数据挖掘实战一：输入预测分类

# 导入第三方包
import pandas as pd
import numpy as np
import seaborn as sns

# 数据读取
income = pd.read_excel(r'./income.xlsx')
income.head()
#了解数据的大体结构。输出前几行

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
0	39	State-gov	77516	Bachelors	13	Never-married	Adm-clerical	Not-in-family	White	Male	2174	0	40	United-States	<=50K
1	50	Self-emp-not-inc	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	0	13	United-States	<=50K
2	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	0	40	United-States	<=50K
3	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	0	40	United-States	<=50K
4	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	0	40	Cuba	<=50K

# 查看数据集是否存在缺失值
income.apply(lambda x:np.sum(x.isnull()))
##info()用来查看数据是否有缺失值，以及数据类型。
income.info()
### 3万条数据

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 32561 entries, 0 to 32560
Data columns (total 15 columns):
age               32561 non-null int64
workclass         30725 non-null object
fnlwgt            32561 non-null int64
education         32561 non-null object
education-num     32561 non-null int64
marital-status    32561 non-null object
occupation        30718 non-null object
relationship      32561 non-null object
race              32561 non-null object
sex               32561 non-null object
capital-gain      32561 non-null int64
capital-loss      32561 non-null int64
hours-per-week    32561 non-null int64
native-country    31978 non-null object
income            32561 non-null object
dtypes: int64(6), object(9)
memory usage: 3.7+ MB

从上可以看出,存在缺失值，workclass，occupation，native-country ,缺失值都是类别值，因此用众数进行填充

# 缺失值处理
income.fillna(value = {
   'workclass':income.workclass.mode()[0],
                              'occupation':income.occupation.mode()[0],
                              'native-country':income['native-country'].mode()[0]}, inplace = True)
income.head()

	age	workclass	fnlwgt	education	education-num	marital-status	occupation	relationship	race	sex	capital-gain	capital-loss	hours-per-week	native-country	income
0	39	State-gov	77516	Bachelors	13	Never-married	Adm-clerical	Not-in-family	White	Male	2174	0	40	United-States	<=50K
1	50	Self-emp-not-inc	83311	Bachelors	13	Married-civ-spouse	Exec-managerial	Husband	White	Male	0	0	13	United-States	<=50K
2	38	Private	215646	HS-grad	9	Divorced	Handlers-cleaners	Not-in-family	White	Male	0	0	40	United-States	<=50K
3	53	Private	234721	11th	7	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0	0	40	United-States	<=50K
4	28	Private	338409	Bachelors	13	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0	0	40	Cuba	<=50K

# 数据的探索性分析
income.describe()

#了解数据的大致分布，但是这种分布不包括字符串类型

	age	fnlwgt	education-num	capital-gain	capital-loss	hours-per-week
count	32561.000000	3.256100e+04	32561.000000	32561.000000	32561.000000	32561.000000
mean	38.581647	1.897784e+05	10.080679	1077.648844	87.303830	40.437456
std	13.640433	1.055500e+05	2.572720	7385.292085	402.960219	12.347429
min	17.000000	1.228500e+04	1.000000	0.000000	0.000000	1.000000
25%	28.000000	1.178270e+05	9.000000	0.000000	0.000000	40.000000
50%	37.000000	1.783560e+05	10.000000	0.000000	0.000000	40.000000
75%	48.000000	2.370510e+05	12.000000	0.000000	0.000000	45.000000
max	90.000000	1.484705e+06	16.000000	99999.000000	4356.000000	99.000000

income.describe(include =[ 'object'])

	workclass	education	marital-status	occupation	relationship	race	sex	native-country	income
count	32561	32561	32561	32561	32561	32561	32561	32561	32561
unique	8	16	7	14	6	5	2	41	2
top	Private	HS-grad	Married-civ-spouse	Prof-specialty	Husband	White	Male	United-States	<=50K
freq	24532	10501	14976	5983	13193	27816	21790	29753	24720

绘制不同收入水平下的年龄核密度图

# 导入绘图模块
import matplotlib.pyplot as plt
# 设置绘图风格
plt.style.use('ggplot')
# 设置多图形的组合
fig, axes = plt.subplots(2, 1)
# 绘制不同收入水平下的年龄核密度图
income.age[income.income == ' <=50K'].plot(kind = 'kde', label = '<=50K', ax = axes[0], legend = True, linestyle = '-')
income.age[income.income == ' >50K'].plot(kind = 'kde', label = '>50K', ax = axes[0], legend = True, linestyle = '--')
# 绘制不同收入水平下的周工作小时数和密度图
income['hours-per-week'][income.income == ' <=50K'].plot(kind = 'kde', label = '<=50K', ax = axes[1], legend = True, linestyle = '-')
income['hours-per-week'][income.income == ' >50K'].plot(kind = 'kde', label = '>50K', ax = axes[1], legend = True, linestyle = '--')
# 显示图形
plt.show()