构建基于数据分析系统的源码实践

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

]]>

# 加载示例数据集

data = pd.read_csv('sample_data.csv')

print(data.head())

]]>

# 显示统计数据

statistics = data.describe()

print(statistics)

]]>

# 绘制直方图

plt.hist(data['value'], bins=20, color='blue', alpha=0.7)

plt.title('Data Distribution')

plt.xlabel('Value')

plt.ylabel('Frequency')

plt.show()

]]>

# 按类别分组并绘制条形图

grouped_data = data.groupby('category')['value'].mean()

grouped_data.plot(kind='bar', color=['red', 'green', 'blue'])

plt.title('Average Value by Category')

plt.xlabel('Category')

plt.ylabel('Average Value')

plt.show()

]]>