Time_Series_Forecasting: unexpected content_type paramenter about ml_sagemaker_studies HOT 3 CLOSED

from sagemaker.deserializers import JSONDeserializer
from sagemaker.serializers import JSONSerializer

predictor = estimator.deploy(
    initial_instance_count=1,
    instance_type='ml.t2.medium',
    # content_type="application/json" # specify that it will accept/produce JSON
    serializer=JSONSerializer(),
    deserializer=JSONDeserializer()
)

def json_predictor_input(input_ts, num_samples=50, quantiles=['0.1', '0.5', '0.9']):
    '''Accepts a list of input time series and produces a formatted input.
       :input_ts: An list of input time series.
       :num_samples: Number of samples to calculate metrics with.
       :quantiles: A list of quantiles to return in the predicted output.
       :return: The JSON-formatted input.
       '''
    # request data is made of JSON objects (instances)
    # and an output configuration that details the type of data/quantiles we want
    
    instances = []
    for k in range(len(input_ts)):
        # get JSON objects for input time series
        instances.append(series_to_json_obj(input_ts[k]))

    # specify the output quantiles and samples
    configuration = {"num_samples": num_samples, 
                     "output_types": ["quantiles"], 
                     "quantiles": quantiles}

    request_data = {"instances": instances, 
                    "configuration": configuration}
    
    # not needed
    # json_request = json.dumps(request_data).encode('utf-8')
    
    return request_data

def decode_prediction(prediction_data):
    '''Accepts a JSON prediction and returns a list of prediction data.
    '''
    prediction_list = []
    for k in range(len(prediction_data['predictions'])):
        prediction_list.append(pd.DataFrame(data=prediction_data['predictions'][k]['quantiles']))
    return prediction_list

# get prediction response
json_prediction = predictor.predict(request_data)

prediction_2010 = decode_prediction(json_prediction)