Sangwon78 commited on
Commit
99ea4b9
·
verified ·
1 Parent(s): 1033f9b

Upload 2 files

Browse files
Files changed (2) hide show
  1. app (2).py +95 -0
  2. requirements (1).txt +4 -0
app (2).py ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ import pandas as pd
3
+ import re
4
+ import io
5
+ import openpyxl
6
+ from openpyxl import Workbook
7
+ import tempfile
8
+
9
+ def remove_special_characters(text: str):
10
+ return re.sub(r"[^\w\sㄱ-힣]", "", text)
11
+
12
+ def extract_keywords(text_list, top_n=3):
13
+ combined_text = " ".join(text_list)
14
+ combined_text = remove_special_characters(combined_text)
15
+ words = combined_text.split()
16
+ freq = {}
17
+ for w in words:
18
+ freq[w] = freq.get(w, 0) + 1
19
+ sorted_words = sorted(freq.items(), key=lambda x: x[1], reverse=True)
20
+ keywords = [w[0] for w in sorted_words[:top_n]]
21
+ return ", ".join(keywords)
22
+
23
+ def process_excel(file):
24
+ # 엑셀 읽기
25
+ df = pd.read_excel(file.name, header=None)
26
+ df.columns = ["고객ID", "리뷰날짜", "리뷰내용", "리뷰점수"] + list(df.columns[4:])
27
+ df["리뷰내용"] = df["리뷰내용"].astype(str).apply(remove_special_characters)
28
+ df_use = df[["고객ID", "리뷰날짜", "리뷰내용", "리뷰점수"]]
29
+
30
+ all_ids = df_use["고객ID"].dropna().unique()
31
+ combined_id = ", ".join(map(str, all_ids))
32
+ all_dates = df_use["리뷰날짜"].dropna().unique()
33
+ combined_dates = ", ".join(map(str, sorted(all_dates)))
34
+
35
+ keywords = extract_keywords(df_use["리뷰내용"].tolist())
36
+ df_use["리뷰점수"] = pd.to_numeric(df_use["리뷰점수"], errors='coerce')
37
+ score_mean = df_use["리뷰점수"].mean()
38
+
39
+ wb = Workbook()
40
+ ws = wb.active
41
+ ws["A1"] = "고객ID"
42
+ ws["B1"] = "리뷰날짜"
43
+ ws["C1"] = "리뷰내용"
44
+ ws["D1"] = "리뷰점수"
45
+
46
+ for i, row in enumerate(df_use.values, start=2):
47
+ ws.cell(row=i, column=1, value=row[0])
48
+ ws.cell(row=i, column=2, value=row[1])
49
+ ws.cell(row=i, column=3, value=row[2])
50
+ ws.cell(row=i, column=4, value=row[3])
51
+
52
+ ws["A8"] = combined_id
53
+ ws["B8"] = combined_dates
54
+ ws["C8"] = keywords
55
+ ws["D8"] = score_mean
56
+
57
+ # 메모리에 저장
58
+ output = io.BytesIO()
59
+ wb.save(output)
60
+ output.seek(0)
61
+
62
+ # 여기서 dict로 반환하지 않고, 임시 파일에 씁니다.
63
+ with tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx") as tmp:
64
+ tmp.write(output.getvalue())
65
+ tmp_path = tmp.name
66
+
67
+ return df_use, tmp_path
68
+
69
+ def create_app():
70
+ with gr.Blocks() as demo:
71
+ gr.Markdown("## 엑셀 파일 업로드 데모")
72
+
73
+ file_input = gr.File(label="엑셀 파일 업로드", file_types=[".xlsx"])
74
+ generate_button = gr.Button("데이터 추출 및 결과 생성")
75
+
76
+ output_df = gr.DataFrame(label="처리된 결과 미리보기")
77
+ download_file = gr.File(label="결과 엑셀 다운로드")
78
+
79
+ def on_click(file):
80
+ df_preview, tmp_path = process_excel(file)
81
+ # 첫 번째 출력: DataFrame 미리보기
82
+ # 두 번째 출력: 실제 파일 경로(str)를 반환
83
+ return df_preview, tmp_path
84
+
85
+ generate_button.click(
86
+ fn=on_click,
87
+ inputs=file_input,
88
+ outputs=[output_df, download_file]
89
+ )
90
+
91
+ return demo
92
+
93
+ if __name__ == "__main__":
94
+ app = create_app()
95
+ app.launch()
requirements (1).txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ gradio
2
+ pandas
3
+ openpyxl
4
+ xlrd