_dataset_import(DatasetName=datasetName)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'ResponseMetadata': {'RequestId': '74570c74-e159-4909-b366-95198928f5cb',\n", " 'HTTPStatusCode': 200,\n", " 'HTTPHeaders': {'content-type': 'application/x-amz-json-1.1',\n", " 'date': 'Fri, 11 Jan 2019 14:51:31 GMT',\n", " 'x-amzn-requestid': '74570c74-e159-4909-b366-95198928f5cb',\n", " 'content-length': '2',\n", " 'connection': 'keep-alive'},\n", " 'RetryAttempts': 0}}" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Delete Dataset Group\n", "forecast.delete_dataset_group(DatasetGroupName=datasetGroupName)" ] } ], "metadata": { "kernelspec": { "display_name": "conda_python3", "language": "python", "name": "conda_python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }