In [40]:
from sklearn import datasets
iris = datasets.load_iris()

In [41]:
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
y_pred = gnb.fit(iris.data, iris.target).predict(iris.data)
print("Number of mislabeled points out of a total %d points : %d"
      % (iris.data.shape[0],(iris.target != y_pred).sum()))


Number of mislabeled points out of a total 150 points : 6

In [3]:
iris.data.shape[0]


Out[3]:
150

In [43]:
type(iris)


Out[43]:
sklearn.datasets.base.Bunch

In [42]:
iris.feature_names


Out[42]:
['sepal length (cm)',
 'sepal width (cm)',
 'petal length (cm)',
 'petal width (cm)']

In [4]:
iris.values()


Out[4]:
dict_values(['Iris Plants Database\n\nNotes\n-----\nData Set Characteristics:\n    :Number of Instances: 150 (50 in each of three classes)\n    :Number of Attributes: 4 numeric, predictive attributes and the class\n    :Attribute Information:\n        - sepal length in cm\n        - sepal width in cm\n        - petal length in cm\n        - petal width in cm\n        - class:\n                - Iris-Setosa\n                - Iris-Versicolour\n                - Iris-Virginica\n    :Summary Statistics:\n\n    ============== ==== ==== ======= ===== ====================\n                    Min  Max   Mean    SD   Class Correlation\n    ============== ==== ==== ======= ===== ====================\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\n    petal width:    0.1  2.5   1.20  0.76     0.9565  (high!)\n    ============== ==== ==== ======= ===== ====================\n\n    :Missing Attribute Values: None\n    :Class Distribution: 33.3% for each of 3 classes.\n    :Creator: R.A. Fisher\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n    :Date: July, 1988\n\nThis is a copy of UCI ML iris datasets.\nhttp://archive.ics.uci.edu/ml/datasets/Iris\n\nThe famous Iris database, first used by Sir R.A Fisher\n\nThis is perhaps the best known database to be found in the\npattern recognition literature.  Fisher\'s paper is a classic in the field and\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\ndata set contains 3 classes of 50 instances each, where each class refers to a\ntype of iris plant.  One class is linearly separable from the other 2; the\nlatter are NOT linearly separable from each other.\n\nReferences\n----------\n   - Fisher,R.A. "The use of multiple measurements in taxonomic problems"\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to\n     Mathematical Statistics" (John Wiley, NY, 1950).\n   - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\n   - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System\n     Structure and Classification Rule for Recognition in Partially Exposed\n     Environments".  