data.csv数据下载
data_for_pie.csv数据下载
import matplotlib.pyplot as plt // plt.plot
散点图
# -*- coding: utf-8 -*-__author__ = 'yuanlei'import matplotlibfrom pandas import read_csvimport matplotlib.pyplot as pltdata = read_csv("data.csv")#####font = {'family' : 'SimHei'}matplotlib.rc('font', **font)###### 注意点1:要把读入的serise类型的数据转化成list# 注意点2:为了在坐标轴上显示中文标题,需要在中文前加上u,以及# 在plt.plot之前加上上面那段话.plt.plot(list(data["广告费用"]),list(data["购买用户数"]), '.')plt.xlabel(u"广告费用")plt.ylabel(u"购买用户数")plt.show()
折线图以及各种设置
# -*- coding: utf-8 -*-__author__ = 'yuanlei'import matplotlibimport pandas#from pandas import read_csvimport matplotlib.pyplot as pltdata = pandas.read_csv("data.csv")data['购买日期']=pandas.to_datetime(data['日期'])#####font = {'family' : 'SimHei'}matplotlib.rc('font', **font)###### 注意点1:要把读入的serise类型的数据转化成list# 注意点2:为了在坐标轴上显示中文标题,需要在中文前加上u,以及# 在plt.plot之前加上上面那段话.#plt.plot(list(data['购买日期']),list(data["购买用户数"]), '.')#'-'顺滑的曲线plt.plot(list(data['购买日期']), list(data['购买用户数']), '-');# #设置颜色# plt.plot(list(data['购买日期']), list(data['购买用户数']), '-', color='r');# #设置线条粗细# plt.plot(list(data['购买日期']), list(data['购买用户数']), '-', color='r', lineWidth=10);## #'--'虚线# plt.plot(list(data['购买日期']), list(data['购买用户数']), '--');# #'-.'线加点# plt.plot(list(data['购买日期']), list(data['购买用户数']), '-.');# #':'由点组成的曲线# plt.plot(list(data['购买日期']), list(data['购买用户数']), ':');# #'.'散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), '.');# #','像素点的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), ',');# #'o'大点的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), 'o');# #'v'下三角标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), 'v');# #'^'上上角标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), '^');# #'<'左角标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), '<');# #'>'右角标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), '>');# #'1'伞形下的标记散点图# #'2'伞形上的标记散点图# #'3'伞形左的标记散点图# #'4'伞形右的标记散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), '4');# #'s'正方形标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), 's');# #'p'五角形标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), 'p');# #'*'五角星标记的散点图# plt.plot(list(data['购买日期']), list(data['购买用户数']), '*');# #'h'多边形标记的散点图# #'H'hexagon2 marker# plt.plot(list(data['购买日期']), list(data['购买用户数']), 'h');# #'+'plus marker# #'x'x marker# #'D'diamond marker# #'d'thin_diamond marker# plt.plot(list(data['购买日期']), list(data['购买用户数']), 'D');# #'|'vline marker# #'_'hline marker# plt.plot(list(data['购买日期']), list(data['购买用户数']), '|');plt.xlabel(u"广告费用")plt.ylabel(u"购买用户数")plt.show()
import matplotlib.pyplot as plt // plt.pie
饼图
# -*- coding: utf-8 -*-import numpy;import matplotlib;from pandas import read_csv;import matplotlib.pyplot as plt;data = read_csv('data_for_pie.csv');gb = data.groupby(by=['通信品牌'], as_index=False)['号码'].agg({'用户数':numpy.size});print(gb['通信品牌'])print(gb["用户数"])#用原来的手段会导致编码问题，目前还没解决a = {0:"全球通",1:"动感地带",2:"神州行"}font = {'family' : 'SimHei'}matplotlib.rc('font', **font);#plt.pie(b, a, autopct='%.2f%%');gb['通信品牌']plt.pie(gb['用户数'], labels=a, autopct='%.2f%%');plt.show()
import matplotlib.pyplot as plt // plt.bar
柱形图
# -*- coding: utf-8 -*-import numpyimport matplotlibfrom pandas import read_csvfrom matplotlib import pyplot as pltfont = {'family' : 'SimHei'}matplotlib.rc('font', **font)data = read_csv('data_for_pie.csv')gb = data.groupby(by=['手机品牌'])['月消费（元）'].agg({'月消费': numpy.sum})index = numpy.arange(gb['月消费'].size)print(gb.index)#竖向柱形图# plt.bar(index, gb['月消费'], 1, color='G')# plt.show()## plt.bar(index, gb['月消费'], 1, color='G')# #仍然是中文编码问题# plt.xticks(index + 1/2, gb.index)# plt.show()## #横向柱形图plt.barh(index, gb['月消费'], 1, color='G')#plt.yticks(index + 1/2, gb.index)plt.show()#
# -*- coding: utf-8 -*-import numpy;import matplotlib;from pandas import read_csv;from matplotlib import pyplot as plt;font = {'family' : 'SimHei'};matplotlib.rc('font', **font);data = read_csv('data_for_pie.csv')d1 = '手机品牌';d2 = '通信品牌';v = "月消费";gb = data.groupby(by=[d1, d2])['月消费（元）'].agg({v: numpy.sum});d1size = gb.index.levels[0].size;d2size = gb.index.levels[1].size;index = numpy.arange(d1size);colors=['r', 'g', 'b'];for i in range(0, d2size): print(i);subgb = gb[v][gb.index.labels[1]==i];bar = plt.bar(index*d2size + i, subgb, color=colors[i]);lIndex = numpy.arange(d1size)*d2size;plt.xticks(lIndex + 3/2, gb.index.levels[0]);plt.legend(gb.index.levels[1]);plt.show();
# -*- coding: utf-8 -*-import numpy;import matplotlib;from pandas import read_csv;from matplotlib import pyplot as plt;font = {'family' : 'SimHei'};matplotlib.rc('font', **font);data = read_csv('data_for_pie.csv')d1 = '手机品牌';d2 = '通信品牌';v = "月消费";gb = data.groupby(by=[d1, d2])['月消费（元）'].agg({v: numpy.sum});d1size = gb.index.levels[0].size;d2size = gb.index.levels[1].size;index = numpy.arange(d1size);colors = ['r', 'g', 'b'];bsum = index*0.0;for i in range(0, d2size): print(i);subgb = gb[v][gb.index.labels[1]==i]; bar = plt.bar(index, subgb, color=colors[i], bottom=bsum);bsum += subgb;plt.xticks(index+1/2, gb.index.levels[0]);plt.legend(gb.index.levels[1]);plt.show();
import matplotlib.pyplot as plt // plt.hist
直方图
# -*- coding: utf-8 -*-import matplotlib;from pandas import read_csv;from matplotlib import pyplot as plt;font = {'family' : 'SimHei'};matplotlib.rc('font', **font);data = read_csv('data.csv')# plt.hist(data['购买用户数']);# plt.show();## plt.hist(data['购买用户数'], bins=20);# plt.show();#plt.hist(data['购买用户数'], bins=20, cumulative=True);plt.show();
