Create app.py

app.py

@@ -0,0 +1,168 @@
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+import numpy as np
+from plotly.subplots import make_subplots
+import streamlit as st
+
+# 讀取數據
+@st.cache_data
+def load_data():
+    df = pd.read_csv('booking_hotels_tainan.csv')
+    
+    # 數據預處理
+    def clean_rating(x):
+        if pd.isna(x) or x == '無評分':
+            return 0
+        return float(str(x).replace('分數', '').replace('分', ''))
+    
+    # 清理評分數據
+    df['評分'] = df['評分'].apply(clean_rating)
+    
+    # 創建價格區間
+    df['價格區間'] = pd.qcut(df['價格'], 
+                         q=3, 
+                         labels=['經濟型', '中價位', '高價位'])
+    return df
+
+df = load_data()
+
+def create_price_rating_scatter():
+    """價格vs評分散點圖"""
+    fig = px.scatter(
+        df,
+        x='價格',
+        y='評分',
+        text='飯店名稱',
+        size='價格',  # 點的大小根據價格變化
+        color='評分',  # 顏色根據評分變化
+        title='台南飯店價格與評分關係圖',
+        labels={'價格': '房價 (TWD)', '評分': '評分 (0-10)'}
+    )
+    
+    fig.update_traces(
+        textposition='top center',
+        marker=dict(sizeref=2.*max(df['價格'])/(40.**2))
+    )
+    
+    fig.update_layout(
+        height=600,
+        showlegend=True,
+        title_x=0.5,
+        title_font_size=20
+    )
+    
+    return fig
+
+def create_price_distribution():
+    """價格分布圖"""
+    fig = go.Figure()
+    
+    # 添加直方圖
+    fig.add_trace(go.Histogram(
+        x=df['價格'],
+        name='價格分布',
+        nbinsx=10,
+        marker_color='rgb(55, 83, 109)'
+    ))
+    
+    # 添加箱型圖
+    fig.add_trace(go.Box(
+        x=df['價格'],
+        name='價格箱型圖',
+        marker_color='rgb(26, 118, 255)'
+    ))
+    
+    fig.update_layout(
+        title_text='台南飯店價格分布',
+        title_x=0.5,
+        title_font_size=20,
+        xaxis_title='價格 (TWD)',
+        yaxis_title='數量',
+        height=500,
+        bargap=0.2,
+        showlegend=True
+    )
+    
+    return fig
+
+def create_rating_box_by_price_range():
+    """不同價格區間的評分箱型圖"""
+    fig = px.box(
+        df,
+        x='價格區間',
+        y='評分',
+        title='不同價格區間的評分分布',
+        labels={'價格區間': '價格類型', '評分': '評分 (0-10)'},
+        color='價格區間'
+    )
+    
+    fig.update_layout(
+        title_x=0.5,
+        title_font_size=20,
+        height=500,
+        showlegend=False
+    )
+    
+    return fig
+
+def create_hotel_comparison():
+    """飯店評分與價格比較圖"""
+    fig = make_subplots(specs=[[{"secondary_y": True}]])
+    
+    # 排序數據
+    df_sorted = df.sort_values('評分', ascending=True)
+    
+    # 添加評分柱狀圖
+    fig.add_trace(
+        go.Bar(
+            x=df_sorted['飯店名稱'],
+            y=df_sorted['評分'],
+            name="評分",
+            marker_color='rgb(55, 83, 109)'
+        )
+    )
+    
+    # 添加價格線圖
+    fig.add_trace(
+        go.Scatter(
+            x=df_sorted['飯店名稱'],
+            y=df_sorted['價格'],
+            name="價格",
+            marker_color='rgb(26, 118, 255)'
+        ),
+        secondary_y=True
+    )
+    
+    fig.update_layout(
+        title_text='台南飯店評分與價格比較',
+        title_x=0.5,
+        title_font_size=20,
+        height=700,
+        showlegend=True,
+        xaxis_tickangle=45
+    )
+    
+    fig.update_yaxes(title_text="評分", secondary_y=False)
+    fig.update_yaxes(title_text="價格 (TWD)", secondary_y=True)
+    
+    return fig
+
+def main():
+    st.set_page_config(page_title="台南飯店分析", layout="wide")
+    st.title("台南飯店分析")
+    
+    scatter_fig = create_price_rating_scatter()
+    dist_fig = create_price_distribution()
+    box_fig = create_rating_box_by_price_range()
+    comparison_fig = create_hotel_comparison()
+    
+    st.plotly_chart(scatter_fig, use_container_width=True)
+    st.plotly_chart(dist_fig, use_container_width=True)
+    st.plotly_chart(box_fig, use_container_width=True)
+    st.plotly_chart(comparison_fig, use_container_width=True)
+    
+    st.write("分析完成！請查看上方產生的互動式視覺化圖表。")
+
+if __name__ == "__main__":
+    main()