From d4ce992db21435ac51ba1af388030fdbb8ec8a03 Mon Sep 17 00:00:00 2001 From: HyeonhoonLee <68671051+HyeonhoonLee@users.noreply.github.com> Date: Tue, 20 Oct 2020 13:57:40 +0900 Subject: [PATCH] init: Attention layer is added to previous LSTM model --- models/Okt_LSTM/LSTM+Attention.ipynb | 3167 ++++++++++++++++++++++++++ 1 file changed, 3167 insertions(+) create mode 100644 models/Okt_LSTM/LSTM+Attention.ipynb diff --git a/models/Okt_LSTM/LSTM+Attention.ipynb b/models/Okt_LSTM/LSTM+Attention.ipynb new file mode 100644 index 0000000..375f25a --- /dev/null +++ b/models/Okt_LSTM/LSTM+Attention.ipynb @@ -0,0 +1,3167 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.4" + }, + "colab": { + "name": "LSTM", + "provenance": [], + "collapsed_sections": [] + }, + "accelerator": "GPU" + }, + "cells": [ + { + "cell_type": "code", + "metadata": { + "id": "sco7gWp7ej-9", + "outputId": "ce6a2b1f-86c9-44de-8cdd-952c4e95bd73", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + } + }, + "source": [ + "from google.colab import drive\n", + "drive.mount('/content/drive')" + ], + "execution_count": 1, + "outputs": [ + { + "output_type": "stream", + "text": [ + "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "uzob-2SXZp4m", + "outputId": "db51f468-4e6c-4fc0-a768-4d5dc2980833", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 419 + } + }, + "source": [ + "import numpy as np \n", + "import pandas as pd\n", + "import tensorflow as tf\n", + "import tensorflow.keras as keras\n", + "from tensorflow.keras.preprocessing.text import Tokenizer\n", + "from tensorflow.keras.preprocessing.sequence import pad_sequences\n", + "\n", + "df = pd.read_csv('https://raw.githubusercontent.com/HyeonhoonLee/Infra_Meditact_Meditact/master/data/preprocessed_clean20571.csv')\n", + "df" + ], + "execution_count": 2, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
nounslabel
0이어폰 음량 귀6
1독감 예방주사2
2목 음식물 계속 물감6
3케겔 운동10
4등 통증 문의11
.........
20566허리 통증 다리 저림11
20567척추 분리 증 글11
20568뼈 통증17
20569무릎 연골 수술 운동 방법10
20570마지막 좀 감 전시 흉부5
\n", + "

20571 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " nouns label\n", + "0 이어폰 음량 귀 6\n", + "1 독감 예방주사 2\n", + "2 목 음식물 계속 물감 6\n", + "3 케겔 운동 10\n", + "4 등 통증 문의 11\n", + "... ... ...\n", + "20566 허리 통증 다리 저림 11\n", + "20567 척추 분리 증 글 11\n", + "20568 뼈 통증 17\n", + "20569 무릎 연골 수술 운동 방법 10\n", + "20570 마지막 좀 감 전시 흉부 5\n", + "\n", + "[20571 rows x 2 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 2 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "scrolled": true, + "id": "dX4lUamEZp4q", + "outputId": "d7b487d0-7dd2-41ff-b009-7810d93c9268", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 419 + } + }, + "source": [ + "df['nounlist'] = df['nouns'].str.split()\n", + "df.dropna(inplace=True)\n", + "df" + ], + "execution_count": 3, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
nounslabelnounlist
0이어폰 음량 귀6[이어폰, 음량, 귀]
1독감 예방주사2[독감, 예방주사]
2목 음식물 계속 물감6[목, 음식물, 계속, 물감]
3케겔 운동10[케겔, 운동]
4등 통증 문의11[등, 통증, 문의]
............
20566허리 통증 다리 저림11[허리, 통증, 다리, 저림]
20567척추 분리 증 글11[척추, 분리, 증, 글]
20568뼈 통증17[뼈, 통증]
20569무릎 연골 수술 운동 방법10[무릎, 연골, 수술, 운동, 방법]
20570마지막 좀 감 전시 흉부5[마지막, 좀, 감, 전시, 흉부]
\n", + "

20420 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " nouns label nounlist\n", + "0 이어폰 음량 귀 6 [이어폰, 음량, 귀]\n", + "1 독감 예방주사 2 [독감, 예방주사]\n", + "2 목 음식물 계속 물감 6 [목, 음식물, 계속, 물감]\n", + "3 케겔 운동 10 [케겔, 운동]\n", + "4 등 통증 문의 11 [등, 통증, 문의]\n", + "... ... ... ...\n", + "20566 허리 통증 다리 저림 11 [허리, 통증, 다리, 저림]\n", + "20567 척추 분리 증 글 11 [척추, 분리, 증, 글]\n", + "20568 뼈 통증 17 [뼈, 통증]\n", + "20569 무릎 연골 수술 운동 방법 10 [무릎, 연골, 수술, 운동, 방법]\n", + "20570 마지막 좀 감 전시 흉부 5 [마지막, 좀, 감, 전시, 흉부]\n", + "\n", + "[20420 rows x 3 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 3 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "scrolled": true, + "id": "sBokAcMCZp4t", + "outputId": "8e736413-f4bd-46e5-c2b8-d5b9e9acbba8", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + } + }, + "source": [ + "from sklearn.model_selection import train_test_split\n", + "x_train_, x_test_, y_train, y_test = train_test_split(\n", + " df['nounlist'], df['label'], \n", + " test_size=0.2, random_state=1234, \n", + " stratify=df['label']\n", + " )\n", + "\n", + "x_train_.shape, x_test_.shape, y_train.shape, y_test.shape" + ], + "execution_count": 4, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "((16336,), (4084,), (16336,), (4084,))" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 4 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "scrolled": true, + "id": "AYE2TMOgZp4x", + "outputId": "312d4286-4f2e-468d-e554-7e97b63f6d41", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + } + }, + "source": [ + "x_train_.head(10)" + ], + "execution_count": 5, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "2760 [안압]\n", + "12483 [무대, 공포]\n", + "6704 [뇌출혈, 인지, 기능, 저하]\n", + "5829 [요산, 수치]\n", + "4666 [대변, 볼때, 피, 가득]\n", + "17675 [냄새, 못, 얼굴, 경련, 증상, 검사]\n", + "20076 [추간판탈출증, 관]\n", + "4211 [대상포진]\n", + "9775 [중학생, 식탐, 심해]\n", + "147 [장, 위장, 것]\n", + "Name: nounlist, dtype: object" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 5 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "AQEbT1e2Zp40", + "outputId": "af855b7e-acf9-4038-951c-e50a277c6d29", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + } + }, + "source": [ + "vocab_size = 8000\n", + "t = Tokenizer(num_words=vocab_size)\n", + "t.fit_on_texts(df['nounlist'])\n", + "\n", + "t.word_index" + ], + "execution_count": 6, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "{'통증': 1,\n", + " '증상': 2,\n", + " '무릎': 3,\n", + " '허리': 4,\n", + " '약': 5,\n", + " '목': 6,\n", + " '운동': 7,\n", + " '치료': 8,\n", + " '복용': 9,\n", + " '수술': 10,\n", + " '잠': 11,\n", + " '왼쪽': 12,\n", + " '우울증': 13,\n", + " '머리': 14,\n", + " '디스크': 15,\n", + " '다리': 16,\n", + " '어깨': 17,\n", + " '가슴': 18,\n", + " '스트레스': 19,\n", + " '두통': 20,\n", + " '검사': 21,\n", + " '오른쪽': 22,\n", + " '질문': 23,\n", + " '증': 24,\n", + " '골절': 25,\n", + " '근육': 26,\n", + " '수': 27,\n", + " '방법': 28,\n", + " '심장': 29,\n", + " '발목': 30,\n", + " '관절': 31,\n", + " '부분': 32,\n", + " '인대': 33,\n", + " '몸': 34,\n", + " '등': 35,\n", + " '정신과': 36,\n", + " '신경': 37,\n", + " '불안': 38,\n", + " '소리': 39,\n", + " '뼈': 40,\n", + " '병원': 41,\n", + " '손가락': 42,\n", + " '파열': 43,\n", + " '불면증': 44,\n", + " '수면': 45,\n", + " '척추': 46,\n", + " '문의': 47,\n", + " '이상': 48,\n", + " '공황장애': 49,\n", + " '상담': 50,\n", + " '주사': 51,\n", + " '힘': 52,\n", + " '요': 53,\n", + " '발': 54,\n", + " '술': 55,\n", + " '손': 56,\n", + " '걸': 57,\n", + " '저림': 58,\n", + " '염': 59,\n", + " '연골': 60,\n", + " '사람': 61,\n", + " '장애': 62,\n", + " '배': 63,\n", + " '강박증': 64,\n", + " '팔': 65,\n", + " '눈': 66,\n", + " '수치': 67,\n", + " '증후군': 68,\n", + " '부작용': 69,\n", + " '건강': 70,\n", + " '생각': 71,\n", + " '진단': 72,\n", + " '위': 73,\n", + " '종아리': 74,\n", + " '이유': 75,\n", + " '감': 76,\n", + " '번': 77,\n", + " '걱정': 78,\n", + " '호흡': 79,\n", + " '과': 80,\n", + " '살': 81,\n", + " '골반': 82,\n", + " '밤': 83,\n", + " '정신': 84,\n", + " '임신': 85,\n", + " '아침': 86,\n", + " '손목': 87,\n", + " '생리': 88,\n", + " '중': 89,\n", + " '대한': 90,\n", + " '허벅지': 91,\n", + " '숨': 92,\n", + " '개월': 93,\n", + " '조금': 94,\n", + " '아이': 95,\n", + " '약물': 96,\n", + " '증세': 97,\n", + " '재활': 98,\n", + " '음식': 99,\n", + " '상태': 100,\n", + " '환자': 101,\n", + " '관절염': 102,\n", + " '건가': 103,\n", + " '팔꿈치': 104,\n", + " '알': 105,\n", + " '하루': 106,\n", + " '재': 107,\n", + " '피': 108,\n", + " '코': 109,\n", + " '부위': 110,\n", + " '변': 111,\n", + " '엉덩이': 112,\n", + " '더': 113,\n", + " '염증': 114,\n", + " '기억': 115,\n", + " '당뇨': 116,\n", + " '시간': 117,\n", + " '식도염': 118,\n", + " '발바닥': 119,\n", + " '발가락': 120,\n", + " '자고': 121,\n", + " '도움': 122,\n", + " '일': 123,\n", + " '마비': 124,\n", + " '처방': 125,\n", + " '내시경': 126,\n", + " '가능성': 127,\n", + " '원인': 128,\n", + " '현상': 129,\n", + " '류마티스': 130,\n", + " '역류성': 131,\n", + " '불안장애': 132,\n", + " '손상': 133,\n", + " '추가': 134,\n", + " '관': 135,\n", + " '혈압': 136,\n", + " '피부': 137,\n", + " '형': 138,\n", + " '질환': 139,\n", + " '조울증': 140,\n", + " '법': 141,\n", + " '갈비뼈': 142,\n", + " '근육통': 143,\n", + " '뇌': 144,\n", + " '꿈': 145,\n", + " '심해': 146,\n", + " '효과': 147,\n", + " '비': 148,\n", + " '진료': 149,\n", + " '못': 150,\n", + " '개': 151,\n", + " '안쪽': 152,\n", + " '병': 153,\n", + " '승': 154,\n", + " '비타민': 155,\n", + " '어지럼증': 156,\n", + " '얼굴': 157,\n", + " '정': 158,\n", + " '치매': 159,\n", + " '양쪽': 160,\n", + " '데': 161,\n", + " '십자': 162,\n", + " '해도': 163,\n", + " '매일': 164,\n", + " '염려': 165,\n", + " '양제': 166,\n", + " '약간': 167,\n", + " '모근': 168,\n", + " '자세': 169,\n", + " '소화': 170,\n", + " '결과': 171,\n", + " '혈당': 172,\n", + " '간염': 173,\n", + " '긴장': 174,\n", + " '뇌경색': 175,\n", + " '변비': 176,\n", + " '관리': 177,\n", + " '한번': 178,\n", + " '감각': 179,\n", + " '피임': 180,\n", + " '정상': 181,\n", + " '관계': 182,\n", + " '한쪽': 183,\n", + " '골': 184,\n", + " '피로': 185,\n", + " '시작': 186,\n", + " '항우울제': 187,\n", + " '강박': 188,\n", + " '남자': 189,\n", + " '명치': 190,\n", + " '자도': 191,\n", + " '주': 192,\n", + " '대하': 193,\n", + " '걷기': 194,\n", + " '어지러움': 195,\n", + " '초기': 196,\n", + " '소변': 197,\n", + " '교정': 198,\n", + " '기분': 199,\n", + " '밑': 200,\n", + " '저하': 201,\n", + " '입': 202,\n", + " '설사': 203,\n", + " '무기': 204,\n", + " '대장': 205,\n", + " '저리': 206,\n", + " '경추': 207,\n", + " '새벽': 208,\n", + " '내': 209,\n", + " '팔이': 210,\n", + " '해': 211,\n", + " '기침': 212,\n", + " '통': 213,\n", + " '스트레칭': 214,\n", + " '우측': 215,\n", + " '제거': 216,\n", + " '기능': 217,\n", + " '섭취': 218,\n", + " '집중': 219,\n", + " '속': 220,\n", + " '후유증': 221,\n", + " '느낌': 222,\n", + " '교통사고': 223,\n", + " '다이어트': 224,\n", + " '평소': 225,\n", + " '생활': 226,\n", + " '심박수': 227,\n", + " '듭니': 228,\n", + " '앞': 229,\n", + " '경련': 230,\n", + " '시술': 231,\n", + " '물': 