File size: 5,580 Bytes
e221c83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
150
151
152
153
154
155
156
157
158
159
160
import pandas as pd
import json
import re
import matplotlib.pyplot as plt
import seaborn as sns

# --- Matplotlib ν•œκΈ€ 폰트 μ„€μ • (Windows: Malgun Gothic) ---
try:
    plt.rcParams['font.family'] = 'Malgun Gothic'
    plt.rcParams['axes.unicode_minus'] = False 
except:
    print("ν•œκΈ€ 폰트 섀정에 μ‹€νŒ¨ν–ˆμŠ΅λ‹ˆλ‹€. κ·Έλž˜ν”„μ˜ 라벨이 깨질 수 μžˆμŠ΅λ‹ˆλ‹€.")

# --- 감정 λ§€ν•‘ ν•¨μˆ˜ μ •μ˜ --- 
def map_emotion_code(ecode):
    """
    Eμ½”λ“œ λ¬Έμžμ—΄μ„ λŒ€λΆ„λ₯˜ 감정 λ¬Έμžμ—΄λ‘œ λ§€ν•‘ν•©λ‹ˆλ‹€. (예: 'E11' -> 'λΆ„λ…Έ')
    """
    # Eμ½”λ“œ λ¬Έμžμ—΄μ΄ μ•„λ‹ˆκ±°λ‚˜ ν˜•μ‹μ΄ λ§žμ§€ μ•ŠμœΌλ©΄ None λ°˜ν™˜
    if not isinstance(ecode, str) or len(ecode) < 2 or ecode[0] != 'E':
        return None

    try:
        # 'E'λ₯Ό μ œκ±°ν•˜κ³  숫자 λΆ€λΆ„λ§Œ μΆ”μΆœ
        code_num = int(ecode[1:])
    except ValueError:
        return None 

    if 10 <= code_num <= 19:
        return 'λΆ„λ…Έ'
    elif 20 <= code_num <= 29:
        return 'μŠ¬ν””'
    elif 30 <= code_num <= 39:
        return 'λΆˆμ•ˆ'
    elif 40 <= code_num <= 49:
        return 'μƒμ²˜'
    elif 50 <= code_num <= 59:
        return 'λ‹Ήν™©'
    elif 60 <= code_num <= 69:
        return '기쁨'
    else:
        return None

# --- [Phase 1] 데이터 λ‘œλ”© 및 병합 ---
print("---" + "[Phase 1] 데이터 λ‘œλ”© 및 병합 μ‹œμž‘" + "---")

# 파일 경둜 μ„€μ •
data_path = 'data/'
train_text_path = data_path + 'training-origin.xlsx'
train_label_path = data_path + 'training-label.json'
val_text_path = data_path + 'validation-origin.xlsx' 
val_label_path = data_path + 'test.json'

# 1. 데이터 뢈러였기
try:
    df_train_text = pd.read_excel(train_text_path, header=0)
    df_val_text = pd.read_excel(val_text_path, header=0)

    with open(train_label_path, 'r', encoding='utf-8') as f:
        train_labels_raw = json.load(f)
    with open(val_label_path, 'r', encoding='utf-8') as f:
        val_labels_raw = json.load(f)

    print("파일 λ‘œλ”© 성곡!")

except FileNotFoundError as e:
    print(f"νŒŒμΌμ„ 찾을 수 μ—†μŠ΅λ‹ˆλ‹€: {e}")
    print("파일 κ²½λ‘œμ™€ 파일 이름을 λ‹€μ‹œ ν™•μΈν•΄μ£Όμ„Έμš”.")
    exit()


# 2. 라벨 데이터 μ •μ œ 및 μΆ”μΆœ
def extract_emotions(raw_labels):
    emotions = []
    for dialogue in raw_labels:
        try:
            emotions.append(dialogue['profile']['emotion']['type'])
        except KeyError:
            emotions.append(None)
    return emotions

df_train_labels = pd.DataFrame({'emotion': extract_emotions(train_labels_raw)})
df_val_labels = pd.DataFrame({'emotion': extract_emotions(val_labels_raw)})

# 3. ν…μŠ€νŠΈ 데이터와 라벨 데이터 병합
def combine_dialogues(df):
    dialogue_cols = [col for col in df.columns if 'λ¬Έμž₯' in str(col)]
    for col in dialogue_cols:
        df[col] = df[col].astype(str).fillna('')
    df['text'] = df[dialogue_cols].apply(lambda row: ' '.join(row), axis=1)
    return df

df_train = pd.concat([df_train_text, df_train_labels], axis=1)
df_val = pd.concat([df_val_text, df_val_labels], axis=1)
df_train = combine_dialogues(df_train)
df_val = combine_dialogues(df_val)


