Merge branch 'main' into all-contributors/add-tom-andersson

.all-contributorsrc

@@ -1,13 +1,25 @@
 {
   "projectName": "deepsensor",
   "projectOwner": "tom-andersson",
+  "skipCI": true,
   "files": [
     "README.md"
   ],
   "commitType": "docs",
   "commitConvention": "angular",
   "contributorsPerLine": 7,
+  "contributorsSortAlphabetically": true,
   "contributors": [
+    {
+      "login": "kallewesterling",
+      "name": "Kalle Westerling",
+      "avatar_url": "https://avatars.githubusercontent.com/u/7298727?v=4",
+      "profile": "http://www.westerling.nu",
+      "contributions": [
+        "code",
+        "doc"
+      ]
+    },
     {
       "login": "tom-andersson",
       "name": "Tom Andersson",

.github/workflows/docs.yml

@@ -8,6 +8,7 @@ jobs:
         steps:
             - uses: actions/checkout@v3
             - uses: actions/setup-python@v3
+            - uses: nikeee/setup-pandoc@v1
             - name: "Install dependencies"
               run: pip install -r requirements.txt
             - name: "Install sphinx"
@@ -23,4 +24,4 @@ jobs:
                     publish_branch: gh-pages
                     github_token: ${{ secrets.GITHUB_TOKEN }}
                     publish_dir: docs/_build/
-                    force_orphan: true
+                    force_orphan: true

README.md

@@ -189,6 +189,7 @@ DeepSensor is funded by [The Alan Turing Institute](https://www.turing.ac.uk/).
   <tbody>
     <tr>
       <td align="center" valign="top" width="14.28%"><a href="https://www.bas.ac.uk/profile/tomand"><img src="https://avatars.githubusercontent.com/u/26459412?v=4?s=100" width="100px;" alt="Tom Andersson"/><br /><sub><b>Tom Andersson</b></sub></a><br /><a href="#code-tom-andersson" title="Code">💻</a> <a href="#research-tom-andersson" title="Research">🔬</a> <a href="#maintenance-tom-andersson" title="Maintenance">🚧</a> <a href="#bug-tom-andersson" title="Bug reports">🐛</a> <a href="#test-tom-andersson" title="Tests">⚠️</a> <a href="#tutorial-tom-andersson" title="Tutorials">✅</a> <a href="#doc-tom-andersson" title="Documentation">📖</a> <a href="#review-tom-andersson" title="Reviewed Pull Requests">👀</a> <a href="#talk-tom-andersson" title="Talks">📢</a> <a href="#question-tom-andersson" title="Answering Questions">💬</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="http://www.westerling.nu"><img src="https://avatars.githubusercontent.com/u/7298727?v=4?s=100" width="100px;" alt="Kalle Westerling"/><br /><sub><b>Kalle Westerling</b></sub></a><br /><a href="#code-kallewesterling" title="Code">💻</a> <a href="#doc-kallewesterling" title="Documentation">📖</a></td>
     </tr>
   </tbody>
 </table>

deepsensor/data/loader.py

@@ -727,7 +727,7 @@ def sample_df(
             idx = rng.choice(df.index, N)
             X_c = df.loc[idx].reset_index()[["x1", "x2"]].values.T.astype(self.dtype)
             Y_c = df.loc[idx].values.T
-        elif sampling_strat in ["all", "split"]:
+        elif isinstance(sampling_strat, str) and sampling_strat in ["all", "split"]:
             # NOTE if "split", we assume that the context-target split has already been applied to the df
             # in an earlier scope with access to both the context and target data. This is maybe risky!
             X_c = df.reset_index()[["x1", "x2"]].values.T.astype(self.dtype)
@@ -1011,10 +1011,18 @@ def sample_variable(var, sampling_strat, seed):
             raise ValueError(f"split_frac must be between 0 and 1, got {split_frac}")
         if self.links is None:
             b1 = any(
-                [strat == _ for _ in ["split", "gapfill"] for strat in context_sampling]
+                [
+                    strat in ["split", "gapfill"]
+                    for strat in context_sampling
+                    if isinstance(strat, str)
+                ]
             )
             b2 = any(
-                [strat == _ for _ in ["split", "gapfill"] for strat in target_sampling]
+                [
+                    strat in ["split", "gapfill"]
+                    for strat in target_sampling
+                    if isinstance(strat, str)
+                ]
             )
             if b1 or b2:
                 raise ValueError(
@@ -1028,7 +1036,11 @@ def sample_variable(var, sampling_strat, seed):
                     target_sampling[target_idx],
                 )
                 if any(
-                    [strat == _ for _ in ["split", "gapfill"] for strat in link_strats]
+                    [
+                        strat in ["split", "gapfill"]
+                        for strat in link_strats
+                        if isinstance(strat, str)
+                    ]
                 ):
                     # If one of the sampling strategies is "split" or "gapfill", the other must
                     # use the same splitting strategy

docs/getting-started/tutorials/quickstart.ipynb

@@ -9,7 +9,10 @@
    "outputs": [],
    "source": [
     "import sys, os\n",
-    "sys.path.append(os.path.abspath(\"../../../\"))"
+    "sys.path.append(os.path.abspath(\"../../../\"))\n",
+    "\n",
+    "import logging\n",
+    "logging.captureWarnings(True)"
    ]
   },
   {
@@ -60,13 +63,13 @@
     "# Generate training tasks with up to 10% of grid cells passed as context and all grid cells\n",
     "# passed as targets\n",
     "train_tasks = []\n",
-    "for date in pd.date_range(\"2013-01-01\", \"2014-11-30\")[::7]:\n",
+    "for date in pd.date_range(\"2013-01-01\", \"2014-11-30\")[::14]:\n",
     "    task = task_loader(date, context_sampling=np.random.uniform(0.0, 0.1), target_sampling=\"all\")\n",
     "    train_tasks.append(task)\n",
     "\n",
     "# Train model\n",
-    "for epoch in range(10):\n",
-    "    train_epoch(model, train_tasks, progress_bar=True)\n",
+    "for epoch in range(1):\n",
+    "    train_epoch(model, train_tasks)\n",
     "\n",
     "# Predict on new task with 10% of context data and a dense grid of target points\n",
     "test_task = task_loader(\"2014-12-31\", 0.1)\n",