Created
January 17, 2019 23:33
-
-
Save mohapsat/3fd56fe5e0f7bd84dd098573cc20c43d to your computer and use it in GitHub Desktop.
how-to-build-a-machine-learning-classifier-in-python-with-scikit-learn
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# https://www.digitalocean.com/community/tutorials/how-to-build-a-machine-learning-classifier-in-python-with-scikit-learn | |
from sklearn.datasets import load_breast_cancer | |
from sklearn.model_selection import train_test_split | |
from sklearn.naive_bayes import GaussianNB | |
from sklearn.metrics import accuracy_score | |
# Load dataset | |
data = load_breast_cancer() | |
# Organize our data | |
label_names = data['target_names'] | |
labels = data['target'] | |
feature_names = data['feature_names'] | |
features = data['data'] | |
# Look at our data | |
print(label_names) | |
print('Class label = ', labels[0]) | |
print(feature_names) | |
print(features[0]) | |
# Split our data | |
train, test, train_labels, test_labels = train_test_split(features, | |
labels, | |
test_size=0.33, | |
random_state=42) | |
# Initialize our classifier | |
gnb = GaussianNB() | |
# Train our classifier | |
model = gnb.fit(train, train_labels) | |
# Make predictions | |
preds = gnb.predict(test) | |
print(preds) | |
# Evaluate accuracy | |
print(accuracy_score(test_labels, preds)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment