Reviewing the iris dataset

K-nearest neighbors (KNN) classification

Pick a value for K
Search for K observations in the training data that are "nearest" to the measurements of the unknown Iris.
use the most popular response value from the K nearest neighbors as the predicted response value for the unknown Iris.



In [6]:

    
# import load_iris function from datasets module 
from sklearn.datasets import load_iris

iris = load_iris()
X = iris.data
y = iris.target
print X.shape
print y.shape









    



(150L, 4L)
(150L,)

skikit-learn 4-step modeling pattern

Step1: import the class you plan to use



In [7]:

    
from sklearn.neighbors import KNeighborsClassifier

Step 2: "Instantiate" the "estimator"
- "Estimator" is scikit-learn's term for model
- "Instantiate" means "makes an instance of"



In [8]:

    
knn = KNeighborsClassifier(n_neighbors=1)

 + Name of the object does not matter
+ Can specify tuning parameters during this step
+ All parameters not specified are set to defaults.



In [9]:

    
print knn









    



KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_neighbors=1, p=2, weights='uniform')

Step 3: Fit the model with data ("model training")
- Model is learning the relationship between X and y
- Occurs in-place



In [10]:

    
knn.fit(X,y)









    Out[10]:





KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
           metric_params=None, n_neighbors=1, p=2, weights='uniform')

Step 4: predict the response for a new observation
- New observations are called "out-of-sample" data
- Uses the information it learned during the model training shape



In [11]:

    
knn.predict([3,5,4,2])









    Out[11]:





array([2])



In [12]:

    
X_new = [[3,5,4,2], [5,4,3,2]]
knn.predict(X_new)









    Out[12]:





array([2, 1])

Using a different value for K



In [13]:

    
knn = KNeighborsClassifier(n_neighbors=5)

knn.fit(X,y)
knn.predict(X_new)









    Out[13]:





array([1, 1])

Using a different classification model



In [14]:

    
from sklearn.linear_model import LogisticRegression

logreg = LogisticRegression()

logreg.fit(X,y)

logreg.predict(X_new)









    Out[14]:





array([2, 0])



In [ ]: