Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,114 +1,4 @@
|
|
1 |
-
|
2 |
-
# 設置頁面配置
|
3 |
-
st.set_page_config(
|
4 |
-
page_title="114年度樂齡學習數位示範體驗場域 服務滿意度調查分析報告",
|
5 |
-
page_icon="📊",
|
6 |
-
layout="wide"
|
7 |
-
)
|
8 |
-
|
9 |
-
# 添加標題和子標題
|
10 |
-
st.markdown("""
|
11 |
-
# 114年度樂齡學習數位示範體驗場域 服務滿意度調查分析報告
|
12 |
-
## 全面理解樂齡學習者數位服務體驗
|
13 |
-
|
14 |
-
本報告提供全面的問卷調查分析與視覺化圖表,深入剖析樂齡學習者參與數位示範場域服務的滿意情形。
|
15 |
-
透過詳細的統計分析和互動式圖表,我們旨在呈現樂齡學習者的服務體驗和需求洞察。
|
16 |
-
|
17 |
-
### 報告製作單位
|
18 |
-
**國立中正大學高齡教育研究中心專案管理團隊**
|
19 |
-
""")
|
20 |
-
|
21 |
-
# 分隔線
|
22 |
-
st.markdown("---")
|
23 |
-
|
24 |
-
# 上傳 CSV 檔案
|
25 |
-
uploaded_file = st.file_uploader("上傳 CSV 檔案", type=['csv'])
|
26 |
-
|
27 |
-
# 預設數據按鈕
|
28 |
-
use_default_data = st.button('使用預設範例數據')
|
29 |
-
|
30 |
-
# 數據載入和處理
|
31 |
-
df = None
|
32 |
-
analyzer = None
|
33 |
-
|
34 |
-
if uploaded_file is not None:
|
35 |
-
# 讀取上傳的 CSV 檔案
|
36 |
-
try:
|
37 |
-
df = pd.read_csv(uploaded_file, encoding='utf-8')
|
38 |
-
st.success("CSV 檔案上傳成功!")
|
39 |
-
except Exception as e:
|
40 |
-
st.error(f"無法讀取檔案:{e}")
|
41 |
-
return
|
42 |
-
|
43 |
-
elif use_default_data:
|
44 |
-
# 使用預設數據
|
45 |
-
df = read_google_sheet(sheet_id, gid)
|
46 |
-
|
47 |
-
if df is None:
|
48 |
-
st.error("無法讀取預設數據,請上傳 CSV 檔案")
|
49 |
-
return
|
50 |
-
|
51 |
-
# 如果有數據,則進行分析
|
52 |
-
if df is not None:
|
53 |
-
analyzer = SurveyAnalyzer()
|
54 |
-
|
55 |
-
# 新增場域和月份篩選器
|
56 |
-
st.sidebar.header("🔍 數據篩選")
|
57 |
-
|
58 |
-
# 假設數據有「場域名稱」欄位,如果名稱不同請調整
|
59 |
-
if '場域名稱' in df.columns:
|
60 |
-
venues = ['全部'] + sorted(df['場域名稱'].unique().tolist())
|
61 |
-
selected_venues = st.sidebar.multiselect("選擇場域", venues, default=['全部'])
|
62 |
-
else:
|
63 |
-
# 如果沒有場域欄位,創建10個虛擬場域供選擇
|
64 |
-
venues = ['全部'] + [f'場域{i+1}' for i in range(10)]
|
65 |
-
selected_venues = st.sidebar.multiselect("選擇場域", venues, default=['全部'])
|
66 |
-
|
67 |
-
# 假設數據有「月份」欄位,如果沒有請調整
|
68 |
-
if '月份' in df.columns:
|
69 |
-
months = ['全部'] + sorted(df['月份'].unique().tolist())
|
70 |
-
selected_month = st.sidebar.selectbox("選擇月份", months)
|
71 |
-
else:
|
72 |
-
# 如果沒有月份欄位,可以創建虛擬月份選項
|
73 |
-
months = ['全部'] + [f'{i+1}月' for i in range(12)]
|
74 |
-
selected_month = st.sidebar.selectbox("選擇月份", months)
|
75 |
-
|
76 |
-
# 📌 基本統計數據
|
77 |
-
st.sidebar.header("📌 選擇數據分析")
|
78 |
-
selected_analysis = st.sidebar.radio("選擇要查看的分析",
|
79 |
-
["📋 問卷統計報告", "📊 滿意度統計", "🟠 性別分佈"])
|
80 |
-
|
81 |
-
if selected_analysis == "📋 問卷統計報告":
|
82 |
-
st.header("📋 問卷統計報告")
|
83 |
-
report = analyzer.generate_report(df)
|
84 |
-
for category, stats in report.items():
|
85 |
-
with st.expander(f"🔍 {category}", expanded=True):
|
86 |
-
for key, value in stats.items():
|
87 |
-
if key == '各項滿意度':
