First program to predict from real world data

02-RealWorldData-Program.py

'''
A simple program to calculate if a tumor is malignant or benign and judging our trained gaussianNB classifiers accuracy
using scikit learn module accuracy_score
'''
from sklearn.datasets import load_breast_cancer # Importing cancer dataset
from sklearn.model_selection import train_test_split # Importing train_test_split module to split our bulk data into training data and testing data
from sklearn.naive_bayes import GaussianNB # Importing classifier called 'GaussianNaiveBayes'
from sklearn.metrics import accuracy_score # Importing scikit learn module to evaluate accuracy of our classifier model

#Storing imported data into 'data'
data = load_breast_cancer()

# Organize our data for usage convinency
label_names = data['target_names']
labels = data['target']
feature_names = data['feature_names']
features = data['data']

# Remove quotations to print description of dataset
'''
description = data['DESCR']
print (description)
'''

# Remove the quotations to view the organized data.
''' 
print(label_names)
print('Class label = ', labels[0])
print(feature_names)
print(features[0])
'''

# Splitting our data into training data and testing data from the bulk data
# Where 33 percent data is stored as testing purpose and rest for training purpose
train, test, train_labels, test_labels = train_test_split(features, labels, test_size=0.33, random_state=42)

# Initialize classifier 'GaussianNB'
imported_classifier = GaussianNB()

# Training our classifier by feeding training data
trained_classifier = imported_classifier.fit(train, train_labels)

# Feeding testing data to our trained classifier to predict the probablity
predictions = trained_classifier.predict(test)

# Printing out the predctions
print(predictions)

print("\n")

# Evaluate accuracy by using the imported scikit module
print(accuracy_score(test_labels, predictions))