Upload 104 files
#1
by
zklmorales
- opened
- Final.ipynb +25 -13
- test.ipynb +5 -5
Final.ipynb
CHANGED
|
@@ -2,23 +2,35 @@
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
-
"execution_count":
|
| 6 |
"metadata": {},
|
| 7 |
"outputs": [
|
| 8 |
-
{
|
| 9 |
-
"name": "stderr",
|
| 10 |
-
"output_type": "stream",
|
| 11 |
-
"text": [
|
| 12 |
-
"c:\\Users\\Admin\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\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",
|
| 13 |
-
" from .autonotebook import tqdm as notebook_tqdm\n"
|
| 14 |
-
]
|
| 15 |
-
},
|
| 16 |
{
|
| 17 |
"name": "stdout",
|
| 18 |
"output_type": "stream",
|
| 19 |
"text": [
|
| 20 |
-
"
|
| 21 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
]
|
| 23 |
}
|
| 24 |
],
|
|
@@ -86,7 +98,7 @@
|
|
| 86 |
" 'prev2pos': prev2pos \n",
|
| 87 |
" }\n",
|
| 88 |
"\n",
|
| 89 |
-
"new_sentence = \"
|
| 90 |
"\n",
|
| 91 |
"tokens = nltk.word_tokenize(new_sentence)\n",
|
| 92 |
"\n",
|
|
@@ -114,7 +126,7 @@
|
|
| 114 |
"predicted_class = torch.argmax(outputs_cls.logits, dim=1).item()\n",
|
| 115 |
"\n",
|
| 116 |
"# Check if the sentence is grammatically correct\n",
|
| 117 |
-
"if predicted_class == 1
|
| 118 |
" print(\"The sentence is grammatically correct.\")\n",
|
| 119 |
"else:\n",
|
| 120 |
" # Proceed with grammar correction candidates\n",
|
|
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
+
"execution_count": 14,
|
| 6 |
"metadata": {},
|
| 7 |
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
{
|
| 9 |
"name": "stdout",
|
| 10 |
"output_type": "stream",
|
| 11 |
"text": [
|
| 12 |
+
"Grammar correction candidates:\n",
|
| 13 |
+
"Candidate: Siya ay nagising kanina .\n",
|
| 14 |
+
"Probability: 0.9917004704475403\n",
|
| 15 |
+
"Cosine Similarity: 0.18928596377372742\n",
|
| 16 |
+
"\n",
|
| 17 |
+
"Candidate: Siya ay dumating kanina .\n",
|
| 18 |
+
"Probability: 0.9892023205757141\n",
|
| 19 |
+
"Cosine Similarity: 0.002990148961544037\n",
|
| 20 |
+
"\n",
|
| 21 |
+
"Candidate: Siya ay namatay kanina .\n",
|
| 22 |
+
"Probability: 0.9889046549797058\n",
|
| 23 |
+
"Cosine Similarity: -0.04294966533780098\n",
|
| 24 |
+
"\n",
|
| 25 |
+
"Candidate: Siya ay nagbitiw kanina .\n",
|
| 26 |
+
"Probability: 0.9842618703842163\n",
|
| 27 |
+
"Cosine Similarity: -0.029277324676513672\n",
|
| 28 |
+
"\n",
|
| 29 |
+
"Candidate: Siya ay nahuli kanina .\n",
|
| 30 |
+
"Probability: 0.9830281734466553\n",
|
| 31 |
+
"Cosine Similarity: -0.02716892771422863\n",
|
| 32 |
+
"\n",
|
| 33 |
+
"Original sentence POS Tags: ['PRS', 'LM', 'VBTF', 'RBW', 'PMP']\n"
|
| 34 |
]
|
| 35 |
}
|
| 36 |
],
|
|
|
|
| 98 |
" 'prev2pos': prev2pos \n",
|
| 99 |
" }\n",
|
| 100 |
"\n",
|
| 101 |
+
"new_sentence = \"Siya ay magigising kanina.\"\n",
|
| 102 |
"\n",
|
| 103 |
"tokens = nltk.word_tokenize(new_sentence)\n",
|
| 104 |
"\n",
|
|
|
|
| 126 |
"predicted_class = torch.argmax(outputs_cls.logits, dim=1).item()\n",
|
| 127 |
"\n",
|
| 128 |
"# Check if the sentence is grammatically correct\n",
|
| 129 |
+
"if predicted_class == 1: # Assuming class 0 represents grammatical correctness\n",
|
| 130 |
" print(\"The sentence is grammatically correct.\")\n",
|
| 131 |
"else:\n",
|
| 132 |
" # Proceed with grammar correction candidates\n",
|
test.ipynb
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
-
"execution_count":
|
| 6 |
"metadata": {},
|
| 7 |
"outputs": [
|
| 8 |
{
|
|
@@ -96,7 +96,7 @@
|
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"cell_type": "code",
|
| 99 |
-
"execution_count":
|
| 100 |
"metadata": {},
|
| 101 |
"outputs": [
|
| 102 |
{
|
|
@@ -104,7 +104,7 @@
|
|
| 104 |
"output_type": "stream",
|
| 105 |
"text": [
|
| 106 |
"Sentence is grammatically wrong.\n",
|
| 107 |
-
"Probabilities: [0.
|
| 108 |
]
|
| 109 |
}
|
| 110 |
],
|
|
@@ -115,7 +115,7 @@
|
|
| 115 |
"tokenizer = AutoTokenizer.from_pretrained(\"zklmorales/bert_finetuned\")\n",
|
| 116 |
"model = AutoModelForSequenceClassification.from_pretrained(\"zklmorales/bert_finetuned\")\n",
|
| 117 |
"\n",
|
| 118 |
-
"new_sentence = \"Siya ay
|
| 119 |
"\n",
|
| 120 |
"# Tokenize the input text\n",
|
| 121 |
"inputs = tokenizer(new_sentence, return_tensors=\"pt\")\n",
|
|
@@ -141,7 +141,7 @@
|
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"cell_type": "code",
|
| 144 |
-
"execution_count":
|
| 145 |
"metadata": {},
|
| 146 |
"outputs": [
|
| 147 |
{
|
|
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
+
"execution_count": 2,
|
| 6 |
"metadata": {},
|
| 7 |
"outputs": [
|
| 8 |
{
|
|
|
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"cell_type": "code",
|
| 99 |
+
"execution_count": 11,
|
| 100 |
"metadata": {},
|
| 101 |
"outputs": [
|
| 102 |
{
|
|
|
|
| 104 |
"output_type": "stream",
|
| 105 |
"text": [
|
| 106 |
"Sentence is grammatically wrong.\n",
|
| 107 |
+
"Probabilities: [0.9901305437088013, 0.009869435802102089]\n"
|
| 108 |
]
|
| 109 |
}
|
| 110 |
],
|
|
|
|
| 115 |
"tokenizer = AutoTokenizer.from_pretrained(\"zklmorales/bert_finetuned\")\n",
|
| 116 |
"model = AutoModelForSequenceClassification.from_pretrained(\"zklmorales/bert_finetuned\")\n",
|
| 117 |
"\n",
|
| 118 |
+
"new_sentence = \"Siya ay magigising kanina.\"\n",
|
| 119 |
"\n",
|
| 120 |
"# Tokenize the input text\n",
|
| 121 |
"inputs = tokenizer(new_sentence, return_tensors=\"pt\")\n",
|
|
|
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"cell_type": "code",
|
| 144 |
+
"execution_count": null,
|
| 145 |
"metadata": {},
|
| 146 |
"outputs": [
|
| 147 |
{
|