akhdanre
/
TIF_E41211115_lstm-quiz-generator
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: training model change name

This commit is contained in:
akhdanre 2025-03-12 11:37:17 +07:00
parent 4ca70faf14
commit ed1a3df0d8
2 changed files with 24 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
dataset/training_dataset.json
View File

@ -176,19 +176,19 @@
"qa_pairs": [ "qa_pairs": [
{ {
"type": "fill_in_the_blank", "type": "fill_in_the_blank",
"question": "Apa Kepanjangan dari BPUPKI?", "question": "Apa kepanjangan dari BPUPKI?",
"answer": "Badan Penyelidik Usaha Usaha Persiapan Kemerdekaan Indonesia" "answer": "Badan Penyelidik Usaha-Usaha Persiapan Kemerdekaan Indonesia"
}, },
{ {
"type": "multiple_choice", "type": "multiple_choice",
"question": "BPUPKI dibentuk pada ", "question": "BPUPKI dibentuk pada tanggal?",
"options": [ "options": [
"20 April 1945", "20 April 1945",
"29 April 1945", "29 April 1945",
"10 April 1945", "10 April 1945",
"20 Mei 1945" "20 Mei 1945"
], ],
"answer": "20 Mei 1945" "answer": "29 April 1945"
} }
] ]
} }

28
training_model.ipynb
View File

@ -2,30 +2,37 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 47, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# import library\n", "# import library\n",
"\n", "\n",
"# Data manipulation and visualization\n",
"import pandas as pd\n", "import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n", "import numpy as np\n",
"import json\n", "import matplotlib.pyplot as plt\n",
"from tensorflow.keras.preprocessing.text import Tokenizer\n",
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
"\n", "\n",
"# Natural language processing\n",
"import re\n", "import re\n",
"import string\n", "import string\n",
"import nltk\n", "import nltk\n",
"from nltk.corpus import stopwords\n", "from nltk.corpus import stopwords\n",
"from nltk.tokenize import word_tokenize\n", "from nltk.tokenize import word_tokenize\n",
"from nltk.stem import WordNetLemmatizer\n", "from nltk.stem import WordNetLemmatizer\n",
"import pickle\n",
"\n", "\n",
"# Deep learning\n",
"from tensorflow.keras.preprocessing.text import Tokenizer\n",
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
"from tensorflow.keras.models import Model\n", "from tensorflow.keras.models import Model\n",
"from tensorflow.keras.layers import Input, Embedding, LSTM, Dense, Concatenate\n", "from tensorflow.keras.layers import Input, Embedding, LSTM, Dense, Concatenate\n",
"from sklearn.metrics import classification_report, precision_score, recall_score, accuracy_score\n" "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\n",
"\n",
"# Metrics for model evaluation\n",
"from sklearn.metrics import classification_report, precision_score, recall_score, accuracy_score\n",
"\n",
"# Utility for serialization\n",
"import pickle\n"
] ]
}, },
{ {
@ -346,7 +353,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 52, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -467,6 +474,11 @@
" },\n", " },\n",
")\n", ")\n",
"\n", "\n",
"\n",
"early_stop = EarlyStopping(monitor='val_loss', patience=3)\n",
"checkpoint = ModelCheckpoint(\"best_model.h5\", monitor='val_loss', save_best_only=True)\n",
"\n",
"\n",
"# === Training Model === #\n", "# === Training Model === #\n",
"model.fit(\n", "model.fit(\n",
" [context_padded, question_padded],\n", " [context_padded, question_padded],\n",