# 导入必要库
import streamlit as st
import pandas as pd
import altair as alt

# 数据加载函数（带缓存）
@st.cache_data  # 使用Streamlit缓存加速重复加载
def load_data():
    # 从GitHub原始地址加载数据
    url = "https://raw.githubusercontent.com/UIUC-iSchool-DataViz/is445_data/main/bfro_reports_fall2022.csv"
    df = pd.read_csv(url)
    
    # 日期处理（转换为datetime格式并提取年份）
    df['date'] = pd.to_datetime(df['date'], errors='coerce')  # 转换错误设为NaT
    df['year'] = df['date'].dt.year  # 提取年份
    
    # 过滤无效年份（1900年之前的数据视为异常）
    df = df[df['year'] > 1900]
    
    return df

# 主程序
def main():
    # 设置页面标题
    st.title("Bigfoot Sighting Analysis Report")
    
    # 加载数据
    df = load_data()
    
    # --- 数据概览部分 ---
    st.header("Dataset Overview")
    st.write(f"Total records: {len(df)}")
    st.write(f"Time range: {int(df['year'].min())} - {int(df['year'].max())}")
    
    # --- 第一个可视化：年度趋势 ---
    st.header("Visualization 1: Yearly Sighting Trends")
    
    # 准备数据：按年份分组计数
    yearly_counts = df.groupby('year').size().reset_index(name='counts')
    
    # 创建Altair图表
    chart1 = alt.Chart(yearly_counts).mark_bar().encode(
        x=alt.X('year:O', title="Year"),  # 离散年份
        y=alt.Y('counts:Q', title="Number of Reports"),  # 数量统计
        color=alt.Color('year:O', legend=None),  # 按年份着色
        tooltip=['year', 'counts']  # 悬浮提示
    ).properties(
        width=600,
        height=300
    )
    
    # 显示图表
    st.altair_chart(chart1)
    
    # 图表描述（英文）
    st.write("""
    **Yearly Trend Analysis**  
    This bar chart shows the number of reported sightings per year. Key design choices:
    - Discrete years on X-axis for clear temporal segmentation
    - Color gradient enhances perception of time progression
    - Fixed bar width ensures visual consistency
    
    Potential improvements:
    - Add moving average line for trend visualization
    - Implement interactive year-range selection
    """)
    
    # --- 第二个可视化：各州分布 ---
    st.header("Visualization 2: State Distribution")
    
    # 准备数据：各州计数（取前10）
    state_counts = df['state'].value_counts().reset_index()
    state_counts.columns = ['state', 'counts']
    top_states = state_counts.head(10)
    
    # 创建Altair图表
    chart2 = alt.Chart(top_states).mark_bar().encode(
        y=alt.Y('state:N', title="State", sort='-x'),  # 按数量降序排列
        x=alt.X('counts:Q', title="Number of Reports"),
        color=alt.Color('state:N', legend=None)  # 按州着色
    ).properties(
        width=600,
        height=400
    )
    
    # 显示图表
    st.altair_chart(chart2)
    
    # 图表描述（英文）
    st.write("""
    **Geographic Distribution Analysis**  
    This horizontal bar chart displays the top 10 states with most sightings. Key features:
    - Horizontal orientation improves state name readability
    - Descending sort emphasizes high-frequency states
    - Categorical coloring enhances visual distinction
    
    Potential improvements:
    - Add map-based visualization
    - Normalize data by population density
    """)

# 主程序入口
if __name__ == "__main__":
    main()