update notebooks

notebooks/dvc.yaml

@@ -2,26 +2,26 @@ stages:
   results-mind-val:
     cmd: jupytext --to notebook --execute mind-val.md
     deps:
-      - mind-val.md
+      - mind-val/mind-val.md
       - ../outputs/mind-val/profile-metrics.csv.gz
     outs:
-      - mind-val.ipynb:
+      - mind-val/mind-val.ipynb:
           cache: false
 
   results-mind-small:
     cmd: jupytext --to notebook --execute mind-small.md
     deps:
-      - mind-small.md
+      - mind-small/mind-small.md
       - ../outputs/mind-small/profile-metrics.csv.gz
     outs:
-      - mind-small.ipynb:
+      - mind-small/mind-small.ipynb:
           cache: false
 
   results-mind-subset:
     cmd: jupytext --to notebook --execute mind-subset.md
     deps:
-      - mind-subset.md
+      - mind-subset/mind-subset.md
       - ../outputs/mind-subset/profile-metrics.csv.gz
     outs:
-      - mind-subset.ipynb:
+      - mind-subset/mind-subset.ipynb:
           cache: false

notebooks/mind-small.ipynb → notebooks/mind-small/mind-small.ipynb

@@ -7,7 +7,7 @@
     "# Offline Evaluation Metrics Visualizations\n",
     "This notebook visualizes user-specific performance metrics of various recommenders in the mind-small dataset to assess effectiveness and ranking overlap. We explore two metric groups:\n",
     "1. **Effectiveness Metrics**: We use ranking-based metrics, Normalized Discounted Cumulative Gain (NDCG) and Reciprocal Rank (RR), to evaluate recommender effectiveness.\n",
-    "2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to fianl rankings."
+    "2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to final rankings."
    ]
   },
   {

notebooks/mind-small.md → notebooks/mind-small/mind-small.md

@@ -15,7 +15,7 @@ kernelspec:
 # Offline Evaluation Metrics Visualizations
 This notebook visualizes user-specific performance metrics of various recommenders in the mind-small dataset to assess effectiveness and ranking overlap. We explore two metric groups:
 1. **Effectiveness Metrics**: We use ranking-based metrics, Normalized Discounted Cumulative Gain (NDCG) and Reciprocal Rank (RR), to evaluate recommender effectiveness.
-2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to fianl rankings.
+2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to final rankings.
 
 +++
 
@@ -30,17 +30,17 @@ This notebook visualizes user-specific performance metrics of various recommende
 PyData packages:
 
 ```{code-cell} ipython3
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
 import pandas as pd
 import seaborn as sns
 ```
 
 Local code:
 
 ```{code-cell} ipython3
-from poprox_recommender.eval_tables import EvalTable
 from IPython.display import HTML
+from poprox_recommender.eval_tables import EvalTable
 ```
 
 Set up progress:

notebooks/mind-subset.ipynb → notebooks/mind-subset/mind-subset.ipynb

@@ -7,7 +7,7 @@
     "# Offline Evaluation Metrics Visualizations\n",
     "This notebook visualizes user-specific performance metrics of various recommenders in the mind-subset dataset to assess effectiveness and ranking overlap. We explore two metric groups:\n",
     "1. **Effectiveness Metrics**: We use ranking-based metrics, Normalized Discounted Cumulative Gain (NDCG) and Reciprocal Rank (RR), to evaluate recommender effectiveness.\n",
-    "2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to fianl rankings."
+    "2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to final rankings."
    ]
   },
   {
@@ -814,6 +814,9 @@
   }
  ],
  "metadata": {
+  "jupytext": {
+   "formats": "ipynb,md:myst"
+  },
   "kernelspec": {
    "display_name": "Python 3 (ipykernel)",
    "language": "python",

notebooks/mind-subset.md → notebooks/mind-subset/mind-subset.md

@@ -13,9 +13,9 @@ kernelspec:
 ---
 
 # Offline Evaluation Metrics Visualizations
-This notebook visualizes user-specific performance metrics of various recommenders in the MIND-Subset dataset to assess effectiveness and ranking overlap. We explore two metric groups:
+This notebook visualizes user-specific performance metrics of various recommenders in the mind-subset dataset to assess effectiveness and ranking overlap. We explore two metric groups:
 1. **Effectiveness Metrics**: We use ranking-based metrics, Normalized Discounted Cumulative Gain (NDCG) and Reciprocal Rank (RR), to evaluate recommender effectiveness.
-2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to fianl rankings.
+2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to final rankings.
 
 +++
 
@@ -30,17 +30,17 @@ This notebook visualizes user-specific performance metrics of various recommende
 PyData packages:
 
 ```{code-cell} ipython3
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
 import pandas as pd
 import seaborn as sns
 ```
 
 Local code:
 
 ```{code-cell} ipython3
-from poprox_recommender.eval_tables import EvalTable
 from IPython.display import HTML
+from poprox_recommender.eval_tables import EvalTable
 ```
 
 Set up progress:

notebooks/mind-val.ipynb → notebooks/mind-val/mind-val.ipynb

@@ -7,7 +7,7 @@
     "# Offline Evaluation Metrics Visualizations\n",
     "This notebook visualizes user-specific performance metrics of various recommenders in the mind-val dataset to assess effectiveness and ranking overlap. We explore two metric groups:\n",
     "1. **Effectiveness Metrics**: We use ranking-based metrics, Normalized Discounted Cumulative Gain (NDCG) and Reciprocal Rank (RR), to evaluate recommender effectiveness.\n",
-    "2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to fianl rankings."
+    "2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to final rankings."
    ]
   },
   {

notebooks/mind-val.md → notebooks/mind-val/mind-val.md

@@ -15,7 +15,7 @@ kernelspec:
 # Offline Evaluation Metrics Visualizations
 This notebook visualizes user-specific performance metrics of various recommenders in the mind-val dataset to assess effectiveness and ranking overlap. We explore two metric groups:
 1. **Effectiveness Metrics**: We use ranking-based metrics, Normalized Discounted Cumulative Gain (NDCG) and Reciprocal Rank (RR), to evaluate recommender effectiveness.
-2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to fianl rankings.
+2. **Ranking Overlap Metrics**: We use Rank-Based Overlap (RBO) to assess consistency in top-k recommendations relative to final rankings.
 
 +++
 
@@ -30,17 +30,17 @@ This notebook visualizes user-specific performance metrics of various recommende
 PyData packages:
 
 ```{code-cell} ipython3
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
 import pandas as pd
 import seaborn as sns
 ```
 
 Local code:
 
 ```{code-cell} ipython3
-from poprox_recommender.eval_tables import EvalTable
 from IPython.display import HTML
+from poprox_recommender.eval_tables import EvalTable
 ```
 
 Set up progress: