Holdout.py

import pandas as pd

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

# Import breast cancer (dataset) object from sklearn library
breast_cancer = datasets.load_breast_cancer()

# Define features need to be extracted from breast cancer (dataset) object
feature_names = ['mean radius', 'mean texture', 'mean perimeter', 'mean area',
        'mean smoothness', 'mean compactness', 'mean concavity',
        'mean concave points', 'mean symmetry', 'mean fractal dimension',
        'radius error', 'texture error', 'perimeter error', 'area error',
        'smoothness error', 'compactness error', 'concavity error',
        'concave points error', 'symmetry error', 'fractal dimension error',
        'worst radius', 'worst texture', 'worst perimeter', 'worst area',
        'worst smoothness', 'worst compactness', 'worst concavity',
        'worst concave points', 'worst symmetry', 'worst fractal dimension']

# Extract breast cancer dataset and create a dataframe out of it
fulldata = pd.DataFrame(breast_cancer.data, columns=feature_names)

# Print the shape of the dataframe
print (fulldata.shape)
>> (569, 30)

# Extract breast cancer dataset's target
target = breast_cancer.target

# Create Training and Test (Hold-out) datasets. Split ratio 75:25
X_train, X_test, y_train, y_test = train_test_split(fulldata, target, test_size=0.25, random_state=111)

print ("Train Data Shape: ", X_train.shape, y_train.shape)
print ("Test Data Shape: ", X_test.shape, y_test.shape)
>> Train Data Shape:  (426, 30) (426,)
>> Test Data Shape:  (143, 30) (143,)
    
# Create a Logistic Regression object
logistic_regression = LogisticRegression()

# Train a Logistic Regression model with Train dataset
logistic_regression.fit(X_train, y_train)

# Compute the accuracy score and print it
accuracy_score = logistic_regression.score(X_test, y_test)
print (accuracy_score)
>> 0.951048951049