Lesson 7 Prepare Your Data For Machine Learning

1. Rescale data.
2. Standardize data.
3. Normalize data.
4. Binarize data.

Rescale data.

Rescale to between 0, 1

# Rescale data (between 0 and 1)
from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import MinMaxScaler
filename = 'pima-indians-diabetes.data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(filename, names=names)
array = dataframe.values
# separate array into input and output components
X = array[:,0:8]
Y = array[:,8]
scaler = MinMaxScaler(feature_range=(0, 1))
rescaledX = scaler.fit_transform(X)
# summarize transformed data
set_printoptions(precision=3)

[[ 0.353  0.744  0.59   0.354  0.     0.501  0.234  0.483]
 [ 0.059  0.427  0.541  0.293  0.     0.396  0.117  0.167]
 [ 0.471  0.92   0.525  0.     0.     0.347  0.254  0.183]
 [ 0.059  0.447  0.541  0.232  0.111  0.419  0.038  0.   ]
 [ 0.     0.688  0.328  0.354  0.199  0.642  0.944  0.2  ]]

Standardize Data

x(new) = (x - mean) / stdev.

# Standardize data (0 mean, 1 stdev)
from sklearn.preprocessing import StandardScaler
from pandas import read_csv
from numpy import set_printoptions
filename = 'pima-indians-diabetes.data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(filename, names=names)
array = dataframe.values
# separate array into input and output components
X = array[:,0:8]
Y = array[:,8]
scaler = StandardScaler().fit(X)
rescaledX = scaler.transform(X)
# summarize transformed data
set_printoptions(precision=3)
print(rescaledX[0:5,:])

[[ 0.64   0.848  0.15   0.907 -0.693  0.204  0.468  1.426]
 [-0.845 -1.123 -0.161  0.531 -0.693 -0.684 -0.365 -0.191]
 [ 1.234  1.944 -0.264 -1.288 -0.693 -1.103  0.604 -0.106]
 [-0.845 -0.998 -0.161  0.155  0.123 -0.494 -0.921 -1.042]
 [-1.142  0.504 -1.505  0.907  0.766  1.41   5.485 -0.02 ]]

Normalize Data

Useful when data have a lot of zeroes (result value between 0, 1)

# Normalize data (length of 1)
from sklearn.preprocessing import Normalizer
from pandas import read_csv
from numpy import set_printoptions
filename = 'pima-indians-diabetes.data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(filename, names=names)
array = dataframe.values
# separate array into input and output components
X = array[:,0:8]
Y = array[:,8]
scaler = Normalizer().fit(X)
normalizedX = scaler.transform(X)
# summarize transformed data
set_printoptions(precision=3)
print(normalizedX[0:5,:])

[[ 0.034  0.828  0.403  0.196  0.     0.188  0.004  0.28 ]
 [ 0.008  0.716  0.556  0.244  0.     0.224  0.003  0.261]
 [ 0.04   0.924  0.323  0.     0.     0.118  0.003  0.162]
 [ 0.007  0.588  0.436  0.152  0.622  0.186  0.001  0.139]
 [ 0.     0.596  0.174  0.152  0.731  0.188  0.01   0.144]]

Binarize Data

Only 0 and 1

# Normalize data (length of 1)
from sklearn.preprocessing import Normalizer
from pandas import read_csv
from numpy import set_printoptions
filename = 'pima-indians-diabetes.data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(filename, names=names)
array = dataframe.values
# separate array into input and output components
X = array[:,0:8]
Y = array[:,8]
scaler = Normalizer().fit(X)
normalizedX = scaler.transform(X)
# summarize transformed data
set_printoptions(precision=3)
print(normalizedX[0:5,:])

[[ 0.034  0.828  0.403  0.196  0.     0.188  0.004  0.28 ]
 [ 0.008  0.716  0.556  0.244  0.     0.224  0.003  0.261]
 [ 0.04   0.924  0.323  0.     0.     0.118  0.003  0.162]
 [ 0.007  0.588  0.436  0.152  0.622  0.186  0.001  0.139]
 [ 0.     0.596  0.174  0.152  0.731  0.188  0.01   0.144]]