python数据分析-08透视表以及matplotlib库

最新推荐文章于 2021-03-16 18:50:50 发布
weixin_30578677
最新推荐文章于 2021-03-16 18:50:50 发布
阅读量267
点赞数
文章标签： python
原文链接：http://www.cnblogs.com/nikecode/p/11130955.html
版权
import pandas as pd
import numpy as np
from pandas import Series,DataFrame

"""
df = pd.read_excel("sales-funnel.xlsx")
#print(df)
#     Account                         Name  ...   Price     Status
# 0    714466              Trantow-Barrows  ...   30000  Presented
# 1    714466              Trantow-Barrows  ...   10000  Presented
# 2    714466              Trantow-Barrows  ...    5000    Pending
# 3    737550  Fritsch,Russel and Anderson  ...   35000   declined
# 4    146832                 Kiehn-Spinka  ...   65000        won
# 5    218895                    Kulas Inc  ...   40000    Pending
# 6    218895                    Kulas Inc  ...   10000  Presented
# 7    412290                Jerde-Hilpert  ...    5000    Pending
# 8    740150                   Barton-LLC  ...   35000   declined
# 9    141962                   Barton-LLC  ...   65000        won
# 10   163416                  Purdy-Kunde  ...   30000  Presented
# 11   239344                   Stokes-LLC  ...    5000    Pending
# 12   239344                   Stokes-LLC  ...   10000  Presented
# 13   307599   Kassulke,Ondricka and Metz  ...    7000        won
# 14   688981                  Keeling LLC  ...  100000        won
# 15   729833                    Koepp-Ltd  ...   65000   declined
# 16   729833                    Koepp-Ltd  ...    5000  Presented
#
# [17 rows x 8 columns]

print(pd.pivot_table(df,index=["Name"]))
#                              Account   Price  Quantity
# Name
# Barton-LLC                    441056   50000  1.500000
# Fritsch,Russel and Anderson   737550   35000  1.000000
# Jerde-Hilpert                 412290    5000  2.000000
# Kassulke,Ondricka and Metz    307599    7000  3.000000
# Keeling LLC                   688981  100000  5.000000
# Kiehn-Spinka                  146832   65000  2.000000
# Koepp-Ltd                     729833   35000  2.000000
# Kulas Inc                     218895   25000  1.500000
# Purdy-Kunde                   163416   30000  1.000000
# Stokes-LLC                    239344    7500  1.000000
# Trantow-Barrows               714466   15000  1.333333

print(pd.pivot_table(df,index=["Manager","Rep"],values=["Price","Quantity"],aggfunc=sum))
#                               Price  Quantity
# Manager       Rep
# Debra-Henley  Craig-Booker    80000         5
#               Daniel-Hilton  115000         5
#               John-Smith      40000         3
# Fred-Anderson Cedric-Moss    110000         5
#               Wendy-Yule     177000        12
"""


"""
#------------------
#分组和透视功能实战
link = "https://projects.fivethirtyeight.com/flights"
#假设文件usa_flights.csv 文件数据完整
df = pd.read_csv("usa_flights.csv")
print(df.shape)#(201664,14)

#获取延误时间最长的top10
print(df.sort_values("arr_delay",ascending=False)[:10])

#计算延误和没有延误所占比例
print(df["cancelled"].value_counts())
# 0       196873
# 1       4791
# Name:   cancelled,dtype:int64
df["delayed"] = df["arr_delay"].apply(lambda x:x>0)
print(df.head())
print(df["delayed"].value_counts())
#False  103037
#True   98627
#Name:delayed ,dtype:int64
delay_data = df["delayed"].value_counts()
print(delay_data[1]/(delay_data[0]+delay_data[1]))
#0.4890659...

