python3 matplotlib模块
什么是matplotlib
matplotlib: 最流行的Python底层绘图库，主要做数据可视化图表,名字取材于MATLAB，模仿MATLAB构建
matplotlib基本要点
# 导入pyplot
from matplotlib import pyplot as plt
# 数据在x轴的位置，是一个可迭代对象
x = range(2, 26, 2)
# 数据在y轴的位置，是一个可迭代对象
y = [15, 13, 14.5, 17, 20, 25, 26, 26, 24, 22, 18, 15]
# 传入x和y，通过plot绘制出折线
plt.plot(x, y)
# 在执行程序的时候展示图形
plt.show()
设置图形大小和保存图片
from matplotlib import pyplot as plt
# 设置图形大小
fig = plt.figure(figsize=(20, 8), dpi=80)
x = range(2, 26, 2)
y = [15, 13, 14.5, 17, 20, 25, 26, 26, 24, 22, 18, 15]
plt.plot(x, y)
# 保存图片，可保存svg格式
plt.savefig('./sig_size.jpg')
调整x轴和y轴的刻度
'''
a表示10点到12点中每一分钟的气温，如何绘制每分钟气温的变化情况？
a = [random.randint(20,35) for i in range(120)]
'''
import random
from matplotlib import pyplot as plt
fig = plt.figure(figsize=(20, 8), dpi=80)
x = range(120)
# 设置随机种子，让不同时候随机的结果都一样
random.seed(10)
y = [random.randint(20, 35) for i in range(120)]
plt.plot(x, y)
# 设置x轴的刻度
x_ticks = ['10点{}分'.format(i) for i in x if i < 60]
x_ticks += ['11点{}分'.format(i) for i in x if i > 60]
# 让列表x和x_ticks上的数据都传入，最终会在x轴上一一对应显示
# 两组数据的长度必须保持一致，否则不能完全覆盖整个轴
# 使用列表切片，每隔5个选一个数据进行展示
# 为了让字符串不会被覆盖，使用rotation选项，让字符串旋转90度显示
plt.xticks(x[::5], x_ticks[::5], rotation=90)
plt.show()
设置中文显示
'''
a表示10点到12点中每一分钟的气温，如何绘制每分钟气温的变化情况？
a = [random.randint(20,35) for i in range(120)]
'''
import random
from matplotlib import pyplot as plt
from matplotlib import font_manager
fig = plt.figure(figsize=(20, 8), dpi=80)
# 设置中文字体
myfont = font_manager.FontProperties(fname="C:/Windows/Fonts/simhei.ttf")
x = range(120)
random.seed(10)
y = [random.randint(20, 35) for i in range(120)]
plt.plot(x, y)
x_ticks = ['10点{}分'.format(i) for i in x if i < 60]
x_ticks += ['11点{}分'.format(i) for i in x if i > 60]
# 在需要使用中文的地方，添加fontproperties属性
plt.xticks(x[::5], x_ticks[::5], rotation=45, fontproperties=myfont)
plt.show()
给图形设置描述信息
'''
a表示10点到12点中每一分钟的气温，如何绘制每分钟气温的变化情况？
a = [random.randint(20,35) for i in range(120)]
'''
import random
from matplotlib import pyplot as plt
from matplotlib import font_manager
fig = plt.figure(figsize=(20, 8), dpi=80)
myfont = font_manager.FontProperties(fname="C:/Windows/Fonts/simhei.ttf")
x = range(120)
random.seed(10)
y = [random.randint(20, 35) for i in range(120)]
plt.plot(x, y)
x_ticks = ['10点{}分'.format(i) for i in x if i < 60]
x_ticks += ['11点{}分'.format(i) for i in x if i > 60]
# 设置x轴描述
plt.xlabel('时间', fontproperties=myfont)
# 设置y周描述
plt.ylabel('温度(℃)', fontproperties=myfont)
# 设置标题
plt.title('时间-温度变化曲线', fontproperties=myfont)
plt.xticks(x[::5], x_ticks[::5], rotation=45, fontproperties=myfont)
plt.show()
练习
