In [4]:

    

import sys
sys.path.append('/home/aseem/projects/ud120-projects/choose_your_own')
sys.path.append("/home/aseem/projects/website/udacity_data_science_notes/intro_machine_learning")

%matplotlib inline

def show_picture():
    from ipython_picture import prettyPicture
    
    plt = prettyPicture(clf, features_test, labels_test)
    plt.show()
    
def show_accuracy():
    from sklearn.metrics import accuracy_score
    
    acc = accuracy_score(clf.predict(features_test), labels_test)
    print acc


    

In [5]:

    

from prep_terrain_data import makeTerrainData

features_train, labels_train, features_test, labels_test = makeTerrainData()


    

In [13]:

    

from sklearn.neighbors import KNeighborsClassifier

clf = KNeighborsClassifier(n_neighbors=4)
clf.fit(features_train, labels_train) 

show_picture()
show_accuracy()


    

    













    




0.94

In [59]:

    

from sklearn.cross_validation import cross_val_score
from sklearn.ensemble import AdaBoostClassifier

all_scores = []
for i in xrange(1, 200):
    clf = AdaBoostClassifier(n_estimators=i)
    scores = cross_val_score(clf, features_train, labels_train)
    all_scores.append(scores.mean())


    

In [60]:

    

%matplotlib inline

import matplotlib.pyplot as plt

y = all_scores

plt.plot(range(1, len(y) + 1), y)
plt.show()


    

In [67]:

    

clf = AdaBoostClassifier(n_estimators=all_scores.index(max(all_scores)) + 1)
cross_val_score(clf, features_train, labels_train).mean()


    

    
Out[67]:





0.96134892824951867