232,\n", + " '수면제': 233,\n", + " '감정': 234,\n", + " '키': 235,\n", + " '날': 236,\n", + " '전방': 237,\n", + " '인지': 238,\n", + " '스테로이드': 239,\n", + " '재발': 240,\n", + " '왜': 241,\n", + " '가래': 242,\n", + " '우울': 243,\n", + " '습관': 244,\n", + " '고혈압': 245,\n", + " '족저근막염': 246,\n", + " '회전': 247,\n", + " '아래': 248,\n", + " '가야': 249,\n", + " '위염': 250,\n", + " '여자': 251,\n", + " '어머니': 252,\n", + " '영향': 253,\n", + " '물감': 254,\n", + " '조현병': 255,\n", + " '사진': 256,\n", + " '감기': 257,\n", + " '편두통': 258,\n", + " '아기': 259,\n", + " '꼭': 260,\n", + " '열': 261,\n", + " '장염': 262,\n", + " '현재': 263,\n", + " '성인': 264,\n", + " '사이': 265,\n", + " '여성': 266,\n", + " '퇴': 267,\n", + " '행성': 268,\n", + " '기도': 269,\n", + " '여부': 270,\n", + " '갑상선': 271,\n", + " '듯': 272,\n", + " '심리': 273,\n", + " '간': 274,\n", + " '감염': 275,\n", + " '혈관': 276,\n", + " '부정맥': 277,\n", + " '곤란': 278,\n", + " '점': 279,\n", + " '공포증': 280,\n", + " '게': 281,\n", + " '반복': 282,\n", + " '만성': 283,\n", + " '혀': 284,\n", + " '수도': 285,\n", + " '바로': 286,\n", + " '저녁': 287,\n", + " '기간': 288,\n", + " '온몸': 289,\n", + " '자': 290,\n", + " '마디': 291,\n", + " '자살': 292,\n", + " '협착증': 293,\n", + " '척추측만증': 294,\n", + " '귀': 295,\n", + " '물이': 296,\n", + " '손발': 297,\n", + " '초음파': 298,\n", + " '코로나': 299,\n", + " '부근': 300,\n", + " '발생': 301,\n", + " '간질': 302,\n", + " '수면장애': 303,\n", + " '계속': 304,\n", + " '체중': 305,\n", + " '증가': 306,\n", + " '완치': 307,\n", + " '고생': 308,\n", + " '쥐': 309,\n", + " '다른': 310,\n", + " '반월': 311,\n", + " '항문': 312,\n", + " '구토': 313,\n", + " '마음': 314,\n", + " '곳': 315,\n", + " '침': 316,\n", + " '공복': 317,\n", + " '뇌졸중': 318,\n", + " '복통': 319,\n", + " '복부': 320,\n", + " '정말': 321,\n", + " '외상': 322,\n", + " '깁스': 323,\n", + " '항생제': 324,\n", + " '아버지': 325,\n", + " '밥': 326,\n", + " '장기': 327,\n", + " '편': 328,\n", + " '엄마': 329,\n", + " '토': 330,\n", + " '입술': 331,\n", + " '턱': 332,\n", + " '일자': 333,\n", + " '동안': 334,\n", + " '혹': 335,\n", + " '전체': 336,\n", + " '염좌': 337,\n", + " '옆': 338,\n", + " '불량': 339,\n", + " '적': 340,\n", + " '압박': 341,\n", + " '좌측': 342,\n", + " '엄지손가락': 343,\n", + " '꼬리뼈': 344,\n", + " '후두': 345,\n", + " '살이': 346,\n", + " '위쪽': 347,\n", + " '성격': 348,\n", + " '행동': 349,\n", + " '계단': 350,\n", + " '사회': 351,\n", + " '독감': 352,\n", + " '예방접종': 353,\n", + " '숨쉬기': 354,\n", + " '뒤쪽': 355,\n", + " '언제': 356,\n", + " '가요': 357,\n", + " '땀': 358,\n", + " '팔다리': 359,\n", + " '집': 360,\n", + " '힘줄': 361,\n", + " '기면증': 362,\n", + " '옆구리': 363,\n", + " '폐렴': 364,\n", + " '냄새': 365,\n", + " '맥박': 366,\n", + " '해결': 367,\n", + " '고': 368,\n", + " '요새': 369,\n", + " '얼마': 370,\n", + " '요추': 371,\n", + " '좀': 372,\n", + " '무릎관절': 373,\n", + " '혈액': 374,\n", + " '사용': 375,\n", + " '연관': 376,\n", + " '아픔': 377,\n", + " '주변': 378,\n", + " '나이': 379,\n", + " '뇌출혈': 380,\n", + " '발등': 381,\n", + " '종일': 382,\n", + " '통풍': 383,\n", + " '강직': 384,\n", + " '음주': 385,\n", + " '편도염': 386,\n", + " '거북목': 387,\n", + " '쇄골': 388,\n", + " '전': 389,\n", + " '폐': 390,\n", + " '멍': 391,\n", + " '판': 392,\n", + " '약과': 393,\n", + " '상처': 394,\n", + " '가지': 395,\n", + " '탈모': 396,\n", + " '근막': 397,\n", + " '남성': 398,\n", + " '달리기': 399,\n", + " '정신병': 400,\n", + " '사고': 401,\n", + " '핀': 402,\n", + " '무릅': 403,\n", + " '답변': 404,\n", + " '때': 405,\n", + " '오메가': 406,\n", + " '체': 407,\n", + " '예전': 408,\n", + " '식사': 409,\n", + " '부터': 410,\n", + " '작년': 411,\n", + " '부어': 412,\n", + " '중간': 413,\n", + " '정강이': 414,\n", + " '입원': 415,\n", + " '변화': 416,\n", + " '저혈압': 417,\n", + " '고지혈증': 418,\n", + " '문제': 419,\n", + " '의식': 420,\n", + " '정신분열증': 421,\n", + " '아킬레스건': 422,\n", + " '대변': 423,\n", + " '미열': 424,\n", + " '위장': 425,\n", + " '누우': 426,\n", + " '임파선': 427,\n", + " '친구': 428,\n", + " '간수치': 429,\n", + " '또': 430,\n", + " '안면': 431,\n", + " '찌릿': 432,\n", + " '조절': 433,\n", + " '일주일': 434,\n", + " '정형외과': 435,\n", + " '공부': 436,\n", + " '충격': 437,\n", + " '보톡스': 438,\n", + " '항': 439,\n", + " '움': 440,\n", + " '질병': 441,\n", + " '건': 442,\n", + " '판정': 443,\n", + " '조언': 444,\n", + " '정도': 445,\n", + " '것': 446,\n", + " '몸살': 447,\n", + " '엑스레이': 448,\n", + " '예방': 449,\n", + " '흉부': 450,\n", + " '무리': 451,\n", + " '콜레스테롤': 452,\n", + " '근력': 453,\n", + " '발기부전': 454,\n", + " '나': 455,\n", + " '인공': 456,\n", + " '엄지': 457,\n", + " '날개': 458,\n", + " '신체': 459,\n", + " '마취': 460,\n", + " '자전거': 461,\n", + " '내과': 462,\n", + " '질': 463,\n", + " '기운': 464,\n", + " '성형': 465,\n", + " '혈변': 466,\n", + " '개선': 467,\n", + " '확률': 468,\n", + " '년': 469,\n", + " '혈': 470,\n", + " '추간판탈출증': 471,\n", + " '진통제': 472,\n", + " '부족': 473,\n", + " '얼마나': 474,\n", + " '성관계': 475,\n", + " '분리': 476,\n", + " '끝': 477,\n", + " '체온': 478,\n", + " '화가': 479,\n", + " '제일': 480,\n", + " '저희': 481,\n", + " '눈물': 482,\n", + " '니': 483,\n", + " '만': 484,\n", + " '새끼': 485,\n", + " '폭': 486,\n", + " '물리치료': 487,\n", + " '불편': 488,\n", + " '가스': 489,\n", + " '바이러스': 490,\n", + " '등쪽': 491,\n", + " '원래': 492,\n", + " '남편': 493,\n", + " '의학과': 494,\n", + " '인후': 495,\n", + " '감소': 496,\n", + " '확인': 497,\n", + " '위해': 498,\n", + " '담': 499,\n", + " '놀': 500,\n", + " '출혈': 501,\n", + " '휘': 502,\n", + " '심': 503,\n", + " '발작': 504,\n", + " '완화': 505,\n", + " '충': 506,\n", + " '환청': 507,\n", + " '강화': 508,\n", + " '정신건강': 509,\n", + " '차이': 510,\n", + " '자기': 511,\n", + " '급성': 512,\n", + " '중단': 513,\n", + " '유산균': 514,\n", + " '절제': 515,\n", + " '특정': 516,\n", + " '가나': 517,\n", + " '몸무게': 518,\n", + " '줄': 519,\n", + " '여드름': 520,\n", + " '폭식증': 521,\n", + " '크게': 522,\n", + " '점점': 523,\n", + " '겨드랑이': 524,\n", + " '식욕': 525,\n", + " '뇌졸증': 526,\n", + " '치료법': 527,\n", + " '혼자': 528,\n", + " '음식물': 529,\n", + " '손톱': 530,\n", + " '건강검진': 531,\n", + " '지방': 532,\n", + " '접종': 533,\n", + " '성분': 534,\n", + " '화': 535,\n", + " '이나': 536,\n", + " '거림': 537,\n", + " '낮': 538,\n", + " '함': 539,\n", + " '시험': 540,\n", + " '자위': 541,\n", + " '하체': 542,\n", + " '치가': 543,\n", + " '에이즈': 544,\n", + " '졸음': 545,\n", + " '수면시간': 546,\n", + " '불면': 547,\n", + " '체력': 548,\n", + " '자궁': 549,\n", + " '마그네슘': 550,\n", + " '주기': 551,\n", + " '상황': 552,\n", + " '주위': 553,\n", + " '차': 554,\n", + " '동반': 555,\n", + " '바닥': 556,\n", + " '새끼손가락': 557,\n", + " '자신': 558,\n", + " '판독': 559,\n", + " '잠도': 560,\n", + " '붓기': 561,\n", + " '신경안정제': 562,\n", + " '공포': 563,\n", + " '늘': 564,\n", + " '섬유': 565,\n", + " '전도': 566,\n", + " '자궁경부암': 567,\n", + " '출산': 568,\n", + " '생기': 569,\n", + " '식후': 570,\n", + " '배꼽': 571,\n", + " '물질': 572,\n", + " '여': 573,\n", + " '갑자기': 574,\n", + " '장': 575,\n", + " '촬영': 576,\n", + " '세포': 577,\n", + " '방금': 578,\n", + " '기립': 579,\n", + " '비염': 580,\n", + " '박동': 581,\n", + " '성적': 582,\n", + " '입냄새': 583,\n", + " '아주': 584,\n", + " '칼슘': 585,\n", + " '가운데': 586,\n", + " '쉬': 587,\n", + " '소견': 588,\n", + " '일상생활': 589,\n", + " '부': 590,\n", + " '중독': 591,\n", + " '보': 592,\n", + " '상상': 593,\n", + " '집착': 594,\n", + " '극복': 595,\n", + " '아들': 596,\n", + " '건망증': 597,\n", + " '추간판': 598,\n", + " '편도': 599,\n", + " '식품': 600,\n", + " '안정': 601,\n", + " '과민성': 602,\n", + " '흉통': 603,\n", + " '정수리': 604,\n", + " '저': 605,\n", + " '의': 606,\n", + " '위산': 607,\n", + " '사타구니': 608,\n", + " '바늘': 609,\n", + " '가족': 610,\n", + " '헤르페스': 611,\n", + " '숙면': 612,\n", + " '상': 613,\n", + " '아래쪽': 614,\n", + " '알콜': 615,\n", + " '앞쪽': 616,\n", + " '순간': 617,\n", + " '탈출': 618,\n", + " '남': 619,\n", + " '대칭': 620,\n", + " '슬': 621,\n", + " '불안감': 622,\n", + " '공황': 623,\n", + " '엄지발가락': 624,\n", + " '틱장애': 625,\n", + " '해소': 626,\n", + " '복': 627,\n", + " '흡연': 628,\n", + " '캡슐': 629,\n", + " '수가': 630,\n", + " '트림': 631,\n", + " '부비동염': 632,\n", + " '첨부': 633,\n", + " '종': 634,\n", + " '복합': 635,\n", + " '지속': 636,\n", + " '식도': 637,\n", + " '이명': 638,\n", + " '전신': 639,\n", + " '트': 640,\n", + " '호르몬': 641,\n", + " '활동': 642,\n", + " '볼': 643,\n", + " '알레르기': 644,\n", + " '처럼': 645,\n", + " '호전': 646,\n", + " '학교': 647,\n", + " '고통': 648,\n", + " '돌기': 649,\n", + " '전기': 650,\n", + " '알프': 651,\n", + " '깨': 652,\n", + " '거나': 653,\n", + " '제': 654,\n", + " '유전': 655,\n", + " '고개': 656,\n", + " '방광': 657,\n", + " '부종': 658,\n", + " '루게릭': 659,\n", + " '유도': 660,\n", + " '의욕': 661,\n", + " '화증': 662,\n", + " '잠꼬대': 663,\n", + " '망상': 664,\n", + " '짜증': 665,\n", + " '오른손': 666,\n", + " '탈구': 667,\n", + " '사후': 668,\n", + " '신장': 669,\n", + " '빈혈': 670,\n", + " '타이레놀': 671,\n", + " '천식': 672,\n", + " '일전': 673,\n", + " '흡입': 674,\n", + " '요즘': 675,\n", + " '외': 676,\n", + " '두드러기': 677,\n", + " '골다공증': 678,\n", + " '입안': 679,\n", + " '가능': 680,\n", + " '스쿼트': 681,\n", + " '불': 682,\n", + " '손바닥': 683,\n", + " '벌레': 684,\n", + " '동시': 685,\n", + " '한의원': 686,\n", + " '상승': 687,\n", + " '이제': 688,\n", + " '프로': 689,\n", + " '경직': 690,\n", + " '파이': 691,\n", + " '아빠': 692,\n", + " '의처증': 693,\n", + " '고정': 694,\n", + " '복숭아': 695,\n", + " '자인': 696,\n", + " '용법': 697,\n", + " '중앙': 698,\n", + " '종합': 699,\n", + " '조증': 700,\n", + " '면': 701,\n", + " '도중': 702,\n", + " '병명': 703,\n", + " '균': 704,\n", + " '곤': 705,\n", + " '결절': 706,\n", + " '가루': 707,\n", + " '갈색': 708,\n", + " '하나': 709,\n", + " '종류': 710,\n", + " '자꾸': 711,\n", + " '시기': 712,\n", + " '현기증': 713,\n", + " '보고': 714,\n", + " '직장': 715,\n", + " '갱년기': 716,\n", + " '협심증': 717,\n", + " '하나요': 718,\n", + " '뒤꿈치': 719,\n", + " '대상포진': 720,\n", + " '흉추': 721,\n", + " '지능': 722,\n", + " '여러가지': 723,\n", + " '의자': 724,\n", + " '봉합': 725,\n", + " '금': 726,\n", + " '좌우': 727,\n", + " '피해망상': 728,\n", + " '자낙스': 729,\n", + " '대퇴골': 730,\n", + " '재건': 731,\n", + " '슬개골': 732,\n", + " '이드': 733,\n", + " '유지': 734,\n", + " '짐': 735,\n", + " '선생님': 736,\n", + " '대처': 737,\n", + " '쯤': 738,\n", + " '올해': 739,\n", + " '차고': 740,\n", + " '온': 741,\n", + " '미세': 742,\n", + " '성기': 743,\n", + " '덜': 