假设大家在30岁的时候,根据自己的实际情况,统计出来了你和你同桌各自从11岁到30岁每年交的女(男)朋友的数量如列表a和b,请在一个图中绘制出该数据的折线图,以便比较自己和同桌20年间的差异,同时分析每年交女(男)朋友的数量走势
a = [1, 0, 1, 1, 2, 4, 3, 2, 3, 4, 4, 5, 6, 5, 4, 3, 3, 1, 1, 1]
b = [1, 0, 3, 1, 2, 2, 3, 3, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1]
要求:
y轴表示个数
x轴表示岁数,比如11岁,12岁等
from matplotlib import pyplot as plt
from matplotlib import font_manager
# 设置图形大小
fig = plt.figure(figsize=(20, 8), dpi=80)
# 设置字体
myfont = font_manager.FontProperties(fname='C:/Windows/Fonts/simhei.ttf')
# x轴数据，年龄
x = range(11, 31)
# y轴数据，谈女朋友的个数
y_a = [1, 0, 1, 1, 2, 4, 3, 2, 3, 4, 4, 5, 6, 5, 4, 3, 3, 1, 1, 1]
y_b = [1, 0, 3, 1, 2, 2, 3, 3, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1]
# 绘制折线图
# 通过label属性设置图例
# 通过linestyle属性设置线条样式 -实线 --虚线 -.点划线 :点虚线 ' '无线条
# 通过color属性设置线条颜色 r红色 g绿色 b蓝色 w白色 c青色 m洋红 y黄色 k黑色 支持16进制
# 通过alpha属性设置线条的不透明程度
plt.plot(x, y_a, label='自己', linestyle='--', color='r', alpha=0.1)
plt.plot(x, y_b, label='同桌', linestyle='-', color='b', alpha=1)
# 显示图例
# 通过loc属性设置图形显示的位置，可选值如下：
# best
# upper right
# upper left
# lower right
# lower left
# right
# center right
# center left
# lower center
# upper center
# center
plt.legend(prop=myfont, loc='best')
# 设置刻度
x_ticks = ['{}岁'.format(i) for i in x]
# 显示刻度
plt.xticks(x, x_ticks, fontproperties=myfont, rotation=15)
# 显示图形
plt.show()
绘制散点图
假设通过爬虫你获取到了北京2016年3,10月份每天白天的最高气温(分别位于列表a,b),那么此时如何寻找出气温和随时间(天)变化的某种规律?
a = [11, 17, 16, 11, 12, 11, 12, 6, 6, 7, 8, 9, 12, 15, 14, 17, 18, 21, 16, 17, 20, 14, 15, 15, 15, 19, 21, 22, 22, 22, 23]
b = [26, 26, 28, 19, 21, 17, 16, 19, 18, 20, 20, 19, 22, 23, 17, 20, 21, 20, 22, 15, 11, 15, 5, 13, 17, 10, 11, 13, 12, 13, 6]
from matplotlib import pyplot as plt
from matplotlib import font_manager
plt.figure(figsize=(20, 8), dpi=80)
myfont = font_manager.FontProperties(fname='C:/Windows/Fonts/simhei.ttf')
x_a = range(1, 32)
x_b = range(1+50, 32+50)
y_a = [11, 17, 16, 11, 12, 11, 12, 6, 6, 7, 8, 9, 12, 15, 14, 17,
18, 21, 16, 17, 20, 14, 15, 15, 15, 19, 21, 22, 22, 22, 23]
y_b = [26, 26, 28, 19, 21, 17, 16, 19, 18, 20, 20, 19, 22, 23, 17,
20, 21, 20, 22, 15, 11, 15, 5, 13, 17, 10, 11, 13, 12, 13, 6]
plt.scatter(x_a, y_a, label='3月份')
plt.scatter(x_b, y_b, label='10月份')
plt.legend(loc="upper left", prop=myfont)
x = list(x_a)+list(x_b)
x_ticks = ['3月{}日'.format(i) for i in x_a]
x_ticks += ['10月{}日'.format(i-50) for i in x_b]
plt.xticks(x[::3], x_ticks[::3], fontproperties=myfont, rotation=45)
plt.xlabel('日期', fontproperties=myfont)
plt.ylabel('最高温度', fontproperties=myfont)
plt.title('三月和十月每日最高温度变化', fontproperties=myfont)
plt.show()
绘制条形图
假设你获取到了2017年内地电影票房前20的电影(列表a)和电影票房数据(列表b),那么如何更加直观的展示该数据?
