数据可视化

#绘图和可视化
import matplotlib.pyplot as plt

import numpy as np
data = np.arange(10)
data

array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

plt.plot(data)

[]

fig = plt.figure()
ax1 = fig.add_subplot(221)
ax2 = fig.add_subplot(222)
ax3 = fig.add_subplot(223)

plt.plot(np.random.randn(50).cumsum(),'k--')

[]

ax1.hist(np.random.randn(100), bins=20, color='k', alpha=0.3)

(array([ 1.,  3.,  2.,  3.,  2.,  8.,  1.,  4., 11., 11.,  7., 13., 10.,
         3.,  6.,  2.,  7.,  3.,  1.,  2.]),
 array([-2.62147564, -2.3737514 , -2.12602716, -1.87830293, -1.63057869,
        -1.38285445, -1.13513022, -0.88740598, -0.63968174, -0.39195751,
        -0.14423327,  0.10349097,  0.3512152 ,  0.59893944,  0.84666368,
         1.09438791,  1.34211215,  1.58983639,  1.83756062,  2.08528486,
         2.3330091 ]),
 )

 ax2.scatter(np.arange(30), np.arange(30) + 3 * np.random.randn(30))

fig,axes = plt.subplots(3,3)
axes

array([[,
        ,
        ],
       [,
        ,
        ],
       [,
        ,
        ]],
      dtype=object)

#调整subplot周围的间距
#subplot_adjust(left=None,bottom=None,top=None,wspace=None,hspace=None)

fig,axex = plt.subplots(2,2,sharex=True,sharey=True)
for i in range(2):
    for j in range(2):
        axex[i,j].hist(np.random.randn(500),bins=50,color='k',alpha=0.5)
plt.subplots_adjust(wspace=0,hspace=0) #0间距

#颜色，标记和线型
plt.plot(np.random.randn(30).cumsum(),'k--')

[]

plt.plot(np.random.randn(30).cumsum(), color='r', linestyle='dashed', marker='o')

[]

data = np.random.randn(30).cumsum()

plt.plot(data,'k-',drawstyle='steps-post',label='steps-post')

[]

plt.plot(data,'k--',label='Default')

[]

plt.legend(loc='best')    #标签

#刻度，标签和图例
fig = plt.figure()
ax = fig.add_subplot(111)
ax.set_xticks([0,250,500,750,1000])#设置刻度
ax.set_title("My first matplotlib plot")
ax.set_xlabel('Stages')
ax.plot(np.random.randn(1000).cumsum())

[]

#利用label添加图例
from numpy.random import randn
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(randn(1000).cumsum(),'k',label='one')
ax.plot(randn(1000).cumsum(),'k--',label='two')
ax.plot(randn(1000).cumsum(),'k.',label='three')
ax.legend(loc='best')

#注解以及在Subplot上绘图
#ax.annotate方法可以在指定的x和y坐标轴绘制标签
from datetime import datetime
import pandas as pd
fig = plt.figure()
ax = fig.add_subplot(111)
data = pd.read_csv('examples/spx.csv',index_col=0,parse_dates=True)
spx = data['SPX']
spx.plot(ax=ax,style='k-')
crisis_data = [
    (datetime(2007,10,11),'Peak of bull market'),
    (datetime(2008,3,12),'Bear Stearns Fails'),
    (datetime(2008,9,15),'Lehman Bankruptcy')
]
for date,label in crisis_data:#添加注解
    ax.annotate(label, xy=(date, spx.asof(date) + 75),
                xytext=(date, spx.asof(date) + 225),
                arrowprops=dict(facecolor='black', headwidth=4, width=2,
                                headlength=4),
                horizontalalignment='left', verticalalignment='top')
#设置起始和结束边界    
ax.set_xlim(['1/1/2007', '1/1/2011'])
ax.set_ylim([600, 1800])

ax.set_title('Important dates in the 2008-2009 financial crisis')

Text(0.5,1,'Important dates in the 2008-2009 financial crisis')

