Improved compatibility for pandas<1.4

README.md

@@ -1,11 +1,12 @@
 <div align="center">
     <br><br>
-    <img alt="Torch Spatiotemporal" src=./docs/source/_static/img/tsl_logo_text.svg width="85%"/>
+    <img alt="Torch Spatiotemporal" src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo_text.svg" width="85%"/>
     <h3>Neural spatiotemporal forecasting with PyTorch</h3>
     <hr>
     <p>
     <img alt="PyPI" src="https://img.shields.io/pypi/v/torch-spatiotemporal">
     <img alt="PyPI - Python Version" src="https://img.shields.io/badge/python-%3E%3D3.8-blue">
+    <!-- img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/torch-spatiotemporal" -->
     <img alt="Total downloads" src="https://static.pepy.tech/badge/torch-spatiotemporal">
     <a href='https://torch-spatiotemporal.readthedocs.io/en/latest/?badge=latest'>
         <img src='https://readthedocs.org/projects/torch-spatiotemporal/badge/?version=latest' alt='Documentation Status' />
@@ -16,21 +17,21 @@
     </p>
 </div>
 
-<p><img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> <b>tsl</b> <em>(Torch Spatiotemporal)</em> is a library built to accelerate research on neural spatiotemporal data processing
+<p><img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> <b>tsl</b> <em>(Torch Spatiotemporal)</em> is a library built to accelerate research on neural spatiotemporal data processing
 methods, with a focus on Graph Neural Networks.</p>
 
-<p><img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl is built on several libraries of the <b>Python</b> scientific computing ecosystem, with the final objective of providing a straightforward process that goes from data preprocessing to model prototyping.
-In particular, <img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl offers a wide range of utilities to develop neural networks in <img src="./docs/source/_static/img/logos/pytorch.svg" width="20px" align="center"/> <a href="https://pytorch.org"><b>PyTorch</b></a> for processing spatiotemporal data signals.</p>
+<p><img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl is built on several libraries of the <b>Python</b> scientific computing ecosystem, with the final objective of providing a straightforward process that goes from data preprocessing to model prototyping.
+In particular, <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl offers a wide range of utilities to develop neural networks in <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/logos/pytorch.svg" width="20px" align="center"/> <a href="https://pytorch.org"><b>PyTorch</b></a> for processing spatiotemporal data signals.</p>
 
 ## Getting Started
 
-Before you start using <img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl, please review the <a href="https://torch-spatiotemporal.readthedocs.io/en/latest/">documentation</a> to get an understanding of the library and its capabilities.
+Before you start using <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl, please review the <a href="https://torch-spatiotemporal.readthedocs.io/en/latest/">documentation</a> to get an understanding of the library and its capabilities.
 
 You can also explore the examples provided in the `examples` directory to see how train deep learning models working with spatiotemporal data.
 
