Created
September 11, 2020 04:05
-
-
Save amansk2050/32add953a8e6d4a229f448a29b9351ad to your computer and use it in GitHub Desktop.
Naive Bayes approach without much optimization
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
#Import scikit-learn dataset library | |
from sklearn import datasets | |
#Load dataset | |
wine = datasets.load_wine() | |
# print the names of the 13 features | |
print("Features: ", wine.feature_names) | |
# print the label type of wine(class_0, class_1, class_2) | |
print("Labels: ", wine.target_names) | |
# print data(feature)shape | |
wine.data.shape | |
# print the wine data features (top 5 records) | |
print(wine.data[0:5]) | |
# print the wine labels (0:Class_0, 1:class_2, 2:class_2) | |
print(wine.target) | |
# Import train_test_split function | |
from sklearn.model_selection import train_test_split | |
# Split dataset into training set and test set | |
X_train, X_test, y_train, y_test = train_test_split(wine.data, wine.target, test_size=0.3,random_state=109) # 70% training and 30% test | |
#Import Gaussian Naive Bayes model | |
from sklearn.naive_bayes import GaussianNB | |
#Create a Gaussian Classifier | |
gnb = GaussianNB() | |
#Train the model using the training sets | |
gnb.fit(X_train, y_train) | |
#Predict the response for test dataset | |
y_pred = gnb.predict(X_test) | |
#Import scikit-learn metrics module for accuracy calculation | |
from sklearn import metrics | |
# Model Accuracy, how often is the classifier correct? | |
print("Accuracy:",metrics.accuracy_score(y_test, y_pred)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment