SciKit Learn Preprocessing Overview

In [1]:

    

import numpy as np


    

In [2]:

    

# Importing MinMaxScaler
from sklearn.preprocessing import MinMaxScaler


    

In [3]:

    

data = np.random.randint(0,100,(10,2))


    

In [4]:

    

data


    

    
Out[4]:





array([[84, 14],
       [14, 40],
       [81, 60],
       [90, 63],
       [32, 84],
       [82, 34],
       [48, 84],
       [32, 88],
       [ 0, 13],
       [17, 29]])

In [5]:

    

scaler_model = MinMaxScaler()


    

In [6]:

    

scaler_model.fit(data)


    

    




C:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\validation.py:429: DataConversionWarning: Data with input dtype int32 was converted to float64 by MinMaxScaler.
  warnings.warn(msg, _DataConversionWarning)






    
Out[6]:





MinMaxScaler(copy=True, feature_range=(0, 1))

In [7]:

    

scaler_model.transform(data)


    

    
Out[7]:





array([[0.93333333, 0.01333333],
       [0.15555556, 0.36      ],
       [0.9       , 0.62666667],
       [1.        , 0.66666667],
       [0.35555556, 0.94666667],
       [0.91111111, 0.28      ],
       [0.53333333, 0.94666667],
       [0.35555556, 1.        ],
       [0.        , 0.        ],
       [0.18888889, 0.21333333]])

In [8]:

    

# In one step
result = scaler_model.fit_transform(data)


    

    




C:\ProgramData\Anaconda3\lib\site-packages\sklearn\utils\validation.py:429: DataConversionWarning: Data with input dtype int32 was converted to float64 by MinMaxScaler.
  warnings.warn(msg, _DataConversionWarning)

In [9]:

    

result


    

    
Out[9]:





array([[0.93333333, 0.01333333],
       [0.15555556, 0.36      ],
       [0.9       , 0.62666667],
       [1.        , 0.66666667],
       [0.35555556, 0.94666667],
       [0.91111111, 0.28      ],
       [0.53333333, 0.94666667],
       [0.35555556, 1.        ],
       [0.        , 0.        ],
       [0.18888889, 0.21333333]])

In [10]:

    

import pandas as pd


    

In [11]:

    

data = pd.DataFrame(data = np.random.randint(0, 101, size = (50,4)),
                    columns = ['f1','f2','f3','label'])


    

In [12]:

    

data.head()


    

    
Out[12]:







  

    

      

      
f1
      
f2
      
f3
      
label
    
  
  

    

      
0
      
48
      
55
      
73
      
37
    
    

      
1
      
7
      
88
      
83
      
86
    
    

      
2
      
5
      
52
      
21
      
16
    
    

      
3
      
46
      
8
      
7
      
36
    
    

      
4
      
96
      
86
      
35
      
41
    
  

In [13]:

    

x = data[['f1', 'f2', 'f3']] # Alternatively x = data.drop('label',axis=1)
y = data['label']


    

In [14]:

    

# Train-test split
from sklearn.model_selection import train_test_split


    

In [15]:

    

# Splitting the dataset into train and test dataset with given test size and random state (data will be shuffled)
X_train, X_test, y_train, y_test = train_test_split(x, y, 
                                                    test_size = 0.3, 
                                                    random_state = 101)


    

In [16]:

    

X_train.shape


    

    
Out[16]:





(35, 3)

In [17]:

    

X_train[0:5]


    

    
Out[17]:







  

    

      

      
f1
      
f2
      
f3
    
  
  

    

      
3
      
46
      
8
      
7
    
    

      
41
      
42
      
54
      
31
    
    

      
30
      
35
      
61
      
99
    
    

      
15
      
58
      
12
      
48
    
    

      
20
      
38
      
3
      
79
    
  

In [18]:

    

X_test.shape


    

    
Out[18]:





(15, 3)

In [19]:

    

y_train.shape


    

    
Out[19]:





(35,)

In [20]:

    

y_test.shape


    

    
Out[20]:





(15,)