pandas高级用法

import pandas as pd
# 创建多级索引
index = pd.MultiIndex.from_arrays([['A', 'A', 'A', 'B', 'B', 'B'], [1, 2, 3, 1, 2, 3]], names=['group', 'number'])
# 创建DataFrame
data = {'value1': [10, 20, 30, 40, 50, 60], 'value2': [100, 200, 300, 400, 500, 600]}
df = pd.DataFrame(data, index=index)

import pandas as pd
# 创建DataFrame
data = {'name': ['Tom', 'Jerry', 'Mickey'], 'gender': ['M', 'M', 'F'], 'age': [25, 30, 35], 'score': [80, 90, 95]}
df = pd.DataFrame(data)
# 创建透视表
pivot_table = pd.pivot_table(df, values='score', index='gender', columns='age', aggfunc='mean')

import pandas as pd
# 创建时间序列
dates = pd.date_range('2021-01-01', '2021-01-31', freq='D')
# 创建DataFrame
df = pd.DataFrame({'date': dates, 'value': [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160, 170, 180, 190, 200, 210, 220, 230, 240, 250, 260, 270, 280, 290, 300, 310]})
# 将date列设置为索引
df.set_index('date', inplace=True)

import pandas as pd
# 创建DataFrame
df = pd.DataFrame({'name': ['Tom', 'Jerry', 'Mickey'], 'gender': ['M', 'M', 'F'], 'age': [25, 30, 35], 'score': [80, 90, 95]})
# 将gender列转换为分类数据类型
df['gender'] = pd.Categorical(df['gender'], categories=['M', 'F'])
# 对分类数据进行排序
df.sort_values(by='gender')

import pandas as pd
# 创建DataFrame
data = {'value': [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]}
df = pd.DataFrame(data)
# 创建窗口对象
window = df.rolling(window=3)
# 计算滑动窗口平均值
df['rolling_mean'] = window.mean()