# Predict job

> Predict job - Making predictions is an asynchronous process. This means that when starting
> predictions withModel.request_predictions()you will receive aPredictJobobject in return for tracking
> the process responsible for fulfilling your request.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-01T23:10:47.760721+00:00` (UTC).

## Primary page

- [Predict job](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html): Full documentation for this topic (HTML).

## Sections on this page

- [Start making predictions](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#start-making-predictions): In-page section heading.
- [Listing Predictions](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#listing-predictions): In-page section heading.
- [Get an existing PredictJob](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#get-an-existing-predictjob): In-page section heading.
- [Get generated predictions](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#get-generated-predictions): In-page section heading.
- [Retrieve results](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#retrieve-results): In-page section heading.
- [Get previously generated predictions](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#get-previously-generated-predictions): In-page section heading.
- [Training predictions](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#training-predictions): In-page section heading.
- [Quick reference](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/predict_job.html#quick-reference): In-page section heading.

## Related documentation

- [Developer documentation](https://docs.datarobot.com/en/docs/api/index.html): Linked from this page.
- [Developer learning](https://docs.datarobot.com/en/docs/api/dev-learning/index.html): Linked from this page.
- [Python API client user guide](https://docs.datarobot.com/en/docs/api/dev-learning/python/index.html): Linked from this page.
- [Predictions](https://docs.datarobot.com/en/docs/api/dev-learning/python/predictions/index.html): Linked from this page.
- [Model.request_predictions()](https://docs.datarobot.com/en/docs/api/reference/sdk/datarobot-models.html#datarobot.models.Model.request_predictions): Linked from this page.
- [PredictJob](https://docs.datarobot.com/en/docs/api/reference/sdk/batch-predictions.html#predict-job-api): Linked from this page.
- [datarobot.models.TrainingPredictionsJob](https://docs.datarobot.com/en/docs/api/reference/sdk/jobs.html#datarobot.models.TrainingPredictionsJob): Linked from this page.
- [datarobot.models.training_predictions.TrainingPredictions](https://docs.datarobot.com/en/docs/api/reference/sdk/training_predictions.html#datarobot.models.training_predictions.TrainingPredictions): Linked from this page.

## Documentation content

# Predictions

Making predictions is an asynchronous process.
This means that when starting predictions with [Model.request_predictions()](https://docs.datarobot.com/en/docs/api/reference/sdk/datarobot-models.html#datarobot.models.Model.request_predictions) you will receive a `PredictJob` object in return for tracking the process responsible for fulfilling your request.

You can use this object to get information about the predictions generation process before it has finished and be rerouted to the predictions themselves when the process is finished. To do so, use the [PredictJob](https://docs.datarobot.com/en/docs/api/reference/sdk/batch-predictions.html#predict-job-api) class.

## Start making predictions

Before actually requesting predictions, you should upload the dataset you wish to predict via `Project.upload_dataset`.
Previously uploaded datasets can be viewed using `Project.get_datasets`.
When uploading the dataset you can provide the path to a local file, a file object, raw file content, a `pandas.DataFrame` object, or the URL to a publicly available dataset.

To start predicting on new data using a finished model, use [Model.request_predictions()](https://docs.datarobot.com/en/docs/api/reference/sdk/datarobot-models.html#datarobot.models.Model.request_predictions).
It creates a new prediction generation process and returns a `PredictJob` object tracking this process.
With it, you can monitor an existing `PredictJob` and retrieve generated predictions when the corresponding `PredictJob` is finished.

```
import datarobot as dr

project_id = '5506fcd38bd88f5953219da0'
model_id = '5506fcd98bd88f1641a720a3'
project = dr.Project.get(project_id)
model = dr.Model.get(
    project=project_id,
    model_id=model_id,
)

# As of v3.0, in addition to passing a ``dataset_id``, you can pass in a ``dataset``, ``file``, ``file_path`` or
# ``dataframe`` to `Model.request_predictions`.

predict_job = model.request_predictions(file_path='./data_to_predict.csv')

# Alternative version uploading the dataset from a local path and passing it by its id
dataset_from_path = project.upload_dataset('./data_to_predict.csv')
predict_job = model.request_predictions(dataset_id=dataset_from_path.id)

# Alternative version: upload the dataset as a file object and pass it by using its dataset id
with open('./data_to_predict.csv') as data_to_predict:
    dataset_from_file = project.upload_dataset(data_to_predict)
predict_job = model.request_predictions(dataset_id=dataset_from_file.id)  # OR predict_job = model.request_predictions(dataset_id=dataset_from_file.id)
```

## Listing Predictions

Use `Predictions.list()` to return a list of predictions generated on a project:

```
import datarobot as dr
predictions = dr.Predictions.list('58591727100d2b57196701b3')

print(predictions)
>>>[Predictions(prediction_id='5b6b163eca36c0108fc5d411',
                project_id='5b61bd68ca36c04aed8aab7f',
                model_id='5b61bd7aca36c05744846630',
                dataset_id='5b6b1632ca36c03b5875e6a0'),
    Predictions(prediction_id='5b6b2315ca36c0108fc5d41b',
                project_id='5b61bd68ca36c04aed8aab7f',
                model_id='5b61bd7aca36c0574484662e',
                dataset_id='5b6b1632ca36c03b5875e6a0'),
    Predictions(prediction_id='5b6b23b7ca36c0108fc5d422',
                project_id='5b61bd68ca36c04aed8aab7f',
                model_id='5b61bd7aca36c0574484662e',
                dataset_id='55b6b1632ca36c03b5875e6a0')
    ]
```

You can pass following parameters to filter the result:

- model_id : A string used to filter returned predictions by model_id .
- dataset_id : A string used to filter returned predictions by dataset_id .

