Pandas.plot 做图 demo(scatter,bar,pie)

#coding:utf-8import numpy as npimport matplotlib.pyplot as pltplt.rcParams[‘font.sans-serif‘]=[‘SimHei‘] #用来正常显示中文标签plt.rcParams[‘axes.unicode_minus‘]=False #用来正常显示负号import pandas as pdfrom pandas import Series,DataFrame

‘‘‘plt.scatter(x,y)plt.show()

plt.bar(x,y,width=0.3,color=‘y‘)plt.bar(x+0.3,y2,width=0.3,color=‘y‘)plt.bar(x,y2,width=0.3,color=‘y‘,bottom=y)

plt.pie(x=x,labels=y,...)plt.show()

plt.boxplot(data,sym=‘o‘,whis=0.05)plt.boxplot(data,labels=labe)plt.show()‘‘‘data_train=pd.read_csv(r‘C:\python\demo\ML\data\TravelRecords0708.csv‘,encoding=‘gbk‘)title =‘(2017.07-2017.08)‘#print(data_train.loc[:,[‘Name‘,‘Team‘,‘TravelDays‘,‘RequesterAddress‘]])def tongjiByName():

    fig = plt.figure()    fig.set(alpha=0.2)  # 设定图表颜色alpha参数

    #plt.subplot2grid((2, 3), (0, 0))  # 在一张大图里分列几个小图    data_train.Name.value_counts().plot(kind=‘bar‘)  # plots a bar graph of those who surived vs those who did not.    plt.title(u"DB出差同事出差次数情况统计"+title)  # puts a title on our graph    plt.ylabel(u"出差次数")    plt.text(20,4.5,u‘出差总次数(次):‘)    plt.text(25, 4.5, data_train.Name.value_counts().values.sum())    plt.text(20,4.0,u‘出差总人数(个):‘)    plt.text(25, 4.0, len(data_train.Name.value_counts()))    plt.text(20,3.5,u‘出差总天数(天):‘)    plt.text(25, 3.5, data_train.TravelDays.values.sum())    print(data_train.TravelDays.values.sum())    plt.show()

def tongjiByteam():    fig = plt.figure()    fig.set(alpha=0.2)  # 设定图表颜色alpha参数

    #plt.subplot2grid((2, 3), (0, 0))  # 在一张大图里分列几个小图    data_train.Team.value_counts().plot(kind=‘pie‘)  # plots a bar graph of those who surived vs those who did not.    #data_train.Team.value_counts().plot(kind=‘bar‘)  # plots a bar graph of those who surived vs those who did not.    print(data_train.Team.value_counts())

    plt.title(u"深圳马会各team出差人数统计情况(2017.07-08)")  # puts a title on our graph    plt.text(5.5,10.5,u‘出差总人数(次):‘)    plt.text(6.8, 10.5, data_train.Team.value_counts().values.sum()) #统计series的value 总和    #plt.text(5.5, 9.5, u‘出差team数(个):‘)    #plt.text(6.8, 9.5, len(data_train.Team.value_counts().index))    #统计series的index 总和    #plt.ylabel(u"出差人数")    plt.show()

def tongjiByteamPIE():    fig = plt.figure()    fig.set(alpha=0.2)  # 设定图表颜色alpha参数

    labels=data_train.Team.value_counts().index    explode = [0, 0.5,0,0,0,0,0,0,0,0,0,0]  # 0.1 凸出这部分，    plt.pie(x=data_train.Team.value_counts(),labels=labels,autopct=‘%3.1f %%‘,shadow=True,labeldistance=1.1,startangle=90,pctdistance=0.6)

    plt.title(u"DB各team出差人数统计情况"+title)  # puts a title on our graph    plt.text(5.5,10.5,u‘出差总人数(次):‘)    plt.text(6.8, 10.5, data_train.Team.value_counts().values.sum()) #统计series的value 总和    plt.show()

def tongjiByTravelDays():    fig = plt.figure()    fig.set(alpha=0.2)  # 设定图表颜色alpha参数

    #plt.subplot2grid((2, 3), (0, 0))  # 在一张大图里分列几个小图    data_train.TravelDays.value_counts().plot(kind=‘bar‘)  # plots a bar graph of those who surived vs those who did not.    #data_train.Team.value_counts().plot(kind=‘bar‘)  # plots a bar graph of those who surived vs those who did not.    print(data_train.Team.value_counts())

    plt.title(u"DB各team出差时长统计情况"+title)  # puts a title on our graph    plt.text(2.5,30.5,u‘出差人次(人):‘)    plt.text(3.8, 30.5, data_train.TravelDays.value_counts().values.sum()) #统计series的value 总和    plt.text(2.5, 25.5, u‘出差时长种类(类):‘)    plt.text(3.8, 25.5, len(data_train.TravelDays.value_counts().index))    #统计series的index 总和

    plt.text(2.5, 20.5, u‘出差时长最长天数(天):‘)    plt.text(3.8, 20.5, data_train.TravelDays.values.max())    #统计series的index 总和    print(data_train.TravelDays.values.max())    plt.ylabel(u"出差人数")    plt.xlabel(u"出差天数")    plt.show()

def tongjiByRequestAddress():    fig = plt.figure()    fig.set(alpha=0.2)  # 设定图表颜色alpha参数

    #plt.subplot2grid((2, 3), (0, 0))  # 在一张大图里分列几个小图    #data_train.RequesterAddress.value_counts().plot(kind=‘pie‘)  # plots a bar graph of those who surived vs those who did not.    #data_train.Team.value_counts().plot(kind=‘bar‘)  # plots a bar graph of those who surived vs those who did not.    labels=‘HK‘,‘SZ‘    explode = [0, 0.2]  # 0.1 凸出这部分，    plt.pie(x=data_train.RequesterAddress.value_counts(),labels=labels,autopct=‘%1.1f %%‘,shadow=True,labeldistance=1.1,startangle=90,pctdistance=0.6)    print(data_train.RequesterAddress.value_counts())

    plt.title(u"DB同事出差邀请(香港／深圳)统计情况"+title)  # puts a title on our graph    plt.show()

#tongjiByName()#tongjiByteam()tongjiByteamPIE()#tongjiByTravelDays()#tongjiByRequestAddress()