【Python数据分析与可视化】Pandas数据分析与matplotlib绘图

【Python数据分析与可视化】Pandas数据分析与matplotlib绘图

导包

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
plt.rcParams["font.family"]=['SimHei']
plt.rcParams['axes.unicode_minus']=False

matplotlib模仿绘制图表

如下样式的绘图，请写出相应的代码；

fig=plt.figure(figsize=(16,10))
ax1=plt.subplot(2,2,1)
ax2=plt.subplot(2,2,2)
ax3=plt.subplot(2,2,3)

plt.tight_layout(h_pad=2)

x1=np.arange(0,5,0.001)
y1=np.sin(2*np.pi*x1)
ax1.set_xlabel("X轴")
ax1.set_ylabel("Y轴")
ax1.set_xticks([0,1,2,3,4,5])
ax1.set_ylim(-2,2)
ax1.set_yticks([i for i in np.arange(-2.0,2.1,0.5)])
ax1.annotate('local max', xy=(2.2, 1), xytext=(3, 1.5),
            arrowprops=dict(facecolor='red', shrink=0.05),
            bbox={'facecolor':'yellow', 'alpha':0.5, 'pad':2} )
ax1.text(1, 1.2, 'Max', style='italic',fontsize='large')
ax1.text(2, -1.5, 'y=sin(2*np.pi*t)', style='italic',
        bbox={'facecolor':'yellow', 'alpha':0.5, 'pad':2},rotation=15)
ax1.plot(x1,y1)

x2=np.arange(0,np.pi*2,0.01)
y2=np.sin(x2)
ax2.set_xticks([0,np.pi/2,np.pi,3*np.pi/2,2*np.pi] )
ax2.set_xticklabels(('0', 'π/2', 'π', '3π/2', '2π'))
ax2.set_ylim(-1.5,1.5)
ax2.set_title('y=sin(x)',y=-0.14,bbox=dict(facecolor='w',alpha=0.65))
ax2.annotate('sin(x)最小值', xy=(4.71, -1), xytext=(4,-0.2),
            arrowprops=dict(facecolor='red',arrowstyle="->",edgecolor='r'),
            bbox={'facecolor':'yellow', 'alpha':0.5, 'pad':2} )
ax2.plot(x2,y2,"-.",color='#a10cc7')


x3=np.arange(0,np.pi*2,0.01)
y3=np.cos(x3)
ax3.set_ylim(-1.5,1.5)
ax3.set_xticks([0,np.pi/2,np.pi,3*np.pi/2,2*np.pi] )
ax3.set_xticklabels(('0', 'π/2', 'π', '3π/2', '2π'))
ax3.set_title('y=cos(x)',y=-0.14,bbox=dict(facecolor='w',alpha=0.65))
ax3.annotate('cos(x)最小值', xy=(3.14, -1), xytext=(3.2,0.2),
            arrowprops=dict(facecolor='red',arrowstyle="->",edgecolor='r'),
            bbox={'facecolor':'yellow', 'alpha':0.5, 'pad':2} )
ax3.plot(x3,y3,"--",color='#a10cc7')
plt.show()

​

​

如下样式的绘图，请写出相应的代码；

• 1. 绘图函数：y=sin(x), y=cos(x), x = np.linspace(-np.pi, np.pi, 256, endpoint=True)；
• 2. 绘制填充区域: 紫色区域：(-2.5<x)&(x<-0.5)，绿色区域：sinx>0.5

x=np.linspace(-1*np.pi,np.pi,256,endpoint=True)
y1=np.sin(x)
y2=np.cos(x)
# 绘图
plt.figure(figsize=(10,7))
plt.plot(x,y1,'b')
plt.plot(x,y2,'r')
#填充颜色
plt.fill_between(x,y1,where=(y1>0.5),facecolor='green')
plt.fill_between(x,y2,where=(x>-2.5)&(x<-0.5),facecolor='purple')
#图例
plt.legend(['sin(x)','cos[x]'],loc='upper left')
#网格
plt.grid(True)
#设置坐标轴
plt.xticks([-1*np.pi,-1*np.pi/2,0,np.pi/2,np.pi],('-Π', '-π/2', '0', 'π/2', 'π'))
plt.yticks([-1,1])
axes=plt.gca()
axes.spines['top'].set_color('none')
axes.spines['right'].set_color('none')
axes.xaxis.set_ticks_position('bottom')
axes.spines['bottom'].set_position(('data', 0))
axes.yaxis.set_ticks_position('left')
axes.spines['left'].set_position(('data', 0))
#标题
plt.title('绘图实例之SIN()&COS()',color='g')
#标注
plt.annotate('sin(2Π/3)=√3/2', xy=(np.pi*2/3, 0.85), xytext=(2.5,1),
            arrowprops=dict(facecolor='black',arrowstyle="->",edgecolor='black'))
plt.annotate('cos(-Π)=-1', xy=(-1*np.pi, -1), xytext=(-2.5,-1.2),
            arrowprops=dict(facecolor='black',arrowstyle="->",edgecolor='black',shrinkB=0,
                            connectionstyle="arc3,rad=0.3"))
plt.text(2, -1.2, 'python_matplotlib',color='purple')

plt.show()