## Get an existing PredictJob

Use `PredictJob.get` method to retrieve an existing job.
This will give you a `PredictJob` matching the latest status of the job if it has not completed.

If predictions have finished building, `PredictJob.get` will raise a `PendingJobFinished` exception.

```
import time

import datarobot as dr

predict_job = dr.PredictJob.get(
    project_id=project_id,
    predict_job_id=predict_job_id,
)
predict_job.status
>>> 'queue'

# wait for generation of predictions (in a very inefficient way)
time.sleep(10 * 60)
predict_job = dr.PredictJob.get(
    project_id=project_id,
    predict_job_id=predict_job_id,
)
>>> dr.errors.PendingJobFinished

# now the predictions are finished
predictions = dr.PredictJob.get_predictions(
    project_id=project.id,
    predict_job_id=predict_job_id,
)
```

## Get generated predictions

After predictions are generated, use `PredictJob.get_predictions` to get newly-generated predictions.

If predictions have not yet been finished, it will raise a `JobNotFinished` exception.

```
import datarobot as dr

predictions = dr.PredictJob.get_predictions(
    project_id=project.id,
    predict_job_id=predict_job_id,
)
```

## Retrieve results

If you just want to get generated predictions from a `PredictJob`, use `PredictJob.get_result_when_complete`.
This function polls the status of the predictions generation process until it has finished, and then will return predictions.

```
dataset = project.get_datasets()[0]
predict_job = model.request_predictions(dataset.id)
predictions = predict_job.get_result_when_complete()
```

## Get previously generated predictions

If you don’t have a `PredictJob`, there are two more ways to retrieve predictions from the `Predictions` interface:

1. Get all prediction rows as a pandas.DataFrame object:

```
import datarobot as dr

preds = dr.Predictions.get("5b61bd68ca36c04aed8aab7f", prediction_id="5b6b163eca36c0108fc5d411")
df = preds.get_all_as_dataframe()
df_with_serializer = preds.get_all_as_dataframe(serializer='csv')
```

1. Download all prediction rows to a file as a CSV:

```
import datarobot as dr

preds = dr.Predictions.get("5b61bd68ca36c04aed8aab7f", prediction_id="5b6b163eca36c0108fc5d411")
preds.download_to_csv('predictions.csv')

preds.download_to_csv('predictions_with_serializer.csv', serializer='csv')
```

### Training predictions

The training predictions interface allows you to compute and retrieve out-of-sample predictions for a model using the original project dataset.
The predictions can be computed for all the rows, or restricted to validation or holdout data.
As the predictions generated will be out-of-sample, they can be expected to have different results than if the project dataset were re-uploaded as a prediction dataset.

## Quick reference

Training predictions generation is an asynchronous process.
This means that when starting predictions with [datarobot.models.Model.request_training_predictions()](https://docs.datarobot.com/en/docs/api/reference/sdk/datarobot-models.html#datarobot.models.Model.request_training_predictions) you will receive back a [datarobot.models.TrainingPredictionsJob](https://docs.datarobot.com/en/docs/api/reference/sdk/jobs.html#datarobot.models.TrainingPredictionsJob) for tracking the process responsible for fulfilling your request.
Actual predictions may be obtained with the help of a [datarobot.models.training_predictions.TrainingPredictions](https://docs.datarobot.com/en/docs/api/reference/sdk/training_predictions.html#datarobot.models.training_predictions.TrainingPredictions) object returned as the result of the training predictions job.

There are three ways to retrieve training predictions:

1. Iterate prediction rows one by one as named tuples:

```python
  import datarobot as dr

# Calculate new training predictions on all dataset
  training_predictions_job = model.request_training_predictions(dr.enums.DATA_SUBSET.ALL)
  training_predictions = training_predictions_job.get_result_when_complete()

# Fetch rows from API and print them
  for prediction in training_predictions.iterate_rows(batch_size=250):
    print(prediction.row_id, prediction.prediction)
    ```

1. Get all prediction rows as a pandas.DataFrame object:

```
import datarobot as dr

# Calculate new training predictions on holdout partition of dataset
training_predictions_job = model.request_training_predictions(dr.enums.DATA_SUBSET.HOLDOUT)
training_predictions = training_predictions_job.get_result_when_complete()

# Fetch training predictions as data frame
dataframe = training_predictions.get_all_as_dataframe()
```

1. Download all prediction rows to a file as a CSV document:

```
import datarobot as dr

# Calculate new training predictions on all dataset
training_predictions_job = model.request_training_predictions(dr.enums.DATA_SUBSET.ALL)
training_predictions = training_predictions_job.get_result_when_complete()

# Fetch training predictions and save them to file
training_predictions.download_to_csv('my-training-predictions.csv')
```