Homework 2 - Clustering Dataset

In [1]:

    

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split


    

In [2]:

    

# Basic IO
filename = 'clustering/dataset.csv'
dataset  = pd.read_csv(filename)

# Randomize Dataset
dataset = dataset.sample(frac=1,random_state=32).reset_index()
dataset.head()


    

    
Out[2]:







  

    

      

      
index
      
x1
      
x2
      
y
    
  
  

    

      
0
      
1123
      
24.8697
      
14.6393
      
12
    
    

      
1
      
2554
      
23.3448
      
16.4908
      
26
    
    

      
2
      
2362
      
26.6545
      
22.6042
      
24
    
    

      
3
      
687
      
21.8222
      
27.1835
      
7
    
    

      
4
      
18
      
25.8840
      
6.3294
      
1
    
  

In [3]:

    

dataset.drop(['index','y'], axis=1, inplace=True)
dataset.head()


    

    
Out[3]:







  

    

      

      
x1
      
x2
    
  
  

    

      
0
      
24.8697
      
14.6393
    
    

      
1
      
23.3448
      
16.4908
    
    

      
2
      
26.6545
      
22.6042
    
    

      
3
      
21.8222
      
27.1835
    
    

      
4
      
25.8840
      
6.3294
    
  

In [4]:

    

# Write to Text Data
dataset.to_csv('clustering/synth_all.csv', index=False)