Pandas GroupBy Transform：高效数据转换与分组操作

import pandas as pd

# 创建示例数据框
df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, 2, 3, 4, 5]
})

# 使用groupby和transform计算每组的平均值
df['group_mean'] = df.groupby('group')['value'].transform('mean')

print(df)

import pandas as pd

df = pd.DataFrame({
    'website': ['pandasdataframe.com', 'example.com', 'pandasdataframe.com', 'test.com'],
    'visits': [100, 200, 150, 300]
})

# 计算每个网站的访问量占总访问量的百分比
df['percentage'] = df.groupby('website')['visits'].transform(lambda x: x / x.sum() * 100)

print(df)

import pandas as pd

def normalize(x):
    return (x - x.min()) / (x.max() - x.min())

df = pd.DataFrame({
    'category': ['A', 'B', 'A', 'B', 'A'],
    'sales': [100, 200, 150, 250, 180]
})

# 对每个类别的销售额进行归一化
df['normalized_sales'] = df.groupby('category')['sales'].transform(normalize)

print(df)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value1': [1, 2, 3, 4, 5],
    'value2': [10, 20, 30, 40, 50]
})

# 同时对多列进行转换
df[['mean1', 'mean2']] = df.groupby('group')[['value1', 'value2']].transform('mean')

print(df)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, np.nan, 3, np.nan, 5]
})

# 使用分组平均值填充缺失值
df['filled_value'] = df.groupby('group')['value'].transform(lambda x: x.fillna(x.mean()))

print(df)

import pandas as pd

df = pd.DataFrame({
    'website': ['pandasdataframe.com', 'example.com', 'pandasdataframe.com', 'test.com'],
    'visits': [100, 200, 150, 300]
})

# 使用transform
df['mean_visits'] = df.groupby('website')['visits'].transform('mean')

# 使用agg
agg_result = df.groupby('website')['visits'].agg('mean')

print("Transform result:")
print(df)
print("\nAggregation result:")
print(agg_result)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, 2, 3, 4, 5]
})

# 在一个transform调用中使用多个函数
df[['mean', 'max', 'min']] = df.groupby('group')['value'].transform(['mean', 'max', 'min'])

print(df)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [3, 2, 1, 5, 4]
})

# 计算组内排名
df['rank'] = df.groupby('group')['value'].transform('rank', method='dense')

print(df)

import pandas as pd

df = pd.DataFrame({
    'date': pd.date_range(start='2023-01-01', periods=5),
    'website': ['pandasdataframe.com', 'example.com', 'pandasdataframe.com', 'test.com', 'pandasdataframe.com'],
    'visits': [100, 200, 150, 300, 250]
})

# 计算每个网站的3天移动平均访问量
df['moving_avg'] = df.groupby('website')['visits'].transform(lambda x: x.rolling(window=3, min_periods=1).mean())

print(df)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, 2, 3, 4, 5]
})

# 计算组内累积和
df['cumsum'] = df.groupby('group')['value'].transform('cumsum')

print(df)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, 2, 3, 4, 5]
})

# 使用条件逻辑：如果组内值大于组平均值，则标记为1，否则为0
df['above_mean'] = df.groupby('group')['value'].transform(lambda x: (x > x.mean()).astype(int))

print(df)

import pandas as pd

df = pd.DataFrame({
    'date': pd.date_range(start='2023-01-01', periods=5),
    'website': ['pandasdataframe.com', 'example.com', 'pandasdataframe.com', 'test.com', 'pandasdataframe.com'],
    'visits': [100, 200, 150, 300, 250]
})

# 计算每个网站的访问量占比，并标记是否高于平均水平
df['visit_ratio'] = df.groupby('website')['visits'].transform(lambda x: x / x.sum())
df['above_avg'] = df.groupby('website')['visit_ratio'].transform(lambda x: x > x.mean())

print(df)

import pandas as pd

df = pd.DataFrame({
    'date': pd.date_range(start='2023-01-01', periods=10),
    'website': ['pandasdataframe.com', 'example.com'] * 5,
    'visits': [100, 200, 150, 250, 180, 220, 190, 270, 210, 240]
})

# 计算每个网站的7天移动平均访问量
df['7d_ma'] = df.groupby('website')['visits'].transform(lambda x: x.rolling(window='7D').mean())

print(df)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value1': [1, 2, 3, 4, 5],
    'value2': [10, 20, 30, 40, 50]
})

# 计算value1和value2的比率，并与组平均比率比较
df['ratio'] = df.apply(lambda row: row['value1'] / row['value2'], axis=1)
df['above_avg_ratio'] = df.groupby('group').apply(lambda x: x['ratio'] > x['ratio'].mean()).reset_index(level=0, drop=True)

print(df)

import pandas as pd

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, 2, 3, 4, 5]
})

# 对每个组内的数据进行z-score标准化
df['z_score'] = df.groupby('group')['value'].transform(lambda x: (x - x.mean()) / x.std())

print(df)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'group': ['A', 'B', 'A', 'B', 'A'],
    'value': [1, 2, 100, 4, 5]
})

# 将超过3倍标准差的值替换为组平均值
df['cleaned_value'] = df.groupby('group')['value'].transform(lambda x: np.where(np.abs(x - x.mean()) > 3 * x.std(), x.mean(), x))

print(df)