|
88 |
-
st.write(f"**{key}:**")
|
89 |
-
for item, item_stats in value.items():
|
90 |
-
st.write(f" - **{item}**: {', '.join([f'{k}: {v}' for k, v in item_stats.items()])}")
|
91 |
-
else:
|
92 |
-
st.write(f"**{key}**: {value}")
|
93 |
-
|
94 |
-
elif selected_analysis == "📊 滿意度統計":
|
95 |
-
st.header("📊 滿意度統計")
|
96 |
-
analyzer.plot_satisfaction_scores(df)
|
97 |
-
|
98 |
-
elif selected_analysis == "🟠 性別分佈":
|
99 |
-
st.header("🟠 性別分佈")
|
100 |
-
analyzer.plot_gender_distribution(df, selected_venues, selected_month)
|
101 |
-
|
102 |
-
# 報告說明
|
103 |
-
st.markdown("---")
|
104 |
-
st.markdown("""
|
105 |
-
### 報告說明
|
106 |
-
- **數據來源**:114年度樂齡學習數位示範體驗場域調查問卷
|
107 |
-
- **分析目的**:評估樂齡學習者對數位示範場域服務的滿意度
|
108 |
-
- **報告解讀**:本報告提供服務滿意度的客觀量化指標,旨在協助改進服務品質
|
109 |
-
""")
|
110 |
-
else:
|
111 |
-
st.info("請上傳 CSV 檔案或使用預設範例數據")import streamlit as st
|
112 |
import pandas as pd
|
113 |
import plotly.express as px
|
114 |
import numpy as np
|
@@ -143,25 +33,50 @@ class SurveyMappings:
|
|
143 |
class SurveyAnalyzer:
|
144 |
"""📊 問卷分析類"""
|
145 |
|
146 |
-
def __init__(self):
|
147 |
self.mappings = SurveyMappings()
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
]
|
164 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
165 |
def calculate_age(self, birth_year_column):
|
166 |
"""🔢 計算年齡(從民國年到實際年齡)"""
|
167 |
# 獲取當前年份(西元年)
|
@@ -181,14 +96,48 @@ class SurveyAnalyzer:
|
|
181 |
def generate_report(self, df: pd.DataFrame) -> Dict[str, Any]:
|
182 |
"""📝 生成問卷調查報告"""
|
183 |
# 計算年齡
|
184 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
185 |
|
186 |
# 取得教育程度分布(帶計數單位)
|
187 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
188 |
education_with_counts = {k: f"{v}人" for k, v in education_counts.items()}
|
189 |
|
190 |
# 性別分布(帶計數單位)
|
191 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
gender_with_counts = {k: f"{v}人" for k, v in gender_counts.items()}
|
193 |
|
194 |
# 計算每個滿意度���目的平均分數和標準差
|
@@ -260,13 +209,38 @@ class SurveyAnalyzer:
|
|
260 |
"""🟠 性別分佈圓餅圖(使用藍色和紅色)"""
|
261 |
# 過濾數據
|
262 |
filtered_df = df.copy()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
263 |
if venues and '全部' not in venues:
|
264 |
-
filtered_df = filtered_df[filtered_df[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
265 |
if month and month != '全部':
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
270 |
gender_counts.columns = ['性別', '人數']
|
271 |
|
272 |
# 計算百分比
|
@@ -324,85 +298,35 @@ def main():
|
|
324 |
# 上傳 CSV 檔案
|
325 |
uploaded_file = st.file_uploader("上傳 CSV 檔案", type=['csv'])
|
326 |
|
|
|
|
|
|
|
|
|
|
|
327 |
if uploaded_file is not None:
|
328 |
-
# 讀取上傳的 CSV 檔案
|
329 |
try:
|
330 |
df = pd.read_csv(uploaded_file, encoding='utf-8')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
