Pandas数据透视表pivot_table的使用小结

pandas.pivot_table(
    data,
    values=None,
    index=None,
    columns=None,
    aggfunc='mean',
    fill_value=None,
    margins=False,
    dropna=True,
    margins_name='All',
    observed=False,   # pandas 2.2+ 建议显式设为 True
    sort=True
)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    "A": ["foo", "foo", "foo", "foo", "foo", "bar", "bar", "bar", "bar"],
    "B": ["one", "one", "one", "two", "two", "one", "one", "two", "two"],
    "C": ["small", "large", "large", "small", "small", "large", "small", "small", "large"],
    "D": [1, 2, 2, 3, 3, 4, 5, 6, 7],
    "E": [2, 4, 5, 5, 6, 6, 8, 9, 9]
})

table = pd.pivot_table(df, values='D', index=['A', 'B'],
                       columns=['C'], aggfunc="sum")
# C        large  small
# A   B
# bar one    4.0    5.0
#     two    7.0    6.0
# foo one    4.0    1.0
#     two    NaN    6.0

table = pd.pivot_table(df, values='D', index=['A', 'B'],
                       columns=['C'], aggfunc="sum", fill_value=0)

table = pd.pivot_table(df, values=['D', 'E'], index=['A', 'C'],
                       aggfunc={'D': 'mean', 'E': ['min', 'max', 'mean']})
# 结果列变成多层，E 列下挂三个子列

data = {
    '地区': ['华东', '华东', '华北', '华北', '华南', '华南'],
    '产品': ['A', 'B', 'A', 'B', 'A', 'B'],
    '季度': [1, 1, 1, 2, 2, 2],
    '销售额': [150000, 120000, 90000, 110000, 130000, 95000],
    '利润':  [30000,  24000,  18000,  22000,  26000,  19000]
}
df_sales = pd.DataFrame(data)

pivot = pd.pivot_table(
    data=df_sales,
    values=['销售额', '利润'],
    index='季度',
    columns='地区',
    aggfunc='sum',
    fill_value=0,
    margins=True,
    margins_name='总计'
)
print(pivot)

df['月份'] = df['日期'].dt.month

pivot = pd.pivot_table(
    data=df,
    index=['地区', '月份'],   # 两级行索引
    columns='产品',
    values='销售额',
    aggfunc='sum'
)

pivot.xs('华东', level='地区')   # 只看华东的数据

pivot = pd.pivot_table(
    data=df_user,
    index='用户等级',
    columns='访问渠道',
    values='访问次数',
    aggfunc=['sum', 'mean'],
    fill_value=0
)

pivot = pd.pivot_table(df, values='D', index='A',
                       aggfunc=lambda x: x.max() - x.min())

pivot = pd.pivot_table(df, values='D', index='A',
                       aggfunc=['sum', 'mean', 'count', np.std])

pivot.columns = ['_'.join(col).strip() for col in pivot.columns.values]
# 原来的 ('sum', 'D') 变成 'sum_D'，清爽很多

result = (
    pd.pivot_table(df, values='销售额', index='地区', aggfunc='sum')
    .reset_index()
    .sort_values('销售额', ascending=False)
    .query('销售额 > 100000')
)

import pandas as pd
import numpy as np

np.random.seed(42)
n = 200
df = pd.DataFrame({
    '地区':    np.random.choice(['华东', '华北', '华南', '西部'], n),
    '产品类别': np.random.choice(['电子', '服装', '食品'], n),
    '季度':    np.random.choice([1, 2, 3, 4], n),
    '销售额':  np.random.randint(1000, 50000, n),
    '利润':    np.random.randint(100, 10000, n),
    '订单数':  np.random.randint(1, 100, n)
})

# 多维透视：行=地区+季度，列=产品类别
# 销售额求和，利润求均值，末尾加总计
pivot = pd.pivot_table(
    data=df,
    values=['销售额', '利润'],
    index=['地区', '季度'],
    columns='产品类别',
    aggfunc={'销售额': 'sum', '利润': 'mean'},
    fill_value=0,
    margins=True,
    margins_name='汇总'
)

# 扁平化列名，方便后续处理
pivot.columns = ['_'.join(col) for col in pivot.columns]
print(pivot.head(10))

# 单独看华东的数据
print(pivot.xs('华东', level='地区'))