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]:

    

# Split Into Training & Testing Sets
train, test = train_test_split(dataset,test_size=0.33)

# Write to Text Data
train.to_csv('clustering/train_data.csv',index=False)
test.to_csv('clustering/test_data.csv',index=False)


    

In [4]:

    

train.info()


    

    




<class 'pandas.core.frame.DataFrame'>
Int64Index: 2077 entries, 444 to 1262
Data columns (total 4 columns):
index    2077 non-null int64
x1       2077 non-null float64
x2       2077 non-null float64
y        2077 non-null int64
dtypes: float64(2), int64(2)
memory usage: 81.1 KB

In [5]:

    

test.info()


    

    




<class 'pandas.core.frame.DataFrame'>
Int64Index: 1023 entries, 1036 to 988
Data columns (total 4 columns):
index    1023 non-null int64
x1       1023 non-null float64
x2       1023 non-null float64
y        1023 non-null int64
dtypes: float64(2), int64(2)
memory usage: 40.0 KB