addign notebook to create dataset with results

src/create_results_dataset.ipynb

@@ -9,9 +9,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/matthieumeeus/opt/anaconda3/envs/canary/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -22,20 +30,20 @@
       "        num_rows: 13\n",
       "    })\n",
       "})\n",
-      "           Class            Anonymization tool       Type  \\\n",
-      "0           None              No anonymization   Baseline   \n",
-      "1      NER-based                         Azure  NER-based   \n",
-      "2      NER-based                      Presidio  NER-based   \n",
-      "3      NER-based                     Scrubadub  NER-based   \n",
-      "4      NER-based                        Gliner  NER-based   \n",
-      "5      NER-based                        Uniner  NER-based   \n",
-      "6      NER-based                      Textwash  NER-based   \n",
-      "7   Perturbation                           TEM      Pert.   \n",
-      "8      LLM-based           Anthropic (GPT-4.1)  LLM-based   \n",
-      "9      LLM-based  Anthropic (Gemini-2.5-Flash)  LLM-based   \n",
-      "10     LLM-based        Anthropic (Llama-3-8B)  LLM-based   \n",
-      "11     LLM-based           Rescriber (GPT-4.1)  LLM-based   \n",
-      "12     LLM-based        Rescriber (Llama-3-8B)  LLM-based   \n",
+      "           Class            Anonymization tool          Type  \\\n",
+      "0           None              No anonymization      Baseline   \n",
+      "1      NER-based                         Azure     NER-based   \n",
+      "2      NER-based                      Presidio     NER-based   \n",
+      "3      NER-based                     Scrubadub     NER-based   \n",
+      "4      NER-based                        Gliner     NER-based   \n",
+      "5      NER-based                        Uniner     NER-based   \n",
+      "6      NER-based                      Textwash     NER-based   \n",
+      "7   Perturbation                           TEM  Perturbation   \n",
+      "8      LLM-based           Anthropic (GPT-4.1)     LLM-based   \n",
+      "9      LLM-based  Anthropic (Gemini-2.5-Flash)     LLM-based   \n",
+      "10     LLM-based        Anthropic (Llama-3-8B)     LLM-based   \n",
+      "11     LLM-based           Rescriber (GPT-4.1)     LLM-based   \n",
+      "12     LLM-based        Rescriber (Llama-3-8B)     LLM-based   \n",
       "\n",
       "    English Explicit (easy)  English Explicit (hard)  English Implicit  \\\n",
       "0                       100                       98                32   \n",
@@ -99,7 +107,7 @@
     "    [\"NER-based\", \"Gliner\", \"NER-based\", 67, 71, 28, None, None, 0.89],\n",
     "    [\"NER-based\", \"Uniner\", \"NER-based\", 41, 81, 37, None, None, 0.86],\n",
     "    [\"NER-based\", \"Textwash\", \"NER-based\", 39, 55, 32, None, None, 0.96],\n",
-    "    [\"Perturbation\", \"TEM\", \"Pert.\", 90, 85, 31, None, None, 0.69],\n",
+    "    [\"Perturbation\", \"TEM\", \"Perturbation\", 90, 85, 31, None, None, 0.69],\n",
     "    [\"LLM-based\", \"Anthropic (GPT-4.1)\", \"LLM-based\", 26, 58, 19, 26, 24, 0.88],\n",
     "    [\"LLM-based\", \"Anthropic (Gemini-2.5-Flash)\", \"LLM-based\", 48, 64, 33, None, None, 0.95],\n",
     "    [\"LLM-based\", \"Anthropic (Llama-3-8B)\", \"LLM-based\",37, 72, 21, None, None, 0.87],\n",
@@ -146,8 +154,9 @@
      "output_type": "stream",
      "text": [
       "Pushing split train to the Hub.\n",
-      "Pushing dataset shards to the dataset hub: 100%|██████████| 1/1 [00:00<00:00, 5849.80it/s]\n",
-      "Downloading metadata: 100%|██████████| 868/868 [00:00<00:00, 1.09MB/s]\n"
+      "Creating parquet from Arrow format: 100%|██████████| 1/1 [00:00<00:00, 119.09ba/s]\n",
+      "Pushing dataset shards to the dataset hub: 100%|██████████| 1/1 [00:01<00:00,  1.37s/it]\n",
+      "Deleting unused files from dataset repository: 100%|██████████| 1/1 [00:00<00:00,  2.40it/s]\n"
      ]
     }
    ],