744,\n", + " '답답': 745,\n", + " '습': 746,\n", + " '점액': 747,\n", + " '평상시': 748,\n", + " '다발': 749,\n", + " '멍울': 750,\n", + " '종종': 751,\n", + " '다시': 752,\n", + " '지끈': 753,\n", + " '발뒤꿈치': 754,\n", + " '음성': 755,\n", + " '연고': 756,\n", + " '부정': 757,\n", + " '급': 758,\n", + " '무기력증': 759,\n", + " '직업': 760,\n", + " '실감': 761,\n", + " '견갑골': 762,\n", + " '트라우마': 763,\n", + " '뒷쪽': 764,\n", + " '접': 765,\n", + " '골프': 766,\n", + " '의존': 767,\n", + " '감퇴': 768,\n", + " '족': 769,\n", + " '시도': 770,\n", + " '골연화증': 771,\n", + " '건염': 772,\n", + " '장경': 773,\n", + " '중족골': 774,\n", + " '예방주사': 775,\n", + " '대장암': 776,\n", + " '등산': 777,\n", + " '커피': 778,\n", + " '액': 779,\n", + " '목구멍': 780,\n", + " '알러지': 781,\n", + " '어디': 782,\n", + " '암': 783,\n", + " '감사': 784,\n", + " '중이': 785,\n", + " '위증': 786,\n", + " '요법': 787,\n", + " '낭종': 788,\n", + " '애': 789,\n", + " '후': 790,\n", + " '자연': 791,\n", + " '식단': 792,\n", + " '풀': 793,\n", + " '발톱': 794,\n", + " '화장실': 795,\n", + " '보통': 796,\n", + " '구내염': 797,\n", + " '순환': 798,\n", + " '소아': 799,\n", + " '반응': 800,\n", + " '일어나서': 801,\n", + " '유발': 802,\n", + " '성': 803,\n", + " '화끈': 804,\n", + " '외과': 805,\n", + " '자주': 806,\n", + " '땐': 807,\n", + " '바깥쪽': 808,\n", + " '괴사': 809,\n", + " '달전': 810,\n", + " '주차': 811,\n", + " '발기': 812,\n", + " '수영': 813,\n", + " '다한증': 814,\n", + " '변형': 815,\n", + " '트릴': 816,\n", + " '푹': 817,\n", + " '부상': 818,\n", + " '강박장애': 819,\n", + " '읍니': 820,\n", + " '정신질환': 821,\n", + " '고민': 822,\n", + " '요통': 823,\n", + " '테니스': 824,\n", + " '삐끗': 825,\n", + " '뚝뚝': 826,\n", + " '척추관': 827,\n", + " '후방': 828,\n", + " '해석': 829,\n", + " '악화': 830,\n", + " '위암': 831,\n", + " '녹내장': 832,\n", + " '누': 833,\n", + " '실수': 834,\n", + " '쭉': 835,\n", + " '물집': 836,\n", + " '주의': 837,\n", + " '혹시': 838,\n", + " '관자놀이': 839,\n", + " '역류': 840,\n", + " '위축': 841,\n", + " '왼손': 842,\n", + " '검진': 843,\n", + " '응급실': 844,\n", + " '할머니': 845,\n", + " '보충': 846,\n", + " '마사지': 847,\n", + " '아무': 848,\n", + " '운전': 849,\n", + " '조직검사': 850,\n", + " '치질': 851,\n", + " '줄넘기': 852,\n", + " '보조': 853,\n", + " '사정': 854,\n", + " '화상': 855,\n", + " '콘서타': 856,\n", + " '오른': 857,\n", + " '때문': 858,\n", + " '타박상': 859,\n", + " '악몽': 860,\n", + " '동생': 861,\n", + " '매우': 862,\n", + " '십견': 863,\n", + " '검지': 864,\n", + " '상관관계': 865,\n", + " '덩어리': 866,\n", + " '달': 867,\n", + " '당화혈색소': 868,\n", + " '마': 869,\n", + " '효능': 870,\n", + " '이비인후과': 871,\n", + " '완전': 872,\n", + " '뒤통수': 873,\n", + " '식은땀': 874,\n", + " '다가': 875,\n", + " '가면': 876,\n", + " '거': 877,\n", + " '이마': 878,\n", + " '졸': 879,\n", + " '끼': 880,\n", + " '청소년': 881,\n", + " '파상풍': 882,\n", + " '지장': 883,\n", + " '우리': 884,\n", + " '경과': 885,\n", + " '면역': 886,\n", + " '인': 887,\n", + " '팔뚝': 888,\n", + " '어려움': 889,\n", + " '주파': 890,\n", + " '근처': 891,\n", + " '전혀': 892,\n", + " '하품': 893,\n", + " '방': 894,\n", + " '침대': 895,\n", + " '무언가': 896,\n", + " '년전': 897,\n", + " '가끔': 898,\n", + " '삶': 899,\n", + " '능력': 900,\n", + " '성욕': 901,\n", + " '파스': 902,\n", + " '뇌진탕': 903,\n", + " '현실': 904,\n", + " '낙상': 905,\n", + " '리보': 906,\n", + " '터널': 907,\n", + " '대인기피증': 908,\n", + " '기복': 909,\n", + " '회피': 910,\n", + " '정서': 911,\n", + " '딸아이': 912,\n", + " '충격파': 913,\n", + " '오금': 914,\n", + " '길이': 915,\n", + " '경차': 916,\n", + " '단술': 917,\n", + " '말': 918,\n", + " '발열': 919,\n", + " '단백뇨': 920,\n", + " '담배': 921,\n", + " '산소': 922,\n", + " '세균': 923,\n", + " '항체': 924,\n", + " '부탁': 925,\n", + " '단순': 926,\n", + " '자율신경': 927,\n", + " '간혹': 928,\n", + " '헛구역질': 929,\n", + " '지름': 930,\n", + " '죽': 931,\n", + " '주전': 932,\n", + " '백혈구': 933,\n", + " '마지막': 934,\n", + " '양': 935,\n", + " '목젖': 936,\n", + " '즙': 937,\n", + " '단백질': 938,\n", + " '테스트': 939,\n", + " '위험': 940,\n", + " '철분': 941,\n", + " '치': 942,\n", + " '무좀': 943,\n", + " '패턴': 944,\n", + " '요산': 945,\n", + " '학년': 946,\n", + " '이': 947,\n", + " '꿈치': 948,\n", + " '상실': 949,\n", + " '필러': 950,\n", + " '실내': 951,\n", + " '피해': 952,\n", + " '두': 953,\n", + " '판단': 954,\n", + " '이듭': 955,\n", + " '병증': 956,\n", + " '공황발작': 957,\n", + " '시선': 958,\n", + " '알콜중독': 959,\n", + " '뭉치': 960,\n", + " '정신분열': 961,\n", + " '발달': 962,\n", + " '탈골': 963,\n", + " '체외': 964,\n", + " '축구': 965,\n", + " '생리통': 966,\n", + " '인슐린': 967,\n", + " '거품': 968,\n", + " '안이': 969,\n", + " '분': 970,\n", + " '대학병원': 971,\n", + " '틴': 972,\n", + " '영상': 973,\n", + " '바': 974,\n", + " '부담': 975,\n", + " '두피': 976,\n", + " '신생아': 977,\n", + " '유독': 978,\n", + " '배변': 979,\n", + " '뭘': 980,\n", + " '성병': 981,\n", + " '치유': 982,\n", + " '이면': 983,\n", + " '양치': 984,\n", + " '초': 985,\n", + " '피멍': 986,\n", + " '자꾸만': 987,\n", + " '지면': 988,\n", + " '빈맥': 989,\n", + " '한약': 990,\n", + " '비용': 991,\n", + " '스': 992,\n", + " '홍조': 993,\n", + " '피부염': 994,\n", + " '진짜': 995,\n", + " '뇌전증': 996,\n", + " '용량': 997,\n", + " '어': 998,\n", + " '관련': 999,\n", + " '책': 1000,\n", + " ...}" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 6 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "8R4GemyJZp43", + "outputId": "f2fe5cb6-f7a6-4e3c-e7d1-e05d9887ef52", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + } + }, + "source": [ + "x_train = t.texts_to_sequences(x_train_)\n", + "x_train" + ], + "execution_count": 7, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[[2033],\n", + " [1889, 563],\n", + " [380, 238, 217, 201],\n", + " [945, 67],\n", + " [423, 1298, 108, 4583],\n", + " [365, 150, 157, 230, 2, 21],\n", + " [471, 135],\n", + " [720],\n", + " [2030, 2200, 146],\n", + " [575, 425, 446],\n", + " [86, 538, 778],\n", + " [297, 524, 358],\n", + " [34],\n", + " [248, 61, 4, 613],\n", + " [54, 1157, 1884],\n", + " [49, 8, 47],\n", + " [37, 19, 589],\n", + " [207],\n", + " [18],\n", + " [1225, 2],\n", + " [384, 46, 59, 50],\n", + " [49, 434, 752],\n", + " [3371, 3372, 779, 9, 23],\n", + " [1344],\n", + " [1576, 1577, 2957, 2958, 704, 8, 89, 4006],\n", + " [1199, 2883, 67],\n", + " [109, 4557, 4558],\n", + " [4232, 674],\n", + " [13, 90],\n", + " [516, 32, 5647, 2338, 829],\n", + " [771, 72],\n", + " [215, 17, 40, 1652],\n", + " [3696, 58, 2],\n", + " [19, 64, 149, 90],\n", + " [475, 273],\n", + " [66, 2875, 553, 89, 1293, 97, 1548, 76],\n", + " [33, 323, 260],\n", + " [5, 166, 1031],\n", + " [608, 1],\n", + " [88, 266, 2979, 1780, 463, 1569, 163],\n", + " [144, 48, 2060],\n", + " [12, 388, 17],\n", + " [6284, 4, 7, 4, 39],\n", + " [2860, 144, 37, 133],\n", + " [18],\n", + " [941, 3046, 108, 21, 125],\n", + " [151, 1974, 88, 1234, 1543, 1286, 21, 991, 370],\n", + " [29, 1231, 188, 97],\n", + " [13, 908, 5784, 5785, 132],\n", + " [996, 132],\n", + " [215, 73, 1587, 1441, 1320, 984, 583],\n", + " [608, 1],\n", + " [1018, 2113, 2644, 71],\n", + " [12, 18, 12, 491, 1],\n", + " [580],\n", + " [42, 291, 114],\n", + " [475, 38],\n", + " [111, 108],\n", + " [19, 199, 1119, 569, 5235],\n", + " [29, 1114],\n", + " [2561, 577, 831, 4651, 3263],\n", + " [207, 590],\n", + " [3360, 4908],\n", + " [44],\n", + " [19, 1138, 535, 28],\n", + " [12, 65, 18, 1],\n", + " [255, 8],\n", + " [936, 316],\n", + " [139, 84, 139],\n", + " [6, 215, 300, 17, 1912, 215, 222, 4, 94, 4, 94, 1657, 1964],\n", + " [117, 357],\n", + " [212],\n", + " [30, 3412, 1872, 194],\n", + " [3, 1, 82, 1, 121, 4, 1],\n", + " [46, 502, 3648, 5931],\n", + " [12, 91, 1, 178, 2484, 238],\n", + " [1, 28],\n", + " [199, 430, 1490, 1547],\n", + " [578, 160, 762, 61],\n", + " [914],\n", + " [245, 61, 45, 79, 100, 2618, 27],\n", + " [13, 1698, 49],\n", + " [2567, 8, 96, 69],\n", + " [55, 78],\n", + " [411, 199],\n", + " [5847, 53, 597],\n", + " [4, 1, 8, 6669],\n", + " [321, 1771, 1684],\n", + " [115, 50, 925],\n", + " [567, 775, 189],\n", + " [5, 234],\n", + " [46, 237, 786, 10, 16, 27],\n", + " [3347, 1666, 2145, 13, 1856, 3348],\n", + " [3, 1, 60, 51, 1],\n", + " [207, 1267],\n", + " [1236, 279, 1177],\n", + " [145, 45],\n", + " [2713, 84, 148, 1331, 688],\n", + " [41, 16, 309],\n", + " [36, 96, 147],\n", + " [2127, 56, 58],\n", + " [14, 1359, 313, 97],\n", + " [166],\n", + " [736, 178, 15],\n", + " [1260],\n", + " [1510, 2695, 360, 2489, 372, 3133],\n", + " [15, 196, 2],\n", + " [332, 438, 1049],\n", + " [175, 5, 1338, 1043, 218],\n", + " [849, 545, 1075],\n", + " [299, 2, 319],\n", + " [593, 1159],\n", + " [4, 15, 6525, 47],\n", + " [12, 35, 32],\n", + " [758, 12, 3063, 276],\n", + " [3588, 1498, 1884],\n", + " [3],\n", + " [5675, 1038],\n", + " [388, 248, 18, 26],\n", + " [74, 335],\n", + " [13],\n", + " [5674, 2600, 1183, 2],\n", + " [6, 26, 690],\n", + " [66, 26, 75, 527],\n", + " [2101, 69, 159],\n", + " [4341],\n", + " [1712, 6538, 438],\n", + " [144, 1926, 1984],\n", + " [454],\n", + " [7, 3],\n", + " [906, 816, 1330, 2],\n", + " [399, 12, 3],\n", + " [22, 91, 355],\n", + " [13, 459, 97],\n", + " [824, 1778, 104, 161, 824, 1478, 6503, 3135],\n", + " [466, 776],\n", + " [79],\n", + " [762, 727, 265, 148, 620, 3660, 61],\n", + " [387, 618, 28],\n", + " [6, 2, 23],\n", + " [364, 588, 6, 539],\n", + " [88, 551, 34, 113],\n", + " [13, 5, 767],\n", + " [686, 8, 34, 1775, 2950],\n", + " [25, 57, 54, 1572],\n", + " [46, 82, 413, 1],\n", + " [35, 2253, 4, 229, 46, 24],\n", + " [2792, 74, 1],\n", + " [187, 23],\n", + " [5, 1372, 49, 72, 5, 125, 3088, 125, 9],\n", + " [207, 171, 90],\n", + " [18, 200, 137, 1045],\n", + " [14, 17, 6, 1508, 66, 1691, 1118],\n", + " [11, 538],\n", + " [845, 56, 27],\n", + " [2052, 211],\n", + " [62, 50],\n", + " [1261, 20],\n", + " [67],\n", + " [520],\n", + " [81, 596, 647, 90, 1248, 647, 1816],\n", + " [159, 2],\n", + " [548, 201, 49, 709, 1611, 27, 595, 73, 7, 5437],\n", + " [6, 1, 26, 367, 28],\n", + " [871, 6, 1403, 242],\n", + " [30, 337, 122, 7, 2004],\n", + " [342, 621, 31, 1168, 1019, 872, 43, 72],\n", + " [1248, 1503, 473],\n", + " [230, 204, 76],\n", + " [1061, 1205],\n", + " [921, 2614, 