17.11 - Jupyter Notebook http://localhost:8888/notebooks/17.11.

2024_Jupiter_Notebook_doc#

In [4]: # Rescale data (between 0 and 1)

from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import MinMaxScaler

filename = 'D:\\Dataset\pima-indians-diabetes.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)
print(rescaledX[0:5,:])

[[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 ]]

In [7]: # Standardize data (0 mean, 1 stdev)

from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import StandardScaler

filename = 'D:\\Dataset\pima-indians-diabetes.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 ]]

1 of 6 11/17/2024, 4:50 PM
17.11 - Jupyter Notebook http://localhost:8888/notebooks/17.11.2024_Jupiter_Notebook_doc#

In [8]: # Normalize data (length of 1)

from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import Normalizer

filename = 'D:\\Dataset\pima-indians-diabetes.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]]

In [10]: # binarization
from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import Binarizer

filename = 'D:\\Dataset\pima-indians-diabetes.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]

binarizer = Binarizer(threshold=6.0).fit(X)
binaryX = binarizer.transform(X)

# summarize transformed data

set_printoptions(precision=3)
print(binaryX[0:5,:])

[[0. 1. 1. 1. 0. 1. 0. 1.]
[0. 1. 1. 1. 0. 1. 0. 1.]
[1. 1. 1. 0. 0. 1. 0. 1.]
[0. 1. 1. 1. 1. 1. 0. 1.]
[0. 1. 1. 1. 1. 1. 0. 1.]]

2 of 6 11/17/2024, 4:50 PM
17.11 - Jupyter Notebook http://localhost:8888/notebooks/17.11.2024_Jupiter_Notebook_doc#

In [12]: # Feature Extraction with Univariate Statistical Tests (Chi-squared for classification
from pandas import read_csv
from numpy import set_printoptions
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2

# load data
filename = 'D:\\Dataset\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class'
dataframe = read_csv(filename, names=names)
array = dataframe.values

X = array[:,0:8]
Y = array[:,8]

# feature extraction
test = SelectKBest(score_func=chi2, k=3)
fit = test.fit(X, Y)

# summarize scores
set_printoptions(precision=3)
print(fit.scores_)
features = fit.transform(X)

# summarize selected features

print(features[0:5,:])

[ 111.52 1411.887 17.605 53.108 2175.565 127.669 5.393 181.304]

[[148. 0. 50.]
[ 85. 0. 31.]
[183. 0. 32.]
[ 89. 94. 21.]
[137. 168. 33.]]

3 of 6 11/17/2024, 4:50 PM
17.11 - Jupyter Notebook http://localhost:8888/notebooks/17.11.2024_Jupiter_Notebook_doc#

In [21]: # Feature Extraction with RFE

from pandas import read_csv
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression

# load data
filename = 'D:\\Dataset\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class'
dataframe = read_csv(filename, names=names)
array = dataframe.values
X = array[:,0:8]
Y = array[:,8]

# feature extraction
rfe = RFE(estimator=LogisticRegression(), n_features_to_select=3)
fit = rfe.fit(X, Y)

print(fit.n_features_)
print(fit.support_)
print(fit.ranking_)

C:\Users\CSE\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:45
8: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
https://scikit-learn.org/stable/modules/preprocessing.html (https://sciki
t-learn.org/stable/modules/preprocessing.html)
Please also refer to the documentation for alternative solver options:
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regres
sion (https://scikit-learn.org/stable/modules/linear_model.html#logistic-regr
ession)
n_iter_i = _check_optimize_result(

3
[ True False False False False True True False]
[1 2 4 5 6 1 1 3]

4 of 6 11/17/2024, 4:50 PM
17.11 - Jupyter Notebook http://localhost:8888/notebooks/17.11.2024_Jupiter_Notebook_doc#

In [23]: # Feature Extraction with PCA

from pandas import read_csv
from sklearn.decomposition import PCA

# load data
filename = 'D:\\Dataset\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class'
dataframe = read_csv(filename, names=names)
array = dataframe.values
X = array[:,0:8]
Y = array[:,8]

# feature extraction
pca = PCA(n_components=4)
fit = pca.fit(X)

# summarize components
print(fit.explained_variance_ratio_)
print(fit.components_)

[0.889]
[[-2.022e-03 9.781e-02 1.609e-02 6.076e-02 9.931e-01 1.401e-02
5.372e-04 -3.565e-03]]

5 of 6 11/17/2024, 4:50 PM
17.11 - Jupyter Notebook http://localhost:8888/notebooks/17.11.2024_Jupiter_Notebook_doc#

In [25]: # Feature Extraction with PCA

from pandas import read_csv
from sklearn.decomposition import PCA

# load data
filename = 'D:\\Dataset\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class'
dataframe = read_csv(filename, names=names)
array = dataframe.values

X = array[:,0:8]
Y = array[:,8]

# Standardize the features

X_scaled = StandardScaler().fit_transform(X)

# Apply PCA and automatically select the number of components to explain 95% of the va
pca = PCA(n_components=0.75)
X_pca = pca.fit_transform(X_scaled)

# Output: Number of components and explained variance

print(f"Number of components explaining 95% of variance: {X_pca.shape[1]}")
print(f"Explained Variance (in percentage): {pca.explained_variance_ratio_ * 100
print(f"Cumulative Explained Variance: {sum(pca.explained_variance_ratio_) * 100

# Show the transformed data (first 5 samples)

print("PCA Transformed Data (first 5 samples):\n", X_pca[:5])

Number of components explaining 95% of variance: 5

Explained Variance (in percentage): [26.18 21.64 12.87 10.944 9.529]
Cumulative Explained Variance: 81.16%
PCA Transformed Data (first 5 samples):
[[ 1.069 1.235 0.096 0.497 -0.11 ]
[-1.122 -0.734 -0.713 0.285 -0.39 ]
[-0.396 1.596 1.761 -0.07 0.906]
[-1.116 -1.271 -0.664 -0.579 -0.356]
[ 2.359 -2.185 2.963 4.033 0.593]]

In [ ]:

6 of 6 11/17/2024, 4:50 PM