3. 实训针对一组关于全球星巴克门店的统计数据（directory.csv），
   分析了在不同国家和地区以及中国不同城市的星巴克门店的数量；

df=pd.read_csv('directory.csv')

• 读取数据：显示前5行数据

df.head()

	Brand	Store Number	Store Name	Ownership Type	Street Address	City	State/Province	Country	Postcode	Phone Number	Timezone	Longitude	Latitude	Unnamed: 13	Unnamed: 14	Unnamed: 15	Unnamed: 16	Unnamed: 17
0	Starbucks	47370-257954	Meritxell, 96	Licensed	Av. Meritxell, 96	Andorra la Vella	AJ	AD	AD500	376818720	GMT+1:00 Europe/Andorra	1.53	42.51	NaN	NaN	NaN	NaN	NaN
1	Starbucks	22331-212325	Ajman Drive Thru	Licensed	1 Street 69, Al Jarf	Ajman	AJ	AD	NaN	NaN	GMT+04:00 Asia/Dubai	55.47	25.42	NaN	NaN	NaN	NaN	NaN
2	Evolution Fresh	47089-256771	Dana Mall	Licensed	Sheikh Khalifa Bin Zayed St.	Ajman	AJ	AD	NaN	NaN	GMT+04:00 Asia/Dubai	55.47	25.39	NaN	NaN	NaN	NaN	NaN
3	Starbucks	22126-218024	Twofour 54	Licensed	Al Salam Street	Abu Dhabi	AZ	AD	NaN	NaN	GMT+04:00 Asia/Dubai	54.38	24.48	NaN	NaN	NaN	NaN	NaN
4	Starbucks	17127-178586	Al Ain Tower	Licensed	Khaldiya Area, Abu Dhabi Island	Abu Dhabi	AZ	AD	NaN	NaN	GMT+04:00 Asia/Dubai	54.54	24.51	NaN	NaN	NaN	NaN	NaN

数据分析及可视化

查看星巴克旗下有哪些品牌,统计每个品牌有多少家店

print("星巴克旗下品牌有：")
df['Brand'].value_counts()

星巴克旗下品牌有：
Starbucks                6710
Teavana                    97
Evolution Fresh            22
Coffee House Holdings      15
Name: Brand, dtype: int64

查看全世界一共有多少个国家和地区开设了星巴克门店，显示门店数量排名前10

和后10的国家

print("全世界一共有多少个国家开设了星巴克门店",len(df['Country'].unique()))
print("排名前十的国家和数量为：")
country_count = df['Country'].value_counts()
print(country_count[:10])
print("排名后十的国家和数量为：")
print(country_count[-10:])

全世界一共有多少个国家开设了星巴克门店 20

排名前十的国家和数量为：
CN    1546
US    1267
AT    1174
BR     778
AU     745
AZ     525
CA     228
BE     154
AR     148
AE     144
Name: Country, dtype: int64

排名后十的国家和数量为：
GR    28
BN    27
AW    24
HU    16
BS    10
GT     7
AD     7
BH     7
BG     5
BO     4
Name: Country, dtype: int64

用柱状图绘制排名前10国家的分布情况

plt.figure(figsize=(10,5))
labels = list(country_count[:10].index)  # 刻度标签
plt.xlabel('国家')
plt.ylabel('门店数量')
plt.title('星巴克门店数量排名前10的国家')
plt.bar([i for i in labels], country_count[:10])
plt.show()

​

显示拥有星巴克门店数量排名前10的城市

print("排名前十的城市和数量为：")
city_count = df['City'].value_counts()
print(city_count[:10])

排名前十的城市和数量为：
Beijing         342
Shanghai        279
Changchun       195
Suzhou          157
Buenos Aires    148
San Diego       135
Los Angeles     127
Seattle         126
Dalian          119
Guangzhou       119
Name: City, dtype: int64

绘制星巴克门店数量前10的城市分布线型图

plt.figure(figsize=(10,5))
labels = list(city_count[:10].index)  # 刻度标签
plt.xlabel('城市')
plt.ylabel('门店数量')
plt.title('星巴克门店数量排名前10的城市')
plt.plot([i for i in labels], city_count[:10])
plt.show()

​

显示拥有星巴克门在中国的分布情况，店数量排名前10的城市

cn_df = df[df['Country'] == 'CN'] 
cn_city_count=cn_df['City'].value_counts()
print("排名前十的中国城市和数量为：\nCity")
print(cn_city_count[:10])

排名前十的中国城市和数量为：
City
Beijing         342
Shanghai        279
Changchun       195
Suzhou          157
Guangzhou       119
Dalian          119
Zhengzhou        98
Qingdao          89
Shijiazhuang     55
Shenzhen         48
Name: City, dtype: int64

绘制星巴克中国门店数量前10的城市分布柱状图

plt.figure(figsize=(10,5))
labels = list(cn_city_count[:10].index)  # 刻度标签
plt.xlabel('城市')
plt.ylabel('门店数量')
plt.title('星巴克门店数量排名前10的国家')
plt.bar([i for i in labels], cn_city_count[:10])
plt.show()

​

​

用饼状图显示星巴克门店的经营方式有哪几种？

manage_count=df['Ownership Type'].value_counts()
plt.figure(figsize=(10,7))
plt.pie(manage_count,labels=manage_count.index)
plt.title("星巴克门店的经营方式")
plt.show()