a = ["战狼2", "速度与激情8", "功夫瑜伽", "西游伏妖篇", "变形金刚5：最后的骑士", "摔跤吧！爸爸", "加勒比海盗5：死无对证", "金刚：骷髅岛", "极限特工：终极回归", "生化危机6：终章", "乘风破浪", "神偷奶爸3", "智取威虎山", "大闹天竺", "金刚狼3：殊死一战", "蜘蛛侠：英雄归来", "悟空传", "银河护卫队2", "情圣", "新木乃伊", ]b = [56.01, 26.94, 17.53, 16.49, 15.45, 12.96, 11.8, 11.61, 11.28, 11.12, 10.49, 10.3, 8.75, 7.55, 7.32, 6.99, 6.88, 6.86, 6.58, 6.23] 单位：亿
横向条形图
from matplotlib import pyplot as plt
from matplotlib import font_manager
plt.figure(figsize=(20, 8), dpi=80)
myfont = font_manager.FontProperties(fname='C:/Windows/Fonts/simhei.ttf')
x = ["战狼2", "速度与激情8", "功夫瑜伽", "西游伏妖篇", "变形金刚5：最后的骑士", "摔跤吧！爸爸", "加勒比海盗5：死无对证", "金刚：骷髅岛", "极限特工：终极回归",
"生化危机6：终章", "乘风破浪", "神偷奶爸3", "智取威虎山", "大闹天竺", "金刚狼3：殊死一战", "蜘蛛侠：英雄归来", "悟空传", "银河护卫队2", "情圣", "新木乃伊", ]
x = [i.replace('：', '：\n') for i in x]
y = [56.01, 26.94, 17.53, 16.49, 15.45, 12.96, 11.8, 11.61, 11.28,
11.12, 10.49, 10.3, 8.75, 7.55, 7.32, 6.99, 6.88, 6.86, 6.58, 6.23]
plt.bar(range(len(x)), y)
plt.xticks(range(len(x)), x, fontproperties=myfont, rotation=45)
plt.xlabel('电影名', fontproperties=myfont)
plt.ylabel('票房（单位：亿）', fontproperties=myfont)
plt.title('2017年内地电影票房前20票房', fontproperties=myfont, fontsize=20)
plt.show()
纵向条形图
from matplotlib import pyplot as plt
from matplotlib import font_manager
plt.figure(figsize=(20, 8), dpi=80)
myfont = font_manager.FontProperties(fname='C:/Windows/Fonts/simhei.ttf')
x = ["战狼2", "速度与激情8", "功夫瑜伽", "西游伏妖篇", "变形金刚5：最后的骑士", "摔跤吧！爸爸", "加勒比海盗5：死无对证", "金刚：骷髅岛", "极限特工：终极回归",
"生化危机6：终章", "乘风破浪", "神偷奶爸3", "智取威虎山", "大闹天竺", "金刚狼3：殊死一战", "蜘蛛侠：英雄归来", "悟空传", "银河护卫队2", "情圣", "新木乃伊", ]
y = [56.01, 26.94, 17.53, 16.49, 15.45, 12.96, 11.8, 11.61, 11.28,
11.12, 10.49, 10.3, 8.75, 7.55, 7.32, 6.99, 6.88, 6.86, 6.58, 6.23]
plt.barh(range(len(x)), y)
plt.yticks(range(len(x)), x, fontproperties=myfont)
plt.xlabel('票房（单位：亿）', fontproperties=myfont)
plt.ylabel('电影名', fontproperties=myfont)
plt.title('2017年内地电影票房前20票房', fontproperties=myfont, fontsize=20)
plt.show()
绘制多个图例的条形图
假设你知道了列表a中电影分别在2017-09-14(b_14), 2017-09-15(b_15), 2017-09-16(b_16)三天的票房,为了展示列表中电影本身的票房以及同其他电影的数据对比情况,应该如何更加直观的呈现该数据?
a = ["猩球崛起3：终极之战", "敦刻尔克", "蜘蛛侠：英雄归来", "战狼2"]b_16 = [15746, 312, 4497, 319]
b_15 = [12357, 156, 2045, 168]
b_14 = [2358, 399, 2358, 362]
from matplotlib import pyplot as plt
from matplotlib import font_manager
plt.figure(figsize=(20, 8), dpi=80)
myfont = font_manager.FontProperties(fname="C:/Windows/Fonts/simhei.ttf")
a = ["猩球崛起3：终极之战", "敦刻尔克", "蜘蛛侠：英雄归来", "战狼2"]
b_14 = [2358, 399, 2358, 362]
b_15 = [12357, 156, 2045, 168]
b_16 = [15746, 312, 4497, 319]
bar_width = 0.2
x_14 = list(range(len(a)))
x_15 = [i+bar_width for i in x_14]
x_16 = [i+bar_width*2 for i in x_14]
plt.bar(x_14, b_14, width=bar_width, label='2017-09-14')
plt.bar(x_15, b_15, width=bar_width, label='2017-09-15')
plt.bar(x_16, b_16, width=bar_width, label='2017-09-16')
plt.legend()
plt.xticks(x_15, a, fontproperties=myfont)
plt.xlabel('电影', fontproperties=myfont)
plt.ylabel('票房', fontproperties=myfont)
plt.title('电影票房', fontproperties=myfont, fontsize=20)
plt.show()
绘制直方图
假设你获取了250部电影的时长(列表a中),希望统计出这些电影时长的分布状态(比如时长为100分钟到120分钟电影的数量,出现的频率)等信息,你应该如何呈现这些数据?