# 원본 Eμ½”λ“œ(emotion)λ₯Ό λŒ€λΆ„λ₯˜ 감정(major_emotion)으둜 λ§€ν•‘ν•˜κ³ , λ§€ν•‘λ˜μ§€ μ•Šμ€ λ°μ΄ν„°λŠ” μ œκ±°ν•©λ‹ˆλ‹€.
df_train['major_emotion'] = df_train['emotion'].apply(map_emotion_code)
df_val['major_emotion'] = df_val['emotion'].apply(map_emotion_code)

df_train.dropna(subset=['major_emotion'], inplace=True)
df_val.dropna(subset=['major_emotion'], inplace=True)

# 4. ν›ˆλ ¨ 데이터와 검증 데이터 톡합
df_combined = pd.concat([df_train, df_val], ignore_index=True)


print("\n--- 톡합 λ°μ΄ν„°ν”„λ ˆμž„μ˜ 첫 5쀄 (λ§€ν•‘ ν›„) ---")
print(df_combined[['text', 'emotion', 'major_emotion']].head())
print("\n--- 톡합 λ°μ΄ν„°ν”„λ ˆμž„ 크기 ---")
print(f"톡합 데이터: {df_combined.shape}")
print("--- [Phase 1] μ™„λ£Œ ---")


# --- [Phase 2] 데이터 탐색 및 μ „μ²˜λ¦¬ ---
print("\n---" + "[Phase 2] 데이터 탐색 및 μ „μ²˜λ¦¬ μ‹œμž‘" + "---")

# 1. 데이터 탐색 및 μ‹œκ°ν™”
print("\n---" + "톡합 데이터 (ν›ˆλ ¨ + 검증) 감정 뢄포" + "---")
emotion_counts = df_combined['major_emotion'].value_counts() 
print(emotion_counts)
print("-------------------------------------------\n")


# 감정 뢄포 μ‹œκ°ν™”
plt.figure(figsize=(10, 6))
sns.barplot(x=emotion_counts.values, y=emotion_counts.index, color='#2c7bb6') 
for index, value in enumerate(emotion_counts.values):
    plt.text(x=value + 100, y=index, s=f'{value:,}', va='center', ha='left', fontsize=12, color='black')

plt.title('ν›ˆλ ¨ + 검증 데이터 톡합 감정 뢄포 μ‹œκ°ν™”', fontsize=15)
plt.xlabel('개수', fontsize=12)
plt.ylabel('감정', fontsize=12)
plt.grid(axis='x', linestyle='--', alpha=0.7)
plt.xlim(0, 15000)
plt.ticklabel_format(style='plain', axis='x')

plt.show() 

print("\nμ‹œκ°ν™” μ™„λ£Œ. κ·Έλž˜ν”„ 창을 λ‹«μœΌλ©΄ λ‹€μŒ 단계가 μ§„ν–‰λ©λ‹ˆλ‹€.")

# 2. ν…μŠ€νŠΈ μ •μ œ
print("\n---" + "ν…μŠ€νŠΈ μ •μ œ μ‹œμž‘" + "---")

def clean_text(text):
    if not isinstance(text, str):
        return ""
    # μ •κ·œν‘œν˜„μ‹μ„ μ‚¬μš©ν•˜μ—¬ ν•œκΈ€, μ˜μ–΄, 숫자, 곡백을 μ œμ™Έν•œ λͺ¨λ“  문자 제거
    return re.sub(r'[^κ°€-힣a-zA-Z0-9 ]', '', text)


df_combined['cleaned_text'] = df_combined['text'].apply(clean_text)

print("ν…μŠ€νŠΈ μ •μ œ μ™„λ£Œ.")
print(df_combined[['text', 'cleaned_text', 'major_emotion']].head())
print("--- [Phase 2] μ™„λ£Œ ---")

print("\nλͺ¨λ“  과정이 μ™„λ£Œλ˜μ—ˆμŠ΅λ‹ˆλ‹€. 이제 이 λ°μ΄ν„°ν”„λ ˆμž„(df_combined)으둜 뢄석을 계속 μ§„ν–‰ν•  수 μžˆμŠ΅λ‹ˆλ‹€.")