pandas cut

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

# 使用pandas的cut函数划分年龄组
ages = [20,22,25,27,21,23,37,31,61,45,32]
bins = [18,25,35,60,100]
cats = pd.cut(ages,bins)
print(cats)

[(18, 25], (18, 25], (18, 25], (25, 35], (18, 25], ..., (35, 60], (25, 35], (60, 100], (35, 60], (25, 35]]
Length: 11
Categories (4, interval[int64]): [(18, 25] < (25, 35] < (35, 60] < (60, 100]]

cats.codes

array([0, 0, 0, 1, 0, 0, 2, 1, 3, 2, 1], dtype=int8)

pd.value_counts(cats)

(18, 25]     5
(25, 35]     3
(35, 60]     2
(60, 100]    1
dtype: int64

pd.cut(ages,bins,right=False)

[[18, 25), [18, 25), [25, 35), [25, 35), [18, 25), ..., [35, 60), [25, 35), [60, 100), [35, 60), [25, 35)]
Length: 11
Categories (4, interval[int64]): [[18, 25) < [25, 35) < [35, 60) < [60, 100)]

group_names = ['Youth','YoungAdult','MiddleAged','Senior']
pd.cut(ages,bins,labels=group_names)

[Youth, Youth, Youth, YoungAdult, Youth, ..., MiddleAged, YoungAdult, Senior, MiddleAged, YoungAdult]
Length: 11
Categories (4, object): [Youth < YoungAdult < MiddleAged < Senior]

  bins = np.array(['%.2f' % p for p in np.arange(-0.7, 1.2, 0.1) ]).astype('float64')
    cats = pd.cut(ret,bins, include_lowest=True)
#     print(cats)
    cats_value_counts = pd.value_counts(cats)
#     print(cats_value_counts)
    
    plt.ylabel('Count' )
    plt.xlabel('Nasdaq Year Return' )
    ax = cats.value_counts().plot.bar(rot=0, color="b", figsize=(25, 18))

http://www.waitingfy.com/archives/5214

pandas | RSS 2.0 | Respond | Trackback |