Le traduzioni sono generate tramite traduzione automatica. In caso di conflitto tra il contenuto di una traduzione e la versione originale in Inglese, quest'ultima prevarrà.

# Addestramento di un modello con Neptune ML.
<a name="machine-learning-on-graphs-model-training"></a>

Dopo aver elaborato i dati esportati da Neptune per l'addestramento dei modelli, puoi avviare un processo di addestramento dei modelli utilizzando un comando come il seguente:

------
#### [ AWS CLI ]

```
aws neptunedata start-ml-model-training-job \
  --endpoint-url https://{{your-neptune-endpoint}}:{{port}} \
  --id "{{(a unique model-training job ID)}}" \
  --data-processing-job-id "{{(the data-processing job-id of a completed job)}}" \
  --train-model-s3-location "s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer"
```

Per ulteriori informazioni, vedere [start-ml-model-training-job](https://docs.aws.amazon.com/cli/latest/reference/neptunedata/start-ml-model-training-job.html) nel Command Reference. AWS CLI 

------
#### [ SDK ]

```
import boto3
from botocore.config import Config

client = boto3.client(
    'neptunedata',
    endpoint_url='https://{{your-neptune-endpoint}}:{{port}}',
    config=Config(read_timeout=None, retries={'total_max_attempts': 1})
)

response = client.start_ml_model_training_job(
    id='{{(a unique model-training job ID)}}',
    dataProcessingJobId='{{(the data-processing job-id of a completed job)}}',
    trainModelS3Location='s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer'
)

print(response)
```

------
#### [ awscurl ]

```
awscurl https://{{your-neptune-endpoint}}:{{port}}/ml/modeltraining \
  --region {{us-east-1}} \
  --service neptune-db \
  -X POST \
  -H 'Content-Type: application/json' \
  -d '{
        "id" : "{{(a unique model-training job ID)}}",
        "dataProcessingJobId" : "{{(the data-processing job-id of a completed job)}}",
        "trainModelS3Location" : "s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer"
      }'
```

**Nota**  
Questo esempio presuppone che le AWS credenziali siano configurate nel proprio ambiente. Sostituisci {{us-east-1}} con la regione del tuo cluster Neptune.

------
#### [ curl ]

```
curl \
  -X POST https://{{your-neptune-endpoint}}:{{port}}/ml/modeltraining \
  -H 'Content-Type: application/json' \
  -d '{
        "id" : "{{(a unique model-training job ID)}}",
        "dataProcessingJobId" : "{{(the data-processing job-id of a completed job)}}",
        "trainModelS3Location" : "s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer"
      }'
```

------

I dettagli su come utilizzare questo comando sono illustrati in [Comando modeltraining](machine-learning-api-modeltraining.md), insieme a informazioni su come recuperare lo stato di un processo in esecuzione, come arrestare un processo in esecuzione e come elencare tutti i processi in esecuzione.

È inoltre possibile fornire un `previousModelTrainingJobId` per usare le informazioni provenienti dal processo di addestramento di un modello Neptune ML completato per accelerare la ricerca degli iperparametri in un nuovo processo di addestramento. Questo è utile durante il [riaddestramento del modello su nuovi dati del grafo](machine-learning-overview-evolving-data-incremental.md#machine-learning-overview-model-retraining), nonché per l'[addestramento incrementale sugli stessi dati del grafo](machine-learning-overview-evolving-data-incremental.md#machine-learning-overview-incremental). Usa un comando come questo:

------
#### [ AWS CLI ]

```
aws neptunedata start-ml-model-training-job \
  --endpoint-url https://{{your-neptune-endpoint}}:{{port}} \
  --id "{{(a unique model-training job ID)}}" \
  --data-processing-job-id "{{(the data-processing job-id of a completed job)}}" \
  --train-model-s3-location "s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer" \
  --previous-model-training-job-id "{{(the model-training job-id of a completed job)}}"
```

Per ulteriori informazioni, vedere [start-ml-model-training-job](https://docs.aws.amazon.com/cli/latest/reference/neptunedata/start-ml-model-training-job.html) nel Command Reference. AWS CLI 

------
#### [ SDK ]

```
import boto3
from botocore.config import Config

client = boto3.client(
    'neptunedata',
    endpoint_url='https://{{your-neptune-endpoint}}:{{port}}',
    config=Config(read_timeout=None, retries={'total_max_attempts': 1})
)

response = client.start_ml_model_training_job(
    id='{{(a unique model-training job ID)}}',
    dataProcessingJobId='{{(the data-processing job-id of a completed job)}}',
    trainModelS3Location='s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer',
    previousModelTrainingJobId='{{(the model-training job-id of a completed job)}}'
)

print(response)
```

------
#### [ awscurl ]

```
awscurl https://{{your-neptune-endpoint}}:{{port}}/ml/modeltraining \
  --region {{us-east-1}} \
  --service neptune-db \
  -X POST \
  -H 'Content-Type: application/json' \
  -d '{
        "id" : "{{(a unique model-training job ID)}}",
        "dataProcessingJobId" : "{{(the data-processing job-id of a completed job)}}",
        "trainModelS3Location" : "s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer",
        "previousModelTrainingJobId" : "{{(the model-training job-id of a completed job)}}"
      }'
```

**Nota**  
Questo esempio presuppone che le AWS credenziali siano configurate nel proprio ambiente. Sostituisci {{us-east-1}} con la regione del tuo cluster Neptune.