a = [131, 98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124, 101, 110, 116, 117, 110, 128, 128, 115, 99, 136, 126, 134, 95, 138, 117, 111, 78, 132, 124, 113, 150, 110, 117, 86, 95, 144, 105, 126, 130, 126, 130, 126, 116, 123, 106, 112, 138, 123, 86, 101, 99, 136, 123, 117, 119, 105, 137, 123, 128, 125, 104, 109, 134, 125, 127, 105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114, 105, 115, 132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134, 156, 106, 117, 127, 144, 139, 139, 119, 140, 83, 110, 102, 123, 107, 143, 115, 136, 118, 139, 123, 112, 118, 125, 109, 119, 133, 112, 114, 122, 109, 106, 123, 116, 131, 127, 115, 118, 112, 135, 115, 146, 137, 116, 103, 144, 83, 123, 111, 110, 111, 100, 154, 136, 100, 118, 119, 133, 134, 106, 129, 126, 110, 111, 109, 141, 120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126, 114, 140, 103, 130, 141, 117, 106, 114, 121, 114, 133, 137, 92, 121, 112, 146, 97, 137, 105, 98, 117, 112, 81, 97, 139, 113, 134, 106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110, 105, 129, 137, 112, 120, 113, 133, 112, 83, 94, 146, 133, 101, 131, 116, 111, 84, 137, 115, 122, 106, 144, 109, 123, 116, 111, 111, 133, 150]
from matplotlib import pyplot as plt
from matplotlib import font_manager
plt.figure(figsize=(20, 8), dpi=80)
myfont = font_manager.FontProperties(fname="C:/Windows/Fonts/simhei.ttf")
a = [131, 98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124, 101, 110, 116, 117, 110, 128, 128, 115, 99, 136, 126, 134, 95, 138, 117, 111, 78, 132, 124, 113, 150, 110, 117, 86, 95, 144, 105, 126, 130, 126, 130, 126, 116, 123, 106, 112, 138, 123, 86, 101, 99, 136, 123, 117, 119, 105, 137, 123, 128, 125, 104, 109, 134, 125, 127, 105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114, 105, 115, 132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134, 156, 106, 117, 127, 144, 139, 139, 119, 140, 83, 110, 102, 123, 107, 143, 115, 136, 118, 139, 123, 112,
118, 125, 109, 119, 133, 112, 114, 122, 109, 106, 123, 116, 131, 127, 115, 118, 112, 135, 115, 146, 137, 116, 103, 144, 83, 123, 111, 110, 111, 100, 154, 136, 100, 118, 119, 133, 134, 106, 129, 126, 110, 111, 109, 141, 120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126, 114, 140, 103, 130, 141, 117, 106, 114, 121, 114, 133, 137, 92, 121, 112, 146, 97, 137, 105, 98, 117, 112, 81, 97, 139, 113, 134, 106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110, 105, 129, 137, 112, 120, 113, 133, 112, 83, 94, 146, 133, 101, 131, 116, 111, 84, 137, 115, 122, 106, 144, 109, 123, 116, 111, 111, 133, 150]
# 组距
d = 3
# 计算组数
num_bins = (max(a)-min(a))//d
# 通过normed属性，设置y轴显示百分比
plt.hist(a, num_bins, normed=True)
plt.xticks(range(min(a), max(a)+d, d))
plt.xlabel('电影时长（分钟）', fontproperties=myfont)
plt.ylabel('占比（%）', fontproperties=myfont)
plt.title('电影时长在各个时间段的比例', fontproperties=myfont, fontsize=20)
# 绘制网格
plt.grid()
plt.show()
更多绘图工具
plot：可视化工具中的gitbub，相比于matplotlib更加简单，图形更加漂亮，同时兼容matplotlib和pandas
