本笔记来源于B站Up主: 有Li 的影像组学系列教学视频

本节(36)主要介绍: 聚类树状图Dendrogram的python实现

应该注意一下scipy版本的问题：scipy 1.5.0版本画聚类树状图要报错，1.5.2或者1.2.1版本就没有问题。

# modified from https://www.machinelearningplus.com/plots/top-50-matplotlib-visualizations-the-master-plots-python/

import matplotlib.pyplot as plt

import pandas as pd

import scipy.cluster.hierarchy as shc

# import data

df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/USArrests.csv')

print(df)

# Plot

plt.figure(figsize=(16, 10), dpi= 80)

plt.title("USArrests Dendograms", fontsize=22)

dend = shc.dendrogram(shc.linkage(df[['Murder', 'Assault', 'UrbanPop', 'Rape']],

method='ward'), labels=df.State.values, color_threshold=100)

plt.xticks(fontsize=12)

#plt.savefig('USArrests_Dendograms.png')

plt.show()

USArrests_Dendograms.png

import numpy as np

import pandas as pd

from sklearn.utils import shuffle

from sklearn.preprocessing import StandardScaler

from sklearn.linear_model import LassoCV

xlsx1_filePath = '/Users/Mac/Documents/JianShuNotes/data/aa.xlsx'

xlsx2_filePath = '/Users/Mac/Documents/JianShuNotes/data/bb.xlsx'

data_1 = pd.read_excel(xlsx1_filePath)

data_2 = pd.read_excel(xlsx2_filePath)

rows_1,__ = data_1.shape

rows_2,__ = data_2.shape

data_1.insert(0,'label',[0]*rows_1)

data_2.insert(0,'label',[1]*rows_2)

data = pd.concat([data_1,data_2])

data = shuffle(data)

data = data.fillna(0)

X = data[data.columns[1:]]

y = data['label']

colNames = X.columns

X = X.astype(np.float64)

X = StandardScaler().fit_transform(X) #new knowledge

X = pd.DataFrame(X)

X.columns = colNames

# LASSO

alphas = np.logspace(-3,1,50)

model_lassoCV = LassoCV(alphas = alphas, cv = 10, max_iter = 100000).fit(X,y) #cv, cross-validation

print(model_lassoCV.alpha_)

coef = pd.Series(model_lassoCV.coef_,index = X.columns) #new knowledge

# print(coef)

print("Lasso picked " + str(sum(coef != 0)) + " variables and eliminated the other " + str(sum(coef == 0))+ 'variables')

print(coef[coef != 0])

X = X[coef[coef != 0].index]

print(X.head())

# Plot

plt.figure(figsize=(5, 5), dpi= 80)

plt.title("Radiomic Dendograms", fontsize=22)

dend = shc.dendrogram(shc.linkage(X[:].T, method='ward'), labels=X.columns, color_threshold=20) #参数调整

plt.xticks(fontsize=12,rotation = 60, ha = 'right')

plt.show()

Radiomic Dendograms.png