两个新闻源发布新闻时间折线图对比

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates

# 读取数据
laos_data = pd.read_excel("A.xlsx")
indonesia_data = pd.read_excel("B.xlsx")

# 确保日期列是datetime类型
laos_data['时间'] = pd.to_datetime(A_data['时间'])
indonesia_data['时间'] = pd.to_datetime(B_data['时间'])

# 根据日期对文章数量进行分组统计，按季度采样
laos_article_count = A_data.groupby(laos_data['时间'].dt.to_period('Q')).size()
indonesia_article_count = Bdata.groupby(indonesia_data['时间'].dt.to_period('Q')).size()

# 获取季度第一个月和最后一个月的日期
A_dates = A_article_count.index.to_timestamp()
B_dates = A_article_count.index.to_timestamp() + pd.DateOffset(months=2)

# 绘制对比图表
plt.figure(figsize=(12, 6))
plt.plot(A_dates, A_article_count.values, marker='o', label='A News')
plt.plot(B_dates, B_article_count.values, marker='o', label='B News')
plt.xlabel("Quarter")
plt.ylabel("Number of Articles")
plt.title("Comparison of Article Publications between A News and B News")
plt.legend()

# 在每个数据点上显示标签数量
for i, txt in enumerate(A_article_count.values):
    plt.annotate(txt, (A_dates[i], A_article_count.values[i]), textcoords="offset points", xytext=(0, 10), ha='center')

for i, txt in enumerate(B_article_count.values):
    plt.annotate(txt, (B_dates[i], B_article_count.values[i]), textcoords="offset points", xytext=(0, 10), ha='center')

# 格式化季度显示为年份和季度的组合
ax = plt.gca()
ax.xaxis.set_major_locator(mdates.YearLocator())
ax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%b'))

plt.xticks(rotation=45)
plt.tight_layout()
plt.show()