Merge branch 'dev' into irregular

awslabs · Aug 28, 2023 · f442a8e · f442a8e
2 parents c69fa9e + 107a36c
commit f442a8e
Show file tree

Hide file tree

Showing 191 changed files with 8,969 additions and 1,956 deletions.
diff --git a/.github/workflows/tests-xgboost.yaml b/.github/workflows/tests-xgboost.yaml
@@ -21,7 +21,8 @@ jobs:
  python-version: ${{ matrix.python-version }}
  - name: Install other dependencies
  run: |
- python -m pip install -U pip
+ python -m pip install -U pip setuptools wheel
+ python -m pip install -U "Cython<3.0"
  pip install .
  pip install -r requirements/requirements-test.txt
  pip install -r requirements/requirements-rotbaum.txt

diff --git a/docs/getting_started/background.md b/docs/getting_started/background.md
@@ -9,10 +9,10 @@ This article may be extended or reworked in the future.
 ## What is Time Series Forecasting?
 
 Generally speaking, forecasting just means making predictions about events in
-the feature. Trivially, in time series forecasting we want to predict the
+the future. Trivially, in time series forecasting we want to predict the
 future values of a given time series.
 
-For example, in electricy production it is very important that demand and
+For example, in electricity production it is very important that demand and
 supply are in balance. Thus, producers anticipate consumer demand for
 electricity and plan production capacity accordingly. In other words, producers
 rely on accurate time series forecasting of consumer demand for electricity to

diff --git a/docs/getting_started/models.md b/docs/getting_started/models.md
@@ -13,7 +13,7 @@ N-BEATS<br>[Oreshkin et al. 2019][Oreshkin2019] | Global | Un
 Rotbaum<br>[Hasson et al. 2021][Hasson2021] | Global | Univariate | XGBoost, Quantile Regression Forests, LightGBM, Level Set Forecaster | [Numpy][Rotbaum]
 Temporal Fusion Transformer<br>[Lim et al. 2021][Lim2021] | Global | Univariate | LSTM, self attention | [MXNet][TFT]
 Transformer<br>[Vaswani et al. 2017][Vaswani2017] | Global | Univariate | MLP, multi-head attention | [MXNet][Transformer]
-WaveNet<br>[van den Oord et al. 2016][vanDenOord2016] | Global | Univariate | Dilated convolution | [MXNet][WaveNet]
+WaveNet<br>[van den Oord et al. 2016][vanDenOord2016] | Global | Univariate | Dilated convolution | [MXNet][WaveNet_mx], [PyTorch][WaveNet_torch]
 SimpleFeedForward | Global | Univariate | MLP | [MXNet][SFF_mx], [PyTorch][SFF_torch]
 DeepVAR<br>[Salinas et al. 2019][Salinas2019] | Global | Multivariate | RNN | [MXNet][DeepVAR]
 GPVAR<br>[Salinas et al. 2019][Salinas2019] | Global | Multivariate | RNN, Gaussian process | [MXNet][GPVAR]
@@ -60,7 +60,8 @@ NPTS | Local | Un
 [Rotbaum]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/ext/rotbaum/_estimator.py
 [TFT]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/mx/model/tft/_estimator.py
 [Transformer]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/mx/model/transformer/_estimator.py
-[WaveNet]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/mx/model/wavenet/_estimator.py
+[WaveNet_mx]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/mx/model/wavenet/_estimator.py
+[WaveNet_torch]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/torch/model/wavenet/estimator.py
 [SFF_mx]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/mx/model/simple_feedforward/_estimator.py
 [SFF_torch]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/torch/model/simple_feedforward/estimator.py
 [DeepVAR]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/mx/model/deepvar/_estimator.py
@@ -72,4 +73,4 @@ NPTS | Local | Un
 [Prophet]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/ext/prophet/_predictor.py
 [NaiveSeasonal]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/model/seasonal_naive/_predictor.py
 [Naive2]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/ext/naive_2/_predictor.py
-[NPTS]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/ext/npts/_predictor.py
+[NPTS]: https://github.com/awslabs/gluonts/blob/dev/src/gluonts/model/npts/_predictor.py
diff --git a/docs/tutorials/data_manipulation/pandasdataframes.md.template b/docs/tutorials/data_manipulation/pandasdataframes.md.template
@@ -123,8 +123,8 @@ from gluonts.dataset.pandas import PandasDataset
 
