Hugging Face's logo

HyukII
/
text-emotion-model

Text Classification
Transformers
Safetensors
Korean
roberta
emotion
text-embeddings-inference
Model card Files
xet
Community
HyukII commited on
Commit
0de7da6
·
verified ·
1 Parent(s): 8c48e24

Delete 테스트용.ipynb

Browse files
Files changed (1) hide show
  1. 테스트용.ipynb +0 -186
테스트용.ipynb DELETED
@@ -1,186 +0,0 @@
1
- {
2
- "cells": [
3
- {
4
- "cell_type": "code",
5
- "execution_count": 1,
6
- "metadata": {
7
- "id": "HtXIxG2kUpgO"
8
- },
9
- "outputs": [
10
- {
11
- "name": "stderr",
12
- "output_type": "stream",
13
- "text": [
14
- "/home/2021111971/.conda/envs/gpu_env/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
15
- " from .autonotebook import tqdm as notebook_tqdm\n",
16
- "2025-08-17 15:05:50.559882: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
17
- "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
18
- "E0000 00:00:1755410750.582529 76530 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
19
- "E0000 00:00:1755410750.589567 76530 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
20
- "W0000 00:00:1755410750.608699 76530 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
21
- "W0000 00:00:1755410750.608723 76530 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
22
- "W0000 00:00:1755410750.608726 76530 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
23
- "W0000 00:00:1755410750.608728 76530 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
24
- "2025-08-17 15:05:50.614673: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
25
- "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
26
- ]
27
- },
28
- {
29
- "name": "stdout",
30
- "output_type": "stream",
31
- "text": [
32
- "cuda\n"
33
- ]
34
- }
35
- ],
36
- "source": [
37
- "from transformers import AutoTokenizer, AutoModelForSequenceClassification\n",
38
- "import torch, json, os\n",
39
- "import torch.nn.functional as F\n",
40
- "import re\n",
41
- "\n",
42
- "\n",
43
- "LOAD_DIR = \"/home/2021111971/todai/model2/final_model\"\n",
44
- "\n",
45
- "try:\n",
46
- " tok = AutoTokenizer.from_pretrained(LOAD_DIR)\n",
47
- " model = AutoModelForSequenceClassification.from_pretrained(LOAD_DIR).eval()\n",
48
- "except Exception as e:\n",
49
- " print(f\"Error loading model or tokenizer from {LOAD_DIR}: {e}\")\n",
50
- " print(\"Please ensure the path is correct and the directory contains the necessary model files.\")\n",
51
- " raise\n",
52
- "\n",
53
- "\n",
54
- "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
55
- "print(device)\n",
56
- "model.to(device)\n",
57
- "\n",
58
- "with open(os.path.join(LOAD_DIR, \"label_map.json\"), \"r\", encoding=\"utf-8\") as f:\n",
59
- " lm = json.load(f)\n",
60
- "id2label = {int(k): v for k, v in lm[\"id2label\"].items()}\n",
61
- "num_labels = len(id2label)"
62
- ]
63
- },
64
- {
65
- "cell_type": "code",
66
- "execution_count": 2,
67
- "metadata": {
68
- "id": "VE8FmoqOUq3p"
69
- },
70
- "outputs": [],
71
- "source": [
72
- "\n",
73
- "# ==== 2) 단문 예측 ====\n",
74
- "def predict_emotion_and_print(text, max_len=256):\n",
75
- " with torch.no_grad():\n",
76
- " enc = tok(text, truncation=True, padding=True, max_length=max_len, return_tensors=\"pt\").to(device)\n",
77
- " probs = F.softmax(model(**enc).logits, dim=-1).cpu().numpy()[0]\n",
78
- " print(\"=== 감정 분석 결과 ===\")\n",
79
- " for lab, pct in sorted({id2label[i]: float(probs[i]*100) for i in range(num_labels)}.items(),\n",
80
- " key=lambda x: -x[1]):\n",
81
- " print(f\"{lab:<5} : {pct:.2f}%\")\n",
82
- " print(\"======================\")\n"
83
- ]
84
- },
85
- {
86
- "cell_type": "code",
87
- "execution_count": 3,
88
- "metadata": {
89
- "id": "-O-jiHwiUvFx"
90
- },
91
- "outputs": [],
92
- "source": [
93
- "# ==== 3) 일기(여러 문장) → 문장 단위 집계 ====\n",
94
- "# (문장마다 예측 → 개수 비율로 퍼센트 계산)\n",
95
- "def split_sents(text):\n",
96
- " # 마침표/물음표/느낌표/줄바�� 기준\n",
97
- " return [s.strip() for s in re.split(r'[.?!\\n]', text) if s.strip()]\n",
98
- "\n",
99
- "def analyze_diary_percent(diary_text, max_len=256, return_details=False):\n",
100
- " sents = split_sents(diary_text)\n",
101
- " if not sents:\n",
102
- " print(\"문장이 없습니다.\"); return {}\n",
103
- "\n",
104
- " counts = {id2label[i]: 0 for i in range(num_labels)}\n",
105
- " details = []\n",
106
- "\n",
107
- " with torch.no_grad():\n",
108
- " for s in sents:\n",
109
- " enc = tok(s, truncation=True, padding=True, max_length=max_len, return_tensors=\"pt\").to(device)\n",
110
- " logits = model(**enc).logits\n",
111
- " pred = int(logits.argmax(-1).cpu().numpy()[0])\n",
112
- " lab = id2label[pred]\n",
113
- " counts[lab] += 1\n",
114
- " if return_details: details.append((s, lab))\n",
115
- "\n",
116
- " total = sum(counts.values())\n",
117
- " perc = {lab: round((counts.get(lab, 0) / total) * 100, 2) if total > 0 else 0.0 for lab in id2label.values()}\n",
118
- "\n",
119
- " print(\"=== 텍스트 기반 감정 분석 ===\")\n",
120
- " for lab, pct in sorted(perc.items(), key=lambda x: -x[1]):\n",
121
- " print(f\"{lab:<5}: {pct:5.2f}% \")\n",
122
- " print(\"============================\")\n",
123
- "\n"
124
- ]
125
- },
126
- {
127
- "cell_type": "code",
128
- "execution_count": 4,
129
- "metadata": {
130
- "colab": {
131
- "base_uri": "https://localhost:8080/"
132
- },
133
- "id": "dXzmKSI2UjOu",
134
- "outputId": "02d6ce57-ce23-489a-f1ca-0a052ceb2dee"
135
- },
136
- "outputs": [
137
- {
138
- "name": "stdout",
139
- "output_type": "stream",
140
- "text": [
141
- "=== 텍스트 기반 감정 분석 ===\n",
142
- "기쁨 : 66.67% \n",
143
- "슬픔 : 33.33% \n",
144
- "당황 : 0.00% \n",
145
- "분노 : 0.00% \n",
146
- "불안 : 0.00% \n",
147
- "상처 : 0.00% \n",
148
- "============================\n"
149
- ]
150
- }
151
- ],
152
- "source": [
153
- "diary_text = \"\"\"\n",
154
- "아침에 프로젝트 승인 소식을 듣고 너무 기뻤다.\n",
155
- "하지만 오후에는 친한 동료가 쇠사를 고민한다는 말을 듣고 마음이 먹먹해졌다.\n",
156
- "퇴근길 노을을 보며 오늘 하루를 감사한 마음으로 마무리했다.\n",
157
- "\"\"\"\n",
158
- "analyze_diary_percent(diary_text)\n"
159
- ]
160
- }
161
- ],
162
- "metadata": {
163
- "colab": {
164
- "provenance": []
165
- },
166
- "kernelspec": {
167
- "display_name": "gpu_env",
168
- "language": "python",
169
- "name": "python3"
170
- },
171
- "language_info": {
172
- "codemirror_mode": {
173
- "name": "ipython",
174
- "version": 3
175
- },
176
- "file_extension": ".py",
177
- "mimetype": "text/x-python",
178
- "name": "python",
179
- "nbconvert_exporter": "python",
180
- "pygments_lexer": "ipython3",
181
- "version": "3.11.13"
182
- }
183
- },
184
- "nbformat": 4,
185
- "nbformat_minor": 0
186
- }