Python报表自动化之从数据到可视化一站式指南

import pandas as pd
# 从CSV文件加载数据
data = pd.read_csv('sales_data.csv')
# 数据清洗和处理
# ...
# 打印数据摘要
print(data.head())

# 计算销售额统计信息
sales_stats = data.groupby('Product')['Sales'].agg(['sum', 'mean', 'count'])

# 打印销售统计
print(sales_stats)

from jinja2 import Environment, FileSystemLoader
# 使用Jinja2加载报表模板
env = Environment(loader=FileSystemLoader('.'))
template = env.get_template('report_template.html')
# 渲染报表
report_content = template.render(sales_stats=sales_stats)
# 将报表写入HTML文件
with open('sales_report.html', 'w') as report_file:
    report_file.write(report_content)

import matplotlib.pyplot as plt

# 绘制销售额柱状图
plt.bar(sales_stats.index, sales_stats['sum'])
plt.xlabel('Product')
plt.ylabel('Total Sales')
plt.title('Sales Report')

# 保存图表为图片
plt.savefig('sales_chart.png')

# automate_report.py
import pandas as pd
from jinja2 import Environment, FileSystemLoader
import matplotlib.pyplot as plt
# 数据处理
data = pd.read_csv('sales_data.csv')
# ...
# 数据统计
sales_stats = data.groupby('Product')['Sales'].agg(['sum', 'mean', 'count'])
# ...
# 报表生成
env = Environment(loader=FileSystemLoader('.'))
template = env.get_template('report_template.html')
report_content = template.render(sales_stats=sales_stats)
with open('sales_report.html', 'w') as report_file:
    report_file.write(report_content)
# 数据可视化
plt.bar(sales_stats.index, sales_stats['sum'])
plt.xlabel('Product')
plt.ylabel('Total Sales')
plt.title('Sales Report')
plt.savefig('sales_chart.png')

# automate_report.ipynb
# 数据处理
import pandas as pd
data = pd.read_csv('sales_data.csv')
# ...
# 数据统计
sales_stats = data.groupby('Product')['Sales'].agg(['sum', 'mean', 'count'])
# ...
# 报表生成
from jinja2 import Environment, FileSystemLoader
env = Environment(loader=FileSystemLoader('.'))
template = env.get_template('report_template.html')
report_content = template.render(sales_stats=sales_stats)
with open('sales_report.html', 'w') as report_file:
    report_file.write(report_content)
# 数据可视化
import matplotlib.pyplot as plt
plt.bar(sales_stats.index, sales_stats['sum'])
plt.xlabel('Product')
plt.ylabel('Total Sales')
plt.title('Sales Report')
plt.savefig('sales_chart.png')