Merge pull request #67 from haesleinhuepf/git-bob-mod-GXp68aDJ2c

Add markdown explanations and include "feature_selection" in table of contents.

docs/47_clustering/feature_selection.ipynb

@@ -5,7 +5,9 @@
    "id": "bea6da31-a5ef-4b44-b96c-7570e8659b34",
    "metadata": {},
    "source": [
-    "# Feature selection"
+    "# Feature selection\n",
+    "\n",
+    "Feature selection involves selecting a subset of relevant features for use in model construction. It helps improve the performance of machine learning models by eliminating redundant and irrelevant data."
    ]
   },
   {
@@ -26,6 +28,15 @@
     "import matplotlib.pyplot as plt"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "61828c9a-b6bc-4623-b391-88a35f112ff9",
+   "metadata": {},
+   "source": [
+    "### Load data\n",
+    "We first load the image data that will be used for feature extraction."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,
@@ -235,7 +246,7 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>1200 rows × 12 columns</p>\n",
+       "<p>1200 rows \u00d7 12 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -321,6 +332,15 @@
     "selected_table"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "1efc67e1-3919-4141-b881-0323cfd6f5cb",
+   "metadata": {},
+   "source": [
+    "### Feature correlation\n",
+    "We examine the correlation between the selected features to understand their relationships."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 8,

docs/_toc.yml

@@ -61,7 +61,6 @@ parts:
       - file: 12b_remote_files/exploring_zenodo
       - file: 12b_remote_files/exploring_doi
 
-
     #  - file: 12_image_analysis_basics/skeletonization
     # todo: https://github.com/jni/skan
     #  - file: 12_image_analysis_basics/analyse_banana_data_set
@@ -150,7 +149,6 @@ parts:
       - file: 20a_pixel_classification/feature_stacks
       - file: 20a_pixel_classification/selecting_features
 
-
     - file: 20b_deep_learning/readme
       sections:
       - file: 20b_deep_learning/cellpose
@@ -221,7 +219,6 @@ parts:
       - file: 22_feature_extraction/distance_from_center
       - file: 22_feature_extraction/distance_along_line
 
-
     - file: 25_neighborhood_relationships_between_cells/readme
       sections:
       - file: 25_neighborhood_relationships_between_cells/01_neighborhood_definitions
@@ -324,7 +321,7 @@ parts:
       - file: 35_parameter_optimization/optimization_basics
       - file: 35_parameter_optimization/label_image_optimizer
       - file: 35_parameter_optimization/membrane_segmentation
-      
+
     - file: 07_prompt_engineering/readme
       sections:
       - file: 07_prompt_engineering/01_prompting
@@ -359,7 +356,6 @@ parts:
       - file: 70_workflows/notebook_export
       - file: 70_workflows/napari_workflows
 
-
   - caption: Tabular data, plots and statistics
     chapters:
     - file: 40_tabular_data_wrangling/readme
@@ -396,7 +392,6 @@ parts:
     #   - file: 44_hypothesis_testing/Testing_tomato_ripen_time
     #   - file: 44_hypothesis_testing/The_p-value
 
-
     - file: 47_clustering/readme
       sections:
       - file: 47_clustering/trailer
@@ -406,7 +401,8 @@ parts:
       #- file: 47_clustering/tissue_clustering
       - file: 47_clustering/interactive_dimensionality_reduction_and_clustering/readme
       - file: 47_clustering/interpolating_between_feature_spaces
-
+      - file: 47_clustering/feature_selection
+
     - file: 51_plotting/readme
       sections:
       - file: 51_plotting/plotting_matplotlib
@@ -432,3 +428,4 @@ parts:
     - file: 01_introduction/glossary
 
     - file: imprint
+