dendograma.py

gistfile1.txt

# Load the Pandas libraries with alias 'pd' 
import pandas as pd 

from matplotlib import pyplot as plt
from scipy.cluster.hierarchy import dendrogram, linkage
from sklearn import datasets
import numpy as np



# Read data from file 'filename.csv' 
# (in the same directory that your python process is based)
# Control delimiters, rows, column names with read_csv (see later) 
data = pd.read_csv("C:\\Users\\jviejo\\womantech\\python\\small.csv", sep='\t') 
print(data.head())

X=data

#single, media, complete, ward
Z = linkage(X, 'complete' ,  metric='euclidean')

plt.figure(figsize=(10, 8))
plt.title('Dendograma single')
plt.xlabel('Indice')
plt.ylabel('Distancia')
max_d = 10
dendrogram(
        Z,
        leaf_rotation=90.,  
        leaf_font_size=8.,  
        show_contracted=True
    )
plt.axhline(y= max_d, c ='k')
plt.show()

gistfile2.txt

PRICE,MAINT,DOORS,PERSONS,SAFETY,CLASS
40000,2000,2,2,1,0
30000,500,3,5,3,1
10000,2000,5,4,3,1
20000,1000,2,4,2,1
40000,2000,5,2,3,0
30000,1000,4,2,3,0
30000,2000,3,4,3,0
20000,1500,2,2,2,0
10000,500,3,5,2,1
40000,1000,2,4,3,1