# ========================================================= # Basic pipeline # From: www.youtube.com/watch?v=84gqSblcBEF # ========================================================= from sklearn import datasets iris = datasets.load_iris() x = iris.data y = iris.target # --- create train and test data from sklearn.cross_validation import train_test_split x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.5) # --- create classifier using train data # --- use decision tree classifier #from sklearn import tree #my_classifier = tree.DecisionTreeClassifier() # --- create nearest neighbor classifier from sklearn.neighbors import KNeighborsClassifier my_classifier = KNeighborsClassifier() my_classifier.fit(x_train, y_train) # --- create test data predictions predictions = my_classifier.predict(x_test) print(predictions) # --- how accuracet is the classifier based on the train/test data from sklearn.metrics import accuracy_score print(accuracy_score(y_test, predictions))