 max_end = max(df.groupby("item_id").apply(lambda _df: _df.index[-1]))
 dfs_dict = {}
-for item_id, gdf in df.groupby("item_id"):
- new_index = pd.date_range(gdf.index[0], end=max_end, freq="1D")
+for item_id, gdf in df_missing_val.groupby("item_id"):
+ new_index = pd.date_range(gdf.index[0], end=max_end, freq="1H")
  dfs_dict[item_id] = gdf.reindex(new_index).drop("item_id", axis=1)
 
 ds = PandasDataset(dfs_dict, target="target")

diff --git a/docs/tutorials/forecasting/hierarchical_model_tutorial.md.template b/docs/tutorials/forecasting/hierarchical_model_tutorial.md.template
@@ -105,7 +105,6 @@ estimator = DeepVARHierarchicalEstimator(
  freq=hts.freq,
  prediction_length=prediction_length,
  trainer=Trainer(epochs=2),
- target_dim=hts.num_ts,
  S=S,
 )
 predictor = estimator.train(dataset)
@@ -159,7 +158,6 @@ estimator = DeepVARHierarchicalEstimator(
  freq=hts.freq,
  prediction_length=prediction_length,
  trainer=Trainer(epochs=2),
- target_dim=hts.num_ts,
  S=S,
 )
 predictor = estimator.train(dataset_train)
@@ -233,7 +231,6 @@ estimator = DeepVARHierarchicalEstimator(
  freq=hts.freq,
  prediction_length=prediction_length,
  trainer=Trainer(epochs=2),
- target_dim=hts_train.num_ts,
  S=S,
 )
 

diff --git a/evaluations/README.md b/evaluations/README.md
diff --git a/evaluations/electricity/DeepAREstimator.json b/evaluations/electricity/DeepAREstimator.json
diff --git a/evaluations/electricity/MQCNNEstimator.json b/evaluations/electricity/MQCNNEstimator.json
diff --git a/evaluations/electricity/MQRNNEstimator.json b/evaluations/electricity/MQRNNEstimator.json
diff --git a/evaluations/electricity/NPTSPredictor.json b/evaluations/electricity/NPTSPredictor.json
diff --git a/evaluations/electricity/RForecastPredictor_ets.json b/evaluations/electricity/RForecastPredictor_ets.json
diff --git a/evaluations/electricity/SeasonalNaivePredictor.json b/evaluations/electricity/SeasonalNaivePredictor.json
diff --git a/evaluations/electricity/SimpleFeedForwardEstimator.json b/evaluations/electricity/SimpleFeedForwardEstimator.json
diff --git a/evaluations/electricity/TransformerEstimator.json b/evaluations/electricity/TransformerEstimator.json
diff --git a/evaluations/exchange_rate/DeepAREstimator.json b/evaluations/exchange_rate/DeepAREstimator.json
diff --git a/evaluations/exchange_rate/MQCNNEstimator.json b/evaluations/exchange_rate/MQCNNEstimator.json
diff --git a/evaluations/exchange_rate/MQRNNEstimator.json b/evaluations/exchange_rate/MQRNNEstimator.json
diff --git a/evaluations/exchange_rate/NPTSPredictor.json b/evaluations/exchange_rate/NPTSPredictor.json
diff --git a/evaluations/exchange_rate/RForecastPredictor_arima.json b/evaluations/exchange_rate/RForecastPredictor_arima.json
diff --git a/evaluations/exchange_rate/RForecastPredictor_ets.json b/evaluations/exchange_rate/RForecastPredictor_ets.json
diff --git a/evaluations/exchange_rate/SeasonalNaivePredictor.json b/evaluations/exchange_rate/SeasonalNaivePredictor.json
diff --git a/evaluations/exchange_rate/SimpleFeedForwardEstimator.json b/evaluations/exchange_rate/SimpleFeedForwardEstimator.json
diff --git a/evaluations/exchange_rate/TransformerEstimator.json b/evaluations/exchange_rate/TransformerEstimator.json