#绘制图形
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)

rect = plt.Rectangle((0.2, 0.75), 0.4, 0.15, color='k', alpha=0.3)
circ = plt.Circle((0.7, 0.2), 0.15, color='b', alpha=0.3)
pgon = plt.Polygon([[0.15, 0.15], [0.35, 0.4], [0.2, 0.6]],
                   color='g', alpha=0.5)

ax.add_patch(rect)
ax.add_patch(circ)
ax.add_patch(pgon)

#保存图片到本地
#plt.savefig('figpath.png', dpi=400, bbox_inches='tight')

#rc配置图片属性

#一，matplotlib简介
plt.plot([1,2,3],[5,7,4])
plt.show()

#二，图例，标题和标签
x = [1,2,3]
y = [5,7,4]

x2 = [1,2,3]
y2 = [10,14,12]

plt.plot(x,y,label='First Line')#为线指明名称
plt.plot(x2,y2,label='Second Line')
plt.xlabel('Plot Number')#为坐标轴命名
plt.ylabel('Important var')
plt.title('Interting Graph\nCheck it out')#为图命名
plt.legend()#显示
plt.show()

#三，条形图和直方图
#条形图bar
#直方图hist
plt.bar([1,3,5,7,9],[5,2,7,8,2],label='Example one')
plt.bar([2,4,6,8,10],[8,6,2,5,6],label='Example two',color='g')
plt.legend()
plt.xlabel('bar number')
plt.ylabel('bar height')
plt.title('Epic Graph\nAnother Line!')
plt.show()

population_ages = [22,55,62,45,21,22,34,42,42,4,99,102,110,120,121,122,130,111,115,112,80,75,65,54,44,43,42,48]
bins = [0,10,20,30,40,50,60,70,80,90,100,110,120,130]

plt.hist(population_ages,bins,histtype = 'bar',rwidth=0.8)

plt.xlabel('x')
plt.ylabel('y')
plt.title("Interesting Graph\nCheck it out")
plt.legend()
plt.show()

#四，散点图
#散点图scatter
x = [1,2,3,4,5,6,7,8]
y = [5,2,4,2,1,4,5,2]
plt.scatter(x,y,label='skitscat',color='k',s=25,marker='o')

plt.xlabel('x')
plt.ylabel('y')
plt.title('Interesting Graph\nCheck it out')
plt.legend()
plt.show()

#五，堆叠图
#堆叠图stackplot
#堆叠图用于显示『部分对整体』随时间的关系
days = [1,2,3,4,5]

sleeping = [7,8,6,11,7]
eating =   [2,3,4,3,2]
working =  [7,8,7,2,2]
playing =  [8,5,7,8,13]

plt.stackplot(days,sleeping,eating,working,playing,colors=['m','c','r','k'])
plt.xlabel('x')
plt.ylabel('y')
plt.title('Interesting Graph\nCheck it out')
plt.show()

#为不同数据添加标签
days = [1,2,3,4,5]

sleeping = [7,8,6,11,7]
eating =   [2,3,4,3,2]
working =  [7,8,7,2,2]
playing =  [8,5,7,8,13]

plt.plot([],[],color='m',label='Sleeping',linewidth=5)
plt.plot([],[],color='c', label='Eating', linewidth=5)
plt.plot([],[],color='r', label='Working', linewidth=5)
plt.plot([],[],color='k', label='Playing', linewidth=5)

plt.stackplot(days,sleeping,eating,working,playing,colors=['m','c','r','k'])
plt.xlabel('x')
plt.ylabel('y')
plt.title('Interesting Graph\nCheck it out')
plt.legend()
plt.show()

#六，饼图
#饼图pie
slices = [7,2,2,13]
activities = ['sleeping','eating','working','playing']
cols=['c','m','r','b']
plt.pie(slices,labels=activities,colors=cols,startangle=90,shadow=True,explode=(0,0.1,0,0),autopct='%1.1f%%')
#startangle:起始角度；shawdow:阴影；explode:拉出一个切片；autopct:显示百分比
plt.title('Interesting Graph\nCheck it out')
plt.show()

