Spaces:
Runtime error
Runtime error
File size: 5,849 Bytes
e850536 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
# train_model.py
# AI λͺ¨λΈμ νλ ¨νλ μ€ν¬λ¦½νΈ, λ€μ μ¬μ©κ°λ₯ν μμ x
import pandas as pd
import json
import re
import sys
import transformers
import torch
from transformers import AutoTokenizer
# --- 1. λ°μ΄ν° λ‘λ© λ° μ μ²λ¦¬ ---
print("--- [Phase 1] λ°μ΄ν° λ‘λ© λ° μ μ²λ¦¬ μμ ---")
# νμΌ κ²½λ‘ μ€μ
file_path = './data/'
# νλ ¨/κ²μ¦ λ°μ΄ν° λ‘λ© (μ΄μ κ³Ό λμΌ)
with open(file_path + 'training-label.json', 'r', encoding='utf-8') as file:
training_data_raw = json.load(file)
with open(file_path + 'validation-label.json', 'r', encoding='utf-8') as file:
validation_data_raw = json.load(file)
# DataFrame μμ± ν¨μ (μ½λλ₯Ό κΉλνκ² νκΈ° μν΄ ν¨μλ‘ λ¬Άμ)
def create_dataframe(data_raw):
extracted_data = []
for dialogue in data_raw:
try:
emotion_type = dialogue['profile']['emotion']['type']
dialogue_content = dialogue['talk']['content']
full_text = " ".join(list(dialogue_content.values()))
if full_text and emotion_type:
extracted_data.append({'text': full_text, 'emotion': emotion_type})
except KeyError:
continue
return pd.DataFrame(extracted_data)
df_train = create_dataframe(training_data_raw)
df_val = create_dataframe(validation_data_raw)
# ν
μ€νΈ μ μ
def clean_text(text):
return re.sub(r'[^κ°-ν£a-zA-Z0-9 ]', '', text)
df_train['cleaned_text'] = df_train['text'].apply(clean_text)
df_val['cleaned_text'] = df_val['text'].apply(clean_text)
print("β
λ°μ΄ν° λ‘λ© λ° μ μ²λ¦¬ μλ£!")
# --- 2. AI λͺ¨λΈλ§ μ€λΉ ---
print("\n--- [Phase 2] AI λͺ¨λΈλ§ μ€λΉ μμ ---")
# λͺ¨λΈ λ° ν ν¬λμ΄μ λΆλ¬μ€κΈ°
MODEL_NAME = "klue/roberta-base"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
# ν
μ€νΈ ν ν°ν
train_tokenized = tokenizer(list(df_train['cleaned_text']), return_tensors="pt", max_length=128, padding=True, truncation=True)
val_tokenized = tokenizer(list(df_val['cleaned_text']), return_tensors="pt", max_length=128, padding=True, truncation=True)
# λΌλ²¨ μΈμ½λ©
unique_labels = sorted(df_train['emotion'].unique())
label_to_id = {label: id for id, label in enumerate(unique_labels)}
id_to_label = {id: label for label, id in label_to_id.items()}
df_train['label'] = df_train['emotion'].map(label_to_id)
df_val['label'] = df_val['emotion'].map(label_to_id)
print("β
ν ν°ν λ° λΌλ²¨ μΈμ½λ© μλ£!")
print("μ΄μ λͺ¨λΈ νλ ¨μ μν λͺ¨λ μ€λΉκ° λλ¬μ΅λλ€.")