1333, 27],\n", + " [31, 1],\n", + " [131, 118, 313, 76],\n", + " [1404, 1647],\n", + " [4227, 4228, 923, 275, 2],\n", + " [4, 1137, 103],\n", + " [111],\n", + " [1850, 68, 646, 270],\n", + " [189, 3, 6468, 133, 1, 7, 202],\n", + " [92, 893, 22, 363, 614, 35],\n", + " [13, 233, 11],\n", + " [456, 15, 47],\n", + " [1004, 496, 24, 101, 603],\n", + " [79, 109, 535],\n", + " [312],\n", + " [14],\n", + " [212, 2],\n", + " [606, 84, 100],\n", + " [3],\n", + " [4805, 36, 96, 125, 264, 4806, 2880, 555, 125],\n", + " [15, 1520, 213, 21, 8],\n", + " [679, 4612, 679, 4613],\n", + " [99, 554, 242, 109],\n", + " [6, 969, 410],\n", + " [319, 94, 423, 747, 463],\n", + " [6, 377],\n", + " [1193, 171, 829],\n", + " [544, 1579],\n", + " [93, 259, 16, 6049],\n", + " [71],\n", + " [83, 11],\n", + " [175, 1344, 9, 224, 1239, 852, 186, 3645, 7, 163],\n", + " [45, 1310, 376],\n", + " [20, 359, 58, 1530],\n", + " [20],\n", + " [4, 1],\n", + " [3104, 1110, 2059, 972, 4284, 4285],\n", + " [70, 165, 24, 132, 459, 2],\n", + " [1208, 546],\n", + " [4314, 1980, 42],\n", + " [4416, 69],\n", + " [18, 354],\n", + " [130, 114, 67],\n", + " [4789],\n", + " [760, 2454, 810, 3, 31, 27],\n", + " [75],\n", + " [2441, 23],\n", + " [288, 151, 1974, 475, 150],\n", + " [3, 60, 788, 681],\n", + " [5946, 2081, 17, 1703, 39],\n", + " [1580, 396],\n", + " [21, 163, 48, 164, 86, 258, 11, 113],\n", + " [74, 112, 347, 26, 82, 160, 26],\n", + " [758, 283, 1514],\n", + " [3, 60, 662],\n", + " [299, 97, 226, 1402, 476, 356],\n", + " [2124, 37, 2048, 657],\n", + " [1040, 203],\n", + " [18, 2548],\n", + " [115, 858],\n", + " [87, 1263, 1269, 55, 3686],\n", + " [4577, 4578, 296],\n", + " [297, 309, 174],\n", + " [1631, 5243, 503, 862, 11],\n", + " [5884],\n", + " [2036, 313],\n", + " [104, 1910, 25, 153],\n", + " [898, 75, 29],\n", + " [7, 1865, 736, 81, 189, 235, 518],\n", + " [3423, 547, 308],\n", + " [833, 113, 20],\n", + " [6, 154, 168],\n", + " [362, 1156, 504],\n", + " [5812, 188, 5813],\n", + " [294, 2794, 2833],\n", + " [2889, 108, 167],\n", + " [1057, 21, 5492],\n", + " [1108, 1289],\n", + " [49, 29, 1],\n", + " [257, 393, 180, 5, 9, 1741],\n", + " [239, 5],\n", + " [585, 9],\n", + " [371, 3768],\n", + " [2306, 489, 147],\n", + " [15, 10, 1486],\n", + " [602, 205, 68, 312, 1, 743, 440],\n", + " [65, 16, 34, 129],\n", + " [1004, 67, 306],\n", + " [5580, 75],\n", + " [132, 113],\n", + " [352, 775, 65, 1],\n", + " [2428, 276, 21, 80],\n", + " [17],\n", + " [619, 37, 619, 37, 153, 4931, 947, 153],\n", + " [162, 33, 43, 461],\n", + " [596, 120],\n", + " [138, 173, 107],\n", + " [137],\n", + " [1698, 908, 64, 1245],\n", + " [656],\n", + " [64, 23],\n", + " [19, 122, 7],\n", + " [274, 217, 67],\n", + " [1161, 64, 151, 113],\n", + " [259, 56, 1111],\n", + " [262, 5, 2859],\n", + " [187, 3076, 2553, 125],\n", + " [282, 1012, 1118],\n", + " [1148, 655, 78],\n", + " [29, 2386, 206],\n", + " [302],\n", + " [136, 2948],\n", + " [313, 34],\n", + " [342, 119, 1552, 6459, 6460],\n", + " [224, 89, 44, 106, 236],\n", + " [124, 16, 74, 200, 1],\n", + " [1683, 29],\n", + " [172, 2, 1820, 357],\n", + " [18, 73, 1],\n", + " [2210, 2],\n", + " [318, 1317, 2],\n", + " [21, 23],\n", + " [564, 14],\n", + " [107, 1213],\n", + " [757, 501],\n", + " [137, 167, 1047, 2133],\n", + " [456, 31, 93, 608, 10, 110, 6509],\n", + " [6, 254],\n", + " [12, 1051, 1581, 97],\n", + " [25, 16, 90, 177],\n", + " [1114, 69, 775, 1311, 113],\n", + " [176, 5, 869, 1562, 851, 5, 942, 324, 9],\n", + " [1408, 1290, 287, 117],\n", + " [294, 198, 7],\n", + " [66, 20],\n", + " [264, 1484, 900, 1668],\n", + " [1502, 6, 335],\n", + " [4, 15, 1842, 24],\n", + " [4976, 1080],\n", + " [4, 1, 112, 265, 179, 3681],\n", + " [2249, 3, 39],\n", + " [277],\n", + " [109],\n", + " [29, 462, 75],\n", + " [18, 537],\n", + " [24, 19],\n", + " [4047, 2013, 155, 1096],\n", + " [31, 10, 3699, 30, 1334],\n", + " [269, 99, 390, 364],\n", + " [766, 2766, 4, 1157, 6126, 56, 1157, 214],\n", + " [63, 1764, 75],\n", + " [324, 803],\n", + " [679, 4390],\n", + " [262, 250, 1117],\n", + " [6, 129],\n", + " [423, 1297, 866],\n", + " [73, 1305, 1759],\n", + " [94, 74],\n", + " [348, 5509],\n", + " [349, 64],\n", + " [234],\n", + " [297, 58, 45, 129],\n", + " [6, 164, 6, 1427, 3925, 40, 39],\n", + " [137, 1590],\n", + " [579, 417],\n", + " [2736, 726, 323, 192],\n", + " [36, 5, 9, 23],\n", + " [44, 244, 99],\n", + " [1533, 309, 457, 42, 6301, 1390],\n", + " [233, 627, 697],\n", + " [4, 15, 371, 238, 448, 21, 105, 27],\n", + " [611, 275, 316, 66, 1652],\n", + " [70, 899, 90, 736, 444],\n", + " [1024, 199, 1879, 5119, 78],\n", + " [17, 57, 4, 272],\n", + " [4000, 792],\n", + " [30],\n", + " [267, 268, 15],\n", + " [175, 221],\n", + " [3, 2234, 94, 1],\n", + " [187],\n", + " [73, 126, 21, 1601, 108, 1177],\n", + " [824, 1265, 104, 87, 377],\n", + " [526, 1155, 6648, 47],\n", + " [562, 125],\n", + " [208, 366, 1445, 75],\n", + " [6, 15, 10, 1],\n", + " [344, 1],\n", + " [159, 523],\n", + " [109, 365],\n", + " [481, 252, 116, 418, 245, 1211, 70, 600, 534],\n", + " [486, 518],\n", + " [2775, 68],\n", + " [2685, 38, 62],\n", + " [92, 6, 302, 212],\n", + " [485, 120, 25, 402, 694],\n", + " [763],\n", + " [34, 110, 1],\n", + " [2, 261],\n", + " [1997, 673, 86, 682],\n", + " [84],\n", + " [977, 2418],\n", + " [11],\n", + " [1443, 2058, 527],\n", + " [3624, 1383, 10, 135, 57],\n", + " [485, 120, 10, 93, 1, 41],\n", + " [83, 11, 273, 105, 27],\n", + " [15, 10, 23, 3529, 1450],\n", + " [1082, 21],\n", + " [383, 67, 2],\n", + " [264, 3384, 244, 1374],\n", + " [6, 17, 35, 368],\n", + " [1203, 468],\n", + " [140, 244],\n", + " [5, 313],\n", + " [61, 315, 1384],\n", + " [1071, 640, 1459, 7, 20, 195, 1532],\n", + " [550, 90],\n", + " [4, 2721],\n", + " [130, 102],\n", + " [86, 2374, 1887, 405, 14],\n", + " [4],\n", + " [4, 15, 10, 752, 58, 129],\n", + " [968, 1391, 21],\n", + " [12, 18],\n", + " [88, 1234],\n", + " [1131, 995, 4, 3625, 1872],\n", + " [380, 1015, 2],\n", + " [16, 915, 160, 46],\n", + " [4017],\n", + " [1146, 1487, 282, 1660],\n", + " [700, 3556, 62],\n", + " [4, 15, 10, 192, 741, 381, 206, 82, 1],\n", + " [5, 238, 900],\n", + " [1296, 1767],\n", + " [514, 1325, 270, 193],\n", + " [215, 320, 363],\n", + " [5656, 18, 29],\n", + " [154, 168, 960, 18],\n", + " [3, 162, 33, 60, 133, 468],\n", + " [262, 1790, 20, 1195, 213, 170, 339, 1302, 37, 5],\n", + " [137, 2268, 2985, 4044, 1586, 35, 4045],\n", + " [479, 807],\n", + " [14, 1199],\n", + " [3, 3590, 51],\n", + " [197, 714, 2900, 232, 1419],\n", + " [75, 1407],\n", + " [19, 348, 94],\n", + " [4552, 707, 4553, 4554, 1477, 2546, 1477, 35, 1477, 2403, 218, 99, 4555],\n", + " [1004, 67],\n", + " [37, 1119, 19],\n", + " [3, 33],\n", + " [75],\n", + " [544, 1221],\n", + " [13, 41],\n", + " [180, 9, 513],\n", + " [672, 781, 2301, 50, 1192],\n", + " [191, 191],\n", + " [20, 18, 1],\n", + " [5613, 733, 756, 50],\n", + " [495, 59],\n", + " [159, 597],\n", + " [303],\n", + " [4, 15, 3, 1, 61, 1620, 7],\n", + " [22, 6222, 725, 55, 98],\n", + " [65, 26, 104, 152],\n", + " [5798, 313],\n", + " [36, 5, 9, 297, 58, 195, 646, 885, 357],\n", + " [1395, 477, 466, 2421],\n", + " [4, 373],\n", + " [1008, 71, 1497, 314],\n", + " [160, 30, 10, 680, 270, 1984],\n", + " [42, 1, 446],\n", + " [104, 1927, 68, 6278, 415, 288, 474],\n", + " [155],\n", + " [6616],\n", + " [15, 8],\n", + " [572, 35, 886, 577, 2098],\n", + " [495, 59, 791, 982, 41, 249, 107],\n", + " [6, 15, 65, 453, 201],\n", + " [1438, 122, 166],\n", + " [1222, 684],\n", + " [42],\n", + " [13, 8],\n", + " [182, 266, 743, 4403, 4404, 94],\n", + " [3],\n", + " [18, 2691],\n", + " [6, 242, 108],\n", + " [162, 33, 43, 10, 296],\n", + " [546, 7],\n", + " [369, 19, 238, 41, 5258, 660, 1190, 11, 53],\n", + " [2306, 5],\n", + " [447],\n", + " [1],\n", + " [22, 624, 808, 32, 1233],\n", + " [1154, 11],\n", + " [2970, 2971],\n", + " [427, 59, 1],\n", + " [267, 268, 373, 10, 1, 505, 498, 487],\n", + " [2073, 67],\n", + " [6, 15, 4, 15],\n", + " [1921, 1063, 10, 98, 56],\n", + " [661, 14, 108],\n", + " [42, 230, 801, 1072],\n", + " [42, 31, 110, 1, 2],\n", + " [64, 736, 50],\n", + " [304, 282, 349],\n", + " [1730, 3998, 1047, 129],\n", + " [6, 32],\n", + " [176, 269],\n", + " [119, 804, 1219],\n", + " [1237, 188, 97],\n", + " [64, 238, 2687],\n", + " [1575, 588, 559],\n", + " [208, 560, 86, 2462, 19, 27],\n", + " [3],\n", + " [204, 96, 1160],\n", + " [93, 95, 203],\n", + " [188, 71, 228],\n", + " [2157, 2716, 2161],\n", + " [3494, 2570],\n", + " [504, 503, 5503, 989],\n", + " [379, 251, 235, 518, 2645],\n", + " [4194],\n", + " [30, 337],\n", + " [280],\n", + " [187],\n", + " [4941, 230, 431, 124, 4942, 4943],\n", + " [884, 56, 2556, 647, 2462, 330],\n", + " [36, 41, 47],\n", + " [887, 2602, 9],\n", + " [392, 3882, 2880, 3883, 640],\n", + " [831, 196, 2],\n", + " [3012, 717, 101],\n", + " [1072, 26, 2552, 359, 52],\n", + " [155, 585],\n", + " [3569, 8, 90, 1046],\n", + " [2483, 847, 1139, 78],\n", + " [17],\n", + " [485, 120, 25, 402, 694],\n", + " [112, 3166],\n", + " [1422],\n", + " [813, 163],\n", + " [36, 2275, 149],\n", + " [1293, 5941, 5942, 2747, 198, 1020, 1975],\n", + " [6, 17],\n", + " [512, 20, 636],\n", + " [52, 228, 170, 2324],\n", + " [4914, 1478, 4915],\n", + " [2881, 2312, 158],\n", + " [12, 363, 230],\n", + " [692, 1151],\n", + " [773, 33, 114, 103],\n", + " [663, 146, 109, 45, 79, 2114],\n", + " [2621],\n", + " [12, 16],\n", + " [70, 165, 593],\n", + " [2700],\n", + " [56],\n", + " [37, 2459, 3112, 509, 494, 149, 5, 534, 105],\n", + " [1753, 4792, 4793, 3309],\n", + " [3, 60, 43, 90, 50],\n", + " [65, 210],\n", + " [1202, 209, 3206, 4489, 1],\n", + " [1362, 556, 57, 128],\n", + " [22, 1409, 120, 25],\n", + " [18, 73, 190, 1547, 2],\n", + " [2313, 425, 7, 3151],\n", + " [4, 28],\n", + " [1492, 204],\n", + " [156, 21],\n", + " [307],\n", + " [247, 1711, 43, 71, 10, 