#每个航空公司延误的情况
delay_group = df.groupby(["unique_carrier","delayed"])
print(delay_group.size())
df_delay = delay_group.size().unstack()
print(df_delay)
import matplotlib.pyplot as plt
df_delay.plot()
plt.show()
"""


#---------------------------------------------
#Matplotlib介绍
#为什么用Python画图
    #GUI太复杂
    #Excel太头疼
    #Python简单免费（）

#什么是matplotlib？
    #一个Python包
    #用于2D绘图
    #非常强大和流行
    #有很多扩展

import matplotlib.pyplot as plt
import numpy as np

# x = np.linspace(0,2*np.pi,100)
# y = np.sin(x)
# plt.plot(x,y)
# plt.show()

#Matplotlib Architecture 架构
    #Backend：主要处理把图显示到哪里和画到哪里：
    #Artist：图像显示成什么样？
    #Scripting：pyplot，python语法和API

"""
#matplotlib的简单绘图-plot
import numpy as np
import matplotlib.pyplot as plt

# a = [1,2,3]
# #plt.plot(a)#这里画图取值x轴分别是a的index指标，0,1,2，y轴是1,2,3
# b = [4,5,6]
# plt.plot(a,b)#这里画图取值x轴分别是a的值，1,2,3，y轴是4,5,6
# plt.show()

# #会报错
# a = [1,2,3]
# b = [4,5,6,7]
# plt.plot(a,b)
# plt.show()

# a = [1,2,3]
# #plt.plot(a)#这里画图取值x轴分别是a的index指标，0,1,2，y轴是1,2,3
# b = [4,5,6]
# # plt.plot(a,b,"*")#用*号表示点
# # plt.plot(a,b,"b--")
# # plt.show()
#
# c = [10,8,6]
# d = [1,8,3]
# plt.plot(a,b,"b--",c,d,"r*")
# plt.show()

t = np.arange(0.0,2.0,0.1)
print(t.size)
s = np.sin(t*np.pi)
print(s.size)
plt.plot(t,s,"r--",label="aaaa")
plt.plot(t*2,s,"--",label='bbbb')
plt.xlabel("This is X")
plt.ylabel("This is Y")
plt.title("This is a Demo")
plt.legend()#这里是将label显示出来
plt.show()
"""

#---------------------------------------
#matplotlib简单绘图之subplot
# x = np.linspace(0.0,5.0)
# y1 = np.sin(np.pi*x)
# y2 = np.sin(np.pi*x*2)
# plt.subplot(2,1,1)#表示切换到2行1列子图的第一个位置画图
# plt.plot(x,y1,"b--")
# plt.ylabel("y1")
# plt.subplot(2,1,2)#表示切换到2行1列子图的第二个位置画图
# plt.plot(x,y2,"r--")
# plt.ylabel("y2")
# plt.xlabel("X")
# plt.show()


#更改图片布局：改为两行两列，左右图片
# x = np.linspace(0.0,5.0)
# y1 = np.sin(np.pi*x)
# y2 = np.sin(np.pi*x*2)

# plt.subplot(2,2,1)
# plt.plot(x,y1,"b--")
# plt.ylabel("y1")

# plt.subplot(2,2,2)
# plt.plot(x,y2,"r--")
# plt.ylabel("y2")

# plt.xlabel("X")
# plt.show()


#更改图片布局：改为两行两列
# x = np.linspace(0.0,5.0)
# y1 = np.sin(np.pi*x)
# y2 = np.sin(np.pi*x*2)
#
# plt.subplot(2,2,1)
# plt.plot(x,y1,"b--")
# plt.ylabel("y1")
#
# plt.subplot(2,2,2)#表示切换到2行1列子图的第二个位置画图
# plt.plot(x,y2,"r--")
# plt.ylabel("y2")
#
#
# plt.subplot(2,2,3)#表示切换到2行1列子图的第二个位置画图
# plt.plot(x,y2,"r*")
# plt.ylabel("y2")
#
# plt.subplot(2,2,4)
# plt.plot(x,y1,"b*")
# plt.ylabel("y1")
#
# plt.xlabel("X")
# plt.show()


#a = plt.subplots()
#print(a)#(<Figure size 640x480 with 1 Axes>, <matplotlib.axes._subplots.AxesSubplot object at 0x000000000BE2B438>)
# print(type(a))#<class 'tuple'>
# print(a[0])#Figure(640x480) 表示画图，一块画布
# print(a[1])#AxesSubplot(0.125,0.11;0.775x0.77)#表示画笔

# figure,ax = plt.subplots()
# ax.plot([1,2,3,4,5])
# plt.show()#是正常的画图


# x = np.linspace(0.0,5.0)
# y1 = np.sin(np.pi*x)
# y2 = np.sin(np.pi*x*2)
# figure,ax = plt.subplots(2,2)#设为2行2列
# ax[0][0].plot(x,y1)
# ax[0][1].plot(x,y2)
# plt.show()#是正常的画图