#七，从文件中加载数据

#从网络加载数据

#时间戳的转换

#3D绘图
from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import style
style.use('ggplot')

fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')

x3 = [1,2,3,4,5,6,7,8,9,10]
y3 = [5,6,7,8,2,5,6,3,7,2]
z3 = np.zeros(10)

dx = np.ones(10)
dy = np.ones(10)
dz = [1,2,3,4,5,6,7,8,9,10]

ax1.bar3d(x3, y3, z3, dx, dy, dz)


ax1.set_xlabel('x axis')
ax1.set_ylabel('y axis')
ax1.set_zlabel('z axis')

plt.show()

from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
from matplotlib import style

style.use('ggplot')

fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')

x = [1,2,3,4,5,6,7,8,9,10]
y = [5,6,7,8,2,5,6,3,7,2]
z = [1,2,6,3,2,7,3,3,7,2]

x2 = [-1,-2,-3,-4,-5,-6,-7,-8,-9,-10]
y2 = [-5,-6,-7,-8,-2,-5,-6,-3,-7,-2]
z2 = [1,2,6,3,2,7,3,3,7,2]

ax1.scatter(x, y, z, c='g', marker='o')
ax1.scatter(x2, y2, z2, c ='r', marker='o')

ax1.set_xlabel('x axis')
ax1.set_ylabel('y axis')
ax1.set_zlabel('z axis')

plt.show()

from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import style
style.use('ggplot')

fig = plt.figure()
ax1 = fig.add_subplot(111, projection='3d')

x, y, z = axes3d.get_test_data()

print(axes3d.__file__)
ax1.plot_wireframe(x,y,z, rstride = 3, cstride = 3)

ax1.set_xlabel('x axis')
ax1.set_ylabel('y axis')
ax1.set_zlabel('z axis')

plt.show()

C:\Anaconda\lib\site-packages\mpl_toolkits\mplot3d\axes3d.py

from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plot
import numpy as np
from matplotlib import style

x = np.linspace(-10, 10, 101)
y = x
x, y = np.meshgrid(x, y)
z = x ** 2 + y ** 2
ax = plot.subplot(111, projection='3d')
ax.plot_wireframe(x, y, z)
plot.show()

t = np.linspace(0, np.pi * 2, 100)
s = np.linspace(0, np.pi, 100)
t, s = np.meshgrid(t, s)
x = np.cos(t) * np.sin(s)
y = np.sin(t) * np.sin(s)
z = np.cos(s)
ax = plot.subplot(111, projection='3d')
ax.plot_wireframe(x, y, z)
plot.show()

#使用pandas和seaborn绘图

#线型图
import pandas as pd
s = pd.Series(np.random.randn(10).cumsum(),index=np.arange(0,100,10))
s.plot() #索引为x轴

df = pd.DataFrame(np.random.rand(10,4).cumsum(0),
                 columns=['A','B','C','D'],
                 index = np.arange(0,100,10))
df

	A	B	C	D
0	0.597104	0.589393	0.735777	0.767290
10	0.796663	0.869799	1.512095	1.604585
20	1.040885	1.346473	1.774127	2.543832
30	1.362510	1.362242	2.673032	2.946192
40	1.581508	2.174047	3.090430	3.386457
50	2.256305	2.629983	3.372889	4.060371
60	2.385461	3.130221	4.222364	4.311171
70	2.896483	3.595163	4.260149	4.468304
80	3.099516	4.335802	5.207953	5.096282
90	3.680995	4.779841	5.865332	5.155942

df.plot()

#柱形图
fig,axes = plt.subplots(2,1)
data = pd.Series(np.random.rand(16),index=list('abcdefghijklmnop'))
data.plot.bar(ax=axes[0],color='k',alpha=0.7) #x轴为基准
data.plot.barh(ax=axes[1],color='k',alpha=0.7) #y轴为基准

#堆积柱状图
data = pd.DataFrame(np.random.rand(6,4),
                   index=['one','two','three','four','five','six'],
                   columns=pd.Index(list('ABCD'),name='Genus'))
data

Genus	A	B	C	D
one	0.594853	0.189521	0.130311	0.998033
two	0.247427	0.221326	0.663043	0.141174
three	0.398459	0.242788	0.112028	0.985286
four	0.365095	0.167354	0.545588	0.185118
five	0.024861	0.389038	0.277269	0.950699
six	0.708134	0.898126	0.259565	0.452563

data.plot.bar()