527],\n", + " [207, 590, 1922, 956, 23],\n", + " [700, 140],\n", + " [49],\n", + " [516, 39, 19],\n", + " [13, 96, 240],\n", + " [136, 1281, 474],\n", + " [1560, 214],\n", + " [134, 1266, 51, 1038],\n", + " [251, 571, 63, 1],\n", + " [14, 442, 53],\n", + " [44],\n", + " [176, 1553],\n", + " [1857, 3138, 1789],\n", + " [4, 3, 1, 472, 9, 591, 27],\n", + " [302, 10],\n", + " [4020, 155, 89],\n", + " [1327, 2, 260],\n", + " [214, 7],\n", + " [3207, 46, 293, 77, 77, 265, 1031, 239, 51, 4],\n", + " [484, 189, 95, 1145, 2],\n", + " [20, 41, 249],\n", + " [132, 75, 459, 48, 1117],\n", + " [180, 5, 1971, 4237, 9],\n", + " [242],\n", + " [778, 474],\n", + " [97, 636, 5, 125, 5, 767],\n", + " [3584, 814],\n", + " [215, 2483, 32, 220, 969, 222],\n", + " [96, 69, 297, 58],\n", + " [4631, 620],\n", + " [15, 10, 991, 474, 415, 105],\n", + " [1324, 1022, 2118, 7],\n", + " [6555, 310, 441, 182],\n", + " [303],\n", + " [313, 1825],\n", + " [112, 2115],\n", + " [20],\n", + " [386],\n", + " [36, 393, 871, 5],\n", + " [154, 168],\n", + " [544, 127],\n", + " [418, 5, 263, 93, 4796, 9],\n", + " [2767, 956, 161, 256, 2440, 6123, 46, 265],\n", + " [75],\n", + " [4, 15, 72, 7, 1, 505, 7, 587, 1],\n", + " [6, 15],\n", + " [155, 67, 184, 1099, 184, 496, 24, 155, 4778],\n", + " [140, 161],\n", + " [60, 392, 193],\n", + " [1792, 110, 27],\n", + " [916, 917, 51, 16, 58],\n", + " [603],\n", + " [916, 917],\n", + " [57, 3, 39],\n", + " [608, 152, 750],\n", + " [3735, 10, 23],\n", + " [984, 2896, 6, 108, 365],\n", + " [1123, 284],\n", + " [227, 947],\n", + " [20, 1351, 148, 620],\n", + " [3832, 3833, 327, 9, 2288, 1101, 1942],\n", + " [81, 421],\n", + " [7, 358, 669, 975, 744, 3844],\n", + " [10],\n", + " [131, 118, 345, 59, 1400],\n", + " [30, 414, 1],\n", + " [19, 18, 97],\n", + " [38, 4988, 62],\n", + " [148, 761],\n", + " [1424, 1558, 3920, 62],\n", + " [4, 15, 293, 231, 1491, 1098, 922, 7],\n", + " [190, 203],\n", + " [3, 1],\n", + " [22, 6023, 2605, 1246, 804, 537, 1812],\n", + " [81, 95, 3427, 2192],\n", + " [207, 77, 10, 6, 488, 76, 215, 359, 58],\n", + " [435, 3733, 30, 114],\n", + " [22, 82, 616, 1, 16, 6445, 128],\n", + " [87, 907, 68, 87, 33],\n", + " [13, 597],\n", + " [56, 28],\n", + " [144, 6, 15, 72],\n", + " [333, 6, 2, 1041, 40],\n", + " [49, 193, 5558],\n", + " [183, 359, 52],\n", + " [512, 19, 62],\n", + " [232, 3181, 2319],\n", + " [1010, 106, 382, 801],\n", + " [17, 1, 7, 8, 7],\n", + " [12, 1716, 5908, 363],\n", + " [54, 1929],\n", + " [1545, 1800, 1603, 1737],\n", + " [42, 31, 25, 10, 98, 135],\n", + " [3576, 1084],\n", + " [17, 361, 43],\n", + " [42, 561],\n", + " [12, 888, 199],\n", + " [333, 6, 198, 27, 214],\n", + " [191, 53],\n", + " [99],\n", + " [333, 6, 387],\n", + " [390, 110, 2412, 1032],\n", + " [4546, 2473, 2284],\n", + " [91, 347],\n", + " [965, 403, 355],\n", + " [603, 7, 6, 4506],\n", + " [19, 929],\n", + " [518, 88, 34, 253],\n", + " [594, 24],\n", + " [54, 948, 1],\n", + " [615, 591, 8, 28],\n", + " [823, 438, 8],\n", + " [1564, 127, 1317, 2],\n", + " [4867, 1126, 125, 5, 562],\n", + " [145, 164, 11, 11, 191],\n", + " [30, 60, 135],\n", + " [427, 839, 6, 17, 1],\n", + " [44, 8, 89],\n", + " [88, 18, 1],\n", + " [4102, 3014, 629, 80, 4103, 3015],\n", + " [245, 1824, 937, 147],\n", + " [3082, 1459, 4532],\n", + " [1227],\n", + " [4115],\n", + " [252, 421, 72],\n", + " [214, 87, 907, 68, 449],\n", + " [18, 227, 196, 5272],\n", + " [4321, 1328, 2462, 4322],\n", + " [951, 1461, 163, 208, 149],\n", + " [2, 64],\n", + " [408, 132, 227],\n", + " [157, 183, 179],\n", + " [724, 556, 112, 40, 4, 1],\n", + " [61, 66],\n", + " [453, 7, 235],\n", + " [271],\n", + " [64, 264],\n", + " [197, 1612, 21, 2505, 1751],\n", + " [516, 3572, 2690, 464, 1452],\n", + " [1, 23],\n", + " [1366, 622, 844, 48, 499, 1228],\n", + " [19, 50],\n", + " [175],\n", + " [49, 5],\n", + " [1011, 47],\n", + " [452, 67],\n", + " [484, 3706, 21],\n", + " [1214],\n", + " [17, 1],\n", + " [82, 1528, 100, 2254, 122],\n", + " [362, 105, 307],\n", + " [84, 430, 165, 24],\n", + " [1625, 1],\n", + " [887, 2602, 1274],\n", + " [1253],\n", + " [207, 25, 1, 23],\n", + " [622],\n", + " [664, 24, 8, 28, 105],\n", + " [21, 114, 543, 27],\n", + " [22, 91, 179],\n", + " [966, 76, 301],\n", + " [17, 65, 1],\n", + " [2621],\n", + " [207, 15, 1, 147, 28],\n", + " [262, 250, 510],\n", + " [169, 681, 163, 31, 39],\n", + " [99],\n", + " [20, 156],\n", + " [269, 1403, 79, 18],\n", + " [140, 271, 1037, 24, 240, 185, 68, 105],\n", + " [1355],\n", + " [934, 372, 76, 2670, 450],\n", + " [54, 1526, 561],\n", + " [7, 938, 846],\n", + " [5, 304, 35, 63, 265],\n", + " [3, 1],\n", + " [302, 230],\n", + " [15, 6609, 24],\n", + " [35, 76, 146],\n", + " [1354, 90],\n", + " [283, 13],\n", + " [1227],\n", + " [386, 72, 324, 125, 1536, 2872],\n", + " [2033, 136, 5],\n", + " [115, 768],\n", + " [512, 632, 5, 791, 982],\n", + " [29],\n", + " [3, 10],\n", + " [294, 791, 982, 27, 7, 28],\n", + " [3, 209, 33, 43, 221],\n", + " [5549, 5550, 1126],\n", + " [299, 38, 24, 70, 165, 24, 38, 24],\n", + " [11, 121],\n", + " [2481, 50],\n", + " [30, 4561],\n", + " [160, 3, 1],\n", + " [118, 5, 1757, 1985, 23],\n", + " [1110, 259, 66],\n", + " [57, 124, 30, 1, 690],\n", + " [1935, 2521, 3251, 1477],\n", + " [37, 1],\n", + " [266, 99, 2593, 1396, 2645],\n", + " [81, 2043, 75, 665],\n", + " [116, 136, 4275, 9, 715, 106],\n", + " [261, 203, 143, 109, 3908, 2],\n", + " [3, 148, 10, 527],\n", + " [12, 74],\n", + " [29, 29, 94, 5232],\n", + " [406],\n", + " [180, 5, 9, 125, 257, 5],\n", + " [45, 66],\n", + " [1687, 266, 41, 243, 97, 94],\n", + " [6, 154, 168, 76],\n", + " [368, 675, 2175, 219, 52],\n", + " [1763, 779, 3967, 57, 9],\n", + " [34],\n", + " [1954, 154, 2305, 3864, 2305, 840, 24],\n", + " [138, 352],\n", + " [322, 19, 62, 1012],\n", + " [728, 101, 41],\n", + " [166, 23],\n", + " [1953, 1403, 99],\n", + " [4386, 4387, 57, 4388],\n", + " [29, 18, 1],\n", + " [190, 35, 110, 1],\n", + " [379, 22, 14, 1067, 3719],\n", + " [3, 6357, 725, 10, 2233, 98],\n", + " [322, 19, 68, 64, 94],\n", + " [6, 154, 168, 76, 129],\n", + " [673, 2318, 4],\n", + " [700, 2, 140, 310, 139, 285],\n", + " [184, 261, 1427],\n", + " [166],\n", + " [30, 5995],\n", + " [582, 4],\n", + " [4317, 2350, 2344, 1462, 2461, 158],\n", + " [578, 350, 3254, 92, 1673],\n", + " [670],\n", + " [64, 122],\n", + " [30, 2, 90, 1046],\n", + " [898, 3433, 123, 2637, 1452, 536],\n", + " [92, 735],\n", + " [1023, 2],\n", + " [663, 146],\n", + " [3282, 176],\n", + " [4139, 21, 171, 829],\n", + " [1216, 831],\n", + " [331, 611],\n", + " [1044, 1],\n", + " [247, 151, 43, 65, 58, 2],\n", + " [390, 296],\n", + " [344, 465],\n", + " [74, 1, 135],\n", + " [385, 115, 768, 219, 201, 75, 53, 45, 79, 13],\n", + " [1022, 1252, 622, 19, 1081, 62],\n", + " [132],\n", + " [4, 108],\n", + " [30, 52, 642, 30, 1],\n", + " [112, 1, 16, 58, 471],\n", + " [596, 814, 358, 491, 455],\n", + " [570, 172],\n", + " [959, 1034],\n", + " [1292],\n", + " [16, 1],\n", + " [359],\n", + " [1078, 40, 39],\n", + " [521, 78],\n", + " [60, 2363, 24, 3, 33],\n", + " [6, 1328],\n", + " [475, 85, 127],\n", + " [4, 15, 196, 399, 229, 163],\n", + " [3, 3663, 1053, 5, 93, 598, 618, 890],\n", + " [724, 4, 70, 865],\n", + " [255, 9],\n", + " [1966, 2320, 62],\n", + " [3342, 3343, 575, 4863, 1647, 463, 27],\n", + " [208, 29, 92, 2054],\n", + " [3888, 3889, 327, 9],\n", + " [134, 2299, 101, 197, 2300, 3851, 1733],\n", + " [56, 1406],\n", + " [255],\n", + " [46, 1388, 101, 964, 913, 231, 6531],\n", + " [1022, 3641, 3642, 1920, 857],\n", + " [246, 308, 266],\n", + " [65, 592, 93, 308, 7, 122],\n", + " [255, 1499],\n", + " [74, 1],\n", + " [828, 696, 872, 43, 442, 10],\n", + " [855, 855, 805],\n", + " [255, 96, 101, 253],\n", + " [13],\n", + " [17, 247, 151, 43, 10],\n", + " [29, 34, 100],\n", + " [15, 10, 221],\n", + " [2390, 830],\n", + " [46, 476, 24, 6596, 6597, 1220],\n", + " [14, 893, 260],\n", + " [2254, 6, 15, 122],\n", + " [209, 558],\n", + " [115, 115],\n", + " [1123],\n", + " [567, 21, 171],\n", + " [66, 254, 20],\n", + " [2131],\n", + " [3, 1088],\n", + " [436, 6, 222, 6],\n", + " [84, 19],\n", + " [252, 1465, 4794, 411, 985, 108, 21],\n", + " [9, 36, 96, 259, 253],\n", + " [180, 5, 4443, 135],\n", + " [454, 45, 416],\n", + " [83, 5412, 3141, 197, 1610],\n", + " [19, 92],\n", + " [514, 602, 205, 68, 122],\n", + " [331, 3008],\n", + " [1347, 470, 1347, 2533, 82],\n", + " [819, 96],\n", + " [3, 377],\n", + " [351, 1009, 174, 38, 1897, 1503],\n", + " [111],\n", + " [408, 162, 33, 32, 43, 323, 853, 1383, 1056, 1052],\n", + " [958, 563],\n", + " [11],\n", + " [210, 53],\n", + " [162, 33, 1053, 55, 91, 52, 1322],\n", + " [136, 1345, 2348, 136, 5, 5],\n", + " [22, 56, 412],\n", + " [6650],\n", + " [215, 16, 6461, 74, 346, 2255, 1902, 124, 97, 6462, 925],\n", + " [13, 1160, 219, 115, 201],\n", + " [108, 51, 1334, 378, 391],\n", + " [452, 2039, 124, 4801, 5, 218],\n", + " [262, 57, 549, 3807],\n", + " [54, 128],\n", + " [44, 308],\n", + " [233, 2187],\n", + " [36, 5, 9, 785, 45, 460],\n", + " [329, 400],\n", + " [93, 962, 2717, 66],\n", + " [871, 1403, 390, 21, 643, 27],\n", + " [3265, 114, 67],\n", + " [222, 181],\n", + " [295, 4986, 653, 39],\n", + " [199, 368, 464, 234],\n", + " [85, 374, 21],\n", + " [4],\n", + " [20, 6],\n", + " [138, 173, 8, 22, 35, 26, 48],\n", + " [199, 71, 301, 5723, 3376, 78],\n", + " [1070, 782],\n", + " [60, 51, 752, 1, 240],\n", + " [19, 1108, 1289, 376],\n", + " [38, 24, 1068],\n", + " [13, 123],\n", + " [4, 198, 8],\n", + " [869, 1718, 106, 105],\n", + " [148, 173, 1181, 70, 600, 47],\n", + " [230],\n", + " [2577],\n", + " [85, 127],\n", + " [19, 20],\n", + " [2],\n", + " [55, 190, 110],\n", + " [25, 98, 8],\n", + " [4, 15, 10, 192, 385, 628, 163],\n", + " [2250, 25, 10],\n", + " [132, 5, 69],\n", + " [566, 21],\n", + " [22, 3, 1652],\n", + " [1776, 103],\n", + " [22, 16, 