[FIX] Default AutoPatchTST config (#811)

* fix default patchtst

* base recurrent import split

nbs/common.base_recurrent.ipynb

@@ -691,11 +691,19 @@
    "outputs": [],
    "source": [
     "#| hide\n",
-    "# add h=0,1 unit test for _parse_windows \n",
     "from neuralforecast.losses.pytorch import MAE\n",
     "from neuralforecast.utils import AirPassengersDF\n",
-    "from neuralforecast.tsdataset import TimeSeriesDataset, TimeSeriesDataModule\n",
-    "\n",
+    "from neuralforecast.tsdataset import TimeSeriesDataset, TimeSeriesDataModule"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "# add h=0,1 unit test for _parse_windows \n",
     "# Declare batch\n",
     "AirPassengersDF['x'] = np.array(len(AirPassengersDF))\n",
     "AirPassengersDF['x2'] = np.array(len(AirPassengersDF)) * 2\n",
@@ -729,13 +737,6 @@
     "test_eq(set(temporal_data_cols), set(['y', 'x', 'x2']))\n",
     "test_eq(windows['temporal'].shape, torch.Size([1,len(['y', 'x', 'x2', 'available_mask']),117,12+1]))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

nbs/models.ipynb

@@ -1683,7 +1683,7 @@
     "        \"input_size_multiplier\": [1, 2, 3],\n",
     "        \"h\": None,\n",
     "        \"hidden_size\": tune.choice([16, 128, 256]),\n",
-    "        \"n_head\": tune.choice([4, 16]),\n",
+    "        \"n_heads\": tune.choice([4, 16]),\n",
     "        \"patch_len\": tune.choice([16, 24]),\n",
     "        \"learning_rate\": tune.loguniform(1e-4, 1e-1),\n",
     "        \"scaler_type\": tune.choice([None, 'robust', 'standard']),\n",

neuralforecast/auto.py

@@ -985,7 +985,7 @@ class AutoPatchTST(BaseAuto):
         "input_size_multiplier": [1, 2, 3],
         "h": None,
         "hidden_size": tune.choice([16, 128, 256]),
-        "n_head": tune.choice([4, 16]),
+        "n_heads": tune.choice([4, 16]),
         "patch_len": tune.choice([16, 24]),
         "learning_rate": tune.loguniform(1e-4, 1e-1),
         "scaler_type": tune.choice([None, "robust", "standard"]),

neuralforecast/models/hint.py

@@ -24,7 +24,7 @@ def get_bottomup_P(S: np.ndarray):
 
     **References:**<br>
     - [Orcutt, G.H., Watts, H.W., & Edwards, J.B.(1968). \"Data aggregation and information loss\". The American
-    Economic Review, 58 , 773{787)](http://www.jstor.org/stable/1815532).
+    Economic Review, 58 , 773(787)](http://www.jstor.org/stable/1815532).
     """
     n_series = len(S)
     n_agg = n_series - S.shape[1]