AttributeError: 'Series' object has no attribute 'freq' (DeepAR algorithm in Time series forecasting)

[sylviahangnguyen]

Describe the bug
I'm running dbg-deepar.ipynb, provided module deepar_util.py by following the tutorial
Stock Price Prediction, using SageMaker DeepAR.
The problem may be that I cannot update Pandas on SageMaker Studio Notebook. My Pandas version '1.0.1'

class DeepARPredictor in deepar_util.py

class DeepARPredictor(sagemaker.predictor.RealTimePredictor):
    
    def __init__(self, *args, **kwargs):
        super().__init__(*args, content_type=sagemaker.content_types.CONTENT_TYPE_JSON, **kwargs)
        
    def predict(self, ts, cat=None, dynamic_feat=None, 
                num_samples=100, return_samples=False, quantiles=["0.1", "0.5", "0.9"]):
        """Requests the prediction of for the time series listed in `ts`, each with the (optional)
        corresponding category listed in `cat`.
        
        ts -- `pandas.Series` object, the time series to predict
        cat -- integer, the group associated to the time series (default: None)
        num_samples -- integer, number of samples to compute at prediction time (default: 100)
        return_samples -- boolean indicating whether to include samples in the response (default: False)
        quantiles -- list of strings specifying the quantiles to compute (default: ["0.1", "0.5", "0.9"])
        
        Return value: list of `pandas.DataFrame` objects, each containing the predictions
        """
        prediction_time = ts.index[-1] + pd.Timedelta(1, unit='D')
        quantiles = [str(q) for q in quantiles]
        req = self.__encode_request(ts, cat, dynamic_feat, num_samples, return_samples, quantiles)
        res = super(DeepARPredictor, self).predict(req)
        return self.__decode_response(res, ts.index.freq, prediction_time, return_samples)
    
    def __encode_request(self, ts, cat, dynamic_feat, num_samples, return_samples, quantiles):
        instance = series_to_dict(ts, cat if cat is not None else None, dynamic_feat if dynamic_feat else None)

        configuration = {
            "num_samples": num_samples,
            "output_types": ["quantiles", "samples"] if return_samples else ["quantiles"],
            "quantiles": quantiles
        }
        
        http_request_data = {
            "instances": [instance],
            "configuration": configuration
        }
        
        return json.dumps(http_request_data).encode('utf-8')
    
    def __decode_response(self, response, freq, prediction_time, return_samples):
        # we only sent one time series so we only receive one in return
        # however, if possible one will pass multiple time series as predictions will then be faster
        predictions = json.loads(response.decode('utf-8'))['predictions'][0]
        prediction_length = len(next(iter(predictions['quantiles'].values())))
        prediction_index = pd.DatetimeIndex(start=prediction_time, freq=freq, periods=prediction_length)        
        if return_samples:
            dict_of_samples = {'sample_' + str(i): s for i, s in enumerate(predictions['samples'])}
        else:
            dict_of_samples = {}
        return pd.DataFrame(data={**predictions['quantiles'], **dict_of_samples}, index=prediction_index)

    def set_frequency(self, freq):
        self.freq = freq    

Function in dbg-deepar.ipynb

predictor = DeepARPredictor(estimator_job)

ts, dynamic_feat, observed = util.query_for_stock('BMW', target_column, covariate_columns, stock_data_series, prediction_length)

prediction = predictor.predict(ts=ts, dynamic_feat = dynamic_feat, quantiles=[0.10, 0.5, 0.90], return_samples=False)

** Error logs**

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-118-6bae3056850a> in <module>
----> 1 prediction = predictor.predict(ts=ts, dynamic_feat = dynamic_feat, quantiles=[0.10, 0.5, 0.90], return_samples=False)
      2 prediction.head()

~/deepar_util.py in predict(self, ts, cat, dynamic_feat, num_samples, return_samples, quantiles)
    201 
    202         Return value: list of `pandas.DataFrame` objects, each containing the predictions
--> 203         """
    204         prediction_time = ts.index[-1] + pd.Timedelta(1, unit='D')
    205         quantiles = [str(q) for q in quantiles]

/opt/conda/lib/python3.7/site-packages/pandas/core/generic.py in __getattr__(self, name)
   5272             if self._info_axis._can_hold_identifiers_and_holds_name(name):
   5273                 return self[name]
-> 5274             return object.__getattribute__(self, name)
   5275 
   5276     def __setattr__(self, name: str, value) -> None:

AttributeError: 'Series' object has no attribute 'freq'

System information

• SageMaker Python SDK version:
• Framework name (eg. PyTorch) or algorithm (eg. KMeans):
• Framework version:
• Python version: 3.7.7
• CPU or GPU: CPU
• Custom Docker image (Y/N): N
• **Pandas version 1.0.1

[ajaykarpur]

Hi @fallingstar3107, thanks for reaching out. The example repository you linked looks to be unmaintained. Could you please try one of these examples instead?

• https://github.com/awslabs/amazon-sagemaker-examples/blob/master/introduction_to_amazon_algorithms/deepar_electricity/DeepAR-Electricity.ipynb
• https://github.com/awslabs/amazon-sagemaker-examples/blob/master/introduction_to_amazon_algorithms/deepar_synthetic/deepar_synthetic.ipynb

Please let us know if you run into any issues or have further questions.