blibliCrawler/addition_2.py

# 导入必要的库
import requests
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import folium
from folium.plugins import HeatMap
import streamlit as st
from datetime import datetime, timedelta


# 第一步：数据收集
def fetch_earthquake_data(min_magnitude=4.5, start_time=None, end_time=None):
    url = 'https://earthquake.usgs.gov/fdsnws/event/1/query'
    if not start_time:
        start_time = (datetime.utcnow() - timedelta(days=30)).strftime("%Y-%m-%d")
    if not end_time:
        end_time = datetime.utcnow().strftime("%Y-%m-%d")
    params = {
        'format': 'geojson',
        'starttime': start_time,
        'endtime': end_time,
        'minmagnitude': min_magnitude
    }
    response = requests.get(url, params=params)
    data = response.json()
    features = data['features']
    # 提取所需信息
    earthquakes = []
    for feature in features:
        properties = feature['properties']
        geometry = feature['geometry']
        earthquakes.append({
            'time': pd.to_datetime(properties['time'], unit='ms'),
            'place': properties['place'],
            'magnitude': properties['mag'],
            'depth': geometry['coordinates'][2],
            'latitude': geometry['coordinates'][1],
            'longitude': geometry['coordinates'][0]
        })
    return pd.DataFrame(earthquakes)


# 第二步：数据分析和可视化函数
def plot_magnitude_distribution(df):
    plt.figure(figsize=(10, 6))
    sns.histplot(df['magnitude'], bins=20, kde=True)
    plt.title('magnitude distribution histogram')
    plt.xlabel('magnitude')
    plt.ylabel('frequency')
    st.pyplot(plt)


def plot_time_series(df):
    df_time = df.set_index('time').resample('D').count()
    plt.figure(figsize=(10, 6))
    plt.plot(df_time.index, df_time['magnitude'])
    plt.title('daily earthquake count time series')
    plt.xlabel('date')
    plt.ylabel('number of earthquakes')
    st.pyplot(plt)


def create_interactive_map(df):
    map_center = [df['latitude'].mean(), df['longitude'].mean()]
    base_map = folium.Map(location=map_center, zoom_start=2)
    # 添加地震位置点
    for _, row in df.iterrows():
        folium.CircleMarker(
            location=[row['latitude'], row['longitude']],
            radius=row['magnitude'] * 1.5,
            popup=f"Magnitude: {row['magnitude']}, Depth: {row['depth']} km",
            color='red',
            fill=True,
            fill_color='red'
        ).add_to(base_map)
    # 添加热力图
    heat_data = [[row['latitude'], row['longitude']] for _, row in df.iterrows()]
    HeatMap(heat_data).add_to(base_map)
    return base_map


# 第三步：制作Streamlit应用
def main(streamlit_folium=None):
    st.title("全球地震数据分析与可视化")

    # 侧边栏参数选择
    st.sidebar.header("参数设置")
    min_magnitude = st.sidebar.slider("最小震级", 0.0, 10.0, 4.5, 0.1)
    days = st.sidebar.slider("过去多少天的数据", 1, 90, 30)

    # 获取数据
    start_time = (datetime.utcnow() - timedelta(days=days)).strftime("%Y-%m-%d")
    end_time = datetime.utcnow().strftime("%Y-%m-%d")
    df = fetch_earthquake_data(min_magnitude=min_magnitude, start_time=start_time, end_time=end_time)

    st.subheader(f"从{start_time}到{end_time}，震级大于{min_magnitude}的地震数据，共{len(df)}条")
    st.map(df[['latitude', 'longitude']])

    # 显示数据表
    if st.checkbox("显示原始数据表"):
        st.write(df)

    # 震级分布直方图
    st.subheader("震级分布直方图")
    plot_magnitude_distribution(df)

    # 时间序列图
    st.subheader("每日地震数量时间序列")
    plot_time_series(df)

    # 交互式地图
    st.subheader("地震分布交互式地图")
    folium_map = create_interactive_map(df)
    # 将Folium地图嵌入Streamlit
    from streamlit_folium import st_folium
    st_data = st_folium(folium_map, width=700)


if __name__ == "__main__":
    main()