IEEE Transactions on Pattern Analysis and Machine\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\n   - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule".  IEEE Transactions\n     on Information Theory, May 1972, 431-433.\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al"s AUTOCLASS II\n     conceptual clustering system finds 3 classes in the data.\n   - Many, many more ...\n', ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)'], array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]), array([[ 5.1,  3.5,  1.4,  0.2],
       [ 4.9,  3. ,  1.4,  0.2],
       [ 4.7,  3.2,  1.3,  0.2],
       [ 4.6,  3.1,  1.5,  0.2],
       [ 5. ,  3.6,  1.4,  0.2],
       [ 5.4,  3.9,  1.7,  0.4],
       [ 4.6,  3.4,  1.4,  0.3],
       [ 5. ,  3.4,  1.5,  0.2],
       [ 4.4,  2.9,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5.4,  3.7,  1.5,  0.2],
       [ 4.8,  3.4,  1.6,  0.2],
       [ 4.8,  3. ,  1.4,  0.1],
       [ 4.3,  3. ,  1.1,  0.1],
       [ 5.8,  4. ,  1.2,  0.2],
       [ 5.7,  4.4,  1.5,  0.4],
       [ 5.4,  3.9,  1.3,  0.4],
       [ 5.1,  3.5,  1.4,  0.3],
       [ 5.7,  3.8,  1.7,  0.3],
       [ 5.1,  3.8,  1.5,  0.3],
       [ 5.4,  3.4,  1.7,  0.2],
       [ 5.1,  3.7,  1.5,  0.4],
       [ 4.6,  3.6,  1. ,  0.2],
       [ 5.1,  3.3,  1.7,  0.5],
       [ 4.8,  3.4,  1.9,  0.2],
       [ 5. ,  3. ,  1.6,  0.2],
       [ 5. ,  3.4,  1.6,  0.4],
       [ 5.2,  3.5,  1.5,  0.2],
       [ 5.2,  3.4,  1.4,  0.2],
       [ 4.7,  3.2,  1.6,  0.2],
       [ 4.8,  3.1,  1.6,  0.2],
       [ 5.4,  3.4,  1.5,  0.4],
       [ 5.2,  4.1,  1.5,  0.1],
       [ 5.5,  4.2,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5. ,  3.2,  1.2,  0.2],
       [ 5.5,  3.5,  1.3,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 4.4,  3. ,  1.3,  0.2],
       [ 5.1,  3.4,  1.5,  0.2],
       [ 5. ,  3.5,  1.3,  0.3],
       [ 4.5,  2.3,  1.3,  0.3],
       [ 4.4,  3.2,  1.3,  0.2],
       [ 5. ,  3.5,  1.6,  0.6],
       [ 5.1,  3.8,  1.9,  0.4],
       [ 4.8,  3. ,  1.4,  0.3],
       [ 5.1,  3.8,  1.6,  0.2],
       [ 4.6,  3.2,  1.4,  0.2],
       [ 5.3,  3.7,  1.5,  0.2],
       [ 5. ,  3.3,  1.4,  0.2],
       [ 7. ,  3.2,  4.7,  1.4],
       [ 6.4,  3.2,  4.5,  1.5],
       [ 6.9,  3.1,  4.9,  1.5],
       [ 5.5,  2.3,  4. ,  1.3],
       [ 6.5,  2.8,  4.6,  1.5],
       [ 5.7,  2.8,  4.5,  1.3],
       [ 6.3,  3.3,  4.7,  1.6],
       [ 4.9,  2.4,  3.3,  1. ],
       [ 6.6,  2.9,  4.6,  1.3],
       [ 5.2,  2.7,  3.9,  1.4],
       [ 5. ,  2. ,  3.5,  1. ],
       [ 5.9,  3. ,  4.2,  1.5],
       [ 6. ,  2.2,  4. ,  1. ],
       [ 6.1,  2.9,  4.7,  1.4],
       [ 5.6,  2.9,  3.6,  1.3],
       [ 6.7,  3.1,  4.4,  1.4],
       [ 5.6,  3. ,  4.5,  1.5],
       [ 5.8,  2.7,  4.1,  1. ],
       [ 6.2,  2.2,  4.5,  1.5],
