mf

tira-io · Mar 25, 2024 · 27b06f8 · 27b06f8
1 parent 56c5955
commit 27b06f8
Showing 1 changed file with 18 additions and 16 deletions.
diff --git a/tutorials/tutorial-data-access-from-java.ipynb b/tutorials/tutorial-data-access-from-java.ipynb
@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -27,7 +27,11 @@
      "text": [
       "INFO:root:No settings given in /root/.tira/.tira-settings.json. I will use defaults.\n",
       "INFO:root:No settings given in /root/.tira/.tira-settings.json. I will use defaults.\n",
-      "/root/.tira/extracted_datasets/None/longeval-tiny-train-20240315-training/input-data\n"
+      "Download from Zenodo: https://zenodo.org/records/10628882/files/training-20231104-inputs.zip?download=1\n",
+      "Download: 100%|███████████████████████████| 83.2M/83.2M [00:00<00:00, 89.8MiB/s]\n",
+      "Download finished. Extract...\n",
+      "Extraction finished:  /root/.tira/extracted_datasets/None/training-20231104-training/\n",
+      "/root/.tira/extracted_datasets/None/training-20231104-training/input-data\n"
      ]
     }
    ],
@@ -37,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -49,12 +53,12 @@
     }
    ],
    "source": [
-    "!ls /root/.tira/extracted_datasets/None/longeval-tiny-train-20240315-training/input-data"
+    "!ls /root/.tira/extracted_datasets/None/training-20231104-training/input-data"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -69,7 +73,7 @@
     }
    ],
    "source": [
-    "!zcat /root/.tira/extracted_datasets/None/longeval-tiny-train-20240315-training/input-data/documents.jsonl.gz|head -2 "
+    "!zcat /root/.tira/extracted_datasets/None/training-20231104-training/input-data/documents.jsonl.gz|head -2 "
    ]
   },
   {
@@ -84,7 +88,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -93,9 +97,8 @@
      "text": [
       "INFO:root:No settings given in /root/.tira/.tira-settings.json. I will use defaults.\n",
       "INFO:root:No settings given in /root/.tira/.tira-settings.json. I will use defaults.\n",
-      "Download from the Incubator: https://files.webis.de/data-in-production/data-research/tira-zenodo-dump-preparation/query-processors-in-progress/qpptk-all-predictors-clef-labs.zip\n",
-      "\tThis is only used for last spot checks before archival to Zenodo.\n",
-      "Download: 100%|█████████████████████████████| 969k/969k [00:00<00:00, 3.82MiB/s]\n",
+      "Download from Zenodo: https://zenodo.org/records/10852738/files/qpptk-all-predictors-clef-labs.zip\n",
+      "Download: 100%|█████████████████████████████| 969k/969k [00:00<00:00, 9.43MiB/s]\n",
       "Download finished. Extract...\n",
       "Extraction finished:  /root/.tira/extracted_runs/ir-benchmarks/longeval-train-20230513-training/qpptk\n",
       "/root/.tira/extracted_runs/ir-benchmarks/longeval-train-20230513-training/qpptk/2024-02-27-21-19-19/output\n"
@@ -108,7 +111,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -135,7 +138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -144,9 +147,8 @@
      "text": [
       "INFO:root:No settings given in /root/.tira/.tira-settings.json. I will use defaults.\n",
       "INFO:root:No settings given in /root/.tira/.tira-settings.json. I will use defaults.\n",
-      "Download from the Incubator: https://files.webis.de/data-in-production/data-research/tira-zenodo-dump-preparation/query-processors-in-progress/ows-query-segmentation-hyb-a-clef-labs.zip\n",
-      "\tThis is only used for last spot checks before archival to Zenodo.\n",
-      "Download: 100%|█████████████████████████████| 275k/275k [00:00<00:00, 2.49MiB/s]\n",
+      "Download from Zenodo: https://zenodo.org/records/10852738/files/ows-query-segmentation-hyb-a-clef-labs.zip\n",
+      "Download: 100%|█████████████████████████████| 275k/275k [00:00<00:00, 3.37MiB/s]\n",
       "Download finished. Extract...\n",
       "Extraction finished:  /root/.tira/extracted_runs/ir-benchmarks/longeval-train-20230513-training/ows\n",
       "/root/.tira/extracted_runs/ir-benchmarks/longeval-train-20230513-training/ows/2024-02-25-08-12-47/output\n"
@@ -159,7 +161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {