Last active
September 20, 2019 03:43
-
-
Save amitrani6/cd178a37b6397cbeb2c5f899502b3161 to your computer and use it in GitHub Desktop.
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
# The following code is adapted from Learn.Co's | |
# Naive Bayes Classifier lessons and labs | |
from sklearn.preprocessing import LabelEncoder | |
from sklearn.model_selection import train_test_split | |
from sklearn.preprocessing import StandardScaler | |
from sklearn.naive_bayes import GaussianNB | |
#All the feature columns from the 'countries_classify' data frame | |
X = countries_classify.iloc[:, 3:-1].values | |
#The target variable column from the 'countries_classify' data frame | |
Y = countries_classify.iloc[:, 1:2].values | |
#This converts the Y column's values to numbers representing the continents | |
labelencoder_Y = LabelEncoder() | |
Y = labelencoder_Y.fit_transform(Y) | |
#This creates a train set and test set of data with an 80/20 split | |
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 0) | |
#Scale the features data frame X | |
scaler = StandardScaler() | |
X_train_scaled = scaler.fit_transform(X_train) | |
X_test_scaled = scaler.transform(X_test) | |
#Calculate the class prior probabilities for each continent | |
classifier = GaussianNB() | |
classifier.fit(X_train_scaled, Y_train) | |
#Make a prediction for the test data | |
Y_pred = classifier.predict(X_test_scaled) | |
#Calculate the accuracy of the data | |
accuracy_score(Y_test, Y_pred) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment