根据提供的数据,我们可以进行以下几个方面的分析:
import pandas as pd
# 假设data为包含所有数据的DataFrame
correlation = data['短视频引流占比'].corr(data['销售额'])
print(f"Correlation between video引流占比 and sales: {correlation}")
top_3_livestreams = data.nlargest(3, '引流人数')
total引流人数 = sum(data['引流人数'])
top_3_total = sum(top_3_livestreams['引流人数'])
# 计算TOP3占比
top_3_ratio = (top_3_total / total引流人数) * 100
print(f"Top 3 livestreams引流占比: {top_3_ratio}%")
# 假设'直播类别'为列名
top_categories = data.nlargest(10, '引流人数')['直播类别'].value_counts(normalize=True)
print("Top categories by high traffic:")
print(top_categories)
# 假设'粉丝数'为列名
correlation = data['粉丝数'].corr(data['销售额'])
print(f"Correlation between follower count and sales: {correlation}")
以上分析数据来源:互联岛