Seaborn案例展示

Seabron与matplotlib的对比

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd


x = np.linspace(0,10,500)
y = np.cumsum(np.random.randn(500,6),axis=0)

with plt.style.context('classic'):
    plt.plot(x,y)
    plt.legend("ABCDEF",ncol=2,loc='upper left')

import seaborn as sns

x = np.linspace(0,10,500)
y = np.cumsum(np.random.randn(500,6),axis=0)

sns.set()
plt.figure(figsize=(10,6))
plt.plot(x,y)
plt.legend("ABCDEF", ncol=2, loc='upper left')

<matplotlib.legend.Legend at 0x2ca875b1d48>

x = ['G1','G2','G3','G4','G5']
y = 2 * np.arange(1,6)

plt.figure(figsize=(8,4))
plt.barh(x,y,align='center',height=0.5,alpha=0.8,color='blue')
plt.tick_params(axis='both',labelsize=13)

 np.arange(1,6)
    

array([1, 2, 3, 4, 5])

plt.figure(figsize=(8,4))
x = ['G1','G2','G3','G4','G5']
y = 2 * np.arange(0,5,1)
sns.barplot(y,x,linewidth=5)

<matplotlib.axes._subplots.AxesSubplot at 0x2ca87886f88>

sns.barplot? # 查看参数

iris = sns.load_dataset('iris')

iris.head()

	sepal_length	sepal_width	petal_length	petal_width	species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa

sns.pairplot(data=iris,hue='species')

<seaborn.axisgrid.PairGrid at 0x2ca883d8308>

线形图

df = pd.DataFrame(np.random.randn(1000,4).cumsum(axis=0),columns=list('ABCD'),index=np.arange(1000))
df.head()

	A	B	C	D
0	-1.595314	1.170857	2.677344	-0.405985
1	-0.390817	-0.223825	3.907567	-0.536584
2	0.040567	-1.566435	6.047636	0.590226
3	-0.585928	0.154361	5.763213	0.066904
4	-0.462303	2.255227	8.420961	-0.527309

df.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x2ca88ae7908>

df = pd.DataFrame()

df.plot?

df2 = pd.DataFrame(np.random.rand(10,4),columns=['a','b','c','d'])
df2

	a	b	c	d
0	0.248392	0.423940	0.580817	0.239191
1	0.893146	0.055015	0.604495	0.698673
2	0.460849	0.123619	0.226723	0.655506
3	0.049188	0.560631	0.323672	0.663870
4	0.618608	0.682903	0.180760	0.885659
5	0.236477	0.007245	0.676800	0.602075
6	0.519545	0.670298	0.365168	0.920002
7	0.937450	0.151158	0.328480	0.605270
8	0.030191	0.991296	0.608642	0.105120
9	0.322313	0.234576	0.593675	0.775744

多组数据图

df2.plot.bar()

<matplotlib.axes._subplots.AxesSubplot at 0x2ca886ae148>

多组数据累加竖图

df2.plot.bar(stacked=True)

<matplotlib.axes._subplots.AxesSubplot at 0x2ca886a3788>

df2.plot.barh(stacked=True)

<matplotlib.axes._subplots.AxesSubplot at 0x2ca888509c8>

直方图和密度图

df4 = pd.DataFrame({'A':np.random.randn(1000)-3,'B':np.random.randn(1000),'C':np.random.randn(1000)+3})
df4.head()

	A	B	C
0	-1.994334	0.758106	2.075204
1	-1.467124	-1.909643	1.627641
2	-1.833122	-1.133339	4.232661
3	-3.332893	-1.198335	2.857277
4	-3.581459	-0.131318	1.888054

• 普通直方图

df4.plot.hist(bins=50)

<matplotlib.axes._subplots.AxesSubplot at 0x2ca89062308>

• 累计直方图

df4['A'].plot.hist(cumulative=True)

<matplotlib.axes._subplots.AxesSubplot at 0x2ca87dca408>

df4['A'].plot(kind='kde')

<matplotlib.axes._subplots.AxesSubplot at 0x2ca88e0f508>

• 差分

df = pd.DataFrame(np.random.randn(1000,4).cumsum(axis=0),columns=list('ABCD'),index=np.arange(1000))

df.head()

	A	B	C	D
0	-0.346780	-1.407473	-1.371878	-0.787592
1	0.179860	-0.871498	-2.049004	-0.465820
2	-0.363072	0.280543	-3.830633	0.676657
3	-0.029469	-0.637807	-4.507969	-1.133796
4	0.152041	1.118945	-4.432778	-2.893848

df.diff().hist(bins=50,color='r')

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8905A6C8>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA88F7E588>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8B0A7DC8>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8B0DC708>]],
      dtype=object)

散点图

housing = pd.read_csv(r'G:\BaiduNetdiskDownload\02-Python基础+数据科学入门训练营-【官网最新】\00-资料\00-资料\代码及数据资料合集\03代码及数据资料合集\课程代码及数据\13 第13章 Matplotlib库\housing.csv')

housing.head()

	longitude	latitude	housing_median_age	total_rooms	total_bedrooms	population	households	median_income	median_house_value	ocean_proximity
0	-122.23	37.88	41.0	880.0	129.0	322.0	126.0	8.3252	452600.0	NEAR BAY
1	-122.22	37.86	21.0	7099.0	1106.0	2401.0	1138.0	8.3014	358500.0	NEAR BAY
2	-122.24	37.85	52.0	1467.0	190.0	496.0	177.0	7.2574	352100.0	NEAR BAY
3	-122.25	37.85	52.0	1274.0	235.0	558.0	219.0	5.6431	341300.0	NEAR BAY
4	-122.25	37.85	52.0	1627.0	280.0	565.0	259.0	3.8462	342200.0	NEAR BAY

基于地理数据人口\房价可视化

# 圆的半径大小代表每一个区域人口数量(S),颜色代表价格(C),用预定义的jet标可视化
with sns.axes_style('white'):
    housing.plot(kind='scatter',x='longitude',y='latitude',alpha=0.6,
                s=housing['population']/100,label='population',c='median_house_value',cmap='jet',
                colorbar=True,figsize=(12,8))
    plt.legend()
    plt.axis([-123,-113.5,32,43])

housing.plot(kind='scatter',x='median_income',y='median_house_value',alpha=0.8)

'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'.  Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.





<matplotlib.axes._subplots.AxesSubplot at 0x2ca8bb9f108>

df = pd.DataFrame(np.random.randn(1000,4).cumsum(axis=0),columns=list("ABCD"),index=np.arange(1000))
df.head()

	A	B	C	D
0	-0.032738	-1.294730	1.365266	-0.244759
1	-1.018330	0.346097	1.765546	-1.483448
2	-1.660975	-0.424961	-0.627905	-0.589975
3	-0.823413	2.013352	0.374114	-1.578334
4	0.221646	3.887125	1.166699	-2.109392

df.plot(subplots=True,figsize=(6,16))

array([<matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8BB8F148>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8BD7AFC8>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8B8A8648>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8B8119C8>],
      dtype=object)

df.plot(subplots=True,layout=(2,2),figsize=(16,6),sharex=False)

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8BFF3608>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8C0005C8>],
       [<matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8CC8D608>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x000002CA8CCBEA88>]],
      dtype=object)