 ## Installation
 
-Before installing <img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl, make sure you have installed <img src="./docs/source/_static/img/logos/pytorch.svg" width="20px" align="center"/> <a href="https://pytorch.org">PyTorch</a> (>=1.9.0) and <img src="./docs/source/_static/img/logos/pyg.svg" width="20px" align="center"/> <a href="https://pyg.org">PyG</a> (>=2.0.3) in your virtual environment (see [PyG installation guidelines](https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html)). <img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl is available for Python>=3.8. We recommend installation from github to be up-to-date with the latest version:
+Before installing <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl, make sure you have installed <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/logos/pytorch.svg" width="20px" align="center"/> <a href="https://pytorch.org">PyTorch</a> (>=1.9.0) and <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/logos/pyg.svg" width="20px" align="center"/> <a href="https://pyg.org">PyG</a> (>=2.0.3) in your virtual environment (see [PyG installation guidelines](https://pytorch-geometric.readthedocs.io/en/latest/install/installation.html)). <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl is available for Python>=3.8. We recommend installation from github to be up-to-date with the latest version:
 
 ```bash
 pip install git+https://github.com/TorchSpatiotemporal/tsl.git
@@ -50,7 +51,7 @@ conda env create -f conda_env.yml
 
 ## Tutorial
 
-The best way to start using <img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl is by following the tutorial notebook in `examples/notebooks/a_gentle_introduction_to_tsl.ipynb`.
+The best way to start using <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl is by following the tutorial notebook in `examples/notebooks/a_gentle_introduction_to_tsl.ipynb`.
 
 ## Documentation
 
@@ -73,7 +74,7 @@ If you use Torch Spatiotemporal for your research, please consider citing the li
 
 By [Andrea Cini](https://andreacini.github.io/) and [Ivan Marisca](https://marshka.github.io/).
 
-Thanks to all contributors! Check the [Contributing guidelines](https://github.com/TorchSpatiotemporal/tsl/blob/dev/.github/CONTRIBUTING.md) and help us build a better <img src="./docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl.
+Thanks to all contributors! Check the [Contributing guidelines](https://github.com/TorchSpatiotemporal/tsl/blob/dev/.github/CONTRIBUTING.md) and help us build a better <img src="https://raw.githubusercontent.com/TorchSpatiotemporal/tsl/main/docs/source/_static/img/tsl_logo.svg" width="25px" align="center"/> tsl.
 
 <a href="https://github.com/TorchSpatiotemporal/tsl/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=TorchSpatiotemporal/tsl" />

examples/imputation/run_imputation_experiment.py

@@ -164,12 +164,14 @@ def run_imputation(cfg: DictConfig):
         mode='min',
     )
 
-    trainer = Trainer(max_epochs=cfg.epochs,
-                      default_root_dir=cfg.run.dir,
-                      logger=exp_logger,
-                      gpus=1 if torch.cuda.is_available() else None,
-                      gradient_clip_val=cfg.grad_clip_val,
-                      callbacks=[early_stop_callback, checkpoint_callback])
+    trainer = Trainer(
+        max_epochs=cfg.epochs,
+        default_root_dir=cfg.run.dir,
+        logger=exp_logger,
+        accelerator='gpu' if torch.cuda.is_available() else 'cpu',
+        devices=1,
+        gradient_clip_val=cfg.grad_clip_val,
+        callbacks=[early_stop_callback, checkpoint_callback])
 
     trainer.fit(imputer, datamodule=dm)
 

tsl/datasets/pems_bay.py

@@ -77,11 +77,8 @@ def load_raw(self):
         # load traffic data
         traffic_path = os.path.join(self.root_dir, 'pems_bay.h5')
         df = pd.read_hdf(traffic_path)
-        # add missing values
-        datetime_idx = sorted(df.index)
-        date_range = pd.date_range(datetime_idx[0],
-                                   datetime_idx[-1],
-                                   freq='5T')
+        # add missing values (index is sorted)
+        date_range = pd.date_range(df.index[0], df.index[-1], freq='5T')
         df = df.reindex(index=date_range)
         # load distance matrix
         path = os.path.join(self.root_dir, 'pems_bay_dist.npy')

tsl/datasets/prototypes/casting.py

@@ -99,4 +99,4 @@ def time_unit_to_nanoseconds(time_unit: str):
         return 365.2425 * 24 * 60 * 60 * 10**9
     elif time_unit == 'week':
         time_unit = 'W'
-    return pd.Timedelta('1' + time_unit).delta
+    return pd.Timedelta('1' + time_unit).value

tsl/metrics/torch/metric_base.py

@@ -65,10 +65,9 @@ def __init__(self,
 
         if metric_fn_kwargs is None:
             metric_fn_kwargs = dict()
-        if metric_fn is None:
-            self.metric_fn = None
-        else:
-            self.metric_fn = partial(metric_fn, **metric_fn_kwargs)
+
+        self.metric_fn = partial(metric_fn, **metric_fn_kwargs)
+
         self.mask_nans = mask_nans
         self.mask_inf = mask_inf
         if at is None:

tsl/nn/layers/base/embedding.py

@@ -63,19 +63,18 @@ def get_emb(self):
 
     def forward(self,
                 expand: Optional[List] = None,
-                token_index: OptTensor = None,
-                tokens_first: bool = True):
+                node_index: OptTensor = None,
+                nodes_first: bool = True):
         """"""
         emb = self.get_emb()
-        if token_index is not None:
-            emb = emb[token_index]
-        if not tokens_first:
+        if node_index is not None:
+            emb = emb[node_index]
+        if not nodes_first:
             emb = emb.T
         if expand is None:
             return emb
         shape = [*emb.size()]
         view = [
-            1 if d > 0 else shape.pop(0 if tokens_first else -1)
-            for d in expand
+            1 if d > 0 else shape.pop(0 if nodes_first else -1) for d in expand
         ]
         return emb.view(*view).expand(*expand)