forked from kubapok/en-ner-conll-2003
update main
This commit is contained in:
parent
0e4b12691c
commit
ca4f919157
24
main.ipynb
24
main.ipynb
@ -28,17 +28,13 @@
|
|||||||
"import torch\n",
|
"import torch\n",
|
||||||
"import pandas as pd\n",
|
"import pandas as pd\n",
|
||||||
"\n",
|
"\n",
|
||||||
"from sklearn.model_selection import train_test_split\n",
|
|
||||||
"from torchtext.vocab import Vocab\n",
|
"from torchtext.vocab import Vocab\n",
|
||||||
"from collections import Counter\n",
|
"from collections import Counter\n",
|
||||||
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
|
|
||||||
"from sklearn.metrics import accuracy_score\n",
|
|
||||||
"\n",
|
"\n",
|
||||||
"import lzma\n",
|
"import lzma\n",
|
||||||
"import re\n",
|
"import re"
|
||||||
"import itertools"
|
|
||||||
],
|
],
|
||||||
"execution_count": 2,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -60,7 +56,7 @@
|
|||||||
" x = self.softmax(x)\n",
|
" x = self.softmax(x)\n",
|
||||||
" return x"
|
" return x"
|
||||||
],
|
],
|
||||||
"execution_count": 22,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -82,7 +78,7 @@
|
|||||||
" x = self.fc1(x)\n",
|
" x = self.fc1(x)\n",
|
||||||
" return x"
|
" return x"
|
||||||
],
|
],
|
||||||
"execution_count": 23,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -111,7 +107,7 @@
|
|||||||
"for i in range(len(ner_tags_set)):\n",
|
"for i in range(len(ner_tags_set)):\n",
|
||||||
" ner_tags_dictionary[ner_tags_set[i]] = i"
|
" ner_tags_dictionary[ner_tags_set[i]] = i"
|
||||||
],
|
],
|
||||||
"execution_count": 46,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -141,7 +137,7 @@
|
|||||||
"train_tokens_ids = data_preprocessing(tokens)\n",
|
"train_tokens_ids = data_preprocessing(tokens)\n",
|
||||||
"train_labels = labels_preprocessing(ner_tags)"
|
"train_labels = labels_preprocessing(ner_tags)"
|
||||||
],
|
],
|
||||||
"execution_count": 47,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -215,7 +211,7 @@
|
|||||||
" display('recall: : ', recall)\n",
|
" display('recall: : ', recall)\n",
|
||||||
" display('f1: ', f1_score)"
|
" display('f1: ', f1_score)"
|
||||||
],
|
],
|
||||||
"execution_count": 27,
|
"execution_count": null,
|
||||||
"outputs": [
|
"outputs": [
|
||||||
{
|
{
|
||||||
"output_type": "display_data",
|
"output_type": "display_data",
|
||||||
@ -539,7 +535,7 @@
|
|||||||
"test_tokens_ids = data_preprocessing(dev_0_data)\n",
|
"test_tokens_ids = data_preprocessing(dev_0_data)\n",
|
||||||
"test_labels = labels_preprocessing(dev_0_tags)\n"
|
"test_labels = labels_preprocessing(dev_0_tags)\n"
|
||||||
],
|
],
|
||||||
"execution_count": 41,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -601,7 +597,7 @@
|
|||||||
"display('recall: : ', recall)\n",
|
"display('recall: : ', recall)\n",
|
||||||
"display('f1: ', f1_score)"
|
"display('f1: ', f1_score)"
|
||||||
],
|
],
|
||||||
"execution_count": 42,
|
"execution_count": null,
|
||||||
"outputs": [
|
"outputs": [
|
||||||
{
|
{
|
||||||
"output_type": "display_data",
|
"output_type": "display_data",
|
||||||
@ -763,7 +759,7 @@
|
|||||||
" Y_predictions = ner_model(X)\n",
|
" Y_predictions = ner_model(X)\n",
|
||||||
" result[i].append(int(torch.argmax(Y_predictions)))"
|
" result[i].append(int(torch.argmax(Y_predictions)))"
|
||||||
],
|
],
|
||||||
"execution_count": 49,
|
"execution_count": null,
|
||||||
"outputs": []
|
"outputs": []
|
||||||
}
|
}
|
||||||
]
|
]
|
||||||
|
Loading…
Reference in New Issue
Block a user