pandas之聚合运算

通过聚合运算可以得到我们比较感兴趣的数据以方便处理

import pandas as pd
import numpy as np

# 先创建一组数据表DataFrame
df = pd.DataFrame({'key1':['a','a','b','b','a'],
                  'key2':['one','two','one','two','one'],
                  'data1':np.random.randint(1,10,5),
                  'data2':np.random.randint(1,10,5)})
# 这组数据的key1列与key2列有相同的有各自相同的索引行

df.groupby('key1').describe()  
# 通过这一行我们可以看到关于key1列分组后的一些计算结果，
# count  mean std min 25% 50% 75% max

grouped = df.groupby('key1')
# 它返回的是DataFrom对象

def peak_range(s):
    print(type(s))
    return s.max() - s.min()

# 接下来就是看看聚合的应用了
grouped.agg(['std','mean','sum',('range',peak_range)])
# 这个函数聚合了df.groupby('key1').describe()所展现的一些计算结果
# ('range',peak_range)中的range是peak_range函数计算结果的列名


# 通过创建字典进行聚合自己想要的部分数据
d = {'data1':'mean',
    'data2':'sum'}
grouped.agg(d)

d = {'data1':['mean',('range',peak_range)],
    'data2':'sum'}
grouped.agg(d)
grouped.agg(d).reset_index()  # 不把key1作为索引来处理
df.groupby('key1',as_index=False).agg(d)  # 与上一行效果一样

import pandas as pd
import numpy as np

# 先创建一个DataFrame
df = pd.DataFrame({'key1':['a','a','b','b','a'],
                  'key2':['one','two','one','two','one'],
                  'data1':np.random.randint(1,10,5),
                  'data2':np.random.randint(1,10,5)})
# 合并方式一
k1_mean = df.groupby('key1').mean().add_prefix('mean_')
# 将key1分组取均值，并将data1与data2之前加上mean_
pd.merge(df, k1_mean, left_on='key1',right_index=True)  # 通过merge合并

k1_mean = df.groupby('key1').transform(np.mean).add_prefix('mean_')
# 它通过分组求平均，保持原来的索引位置与行数
# 这样可以通过下面的代码实现合并
df[k1_mean.columns] = k1_mean

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.randint(1,10,(5,5)),
                 columns=['a','b','c','d','e'],
                 index=['Alice','Bob','Candy','Dark','Emily'])

def demean(s):
    return s - s.mean()

key = ['one','one','two','one','two']
demeaned = df.groupby(key).transform(demean)

demeaned.groupby(key).mean()  # 输出的值都是0或者接近0

import pandas as pd
import numpy as np

df = pd.DataFrame({'key1':['a','a','b','b','a','a','a','b','b','a'],
                  'key2':['one','two','one','two','one','one','two','one','two','one'],
                  'data1':np.random.randint(1,10,10),
                  'data2':np.random.randint(1,10,10)})


def top(g, n=2, column='data1'):
    return g.sort_values(by=column,ascending=False)[:n]

df.groupby('key1').apply(top, n=3, column='data2')
# 分组后只对data2列的值排序取出前三行

import pandas as pd
import numpy as np

# 下面的例子是填充NaN值的方法

states = ['Ohio','New York','Vermont','Florida',
         'Oregon','Nevada','California','Idaho']
group_key = ['East'] * 4 + ['West'] * 4
data = pd.Series(np.random.randn(8), index=states)
data[['Vermont','Nevada','Idaho']] = np.nan
# 输出
Ohio          0.133410
New York      2.147483
Vermont            NaN
Florida      -0.608754
Oregon        0.978375
Nevada             NaN
California   -1.297183
Idaho              NaN
dtype: float64

data.groupby(group_key).mean()
# 输出
East    0.557380
West   -0.159404
dtype: float64

data.groupby(group_key).apply(lambda g: g.fillna(g.mean()))
# 输出
Ohio          0.133410
New York      2.147483
Vermont       0.557380
Florida      -0.608754
Oregon        0.978375
Nevada       -0.159404
California   -1.297183
Idaho        -0.159404
dtype: float64