# Split the dataset into two pieces: a training set and a testing set. Train the model on the training set. Test the model on the testing set, and evaluate how well we did.
# STEP 1: split X and y into training and testing sets
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=4)

print(X_train.shape)
print(X_test.shape)
>> (90, 4)  # 90 samples are selected randomly for training the algorithm
>> (60, 4)  # 60 samples are selected randomly for testing the algorithm

# STEP 2: train the model on the training set
logreg = LogisticRegression()
logreg.fit(X_train, y_train)

# STEP 3: make predictions on the testing set
y_pred = logreg.predict(X_test)

# compare actual response values (y_test) with predicted response values (y_pred)
print(metrics.accuracy_score(y_test, y_pred))
>> 0.95

knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
print(metrics.accuracy_score(y_test, y_pred))
>> 0.966666666667

knn = KNeighborsClassifier(n_neighbors=1)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
print(metrics.accuracy_score(y_test, y_pred))
>> 0.95