331 |
|
332 |
-
|
333 |
-
|
334 |
-
|
335 |
-
# 創建分析器
|
336 |
-
analyzer = SurveyAnalyzer()
|
337 |
|
338 |
-
|
339 |
-
|
340 |
-
|
341 |
-
|
342 |
-
if df is None:
|
343 |
-
st.error("無法讀取預設數據,請上傳 CSV 檔案")
|
344 |
-
return
|
345 |
-
|
346 |
-
analyzer = SurveyAnalyzer()
|
347 |
-
else:
|
348 |
-
st.info("請上傳 CSV 檔案或使用預設範例數據")
|
349 |
-
return
|
350 |
|
351 |
# 新增場域和月份篩選器
|
352 |
st.sidebar.header("🔍 數據篩選")
|
353 |
|
354 |
-
#
|
355 |
-
|
356 |
-
|
357 |
-
selected_venues = st.sidebar.multiselect("選擇場域", venues, default=['全部'])
|
358 |
-
else:
|
359 |
-
# 如果沒有場域欄位,創建10個虛擬場域供選擇
|
360 |
-
venues = ['全部'] + [f'場域{i+1}' for i in range(10)]
|
361 |
-
selected_venues = st.sidebar.multiselect("選擇場域", venues, default=['全部'])
|
362 |
-
|
363 |
-
# 假設數據有「月份」欄位,如果沒有請調整
|
364 |
-
if '月份' in df.columns:
|
365 |
-
months = ['全部'] + sorted(df['月份'].unique().tolist())
|
366 |
-
selected_month = st.sidebar.selectbox("選擇月份", months)
|
367 |
-
else:
|
368 |
-
# 如果沒有月份欄位,可以創建虛擬月份選項
|
369 |
-
months = ['全部'] + [f'{i+1}月' for i in range(12)]
|
370 |
-
selected_month = st.sidebar.selectbox("選擇月份", months)
|
371 |
-
|
372 |
-
# 📌 基本統計數據
|
373 |
-
st.sidebar.header("📌 選擇數據分析")
|
374 |
-
selected_analysis = st.sidebar.radio("選擇要查看的分析",
|
375 |
-
["📋 問卷統計報告", "📊 滿意度統計", "🟠 性別分佈"])
|
376 |
-
|
377 |
-
if selected_analysis == "📋 問卷統計報告":
|
378 |
-
st.header("📋 問卷統計報告")
|
379 |
-
report = analyzer.generate_report(df)
|
380 |
-
for category, stats in report.items():
|
381 |
-
with st.expander(f"🔍 {category}", expanded=True):
|
382 |
-
for key, value in stats.items():
|
383 |
-
if key == '各項滿意度':
|
384 |
-
st.write(f"**{key}:**")
|
385 |
-
for item, item_stats in value.items():
|
386 |
-
st.write(f" - **{item}**: {', '.join([f'{k}: {v}' for k, v in item_stats.items()])}")
|
387 |
-
else:
|
388 |
-
st.write(f"**{key}**: {value}")
|
389 |
-
|
390 |
-
elif selected_analysis == "📊 滿意度統計":
|
391 |
-
st.header("📊 滿意度統計")
|
392 |
-
analyzer.plot_satisfaction_scores(df)
|
393 |
-
|
394 |
-
elif selected_analysis == "🟠 性別分佈":
|
395 |
-
st.header("🟠 性別分佈")
|
396 |
-
analyzer.plot_gender_distribution(df, selected_venues, selected_month)
|
397 |
-
|
398 |
-
# 報告說明
|
399 |
-
st.markdown("---")
|
400 |
-
st.markdown("""
|
401 |
-
### 報告說明
|
402 |
-
- **數據來源**:114年度樂齡學習數位示範體驗場域調查問卷
|
403 |
-
- **分析目的**:評估樂齡學習者對數位示範場域服務的滿意度
|
404 |
-
- **報告解讀**:本報告提供服務滿意度的客觀量化指標,旨在協助改進服務品質
|
405 |
-
""")
|
406 |
-
|
407 |
-
if __name__ == "__main__":
|
408 |
-
main()
|
|
|
1 |
+
import streamlit as st
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
import pandas as pd
|
3 |
import plotly.express as px
|
4 |
import numpy as np
|
|
|
33 |
class SurveyAnalyzer:
|
34 |
"""📊 問卷分析類"""
