在matplotlib中拆分大型数据集并绘制平均值

import matplotlib.pyplot as plt
import numpy as np

data = np.random.rand(10000)  # 生成10000个随机数的数据集

subset_size = 100  # 每个子集的大小
num_subsets = len(data) // subset_size  # 子集的数量
averages = np.zeros(num_subsets)  # 存储每个子集的平均值

# 计算每个子集的平均值
for i in range(num_subsets):
    subset = data[i * subset_size : (i + 1) * subset_size]
    averages[i] = np.mean(subset)

plt.plot(averages)
plt.xlabel("Subset")
plt.ylabel("Average")
plt.title("Average of Subsets in Large Dataset")
plt.show()