Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Bugfix for mintaka: Test mode for prepraing subgraphs dataset #132

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Bugfix for mintaka: Test mode for prepraing subgraphs dataset #132

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
143 changes: 83 additions & 60 deletions experiments/subgraphs_datasets_prepare_input_data/mintaka.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,28 +4,7 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/usr/local/lib/python3.8/dist-packages/tqdm/auto.py:22: 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",
"2023-04-06 14:53:59.996607: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA\n",
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"2023-04-06 14:54:00.132818: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
"2023-04-06 14:54:00.165111: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"2023-04-06 14:54:00.840228: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n",
"2023-04-06 14:54:00.840311: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64\n",
"2023-04-06 14:54:00.840318: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n",
"2023-04-06 14:54:02.091424: E tensorflow/stream_executor/cuda/cuda_driver.cc:265] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected\n",
"2023-04-06 14:54:02.091459: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: 4d7d28cf31fc\n",
"2023-04-06 14:54:02.091464: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: 4d7d28cf31fc\n",
"2023-04-06 14:54:02.091542: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: NOT_FOUND: was unable to find libcuda.so DSO loaded into this program\n",
"2023-04-06 14:54:02.091560: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 510.108.3\n"
]
}
],
"outputs": [],
"source": [
"import pandas as pd\n",
"from pywikidata import Entity\n",
Expand Down Expand Up @@ -101,11 +80,11 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"def prepare_data(data_df, results_df, wd_search_results_top_k: int = 1, mgenre=None, ner=None, entities_selection=None):\n",
"def prepare_data(data_df, results_df, wd_search_results_top_k: int = 1, mgenre=None, ner=None, entities_selection=None, test_mode=False):\n",
" answers_cols = [c for c in results_df.columns if 'answer_' in c]\n",
"\n",
" results_df['answers_ids'] = results_df[answers_cols].progress_apply(\n",
Expand All @@ -119,36 +98,37 @@
" df = results_df.merge(data_df, on='question')\n",
"\n",
" for _, row in tqdm(df.iterrows(), total=df.index.size):\n",
" if len(row['answerEntity']) == 0:\n",
" continue\n",
"\n",
" golden_true_entity = [Entity(e['name']) for e in row['answerEntity']]\n",
"\n",
" if mgenre is None or ner is None or entities_selection is None:\n",
" question_entity = [\n",
" Entity(e['name'])\n",
" for e in row['questionEntity']\n",
" if e['entityType'] == 'entity' and e['name'] not in [None, 'None', ''] and e['name'][0] == 'Q'\n",
" ]\n",
" additional_candidates = []\n",
" for qe in question_entity:\n",
" for _,e in qe.forward_one_hop_neighbours:\n",
" if e not in golden_true_entity:\n",
" additional_candidates.append(e.idx)\n",
" random.shuffle(additional_candidates)\n",
" additional_candidates = additional_candidates[:5]\n",
" question_entity = [\n",
" Entity(e['name'])\n",
" for e in row['questionEntity']\n",
" if e['entityType'] == 'entity' and e['name'] not in [None, 'None', ''] and e['name'][0] == 'Q'\n",
" ]\n",
" \n",
" if test_mode:\n",
" candidates_ids = row['answers_ids']\n",
" else:\n",
" question_with_ner, entities_list = ner.entity_labeling(row['question'], True)\n",
" mgenre_results = mgenre(question_with_ner)\n",
" selected_entities = entities_selection(entities_list, mgenre_results)\n",
" if mgenre is None or ner is None or entities_selection is None:\n",
" additional_candidates = []\n",
" for qe in question_entity:\n",
" for _,e in qe.forward_one_hop_neighbours:\n",
" if e not in golden_true_entity:\n",
" additional_candidates.append(e.idx)\n",
" random.shuffle(additional_candidates)\n",
" additional_candidates = additional_candidates[:5]\n",
" else:\n",
" question_with_ner, entities_list = ner.entity_labeling(row['question'], True)\n",
" mgenre_results = mgenre(question_with_ner)\n",
" selected_entities = entities_selection(entities_list, mgenre_results)\n",
"\n",
" questionEntity = list(itertools.chain(*[\n",
" get_wd_search_results(l, 1, language='en')[:1]\n",
" for l in selected_entities\n",
" ]))\n",
" additional_candidates = []\n",
" question_entity = list(itertools.chain(*[\n",
" get_wd_search_results(l, 1, language='en')[:1]\n",
" for l in selected_entities\n",
" ]))\n",
" additional_candidates = []\n",
"\n",
" candidates_ids = set(additional_candidates + row['answers_ids'] + [e.idx for e in golden_true_entity])\n",
" candidates_ids = set(additional_candidates + row['answers_ids'] + [e.idx for e in golden_true_entity])\n",
" \n",
" for candidate_id in candidates_ids:\n",
" candidate_entity = Entity(candidate_id)\n",
Expand All @@ -171,10 +151,23 @@
"name": "stderr",
"output_type": "stream",
"text": [
"Reusing dataset mintaka (/root/.cache/huggingface/datasets/AmazonScience___mintaka/en/1.0.0/bb35d95f07aed78fa590601245009c5f585efe909dbd4a8f2a4025ccf65bb11d)\n",
"100%|██████████| 3/3 [00:00<00:00, 267.76it/s]\n"
"Found cached dataset mintaka (/Users/ms/.cache/huggingface/datasets/AmazonScience___mintaka/en/1.0.0/bb35d95f07aed78fa590601245009c5f585efe909dbd4a8f2a4025ccf65bb11d)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "00fcc9682c374d8eb34158b9004bb915",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/3 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
Expand Down Expand Up @@ -250,26 +243,56 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 4000/4000 [00:06<00:00, 591.16it/s]\n",
"100%|██████████| 4000/4000 [00:03<00:00, 1331.76it/s]\n"
]
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5d336c8e3d55425ab5b2262e97502399",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/4000 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "bfd6fe089f814f7a91527c4fb293c38d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/4000 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"results_test_df: pd.DataFrame = pd.read_csv('./mintaka_results_test.csv') # test\n",
"\n",
"with open('to_subgraphs/mintaka_test.jsonl', 'w') as f:\n",
" for data_line in prepare_data(ds['test'].to_pandas(), results_test_df):\n",
" for data_line in prepare_data(ds['test'].to_pandas(), results_test_df, test_mode=True):\n",
" f.write(ujson.dumps(data_line)+'\\n')"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_json('./to_subgraphs/mintaka_test.jsonl', lines=True)\n",
"df['id'].unique().shape"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand All @@ -294,7 +317,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
"version": "3.10.8"
},
"orig_nbformat": 4
},
Expand Down