       [ 5.6,  2.5,  3.9,  1.1],
       [ 5.9,  3.2,  4.8,  1.8],
       [ 6.1,  2.8,  4. ,  1.3],
       [ 6.3,  2.5,  4.9,  1.5],
       [ 6.1,  2.8,  4.7,  1.2],
       [ 6.4,  2.9,  4.3,  1.3],
       [ 6.6,  3. ,  4.4,  1.4],
       [ 6.8,  2.8,  4.8,  1.4],
       [ 6.7,  3. ,  5. ,  1.7],
       [ 6. ,  2.9,  4.5,  1.5],
       [ 5.7,  2.6,  3.5,  1. ],
       [ 5.5,  2.4,  3.8,  1.1],
       [ 5.5,  2.4,  3.7,  1. ],
       [ 5.8,  2.7,  3.9,  1.2],
       [ 6. ,  2.7,  5.1,  1.6],
       [ 5.4,  3. ,  4.5,  1.5],
       [ 6. ,  3.4,  4.5,  1.6],
       [ 6.7,  3.1,  4.7,  1.5],
       [ 6.3,  2.3,  4.4,  1.3],
       [ 5.6,  3. ,  4.1,  1.3],
       [ 5.5,  2.5,  4. ,  1.3],
       [ 5.5,  2.6,  4.4,  1.2],
       [ 6.1,  3. ,  4.6,  1.4],
       [ 5.8,  2.6,  4. ,  1.2],
       [ 5. ,  2.3,  3.3,  1. ],
       [ 5.6,  2.7,  4.2,  1.3],
       [ 5.7,  3. ,  4.2,  1.2],
       [ 5.7,  2.9,  4.2,  1.3],
       [ 6.2,  2.9,  4.3,  1.3],
       [ 5.1,  2.5,  3. ,  1.1],
       [ 5.7,  2.8,  4.1,  1.3],
       [ 6.3,  3.3,  6. ,  2.5],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 7.1,  3. ,  5.9,  2.1],
       [ 6.3,  2.9,  5.6,  1.8],
       [ 6.5,  3. ,  5.8,  2.2],
       [ 7.6,  3. ,  6.6,  2.1],
       [ 4.9,  2.5,  4.5,  1.7],
       [ 7.3,  2.9,  6.3,  1.8],
       [ 6.7,  2.5,  5.8,  1.8],
       [ 7.2,  3.6,  6.1,  2.5],
       [ 6.5,  3.2,  5.1,  2. ],
       [ 6.4,  2.7,  5.3,  1.9],
       [ 6.8,  3. ,  5.5,  2.1],
       [ 5.7,  2.5,  5. ,  2. ],
       [ 5.8,  2.8,  5.1,  2.4],
       [ 6.4,  3.2,  5.3,  2.3],
       [ 6.5,  3. ,  5.5,  1.8],
       [ 7.7,  3.8,  6.7,  2.2],
       [ 7.7,  2.6,  6.9,  2.3],
       [ 6. ,  2.2,  5. ,  1.5],
       [ 6.9,  3.2,  5.7,  2.3],
       [ 5.6,  2.8,  4.9,  2. ],
       [ 7.7,  2.8,  6.7,  2. ],
       [ 6.3,  2.7,  4.9,  1.8],
       [ 6.7,  3.3,  5.7,  2.1],
       [ 7.2,  3.2,  6. ,  1.8],
       [ 6.2,  2.8,  4.8,  1.8],
       [ 6.1,  3. ,  4.9,  1.8],
       [ 6.4,  2.8,  5.6,  2.1],
       [ 7.2,  3. ,  5.8,  1.6],
       [ 7.4,  2.8,  6.1,  1.9],
       [ 7.9,  3.8,  6.4,  2. ],
       [ 6.4,  2.8,  5.6,  2.2],
       [ 6.3,  2.8,  5.1,  1.5],
       [ 6.1,  2.6,  5.6,  1.4],
       [ 7.7,  3. ,  6.1,  2.3],
       [ 6.3,  3.4,  5.6,  2.4],
       [ 6.4,  3.1,  5.5,  1.8],
       [ 6. ,  3. ,  4.8,  1.8],
       [ 6.9,  3.1,  5.4,  2.1],
       [ 6.7,  3.1,  5.6,  2.4],
       [ 6.9,  3.1,  5.1,  2.3],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 6.8,  3.2,  5.9,  2.3],
       [ 6.7,  3.3,  5.7,  2.5],
       [ 6.7,  3. ,  5.2,  2.3],
       [ 6.3,  2.5,  5. ,  1.9],
       [ 6.5,  3. ,  5.2,  2. ],
       [ 6.2,  3.4,  5.4,  2.3],
       [ 5.9,  3. ,  5.1,  1.8]]), array(['setosa', 'versicolor', 'virginica'], 
      dtype='<U10')])

