import pandasas pd

import numpyas np

import seabornas sns

import matplotlib.pyplotas plt

pd.set_option('display.max_columns', 10000)

pd.set_option('display.max_rows', 10000000000)

pd.set_option('display.width', 100000)

income = pd.read_excel(r'D:\bigData\0629demo\dataSource\income.xlsx')

fill_data = income.fillna(value={'workclass': income.workclass.mode()[0], 'occupation': income.occupation.mode()[0],

                                'native-country': income['native-country'].mode()[0]}, inplace=True)

# print(income.apply(lambda x: np.sum(x.isnull())))

# print(income)

print(income.describe())

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

# 设置绘图风格

plt.style.use('ggplot')

# 设置多图形组合

fig, axes = plt.subplots(2, 1)

# 绘制不同收入水平下的年龄核密度图

# kind='kde', label='<=50K', ax=axes[0], legend=True, linestyle='-'

# kind='kde', label='>50K', ax=axes[0], legend=True, linestyle='--'

income['age'][income.income ==' <=50K'].plot(kind='kde', ax=axes[0], label='<=50K', legend=True, linestyle='-')

income['age'][income.income ==' >50K'].plot(kind='kde', ax=axes[0], label='>50K', legend=True, linestyle='--')

# 绘制不同收入水平下的周工作小时数核密度图

# kind='kde', label='<= 50K', ax=axes[1], legend=True,  linestyle='-'

# 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='-')

income['hours-per-week'][income.income ==' >50K'].plot(kind='kde', label='> 50K', ax=axes[1], legend=True,

                                                        linestyle='--')

plt.show()

# 构造不同收入水平下各种族人数的数据

race = pd.DataFrame(income.groupby(by=['race', 'income']).agg(np.size).loc[:, 'age'])

# 重设行索引

race = race.reset_index()

# 变量重命名

race.rename(columns={'age':'counts'}, inplace=True)

print(race)

# 排序

race.sort_values(by=['race', 'counts'], ascending=False, inplace=True)

# 构造不同收入水平下各家庭关系人数的数据

relationship = pd.DataFrame(income.groupby(by=['relationship', 'income']).agg(np.size).loc[:, 'age'])

relationship = relationship.reset_index()

relationship.rename(columns={'age':'counts'}, inplace=True)

relationship.sort_values(by=['relationship', 'counts'], ascending=False, inplace=True)

plt.figure(figsize=(15, 10))

sns.barplot(x='race', y='counts', hue='income', data=race)

plt.show()

plt.figure(figsize=(15, 10))

sns.barplot(x='relationship', y='counts', hue='income', data=relationship)

plt.show()