Pandas 透视表和交叉表的实现示例

import pandas as pd

# 创建示例数据

data = {

    'Salesperson': ['Alice', 'Bob', 'Alice', 'Bob', 'Alice', 'Bob'],

    'Product': ['A', 'B', 'A', 'B', 'A', 'B'],

    'Month': [1, 1, 2, 2, 3, 3],

    'Amount': [100, 200, 150, 250, 180, 220]

}

df = pd.DataFrame(data)

# 创建交叉表1：统计销售人员和产品类型的数量

cross_table1 = pd.crosstab(df['Salesperson'], df['Product'])

print("Cross Table 1:")

print(cross_table1)

# 创建交叉表2：统计每个销售人员在每个月份的销售总额

cross_table2 = pd.crosstab(df['Salesperson'], df['Month'], values=df['Amount'], aggfunc='sum')

print("\nCross Table 2:")

print(cross_table2)

# 创建交叉表3：包含行/列边距汇总

cross_table3 = pd.crosstab(df['Salesperson'], df['Product'], margins=True)

print("\nCross Table 3:")

print(cross_table3)

# 创建交叉表4：归一化，将每个值除以每行的总和

cross_table4 = pd.crosstab(df['Salesperson'], df['Product'], normalize='index')

print("\nCross Table 4:")

print(cross_table4)

import pandas as pd

data = {

    'Salesperson': ['Alice', 'Bob', 'Alice', 'Bob', 'Alice', 'Bob'],

    'Product': ['A', 'B', 'A', 'B', 'A', 'B'],

    'Amount': [100, 200, 150, 250, 180, 220]

}

df = pd.DataFrame(data)

# 不进行归一化

cross_table_false = pd.crosstab(df['Salesperson'], df['Product'], normalize=False)

print("Without normalization:")

print(cross_table_false)

# 对每个行进行归一化

cross_table_row = pd.crosstab(df['Salesperson'], df['Product'], normalize='index')

print("\nNormalized by row:")

print(cross_table_row)

# 每个列进行归一化

cross_table_col = pd.crosstab(df['Salesperson'], df['Product'], normalize='columns')

print("\nNormalized by column:")

print(cross_table_col)

# 对整个表进行归一化

cross_table_all = pd.crosstab(df['Salesperson'], df['Product'], normalize='all')

print("\nNormalized by all:")

print(cross_table_all)

import pandas as pd
data = {
    'Salesperson': ['Alice', 'Bob', 'Alice', 'Bob', 'Alice', 'Bob'],
    'Product': ['A', 'B', 'A', 'B', 'A', 'B'],
    'Amount': [100, 200, 150, 250, 180, 220]
}
df = pd.DataFrame(data)
# 创建透视表
pivot_table_basic = pd.pivot_table(df, values='Amount', index='Salesperson', columns='Product', aggfunc='sum', fill_value=0)
print("Basic Pivot Table:")
print(pivot_table_basic)
添加行/列边距汇总
# 创建透视表并添加行/列边距汇总
pivot_table_with_margins = pd.pivot_table(df, values='Amount', index='Salesperson', columns='Product', aggfunc='sum', fill_value=0, margins=True)
print("\nPivot Table with Margins:")
print(pivot_table_with_margins)
# 创建透视表并使用不同的聚合函数
pivot_table_aggfunc = pd.pivot_table(df, values='Amount', index='Salesperson', columns='Product', aggfunc='mean', fill_value=0)
print("\nPivot Table with Different Aggregation Function (mean):")
print(pivot_table_aggfunc)
# 创建透视表并填充缺失值
pivot_table_fill_value = pd.pivot_table(df, values='Amount', index='Salesperson', columns='Product', aggfunc='sum', fill_value='No Sales')
print("\nPivot Table with Fill Value for Missing Data:")
print(pivot_table_fill_value)
# 创建透视表并使用多个行索引和列索引
df['Year'] = pd.to_datetime('today').year
pivot_table_multi_index = pd.pivot_table(df, values='Amount', index=['Salesperson', 'Year'], columns=['Product'], aggfunc='sum', fill_value=0)
print("\nPivot Table with Multiple Index and Columns:")
print(pivot_table_multi_index)