parallel coordinates 图做法

parallel coordinates 图做法

Parallel coordinates are a common way of visualizing high-dimensional geometry and analyzing multivariate data.

To show a set of points in an n-dimensional space, a backdrop is drawn consisting of n parallel lines, typically vertical and equally spaced. A point in n-dimensional space is represented as a polyline with vertices on the parallel axes; the position of the vertex on the i-th axis corresponds to the i-th coordinate of the point.

举例：三种方法

from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import warnings
import numpy as np

warnings.filterwarnings('ignore')
sns.set(style="ticks")

pandas.plotting.parallel_coordinates

iris = sns.load_dataset("iris")
print(iris.head())
pd.plotting.parallel_coordinates(iris,'species',color=sns.color_palette("Set2"),alpha=0.3)

   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





<matplotlib.axes._subplots.AxesSubplot at 0x1a5c6345808>

matplotlib.pyplot

fig,ax=plt.subplots()
labels=dict(zip(iris['species'].unique(),sns.color_palette("Set2")[0:3]))

for i in iris.index:
    ax=plt.plot(iris.iloc[i,:-1],c=labels.get(iris.iloc[i,-1]),alpha=0.3,)
plt.legend(labels)

<matplotlib.legend.Legend at 0x1a5c92af1c8>

seaborn.lineplot

grouped=iris.groupby('species')
res=[]
for i in grouped:
    i[1].loc[:,'unit']=np.arange(i[1].shape[0])
    res.append(i[1])
iris_df=pd.concat([i for i in res],axis=0  )
iris_df = pd.melt(iris_df, id_vars=["species","unit"],var_name="measurement")
iris_df

	species	unit	measurement	value
0	setosa	0	sepal_length	5.1
1	setosa	1	sepal_length	4.9
2	setosa	2	sepal_length	4.7
3	setosa	3	sepal_length	4.6
4	setosa	4	sepal_length	5.0
…	…	…	…	…
595	virginica	45	petal_width	2.3
596	virginica	46	petal_width	1.9
597	virginica	47	petal_width	2.0
598	virginica	48	petal_width	2.3
599	virginica	49	petal_width	1.8

600 rows × 4 columns

ax = sns.lineplot(x="measurement", y="value", hue="species",ci=None,units='unit',estimator=None,alpha=0.3,
                  data=iris_df)