1087, 32, 336, 430, 6190, 6191, 282],\n", + " [19, 670, 865],\n", + " [3],\n", + " [295, 4586, 315, 114],\n", + " [27, 7, 151],\n", + " [13, 2701, 90, 3536, 23],\n", + " [324, 1417, 9, 4749, 425],\n", + " [702, 1491, 117, 497, 286],\n", + " [45, 79, 812, 201, 27],\n", + " [4, 825, 8, 1, 41],\n", + " [11, 150, 290],\n", + " [294, 10, 310, 8, 28],\n", + " [369, 210, 129, 301],\n", + " [3319, 46, 31, 956, 96, 9, 47],\n", + " [92, 2],\n", + " [17],\n", + " [86, 7, 4, 825],\n", + " [30, 3637, 192, 752, 765],\n", + " [681, 1342, 453, 7, 1098, 922, 7, 27],\n", + " [182],\n", + " [10, 445, 1],\n", + " [29, 522],\n", + " [2001, 53],\n", + " [11, 574, 29],\n", + " [73, 1189, 1199, 1132],\n", + " [417, 97, 3285, 9],\n", + " [1364, 1017],\n", + " [2034, 111, 3226, 111, 3227],\n", + " [42, 331, 124, 76, 805],\n", + " [106, 2079, 838, 34, 451, 517],\n", + " [14, 248, 976, 1818, 440, 2493],\n", + " [11, 1094, 34, 1095, 919],\n", + " [30, 40, 1198, 135, 1524, 216, 10],\n", + " [41, 280],\n", + " [4, 15, 293],\n", + " [29, 843, 181, 455, 1564, 27],\n", + " [169],\n", + " [371, 471, 890, 231, 2, 830],\n", + " [138, 173, 642, 443],\n", + " [137, 1111, 746],\n", + " [12, 3675, 1],\n", + " [3, 338, 137, 1111, 797],\n", + " [63, 1],\n", + " [12, 624, 179, 48],\n", + " [19, 622, 44, 37, 36, 393, 871, 5],\n", + " [350, 1, 301],\n", + " [289, 26, 3532, 2491, 2],\n", + " [1669, 1669],\n", + " [176, 5],\n", + " [1873, 3417, 1055],\n", + " [12, 3, 1],\n", + " [12, 17],\n", + " [13],\n", + " [1201, 251, 1040, 1978, 174, 2904],\n", + " [1085, 48],\n", + " [648],\n", + " [63, 346, 978, 75],\n", + " [30, 33, 408, 1, 1984, 474],\n", + " [54, 719, 361, 37, 1506, 2718, 181],\n", + " [71, 767],\n", + " [264, 541, 2564, 1382, 122],\n", + " [367, 605, 3355, 199, 2592],\n", + " [669, 1053, 116],\n", + " [36, 5, 9, 14],\n", + " [120, 726],\n", + " [19, 1160],\n", + " [1955, 1550, 3867, 2870],\n", + " [1123],\n", + " [396, 5, 69],\n", + " [15, 23],\n", + " [1382, 1188, 685],\n", + " [4, 15, 1],\n", + " [486],\n", + " [109, 616, 871, 150, 149],\n", + " [661, 204, 479],\n", + " [557, 291, 40, 1236, 1],\n", + " [155, 9],\n", + " [1488, 24, 8],\n", + " [264, 47],\n", + " [229, 2511, 628],\n", + " [405, 1119],\n", + " [73, 126, 850],\n", + " [40, 39, 1, 103],\n", + " [2696, 2095],\n", + " [484, 48, 364],\n", + " [324, 69, 313, 250, 5],\n", + " [1552, 1612, 69],\n", + " ...]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 7 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "scrolled": true, + "id": "rPl6D8_xZp46", + "outputId": "e655df7d-0887-4cad-98af-27c4a657309d", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + } + }, + "source": [ + "sequence_length = 10\n", + "trunc_type = 'post'\n", + "padding_type = 'post'\n", + "padded_x_train = tf.keras.preprocessing.sequence.pad_sequences(x_train, truncating=trunc_type, padding=padding_type, maxlen=sequence_length)\n", + "padded_x_train.shape" + ], + "execution_count": 8, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "(16336, 10)" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 8 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "Q9lxcUfOZp49", + "outputId": "1d33432d-38e5-4b7c-a83b-6247d8c77a2b", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 136 + } + }, + "source": [ + "x_test = t.texts_to_sequences(x_test_)\n", + "padded_x_test = tf.keras.preprocessing.sequence.pad_sequences(x_test, truncating=trunc_type, padding=padding_type, maxlen=sequence_length)\n", + "padded_x_test" + ], + "execution_count": 9, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "array([[ 275, 4955, 0, ..., 0, 0, 0],\n", + " [ 30, 361, 10, ..., 0, 0, 0],\n", + " [ 160, 524, 32, ..., 0, 0, 0],\n", + " ...,\n", + " [ 16, 0, 0, ..., 0, 0, 0],\n", + " [1796, 3, 0, ..., 0, 0, 0],\n", + " [ 28, 0, 0, ..., 0, 0, 0]], dtype=int32)" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 9 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "oxfEGMCwrRLO" + }, + "source": [ + "from sklearn.utils import class_weight\n", + "weight = class_weight.compute_class_weight('balanced', np.unique(y_train), y_train)\n", + "weight = {i : weight[i] for i in range(26)}" + ], + "execution_count": 10, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "9co_FKiXtpp7", + "outputId": "8f18ba24-a415-4293-e302-84888c2f96be", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 51 + } + }, + "source": [ + "np.unique(y_train)" + ], + "execution_count": 11, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "array([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,\n", + " 17, 18, 19, 20, 21, 22, 23, 24, 25])" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 11 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "zM16G4uIZp5A", + "outputId": "46655384-3b79-4e94-f6d7-6843fc8bcea0", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + } + }, + "source": [ + "y_train = keras.utils.to_categorical(y_train)\n", + "y_test = keras.utils.to_categorical(y_test)\n", + "y_train.shape" + ], + "execution_count": 12, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "(16336, 26)" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 12 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "YOZ86XKjPYcn" + }, + "source": [ + "class BahdanauAttention(tf.keras.Model):\n", + " def __init__(self, units):\n", + " super(BahdanauAttention, self).__init__()\n", + " self.W1 = Dense(units)\n", + " self.W2 = Dense(units)\n", + " self.V = Dense(1)\n", + "\n", + " def call(self, values, query): # 단, key와 value는 같음\n", + " # query shape == (batch_size, hidden size)\n", + " # hidden_with_time_axis shape == (batch_size, 1, hidden size)\n", + " # score 계산을 위해 뒤에서 할 덧셈을 위해서 차원을 변경해줍니다.\n", + " hidden_with_time_axis = tf.expand_dims(query, 1)\n", + "\n", + " # score shape == (batch_size, max_length, 1)\n", + " # we get 1 at the last axis because we are applying score to self.V\n", + " # the shape of the tensor before applying self.V is (batch_size, max_length, units)\n", + " score = self.V(tf.nn.tanh(\n", + " self.W1(values) + self.W2(hidden_with_time_axis)))\n", + "\n", + " # attention_weights shape == (batch_size, max_length, 1)\n", + " attention_weights = tf.nn.softmax(score, axis=1)\n", + "\n", + " # context_vector shape after sum == (batch_size, hidden_size)\n", + " context_vector = attention_weights * values\n", + " context_vector = tf.reduce_sum(context_vector, axis=1)\n", + "\n", + " return context_vector, attention_weights" + ], + "execution_count": 13, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "scrolled": true, + "id": "9cpjxmyOZp5C", + "outputId": "02e79a8b-2428-44f9-9bff-62759cabb4eb", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 561 + } + }, + "source": [ + "from tensorflow.keras.layers import Input, Embedding, LSTM, Dense, Bidirectional, Dropout, Concatenate\n", + "\n", + "embedding_dim = 1024\n", + "\n", + "## LSTM model\n", + "# model = keras.models.Sequential([\n", + "# Embedding(vocab_size, embedding_dim),\n", + "# #Bidirectional(LSTM(1024, return_sequences=True)),\n", + "# Bidirectional(LSTM(512)),\n", + "# #Dense(256, activation='relu'),\n", + "# #Dropout(0.5),\n", + "# Dense(256, activation='relu'),\n", + "# Dropout(0.25),\n", + "# Dense(64, activation='relu'),\n", + "# Dropout(0.25),\n", + "# Dense(26, activation='softmax')\n", + "# ])\n", + "\n", + "\n", + "# LSTM + Attention model\n", + "input = Input(shape=(sequence_length,))\n", + "embed = Embedding(vocab_size, embedding_dim, input_length=sequence_length, )(input)\n", + "lstm = Bidirectional(LSTM(512, dropout=0.25, return_sequences = True))(embed)\n", + "lstm, forward_h, forward_c, backward_h, backward_c = Bidirectional \\\n", + " (LSTM(512, dropout=0.25, return_sequences=True, return_state=True))(lstm)\n", + "state_h = Concatenate()([forward_h, backward_h]) # 은닉 상태\n", + "state_c = Concatenate()([forward_c, backward_c]) # 셀 상태\n", + "\n", + "## add attention layers\n", + "attention = BahdanauAttention(256) # 가중치 크기 정의\n", + "context_vector, attention_weights = attention(lstm, state_h)\n", + "\n", + "x = Dense(256, activation='relu')(context_vector)\n", + "x = Dropout(0.25)(x)\n", + "x = Dense(64, activation='relu')(x)\n", + "x = Dropout(0.25)(x)\n", + "output = Dense(26, activation='softmax')(x)\n", + "\n", + "model = tf.keras.Model(input, output)\n", + "\n", + "\n", + "import datetime\n", + "dt = datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n", + "log_dir = \"logs/my_board/\" + dt\n", + "tc = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)\n", + "es = keras.callbacks.EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=4)\n", + "mc = keras.callbacks.ModelCheckpoint('/content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_' + dt + '.h5', monitor='val_accuracy', mode='max', verbose=1, save_best_only=True)\n", + "\n", + "model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n", + "model.summary()" + ], + "execution_count": 14, + "outputs": [ + { + "output_type": "stream", + "text": [ + "Model: \"functional_1\"\n", + "__________________________________________________________________________________________________\n", + "Layer (type) Output Shape Param # Connected to \n", + "==================================================================================================\n", + "input_1 (InputLayer) [(None, 10)] 0 \n", + "__________________________________________________________________________________________________\n", + "embedding (Embedding) (None, 10, 1024) 8192000 input_1[0][0] \n", + "__________________________________________________________________________________________________\n", + "bidirectional (Bidirectional) (None, 10, 1024) 6295552 embedding[0][0] \n", + "__________________________________________________________________________________________________\n", + "bidirectional_1 (Bidirectional) [(None, 10, 1024), ( 6295552 