# [Phase 3]μ κΈ°μ‘΄ μ½λλ₯Ό μλ λ΄μ©μΌλ‘ κ΅μ²΄ν΄μ£ΌμΈμ.
# -----------------------------------------------------------
# --- [Phase 3] λͺ¨λΈ νμ΅ λ° νκ° (μ΅μ κΈ°λ₯ λ²μ ) ---
# -----------------------------------------------------------
import torch
from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
print("\n--- [Phase 3] λͺ¨λΈ νμ΅ λ° νκ° μμ ---")
# 1. PyTorch Dataset ν΄λμ€ μ μ (μ΄μ κ³Ό λμΌ)
class EmotionDataset(torch.utils.data.Dataset):
def __init__(self, encodings, labels):
self.encodings = encodings
self.labels = labels
def __getitem__(self, idx):
item = {key: val[idx].clone().detach() for key, val in self.encodings.items()}
item['labels'] = torch.tensor(self.labels[idx])
return item
def __len__(self):
return len(self.labels)
train_dataset = EmotionDataset(train_tokenized, df_train['label'].tolist())
val_dataset = EmotionDataset(val_tokenized, df_val['label'].tolist())
print("β
PyTorch λ°μ΄ν°μ
μμ±μ΄ μλ£λμμ΅λλ€.")
# 2. AI λͺ¨λΈ λΆλ¬μ€κΈ° (μ΄μ κ³Ό λμΌ)
model = AutoModelForSequenceClassification.from_pretrained(
MODEL_NAME,
num_labels=len(unique_labels),
id2label=id_to_label,
label2id=label_to_id
)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
print(f"β
λͺ¨λΈ λ‘λ© μλ£! λͺ¨λΈμ {device}μμ μ€νλ©λλ€.")
# 3. λͺ¨λΈ μ±λ₯ νκ°λ₯Ό μν ν¨μ μ μ (μμ μλ£)
def compute_metrics(pred):
labels = pred.label_ids
# λ°λ‘ μ΄ λΆλΆμ΄ μμ λμμ΅λλ€.
preds = pred.predictions.argmax(-1)
precision, recall, f1, _ = precision_recall_fscore_support(labels, preds, average='weighted', zero_division=0)
acc = accuracy_score(labels, preds)
return {'accuracy': acc, 'f1': f1, 'precision': precision, 'recall': recall}
# 4. νλ ¨μ μν μμΈ μ€μ (Arguments) μ μ (λͺ¨λ λΆκ° μ΅μ
μ κ±°)
training_args = TrainingArguments(
output_dir='./results', # λͺ¨λΈμ΄ μ μ₯λ μμΉ (νμ)
num_train_epochs=3, # νλ ¨ νμ
per_device_train_batch_size=16, # νλ ¨ λ°°μΉ μ¬μ΄μ¦
# λλ¨Έμ§ λͺ¨λ νκ°/μ μ₯ κ΄λ ¨ μ΅μ
μ λͺ¨λ μ κ±°ν©λλ€.
)
# ---!!! ν΅μ¬ μμ μ¬ν 2 !!!---
# 5. Trainer μ μ (νκ° κ΄λ ¨ κΈ°λ₯ λΉνμ±ν)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_dataset,
# νλ ¨ μ€ νκ°λ₯Ό νμ§ μμΌλ―λ‘ μλ μ΅μ
λ€μ μ μΈν©λλ€.
# eval_dataset=val_dataset,
# compute_metrics=compute_metrics
)
# 6. λͺ¨λΈ νλ ¨ μμ!
print("\nπ₯ AI λͺ¨λΈ νλ ¨μ μμν©λλ€...")
trainer.train()
print("\nπ λͺ¨λΈ νλ ¨ μλ£!")
# 7. μ΅μ’
λͺ¨λΈ νκ°λ νλ ¨μ΄ λλ ν 'λ³λλ‘' μ€ν
print("\n--- μ΅μ’
λͺ¨λΈ μ±λ₯ νκ° ---")
# λΉνμ±ννλ νκ° λ°μ΄ν°μ
μ evaluate ν¨μμ μ§μ μ λ¬ν΄μ€λλ€.
final_evaluation = trainer.evaluate(eval_dataset=val_dataset)
print(final_evaluation)
print("\nλͺ¨λ κ³Όμ μ΄ μ±κ³΅μ μΌλ‘ λλ¬μ΅λλ€! results ν΄λμμ νλ ¨λ λͺ¨λΈμ νμΈνμΈμ.") |