matplotlib入门-直方图、饼图、散点图

直方图

首先需要区分清楚概念：直方图和条形图。

• 条形图：条形图用长条形表示每一个类别，长条形的长度表示类别的频数，宽度表示表示类别。
• 直方图：直方图是一种统计报告图，形式上也是一个个的长条形，但是直方图用长条形的面积表示频数，所以长条形的高度表示频数/组距，宽度表示组距，其长度和宽度均有意义。当宽度相同时，一般就用长条形长度表示频数。
  直方图一般用来描述等距数据，柱状图一般用来描述名称（类别）数据或顺序数据。直观上，直方图各个长条形是衔接在一起的，表示数据间的数学关系；条形图各长条形之间留有空隙，区分不同的类。

单分布

data = np.random.normal(0,20,1000)
bins = np.arange(-100,100,5)

plt.hist(data,bins=bins, edgecolor="black")
plt.xlim([min(data)-5,max(data)+5])
plt.title("直方图")

多分布

import random
data1 = [random.gauss(15,10) for i in range(500)]
data2 = [random.gauss(5,5) for i in range(500)]
bins = np.arange(-50,50,2.5)

plt.hist(data1,bins=bins,label='class 1',alpha = 0.3, edgecolor="black")
plt.hist(data2,bins=bins,label='class 2',alpha = 0.3, edgecolor="black")
plt.legend(loc='best')

散点图

mu_vec1 = np.array([0,0])
cov_mat1 = np.array([[2,0],[0,2]])
#构造数据，np.random.multivariate_normal构造一个二元正态分布矩阵
x1_samples = np.random.multivariate_normal(mu_vec1, cov_mat1, 100)
x2_samples = np.random.multivariate_normal(mu_vec1+0.2, cov_mat1+0.2, 100)
x3_samples = np.random.multivariate_normal(mu_vec1+0.4, cov_mat1+0.4, 100)

plt.figure(figsize = (8,6))
plt.scatter(x1_samples[:,0],x1_samples[:,1],marker ='x',color='blue',alpha=0.6,label='x1')
plt.scatter(x2_samples[:,0],x2_samples[:,1],marker ='o',color='red',alpha=0.6,label='x2')
plt.scatter(x3_samples[:,0],x3_samples[:,1],marker ='^',color='green',alpha=0.6,label='x3')
plt.legend(loc='best')
plt.show()

饼图

m = 51212.
f = 40742.
m_perc = m/(m+f)
f_perc = f/(m+f)

colors = ['navy','lightcoral']
labels = ["Male","Female"]

plt.figure(figsize=(5,5))
#explode缝隙大小，autopct显示百分比
paches,texts,autotexts = plt.pie([m_perc,f_perc],labels = labels,autopct = '%1.1f%%',explode=[0,0.05],colors = colors)

for text in texts+autotexts:
    text.set_fontsize(15)
for text in autotexts:
    text.set_color('white')

嵌套组合

from mpl_toolkits.axes_grid1.inset_locator import inset_axes

#数据标签
def autolabel(rects):
    for rect in rects:
        height = rect.get_height()
        ax1.text(rect.get_x() + rect.get_width()/2., 1.02*height,
        "{:,}".format(float(height)),
        ha='center', va='bottom',fontsize=18)
        
#构造数据
top10_arrivals_countries = ['CANADA','MEXICO','UNITED\nKINGDOM',\
                            'JAPAN','CHINA','GERMANY','SOUTH\nKOREA',\
                            'FRANCE','BRAZIL','AUSTRALIA']
top10_arrivals_values = [16.625687, 15.378026, 3.934508, 2.999718,\
                         2.618737, 1.769498, 1.628563, 1.419409,\
                         1.393710, 1.136974]
arrivals_countries = ['WESTERN\nEUROPE','ASIA','SOUTH\nAMERICA',\
                      'OCEANIA','CARIBBEAN','MIDDLE\nEAST',\
                      'CENTRAL\nAMERICA','EASTERN\nEUROPE','AFRICA']
arrivals_percent = [36.9,30.4,13.8,4.4,4.0,3.6,2.9,2.6,1.5]


fig, ax1 = plt.subplots(figsize=(20,12))
ax = ax1.bar(range(10),top10_arrivals_values,color='blue')
plt.xticks(range(10),top10_arrivals_countries,fontsize=18)
ax2 = inset_axes(ax1,width = 6,height = 6,loc = 5)
explode = (0.08, 0.08, 0.05, 0.05,0.05,0.05,0.05,0.05,0.05)
patches, texts, autotexts = ax2.pie(arrivals_percent,labels=arrivals_countries,autopct='%1.1f%%',explode=explode)

for text in texts+autotexts:
    text.set_fontsize(16)
for spine in ax1.spines.values():
    spine.set_visible(False)

autolabel(ax) 

3D

from mpl_toolkits.mplot3d import Axes3D

fig = plt.figure()
#设置3D
ax = Axes3D(fig)

x = np.arange(-4,4,0.25)
y = np.arange(-4,4,0.25)

X,Y = np.meshgrid(x,y)

Z = (X**2+Y**2)
ax.plot_surface(X,Y,Z,cmap='rainbow')
ax.contour(X,Y,Z,zdim='z',offset = -2 ,cmap='rainbow')

#ax.set_zlim(-2,2)
plt.show()

完整代码