bidirectional[0][0] \n", + "__________________________________________________________________________________________________\n", + "concatenate (Concatenate) (None, 1024) 0 bidirectional_1[0][1] \n", + " bidirectional_1[0][3] \n", + "__________________________________________________________________________________________________\n", + "bahdanau_attention (BahdanauAtt ((None, 1024), (None 525057 bidirectional_1[0][0] \n", + " concatenate[0][0] \n", + "__________________________________________________________________________________________________\n", + "dense_3 (Dense) (None, 256) 262400 bahdanau_attention[0][0] \n", + "__________________________________________________________________________________________________\n", + "dropout (Dropout) (None, 256) 0 dense_3[0][0] \n", + "__________________________________________________________________________________________________\n", + "dense_4 (Dense) (None, 64) 16448 dropout[0][0] \n", + "__________________________________________________________________________________________________\n", + "dropout_1 (Dropout) (None, 64) 0 dense_4[0][0] \n", + "__________________________________________________________________________________________________\n", + "dense_5 (Dense) (None, 26) 1690 dropout_1[0][0] \n", + "==================================================================================================\n", + "Total params: 21,588,699\n", + "Trainable params: 21,588,699\n", + "Non-trainable params: 0\n", + "__________________________________________________________________________________________________\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "scrolled": true, + "id": "1tyjL9G7Zp5G", + "outputId": "a82deff5-4951-484d-b018-095300ffe870", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + } + }, + "source": [ + "history = model.fit(padded_x_train, y_train,\n", + " batch_size=128, epochs=30, \n", + " callbacks=[mc, tc],\n", + " #class_weight=weight,\n", + " validation_data=(padded_x_test, y_test))" + ], + "execution_count": 15, + "outputs": [ + { + "output_type": "stream", + "text": [ + "WARNING:tensorflow:Model failed to serialize as JSON. Ignoring... \n", + "Epoch 1/30\n", + " 1/128 [..............................] - ETA: 0s - loss: 3.2607 - accuracy: 0.0156WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/summary_ops_v2.py:1277: stop (from tensorflow.python.eager.profiler) is deprecated and will be removed after 2020-07-01.\n", + "Instructions for updating:\n", + "use `tf.profiler.experimental.stop` instead.\n", + "128/128 [==============================] - ETA: 0s - loss: 2.2671 - accuracy: 0.3590\n", + "Epoch 00001: val_accuracy improved from -inf to 0.52057, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 18s 144ms/step - loss: 2.2671 - accuracy: 0.3590 - val_loss: 1.6580 - val_accuracy: 0.5206\n", + "Epoch 2/30\n", + "128/128 [==============================] - ETA: 0s - loss: 1.4655 - accuracy: 0.5774\n", + "Epoch 00002: val_accuracy improved from 0.52057 to 0.63418, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 17s 131ms/step - loss: 1.4655 - accuracy: 0.5774 - val_loss: 1.3064 - val_accuracy: 0.6342\n", + "Epoch 3/30\n", + "128/128 [==============================] - ETA: 0s - loss: 1.0930 - accuracy: 0.6996\n", + "Epoch 00003: val_accuracy improved from 0.63418 to 0.68487, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 17s 131ms/step - loss: 1.0930 - accuracy: 0.6996 - val_loss: 1.1670 - val_accuracy: 0.6849\n", + "Epoch 4/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.8743 - accuracy: 0.7634\n", + "Epoch 00004: val_accuracy improved from 0.68487 to 0.70299, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 17s 131ms/step - loss: 0.8743 - accuracy: 0.7634 - val_loss: 1.1791 - val_accuracy: 0.7030\n", + "Epoch 5/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.7169 - accuracy: 0.8099\n", + "Epoch 00005: val_accuracy improved from 0.70299 to 0.71131, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 17s 131ms/step - loss: 0.7169 - accuracy: 0.8099 - val_loss: 1.1834 - val_accuracy: 0.7113\n", + "Epoch 6/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.6044 - accuracy: 0.8359\n", + "Epoch 00006: val_accuracy improved from 0.71131 to 0.71303, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 17s 132ms/step - loss: 0.6044 - accuracy: 0.8359 - val_loss: 1.1891 - val_accuracy: 0.7130\n", + "Epoch 7/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.5311 - accuracy: 0.8554\n", + "Epoch 00007: val_accuracy improved from 0.71303 to 0.71719, saving model to /content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201020-045024.h5\n", + "128/128 [==============================] - 17s 132ms/step - loss: 0.5311 - accuracy: 0.8554 - val_loss: 1.2312 - val_accuracy: 0.7172\n", + "Epoch 8/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.4742 - accuracy: 0.8677\n", + "Epoch 00008: val_accuracy did not improve from 0.71719\n", + "128/128 [==============================] - 17s 132ms/step - loss: 0.4742 - accuracy: 0.8677 - val_loss: 1.2736 - val_accuracy: 0.7079\n", + "Epoch 9/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.4197 - accuracy: 0.8826\n", + "Epoch 00009: val_accuracy did not improve from 0.71719\n", + "128/128 [==============================] - 17s 131ms/step - loss: 0.4197 - accuracy: 0.8826 - val_loss: 1.4095 - val_accuracy: 0.7076\n", + "Epoch 10/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.3816 - accuracy: 0.8924\n", + "Epoch 00010: val_accuracy did not improve from 0.71719\n", + "128/128 [==============================] - 17s 131ms/step - loss: 0.3816 - accuracy: 0.8924 - val_loss: 1.4741 - val_accuracy: 0.7111\n", + "Epoch 11/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.3451 - accuracy: 0.8983\n", + "Epoch 00011: val_accuracy did not improve from 0.71719\n", + "128/128 [==============================] - 17s 132ms/step - loss: 0.3451 - accuracy: 0.8983 - val_loss: 1.6000 - val_accuracy: 0.7059\n", + "Epoch 12/30\n", + "128/128 [==============================] - ETA: 0s - loss: 0.3264 - accuracy: 0.9046\n", + "Epoch 00012: val_accuracy did not improve from 0.71719\n", + "128/128 [==============================] - 17s 132ms/step - loss: 0.3264 - accuracy: 0.9046 - val_loss: 1.5829 - val_accuracy: 0.7123\n", + "Epoch 13/30\n", + " 91/128 [====================>.........] - ETA: 4s - loss: 0.2891 - accuracy: 0.9155" + ], + "name": "stdout" + }, + { + "output_type": "error", + "ename": "KeyboardInterrupt", + "evalue": "ignored", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtc\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m#class_weight=weight,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m validation_data=(padded_x_test, y_test))\n\u001b[0m", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36m_method_wrapper\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 106\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_method_wrapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 107\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_in_multi_worker_mode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 108\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 109\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 110\u001b[0m \u001b[0;31m# Running inside `run_distribute_coordinator` already.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m 1096\u001b[0m batch_size=batch_size):\n\u001b[1;32m 1097\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1098\u001b[0;31m \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1099\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1100\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 778\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 779\u001b[0m \u001b[0mcompiler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"nonXla\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 780\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 781\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 782\u001b[0m \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 805\u001b[0m \u001b[0;31m# In this case we have created variables on the first call, so we run the\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 806\u001b[0m \u001b[0;31m# defunned version which is guaranteed to never create variables.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 807\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateless_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# pylint: disable=not-callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 808\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateful_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 809\u001b[0m \u001b[0;31m# Release the lock early so that multiple threads can perform the call\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 2827\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_lock\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2828\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_define_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2829\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_filtered_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2830\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2831\u001b[0m \u001b[0;34m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_filtered_call\u001b[0;34m(self, args, kwargs, cancellation_manager)\u001b[0m\n\u001b[1;32m 1846\u001b[0m resource_variable_ops.BaseResourceVariable))],\n\u001b[1;32m 1847\u001b[0m \u001b[0mcaptured_inputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcaptured_inputs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1848\u001b[0;31m cancellation_manager=cancellation_manager)\n\u001b[0m\u001b[1;32m 