sklearn.datasets iris数据集绘图 seaborn and matplotlib

sklearn.datasets iris数据集绘图 seaborn and matplotlib

from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
from matplotlib.patches import Ellipse, FancyArrowPatch, ArrowStyle
import pandas as pd
import seaborn as sns
import warnings
import numpy as np
import scipy.stats as ss
warnings.filterwarnings('ignore')

data = sns.load_dataset('iris')
df=data
df.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.jointplot plt版

import seaborn as sns
sns.set(style="ticks")

iris = sns.load_dataset("iris")
g = sns.jointplot("sepal_length", "sepal_width", data=iris,
                  kind="reg", truncate=False,
                  color='m', height=6)

sns.pairplot

sns.pairplot(df, hue="species",palette='deep')

<seaborn.axisgrid.PairGrid at 0x27774c4b108>

sns.palette

print(sns.color_palette())
sns.palplot(sns.color_palette())

[(0.2980392156862745, 0.4470588235294118, 0.6901960784313725), (0.8666666666666667, 0.5176470588235295, 0.3215686274509804), (0.3333333333333333, 0.6588235294117647, 0.40784313725490196), (0.7686274509803922, 0.3058823529411765, 0.3215686274509804), (0.5058823529411764, 0.4470588235294118, 0.7019607843137254), (0.5764705882352941, 0.47058823529411764, 0.3764705882352941), (0.8549019607843137, 0.5450980392156862, 0.7647058823529411), (0.5490196078431373, 0.5490196078431373, 0.5490196078431373), (0.8, 0.7254901960784313, 0.4549019607843137), (0.39215686274509803, 0.7098039215686275, 0.803921568627451)]

matplotlib.patches : Ellipse, FancyArrowPatch, ArrowStyle

sns.set_style('ticks')
fig,ax=plt.subplots(figsize=(8,6))
ax=sns.scatterplot(data=df,x='petal_width',y='sepal_width',hue="species",palette=sns.color_palette()[:3])
means=[]
covariances=[]
labels=[(i,k) for i,k in zip(df['species'].unique(),[i for i in sns.color_palette()[:3]])]
x='petal_width'
y='sepal_width'
inputs=df.loc[:,[x,y]].values
targets=df.loc[:,'species'].values

for label in labels:
    selection = targets == label[0]
    means.append(np.mean(inputs[selection,:],axis=0))
    covariances.append(np.cov(inputs[selection,:],rowvar=0))
stdevs  = []
vectors = []
indexes = np.argsort([ np.arctan2(*mean) for mean in means ])
for mean, covariance, idx in zip(means, covariances, indexes):
    eigvals, eigvecs = np.linalg.eig(covariance)
    indexes = eigvals.argsort()[::-1]
    eigvals = eigvals[indexes]
    eigvecs = eigvecs[:, indexes]
    if all(np.sign(eigvecs[:,0]) == [-1, -1]):
        eigvecs[:,0] *= -1
    vectors.append(eigvecs[:,0])
    stdevs.append(np.sqrt(eigvals[0]))
    ax.add_patch(Ellipse(
            xy     = mean,
            width  = np.sqrt(eigvals[0]*ss.chi2.isf(0.05, 2)) * 2,
            height = np.sqrt(eigvals[1]*ss.chi2.isf(0.05, 2)) * 2,
            angle  = np.degrees(np.arctan2(*eigvecs[::-1,0])),
            fill   = False,
            edgecolor = labels[idx][1]
        ))
    for diff in (np.sqrt(eigvals) * eigvecs).transpose():
        ax.add_patch(FancyArrowPatch(
            posA = mean,
            posB = mean + diff,
            arrowstyle = ArrowStyle.Simple(
                head_width  = 8,
                tail_width  = 3,
                head_length = 8,
            ),
            facecolor = 'grey',
            edgecolor = 'white',
        ))    
        ax.plot(*mean, '*', color = 'yellow', markersize = 10, markeredgecolor = 'grey')

sns.despine()