#堆积柱状图
df.plot.barh(stacked=True, alpha=0.5)

tips = pd.read_csv('examples/tips.csv')
party_counts = pd.crosstab(tips['day'],tips['size'])
party_counts

size	1	2	3	4	5	6
day
Fri	1	16	1	1	0	0
Sat	2	53	18	13	1	0
Sun	0	39	15	18	3	1
Thur	1	48	4	5	1	3

party_counts = party_counts.loc[:,2:5]
party_pcts = party_counts.div(party_counts.sum(1),axis =0)
party_pcts

size	2	3	4	5
day
Fri	0.888889	0.055556	0.055556	0.000000
Sat	0.623529	0.211765	0.152941	0.011765
Sun	0.520000	0.200000	0.240000	0.040000
Thur	0.827586	0.068966	0.086207	0.017241

party_pcts.plot.bar()

#使用seaborn
import seaborn as sns
tips['tip_pct'] = tips['tip'] / (tips['total_bill'] - tips['tip']) #小费比例
tips.head()

	total_bill	tip	smoker	day	time	size	tip_pct
0	16.99	1.01	No	Sun	Dinner	2	0.063204
1	10.34	1.66	No	Sun	Dinner	3	0.191244
2	21.01	3.50	No	Sun	Dinner	3	0.199886
3	23.68	3.31	No	Sun	Dinner	2	0.162494
4	24.59	3.61	No	Sun	Dinner	4	0.172069

sns.barplot(x='tip_pct',y='day',data=tips,orient='h')

C:\Anaconda\lib\site-packages\scipy\stats\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

sns.barplot(x='tip_pct', y='day', hue='time', data=tips, orient='h')

C:\Anaconda\lib\site-packages\scipy\stats\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

#直方图和密度图
tips['tip_pct'].plot.hist(bins=50)

#密度图
tips['tip_pct'].plot.density()

#直方图和密度估计图
comp1 = np.random.normal(0,1,size=200)

comp2 = np.random.normal(10,2,size=200)

values = pd.Series(np.concatenate([comp1,comp2]))
sns.distplot(values,bins=100,color='k')

C:\Anaconda\lib\site-packages\scipy\stats\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

#散点图或点图
macro = pd.read_csv('examples/macrodata.csv')
data = macro[['cpi', 'm1', 'tbilrate', 'unemp']]
trans_data = np.log(data).diff().dropna()#计算对数差
trans_data[-5:]

	cpi	m1	tbilrate	unemp
198	-0.007904	0.045361	-0.396881	0.105361
199	-0.021979	0.066753	-2.277267	0.139762
200	0.002340	0.010286	0.606136	0.160343
201	0.008419	0.037461	-0.200671	0.127339
202	0.008894	0.012202	-0.405465	0.042560

sns.regplot('m1','unemp',data=trans_data)
plt.title('changes in log %s versus log %s'%('m1','unemp'))

C:\Anaconda\lib\site-packages\scipy\stats\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval





Text(0.5,1,'changes in log m1 versus log unemp')

#散点图矩阵
sns.pairplot(trans_data, diag_kind='kde', plot_kws={'alpha': 0.2})

C:\Anaconda\lib\site-packages\scipy\stats\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

#分面网格图 添加额外分组维度
sns.factorplot(x='day', y='tip_pct', hue='time', col='smoker',
                 kind='bar', data=tips[tips.tip_pct < 1])

C:\Anaconda\lib\site-packages\seaborn\categorical.py:3666: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.
  warnings.warn(msg)
C:\Anaconda\lib\site-packages\scipy\stats\stats.py:1713: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
  return np.add.reduce(sorted[indexer] * weights, axis=axis) / sumval

#箱型图
sns.factorplot(x='tip_pct', y='day', kind='box',
                 data=tips[tips.tip_pct < 0.5])

C:\Anaconda\lib\site-packages\seaborn\categorical.py:3666: UserWarning: The `factorplot` function has been renamed to `catplot`. The original name will be removed in a future release. Please update your code. Note that the default `kind` in `factorplot` (`'point'`) has changed `'strip'` in `catplot`.
  warnings.warn(msg)