Python实现对相同数据分箱的小技巧分享

[1,1,1,2,2,2,3,3,4,4,5,5,5,5,5]

# 转变为
[[1, 1, 1], [2, 2, 2], [3, 3], [4, 4], [5, 5, 5, 5, 5]]

box = [1,1,1,2,2,2,3,3,4,4,5,5,5,5,5]

last = box[0]
temp = [box[0]]
box_list = [temp]

for a in box[1::]:
    if a == last:
        temp.append(a)
    else:
        last = a
        temp = [a]
        box_list.append(temp)

print(box_list) # [[1, 1, 1], [2, 2, 2], [3, 3], [4, 4], [5, 5, 5, 5, 5]]

# 实现按每一个分箱列表遍历数据（而不用全部遍历）
for boxs in box_list:
    for i in boxs:
        print(i)

box = [('小黑','20','四川'),('小黑','21','北京'),('张三','18','上海'),('张三','22','上海'),('张三','30','北京'),('李四','10','广州')]

# 实现把名字相同的元组放入一个列表
[[('小黑', '20', '四川'), ('小黑', '21', '北京')], [('张三', '18', '上海'), ('张三', '22', '上海'), ('张三', '30', '北京')], [('李四', '10', '广州')]]

box = [('小黑','20','四川'),('小黑','21','北京'),('张三','18','上海'),('张三','22','上海'),('张三','30','北京'),('李四','10','广州')]


last = box[0][0]
temp = [box[0]]
box_list = [temp]

for a in box[1::]:
    if a[0] == last:
        temp.append(a)
    else:
        last = a[0]
        temp = [a]
        box_list.append(temp)
       
print(box_list)    

# 实现按每一个分箱列表遍历数据（而不用全部遍历）
for boxs in box_list:
    for i in boxs:
        print(i[0]) # 0取的姓名，1取年龄，3取地址

import pandas as pd 
import numpy as np 
from pandas import Series,DataFrame

# 随机生成一组数据
score_list = np.random.randint(25,100,size = 20)  # 随机生成最小值25，最大值100的20个数据

# 分箱的区间
bins = [0,59,70,80,100]

# 分箱
score_cat = pd.cut(score_list,bins)

# 统计不同区间的个数
pd.value_counts(score_cat)


# 生成一个空的DataFrame
df = DataFrame()
df['Score'] = score_list
df['Name'] =  [pd.util.testing.rands(5) for i in range(20)] # 生成20个姓名
df['CateGories'] =pd.cut(df['Score'],bins,labels = ['不及格','一般','优秀','厉害']) 
# labels对应的是bins的