1849\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1850\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_call_flat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcaptured_inputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcancellation_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m 1922\u001b[0m \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1923\u001b[0m return self._build_call_outputs(self._inference_function.call(\n\u001b[0;32m-> 1924\u001b[0;31m ctx, args, cancellation_manager=cancellation_manager))\n\u001b[0m\u001b[1;32m 1925\u001b[0m forward_backward = self._select_forward_and_backward_functions(\n\u001b[1;32m 1926\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m 548\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 549\u001b[0m \u001b[0mattrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattrs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 550\u001b[0;31m ctx=ctx)\n\u001b[0m\u001b[1;32m 551\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 552\u001b[0m outputs = execute.execute_with_cancellation(\n", + "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m 58\u001b[0m \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 59\u001b[0m tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0;32m---> 60\u001b[0;31m inputs, attrs, num_outputs)\n\u001b[0m\u001b[1;32m 61\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mKeyboardInterrupt\u001b[0m: " + ] + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "g_KkDWI9mm8v" + }, + "source": [ + "from keras.models import load_model\n", + "model = load_model('/content/drive/My Drive/Colab Notebooks/Meditact/model/lstm_20571_20201016-132514.h5')\n", + "\n" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "EkMbzfvFrNLu" + }, + "source": [ + "class_to_label = {'DERM': 0, 'GS': 1, 'IP': 2, 'GI':3, 'OPH':4,\n", + " 'NR': 5, 'ENT': 6, 'PSY': 7, 'HEON': 8, 'RHEU': 9,\n", + " 'REHM': 10, 'NS': 11, 'AN': 12, 'DENT': 13, 'PS': 14,\n", + " 'CS': 15, 'INFC': 16, 'OS': 17,\n", + " 'EMR': 18, 'ENDO': 19, 'CA': 20, 'KTM': 21, 'OBGY': 22,\n", + " 'URO': 23, 'ALL': 24, 'NPH': 25}\n", + "label_to_class = {value:key for key, value in class_to_label.items()}\n" + ], + "execution_count": 16, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "iG1Hs-sTXAbj", + "outputId": "58353c07-dd9c-493b-e722-a3216e2ff144", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 598 + } + }, + "source": [ + "!pip install konlpy" + ], + "execution_count": 20, + "outputs": [ + { + "output_type": "stream", + "text": [ + "Collecting konlpy\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/85/0e/f385566fec837c0b83f216b2da65db9997b35dd675e107752005b7d392b1/konlpy-0.5.2-py2.py3-none-any.whl (19.4MB)\n", + "\u001b[K |████████████████████████████████| 19.4MB 161kB/s \n", + "\u001b[?25hRequirement already satisfied: lxml>=4.1.0 in /usr/local/lib/python3.6/dist-packages (from konlpy) (4.2.6)\n", + "Collecting beautifulsoup4==4.6.0\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/9e/d4/10f46e5cfac773e22707237bfcd51bbffeaf0a576b0a847ec7ab15bd7ace/beautifulsoup4-4.6.0-py3-none-any.whl (86kB)\n", + "\u001b[K |████████████████████████████████| 92kB 12.7MB/s \n", + "\u001b[?25hRequirement already satisfied: numpy>=1.6 in /usr/local/lib/python3.6/dist-packages (from konlpy) (1.18.5)\n", + "Collecting colorama\n", + " Downloading https://files.pythonhosted.org/packages/44/98/5b86278fbbf250d239ae0ecb724f8572af1c91f4a11edf4d36a206189440/colorama-0.4.4-py2.py3-none-any.whl\n", + "Collecting JPype1>=0.7.0\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/8b/f7/a368401e630f0e390dd0e62c39fb928e5b23741b53c2360ee7d376660927/JPype1-1.0.2-cp36-cp36m-manylinux2010_x86_64.whl (3.8MB)\n", + "\u001b[K |████████████████████████████████| 3.8MB 57.8MB/s \n", + "\u001b[?25hCollecting tweepy>=3.7.0\n", + " Downloading https://files.pythonhosted.org/packages/bb/7c/99d51f80f3b77b107ebae2634108717362c059a41384a1810d13e2429a81/tweepy-3.9.0-py2.py3-none-any.whl\n", + "Requirement already satisfied: typing-extensions; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from JPype1>=0.7.0->konlpy) (3.7.4.3)\n", + "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.6/dist-packages (from tweepy>=3.7.0->konlpy) (1.3.0)\n", + "Requirement already satisfied: requests[socks]>=2.11.1 in /usr/local/lib/python3.6/dist-packages (from tweepy>=3.7.0->konlpy) (2.23.0)\n", + "Requirement already satisfied: six>=1.10.0 in /usr/local/lib/python3.6/dist-packages (from tweepy>=3.7.0->konlpy) (1.15.0)\n", + "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from requests-oauthlib>=0.7.0->tweepy>=3.7.0->konlpy) (3.1.0)\n", + "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests[socks]>=2.11.1->tweepy>=3.7.0->konlpy) (2.10)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests[socks]>=2.11.1->tweepy>=3.7.0->konlpy) (2020.6.20)\n", + "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests[socks]>=2.11.1->tweepy>=3.7.0->konlpy) (3.0.4)\n", + "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests[socks]>=2.11.1->tweepy>=3.7.0->konlpy) (1.24.3)\n", + "Requirement already satisfied: PySocks!=1.5.7,>=1.5.6; extra == \"socks\" in /usr/local/lib/python3.6/dist-packages (from requests[socks]>=2.11.1->tweepy>=3.7.0->konlpy) (1.7.1)\n", + "Installing collected packages: beautifulsoup4, colorama, JPype1, tweepy, konlpy\n", + " Found existing installation: beautifulsoup4 4.6.3\n", + " Uninstalling beautifulsoup4-4.6.3:\n", + " Successfully uninstalled beautifulsoup4-4.6.3\n", + " Found existing installation: tweepy 3.6.0\n", + " Uninstalling tweepy-3.6.0:\n", + " Successfully uninstalled tweepy-3.6.0\n", + "Successfully installed JPype1-1.0.2 beautifulsoup4-4.6.0 colorama-0.4.4 konlpy-0.5.2 tweepy-3.9.0\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "g_Xc_odzZp5L" + }, + "source": [ + "from konlpy.tag import Okt\n", + "def preprocess_sentence(sentence):\n", + " twitter = Okt()\n", + " nouns = twitter.nouns(sentence)\n", + " stopwords = ['질문', '문의', '관련', '그대로', '계속', '답변', '선생님', '관련문의',\n", + " '한지', '자주', '좀', '쪽', '자꾸', '요즘', '몇개', '무조건', '하나요',\n", + " '안해','요', '경우', '최근', '및', '몇', '달', '일반', '전날', '저번',\n", + " '말', '일어나지', '며칠', '먹기', '지난번', '글', '때문', '너', '무',\n", + " '오늘', '시', '잔', '뒤', '지속', '막', '것', '이건', '뭔가', '다시', '그',\n", + " '무슨', '안', '난', '도', '기', '후', '거리', '이', '뭘', '저', '뭐', '답젼',\n", + " '평생', '회복', '반', '감사', '의사', '보험', '학생', '제발', '살짝',\n", + " '느낌', '제', '대해','갑자기','문제', '전','정도', '왜', '거', '가요',\n", + " '의심', '어제', '추천', '를', '지금', '무엇', '내일', '관해', '리', '세',\n", + " '로', '목적', '그냥', '거의', '고민', '다음', '이틀', '항상', '뭐', '때',\n", + " '요', '가끔', '이후', '혹시', ]\n", + " for word in nouns:\n", + " if word in stopwords:\n", + " while word in nouns:\n", + " nouns.remove(word)\n", + " return nouns\n", + "\n", + "def predict(sen):\n", + " global model\n", + " test = preprocess_sentence(sen)\n", + " test_batch = []\n", + " test_batch.append(test)\n", + " pre_test = t.texts_to_sequences(test_batch)\n", + " padded_pre_test = tf.keras.preprocessing.sequence.pad_sequences(pre_test, truncating=trunc_type, padding=padding_type, maxlen=sequence_length)\n", + "\n", + " result = model.predict(padded_pre_test)\n", + " sorted = result.argsort()\n", + " sp = result.argmax()\n", + " val = result.max()\n", + " base = '{0}확률로 {1}과를 방문하셔야 합니다'\n", + " return base.format(val, label_to_class[sp])" + ], + "execution_count": 21, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "P3CRIDapwRuf", + "outputId": "27bb3907-50d7-4c13-f961-690b465f2462", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 + } + }, + "source": [ + "sentence = \"잠이 너무 안와서 다음날 몽롱해요\"\n", + "predict(sentence)" + ], + "execution_count": 22, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + }, + "text/plain": [ + "'0.9999998807907104확률로 PSY과를 방문하셔야 합니다'" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 22 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "DIRe-9MqnkML", + "outputId": "e23abbc1-7304-44f7-9e94-85b93e659258", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 + } + }, + "source": [ + "sentence = \"통풍으로 엄지발가락이 부었어요\"\n", + "predict(sentence)" + ], + "execution_count": 23, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + }, + "text/plain": [ + "'0.8111918568611145확률로 OS과를 방문하셔야 합니다'" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 23 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "12KQffewyD-R", + "outputId": "e94b1b43-564e-4d44-b00c-55555da35a86", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 + } + }, + "source": [ + "sentence = \"오래된 이명과 비염이 있어요\"\n", + "predict(sentence)" + ], + "execution_count": 24, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + }, + "text/plain": [ + "'0.9991840720176697확률로 ENT과를 방문하셔야 합니다'" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 24 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "nuyvWhbcyJZY", + "outputId": "eaefa362-4764-4170-acb1-be60882026c1", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 + } + }, + "source": [ + "sentence = \"뇌경색 이후에 어떤 운동을 하는게 좋은가요\"\n", + "predict(sentence)" + ], + "execution_count": 25, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + }, + "text/plain": [ + "'0.9163525104522705확률로 REHM과를 방문하셔야 합니다'" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 25 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "RqePT8PbyMvD", + "outputId": "02851002-3f54-49a2-cc43-2149b0db20da", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 35 + } + }, + "source": [ + "sentence = \"항문 주변이 따가워요\"\n", + "predict(sentence)" + ], + "execution_count": 26, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + }, + "text/plain": [ + "'0.976958692073822확률로 GS과를 방문하셔야 합니다'" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 26 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "8mOcGymxyP87" + }, + "source": [ + "" + ], + "execution_count": null, + "outputs": [] + } + ] +} \ No newline at end of file