|
35 |
|
36 |
+
def __init__(self, df):
|
37 |
self.mappings = SurveyMappings()
|
38 |
+
|
39 |
+
# Method to find the closest matching column
|
40 |
+
def find_matching_column(possible_columns):
|
41 |
+
for col in possible_columns:
|
42 |
+
# Try different variations of potential column names
|
43 |
+
variations = [
|
44 |
+
col,
|
45 |
+
col.replace(':', ''),
|
46 |
+
col.replace('.', ''),
|
47 |
+
col.strip()
|
48 |
+
]
|
49 |
+
for var in variations:
|
50 |
+
if var in df.columns:
|
51 |
+
return var
|
52 |
+
return None
|
53 |
+
|
54 |
+
# Predefined column templates
|
55 |
+
column_templates = [
|
56 |
+
('多元課程與活動', ['示範場域提供多元的數位課程與活動', '1: 示範場域提供多元的數位課程與活動']),
|
57 |
+
('生活應用有幫助', ['示範場域的數位課程與活動對我的生活應用有幫助', '2.示範場域的數位課程與活動對我的生活應用有幫助']),
|
58 |
+
('服務人員親切', ['示範場域的服務人員親切有禮貌', '3: 示範場域的服務人員親切有禮貌']),
|
59 |
+
('空間設備友善', ['示範場域的服務空間與數位設備友善方便', '4.示範場域的服務空間與數位設備友善方便']),
|
60 |
+
('獲得需要協助', ['在示範場域可以獲得需要的協助', '5.在示範場域可以獲得需要的協助']),
|
61 |
+
('整體服務滿意', ['對於示範場域的服務感到滿意', '6.對於示範場域的服務感到滿意'])
|
62 |
]
|
63 |
|
64 |
+
# Find matching columns
|
65 |
+
self.satisfaction_short_names = []
|
66 |
+
self.satisfaction_columns = []
|
67 |
+
|
68 |
+
for short_name, column_options in column_templates:
|
69 |
+
matched_col = None
|
70 |
+
for col_option in column_options:
|
71 |
+
matched_col = find_matching_column([col_option])
|
72 |
+
if matched_col:
|
73 |
+
self.satisfaction_columns.append(matched_col)
|
74 |
+
self.satisfaction_short_names.append(short_name)
|
75 |
+
break
|
76 |
+
|
77 |
+
if not matched_col:
|
78 |
+
st.warning(f"Could not find column for {short_name}")
|
79 |
+
|
80 |
def calculate_age(self, birth_year_column):
|
81 |
"""🔢 計算年齡(從民國年到實際年齡)"""
|
82 |
# 獲取當前年份(西元年)
|
|
|
96 |
def generate_report(self, df: pd.DataFrame) -> Dict[str, Any]:
|
97 |
"""📝 生成問卷調查報告"""
|
98 |
# 計算年齡
|
99 |
+
age_column = '2.出生年(民國__年)'
|
100 |
+
# 找到最接近的年齡欄位
|
101 |
+
possible_age_columns = [
|
102 |
+
'2.出生年(民國__年)',
|
103 |
+
'出生年',
|
104 |
+
'出生年(民國__年)'
|
105 |
+
]
|
106 |
+
for col in possible_age_columns:
|
107 |
+
if col in df.columns:
|
108 |
+
age_column = col
|
109 |
+
break
|
110 |
+
|
111 |
+
ages = self.calculate_age(df[age_column])
|
112 |
|
113 |
# 取得教育程度分布(帶計數單位)
|
114 |
+
education_column = '3.教育程度'
|
115 |
+
# 找到最接近的教育程度欄位
|
116 |
+
possible_education_columns = [
|
117 |
+
'3.教育程度',
|
118 |
+
'教育程度'
|
119 |
+
]
|
120 |
+
for col in possible_education_columns:
|
121 |
+
if col in df.columns:
|
122 |
+
education_column = col
|
123 |
+
break
|
124 |
+
|
125 |
+
education_counts = df[education_column].value_counts().to_dict()
|
126 |
education_with_counts = {k: f"{v}人" for k, v in education_counts.items()}
|
127 |
|
128 |
# 性別分布(帶計數單位)
|
129 |
+
gender_column = '1. 性別'
|
130 |
+
# 找到最接近的性別欄位
|
131 |
+
possible_gender_columns = [
|
132 |
+
'1. 性別',
|
133 |
+
'性別'
|
134 |
+
]
|
135 |
+
for col in possible_gender_columns:
|
136 |
+
if col in df.columns:
|
137 |
+
gender_column = col
|
138 |
+
break
|
139 |
+
|
140 |
+
gender_counts = df[gender_column].value_counts().to_dict()
|
141 |
gender_with_counts = {k: f"{v}人" for k, v in gender_counts.items()}
|
142 |
|
143 |
# 計算每個滿意度���目的平均分數和標準差
|
|
|
209 |
"""🟠 性別分佈圓餅圖(使用藍色和紅色)"""
|
210 |
# 過濾數據
|
211 |
filtered_df = df.copy()
|
212 |
+
|
213 |
+
# 場域篩選
|
214 |
+
venue_column = '場域名稱'
|
215 |
+
possible_venue_columns = ['場域名稱', 'venue']
|
216 |
+
for col in possible_venue_columns:
|
217 |
+
if col in filtered_df.columns:
|
218 |
+
venue_column = col
|
219 |
+
break
|
220 |
+
|
221 |
if venues and '全部' not in venues:
|
222 |
+
filtered_df = filtered_df[filtered_df[venue_column].isin(venues)]
|
223 |
+
|
224 |
+
# 月份篩選
|
225 |
+
month_column = '月份'
|
226 |
+
possible_month_columns = ['月份', 'month']
|
227 |
+
for col in possible_month_columns:
|
228 |
+
if col in filtered_df.columns:
|
229 |
+
month_column = col
|
230 |
+
break
|
231 |
+
|
232 |
if month and month != '全部':
|
233 |
+
filtered_df = filtered_df[filtered_df[month_column] == month]
|
234 |
+
|
235 |
+
# 性別欄位
|
236 |
+
gender_column = '1. 性別'
|
237 |
+
possible_gender_columns = ['1. 性別', '性別']
|
238 |
+
for col in possible_gender_columns:
|
239 |
+
if col in filtered_df.columns:
|
240 |
+
gender_column = col
|
241 |
+
break
|
242 |
+
|
243 |
+
gender_counts = filtered_df[gender_column].value_counts().reset_index()
|
244 |
gender_counts.columns = ['性別', '人數']
|
245 |
|
246 |
# 計算百分比
|
|
|
298 |
# 上傳 CSV 檔案
|
299 |
uploaded_file = st.file_uploader("上傳 CSV 檔案", type=['csv'])
|
300 |
|
301 |
+
# 初始化數據和分析器
|
302 |
+
df = None
|
303 |
+
analyzer = None
|
304 |
+
|
305 |
+
# 檢查是否有上傳檔案
|
306 |
if uploaded_file is not None:
|
|
|
307 |
try:
|
308 |
df = pd.read_csv(uploaded_file, encoding='utf-8')
|
309 |
+
st.success("CSV 檔案上傳成功!")
|
310 |
+
except Exception as e:
|
311 |
+
st.error(f"無法讀取檔案:{e}")
|
312 |
+
return
|
313 |
+
|
314 |
+
# 如果沒有上傳檔案,提供使用預設數據的選項
|
315 |
+
if df is None:
|
316 |
+
if st.button('使用預設範例數據'):
|
317 |
+
df = read_google_sheet(sheet_id, gid)
|
318 |
|
319 |
+
if df is None:
|
320 |
+
st.error("無法讀取預設數據,請上傳 CSV 檔案")
|
321 |
+
return
|
|
|
|
|
322 |
|
323 |
+
# 如果有數據,則進行分析
|
324 |
+
if df is not None:
|
325 |
+
analyzer = SurveyAnalyzer(df)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
326 |
|
327 |
# 新增場域和月份篩選器
|
328 |
st.sidebar.header("🔍 數據篩選")
|
329 |
|
330 |
+
# 場域篩選
|
331 |
+
venue_column = '場域名稱'
|
332 |
+
possible_venue_columns = ['場域名稱', 'venue']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|