关于map的一些用法总结

1.  

data = [{"a": 1, "b": 2, "c": 3}, 
        {"a": 11, "b": 22, "c": 33}, 
        {"a": 111, "b": 222, "c": 333}]
df = pd.DataFrame(data)
df

df['stat'] = df['a'].map(lambda x: 'big' if x > 100 else 'small')
df

2. 

def func(i):
    return 'big' if i > 100 else 'small'


df['b_stat'] = df['b'].map(func)
df

3. 分组聚合

data = [{"a": 1, "b": 2, "c": 3, "e": 4}, 
        {"a": 11, "b": 22, "c": 33,"e": 4}, 
        {"a": 111, "b": 222, "c": 333, "e": 41},
        {"a": 1, "b": 21, "c": 3, "e": 41}, 
        {"a": 11, "b": 22, "c": 33}, 
        {"a": 111, "b": 23, "c": 333},
        {"a": 1, "b": 2, "c": 3, "e": 4}, 
        {"a": 11, "b": 22, "c": 33}, 
        {"a": 111, "b": 24, "c": 333},
       ]
import pandas as pd
df = pd.DataFrame(data)
df

 

df = df.groupby(['a', 'b']).agg({'c': 'count', 'e': 'sum'}).reset_index(drop=False)
df