------
#### [ curl ]

```
curl \
  -X POST https://{{your-neptune-endpoint}}:{{port}}/ml/modeltraining \
  -H 'Content-Type: application/json' \
  -d '{
        "id" : "{{(a unique model-training job ID)}}",
        "dataProcessingJobId" : "{{(the data-processing job-id of a completed job)}}",
        "trainModelS3Location" : "s3://{{(your S3 bucket)}}/neptune-model-graph-autotrainer",
        "previousModelTrainingJobId" : "{{(the model-training job-id of a completed job)}}"
      }'
```

------

Puoi addestrare l'implementazione di un modello personalizzato sull'infrastruttura di addestramento di Neptune ML specificando un oggetto `customModelTrainingParameters`, in questo modo:

------
#### [ AWS CLI ]

```
aws neptunedata start-ml-model-training-job \
  --endpoint-url https://{{your-neptune-endpoint}}:{{port}} \
  --id "{{(a unique model-training job ID)}}" \
  --data-processing-job-id "{{(the data-processing job-id of a completed job)}}" \
  --train-model-s3-location "s3://{{(your Amazon S3 bucket)}}/neptune-model-graph-autotrainer" \
  --model-name "custom" \
  --custom-model-training-parameters '{
    "sourceS3DirectoryPath": "s3://{{(your Amazon S3 bucket)}}/{{(path to your Python module)}}",
    "trainingEntryPointScript": "{{(your training script entry-point name in the Python module)}}",
    "transformEntryPointScript": "{{(your transform script entry-point name in the Python module)}}"
  }'
```

Per ulteriori informazioni, vedere [start-ml-model-training-job](https://docs.aws.amazon.com/cli/latest/reference/neptunedata/start-ml-model-training-job.html) nel Command Reference. AWS CLI 

------
#### [ SDK ]

```
import boto3
from botocore.config import Config

client = boto3.client(
    'neptunedata',
    endpoint_url='https://{{your-neptune-endpoint}}:{{port}}',
    config=Config(read_timeout=None, retries={'total_max_attempts': 1})
)

response = client.start_ml_model_training_job(
    id='{{(a unique model-training job ID)}}',
    dataProcessingJobId='{{(the data-processing job-id of a completed job)}}',
    trainModelS3Location='s3://{{(your Amazon S3 bucket)}}/neptune-model-graph-autotrainer',
    modelName='custom',
    customModelTrainingParameters={
        'sourceS3DirectoryPath': 's3://{{(your Amazon S3 bucket)}}/{{(path to your Python module)}}',
        'trainingEntryPointScript': '{{(your training script entry-point name in the Python module)}}',
        'transformEntryPointScript': '{{(your transform script entry-point name in the Python module)}}'
    }
)

print(response)
```

------
#### [ awscurl ]

```
awscurl https://{{your-neptune-endpoint}}:{{port}}/ml/modeltraining \
  --region {{us-east-1}} \
  --service neptune-db \
  -X POST \
  -H 'Content-Type: application/json' \
  -d '{
        "id" : "{{(a unique model-training job ID)}}",
        "dataProcessingJobId" : "{{(the data-processing job-id of a completed job)}}",
        "trainModelS3Location" : "s3://{{(your Amazon S3 bucket)}}/neptune-model-graph-autotrainer",
        "modelName": "custom",
        "customModelTrainingParameters" : {
          "sourceS3DirectoryPath": "s3://{{(your Amazon S3 bucket)}}/{{(path to your Python module)}}",
          "trainingEntryPointScript": "{{(your training script entry-point name in the Python module)}}",
          "transformEntryPointScript": "{{(your transform script entry-point name in the Python module)}}"
        }
      }'
```

**Nota**  
Questo esempio presuppone che le AWS credenziali siano configurate nel proprio ambiente. Sostituisci {{us-east-1}} con la regione del tuo cluster Neptune.

------
#### [ curl ]

```
curl \
  -X POST https://{{your-neptune-endpoint}}:{{port}}/ml/modeltraining \
  -H 'Content-Type: application/json' \
  -d '{
        "id" : "{{(a unique model-training job ID)}}",
        "dataProcessingJobId" : "{{(the data-processing job-id of a completed job)}}",
        "trainModelS3Location" : "s3://{{(your Amazon S3 bucket)}}/neptune-model-graph-autotrainer",
        "modelName": "custom",
        "customModelTrainingParameters" : {
          "sourceS3DirectoryPath": "s3://{{(your Amazon S3 bucket)}}/{{(path to your Python module)}}",
          "trainingEntryPointScript": "{{(your training script entry-point name in the Python module)}}",
          "transformEntryPointScript": "{{(your transform script entry-point name in the Python module)}}"
        }
      }'
```

------



Per ulteriori informazioni, ad esempio su come recuperare lo stato di un processo in esecuzione, su come arrestare un processo in esecuzione e su come elencare tutti i lavori in esecuzione, consulta [Comando modeltraining](machine-learning-api-modeltraining.md). Per ulteriori informazioni su come implementare e usare un modello personalizzato, consulta [Modelli personalizzati in Neptune ML.](machine-learning-custom-models.md).

**Topics**
+ [Modelli e addestramento dei modelli in Amazon Neptune ML](machine-learning-models-and-training.md)
+ [Personalizzazione delle configurazioni degli iperparametri dei modelli in Neptune ML](machine-learning-customizing-hyperparams.md)
+ [Best practice per l'addestramento dei modelli](machine-learning-improve-model-performance.md)