pandas：数据可视化

普通柱状图

'''
普通柱状图
'''

import pandas as pd
import matplotlib.pyplot as plt

file = '/tmp/Students2.xlsx'
student = pd.read_excel(file)
student_filter = student.sort_values(by='Number',ascending=False)
print(student_filter)
plt.bar(student_filter.Field,student_filter.Number,color='orange')
plt.xticks(student_filter.Field,rotation='90')
plt.xlabel('Field')
plt.ylabel('Number')
plt.title('International student by field',fontsize='16')
plt.tight_layout()
plt.show()

'''
原生方法
'''
# student_filter.plot.bar(x='Field',y='Number',color='orange',title='International student by field')
# plt.show()

分组柱状图

'''
分组柱状图
'''

import pandas as pd
import matplotlib.pyplot as plt

file = '/tmp/Students3.xlsx'
student = pd.read_excel(file)
student_filter = student.sort_values(by='2017',ascending=False)
print(student_filter)
# plt.bar(student_filter.Field,[2017,2016],color=['orange','red'])
# plt.show()
student_filter.plot.bar('Field',['2016','2017'],color=['orange','red'])
plt.title('International Students by Field',fontsize=16)
plt.xlabel('Field',fontweight='bold')
plt.ylabel('Number',fontweight='bold')
ax = plt.gca()
ax.set_xticklabels(student_filter['Field'],rotation=40,ha='right')
plt.gcf().subplots_adjust(left=0.2,bottom=0.42)
plt.show()

叠加柱状图-横向叠加柱状图

'''
叠加柱状图
横向叠加柱状图
'''

import pandas as pd
import matplotlib.pyplot as plt

file = '/tmp/Users.xlsx'
users = pd.read_excel(file)
users['Total'] = users['Oct'] + users['Nov'] + users['Dec']
users.sort_values(by='Total',inplace=True,ascending=False)
print(users)

users.plot.bar(x='Name',y=['Oct','Nov','Dec'],stacked=True)
# 水平方向叠加
# users.plot.barh(x='Name',y=['Oct','Nov','Dec'],stacked=True)
plt.tight_layout()
plt.show()

饼状图

'''
饼状图
'''

import pandas as pd
import matplotlib.pyplot as plt

file = '/tmp/Students.xlsx'
# 要显示的列为主键列
students = pd.read_excel(file,index_col='From')
print(students)
# 按照2017列排序
students['2017'].plot.pie(fontsize=8,counterclock=False,startangle=-270)
plt.title('Source of International Students',fontsize=16,fontweight='bold')
plt.ylabel('2017',fontsize=12,fontweight='bold')
plt.show()

曲线图-叠加曲线图

'''
曲线图
叠加曲线图
'''

import pandas as pd
import matplotlib.pyplot as plt

file = '/tmp/Orders.xlsx'
weeks = pd.read_excel(file,index_col='Week')
print(weeks)

# 曲线图
# weeks.plot(y=['Accessories', 'Bikes', 'Clothing', 'Components'])
weeks.plot.area(y=['Accessories', 'Bikes', 'Clothing', 'Components'])
plt.title('Sales Trends',fontsize=16,fontweight='bold')
plt.xticks(weeks.index,fontsize=8)
plt.show()

密度图-离散图-直方图

'''
密度图
离散图
直方图
'''

import pandas as pd
import matplotlib.pyplot as plt

pd.options.display.max_columns = 999
file = '/tmp/home_data.xlsx'
homes = pd.read_excel(file)
print(homes.head())
# 密度图
# homes.plot.scatter(x='sqft_living',y='price')

# 离散图
# homes.sqft_living.plot.kde()

# 直方图
homes.price.plot.hist(bins=200)
plt.xticks(range(0,max(homes.price),100000),fontsize=8,rotation=90)
# homes.sqft_living.plot.hist(bins=100)
# plt.xticks(range(0,max(homes.sqft_living),500),fontsize=8,rotation=90)
plt.show()


# 神奇的相关性
# print(homes.corr())