✨ Test tutorial on colab

.github/workflows/test_pkg_on_colab.yaml

@@ -0,0 +1,26 @@
+name: Test that tutorial runs on latest colab image
+
+on:
+    push:
+        branches: [dev]
+    pull_request:
+        branches: [main]
+    schedule:
+        - cron: '0 2 3 * *'
+
+jobs:
+    test-tutorial-on-colab:
+        name: Test tutorial on latest colab image
+        runs-on: ubuntu-latest-4core # increase disk space  
+        # https://console.cloud.google.com/artifacts/docker/colab-images/europe/public/runtime
+        container:
+            image: europe-docker.pkg.dev/colab-images/public/runtime:latest
+        steps:
+        - uses: actions/checkout@v4
+        - name: Install pimms-learn and papermill
+          run: | 
+            python3 -m pip install pimms-learn papermill
+        - name: Run tutorial
+          run: |
+            cd project
+            papermill 04_1_train_pimms_models.ipynb 04_1_train_pimms_models_output.ipynb

project/04_1_train_pimms_models.ipynb

@@ -5,10 +5,10 @@
    "id": "eae0a078",
    "metadata": {},
    "source": [
-    "# Scikit-learn styple transformers of the data\n",
+    "# PIMMS Tutorial: Scikit-learn style transformers\n",
     "\n",
     "1. Load data into pandas dataframe\n",
-    "2. Fit transformer on training data\n",
+    "2. Fit model on training data, potentially specify validation data\n",
     "3. Impute only missing values with predictions from model\n",
     "\n",
     "Autoencoders need wide training data, i.e. a sample with all its features' intensities, whereas\n",
@@ -34,7 +34,7 @@
     "    except metadata.PackageNotFoundError:\n",
     "        print(\"Install PIMMS...\")\n",
     "        # !pip install git+https://github.com/RasmussenLab/pimms.git@dev\n",
-    "        !pip install pimms-learn   "
+    "        !pip install pimms-learn"
    ]
   },
   {
@@ -74,7 +74,7 @@
     "\n",
     "\n",
     "from vaep.plotting.defaults import color_model_mapping\n",
-    "import vaep.plotting.data \n",
+    "import vaep.plotting.data\n",
     "import vaep.sampling\n",
     "\n",
     "from vaep.sklearn.cf_transformer import CollaborativeFilteringTransformer\n",
@@ -208,7 +208,7 @@
     "\n",
     "\n",
     "def select_features(df, feat_prevalence=.2, axis=0):\n",
-    "    # ! vaep.filter.select_features\n",
+    "    # # ! vaep.filter.select_features\n",
     "    N = df.shape[axis]\n",
     "    minimum_freq = N * feat_prevalence\n",
     "    freq = df.notna().sum(axis=axis)\n",
@@ -273,7 +273,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# # # CollaborativeFilteringTransformer?"
+    "# # # # CollaborativeFilteringTransformer?"
    ]
   },
   {
@@ -680,10 +680,6 @@
   }
  ],
  "metadata": {
-  "mystnb": {
-   "execution_raise_on_error": true,
-   "execution_timeout": 120
-  },
   "jupytext": {
    "cell_metadata_filter": "-all",
    "main_language": "python",
@@ -705,6 +701,10 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.8.17"
+  },
+  "mystnb": {
+   "execution_raise_on_error": true,
+   "execution_timeout": 120
   }
  },
  "nbformat": 4,

project/04_1_train_pimms_models.py

@@ -1,8 +1,8 @@
 # %% [markdown]
-# # Scikit-learn styple transformers of the data
+# # PIMMS Tutorial: Scikit-learn style transformers
 #
 # 1. Load data into pandas dataframe
-# 2. Fit transformer on training data
+# 2. Fit model on training data, potentially specify validation data
 # 3. Impute only missing values with predictions from model
 #
 # Autoencoders need wide training data, i.e. a sample with all its features' intensities, whereas
@@ -21,7 +21,7 @@
     except metadata.PackageNotFoundError:
         print("Install PIMMS...")
         # # !pip install git+https://github.com/RasmussenLab/pimms.git@dev
-        # !pip install pimms-learn   
+        # !pip install pimms-learn
 
 # %% [markdown]
 # If on colab, please restart the environment and run everything from here on.
@@ -42,7 +42,7 @@
 
 
 from vaep.plotting.defaults import color_model_mapping
-import vaep.plotting.data 
+import vaep.plotting.data
 import vaep.sampling
 
 from vaep.sklearn.cf_transformer import CollaborativeFilteringTransformer