import pandas as pd

# 读取数据
data = pd.read_csv('dataset.csv')

# 处理缺失值
data['Age'].fillna(data['Age'].median(), inplace=True)

# 筛选数据
filtered = data.query('Age > 30 & Salary > 50000')

# 分组聚合
result = filtered.groupby('Department')['Salary'].mean()

# 输出结果
print(result)

library(dplyr)

# 读取数据
data <- read.csv('dataset.csv')

# 处理缺失值
data$Age[is.na(data$Age)] <- median(data$Age, na.rm = TRUE)

# 筛选数据
filtered <- data %>% 
  filter(Age > 30, Salary > 50000)

# 分组聚合
result <- filtered %>%
  group_by(Department) %>%
  summarise(avg_salary = mean(Salary))

# 输出结果
print(result)