In [5]:
iris.target


Out[5]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [6]:
y_pred


Out[6]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [7]:
(iris.target != y_pred)


Out[7]:
array([False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False,  True, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False,  True, False,
       False, False, False, False, False,  True, False, False, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False, False,  True, False,
       False, False, False, False, False, False, False, False, False,
       False, False,  True, False, False, False, False, False, False,
       False, False, False, False, False, False, False,  True, False,
       False, False, False, False, False, False, False, False, False,
       False, False, False, False, False, False], dtype=bool)

In [8]:
(iris.target != y_pred).sum()


Out[8]:
6

http://archive.ics.uci.edu/ml/datasets/Pen-Based+Recognition+of+Handwritten+Digits We create a digit database by collecting 250 samples from 44 writers.


In [44]:
from sklearn import datasets
iris = datasets.load_iris()
digits = datasets.load_digits()

In [45]:
from sklearn import svm
clf = svm.SVC(gamma=0.001, C=100.)

In [11]:
digits.data


Out[11]:
array([[  0.,   0.,   5., ...,   0.,   0.,   0.],
       [  0.,   0.,   0., ...,  10.,   0.,   0.],
       [  0.,   0.,   0., ...,  16.,   9.,   0.],
       ..., 
       [  0.,   0.,   1., ...,   6.,   0.,   0.],
       [  0.,   0.,   2., ...,  12.,   0.,   0.],
       [  0.,   0.,  10., ...,  12.,   1.,   0.]])

In [12]:
digits.target


Out[12]:
array([0, 1, 2, ..., 8, 9, 8])

In [13]:
iris.data


Out[13]:
array([[ 5.1,  3.5,  1.4,  0.2],
       [ 4.9,  3. ,  1.4,  0.2],
       [ 4.7,  3.2,  1.3,  0.2],
       [ 4.6,  3.1,  1.5,  0.2],
       [ 5. ,  3.6,  1.4,  0.2],
       [ 5.4,  3.9,  1.7,  0.4],
       [ 4.6,  3.4,  1.4,  0.3],
       [ 5. ,  3.4,  1.5,  0.2],
       [ 4.4,  2.9,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5.4,  3.7,  1.5,  0.2],
       [ 4.8,  3.4,  1.6,  0.2],
       [ 4.8,  3. ,  1.4,  0.1],
       [ 4.3,  3. ,  1.1,  0.1],
       [ 5.8,  4. ,  1.2,  0.2],
       [ 5.7,  4.4,  1.5,  0.4],
       [ 5.4,  3.9,  1.3,  0.4],
       [ 5.1,  3.5,  1.4,  0.3],
       [ 5.7,  3.8,  1.7,  0.3],
       [ 5.1,  3.8,  1.5,  0.3],
       [ 5.4,  3.4,  1.7,  0.2],
       [ 5.1,  3.7,  1.5,  0.4],
       [ 4.6,  3.6,  1. ,  0.2],
       [ 5.1,  3.3,  1.7,  0.5],
       [ 4.8,  3.4,  1.9,  0.2],
       [ 5. ,  3. ,  1.6,  0.2],
       [ 5. ,  3.4,  1.6,  0.4],
       [ 5.2,  3.5,  1.5,  0.2],
       [ 5.2,  3.4,  1.4,  0.2],
       [ 4.7,  3.2,  1.6,  0.2],
       [ 4.8,  3.1,  1.6,  0.2],
       [ 5.4,  3.4,  1.5,  0.4],
       [ 5.2,  4.1,  1.5,  0.1],
       [ 5.5,  4.2,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5. ,  3.2,  1.2,  0.2],
       [ 5.5,  3.5,  1.3,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 4.4,  3. ,  1.3,  0.2],
       [ 5.1,  3.4,  1.5,  0.2],
       [ 5. ,  3.5,  1.3,  0.3],
       [ 4.5,  2.3,  1.3,  0.3],
       [ 4.4,  3.2,  1.3,  0.2],
       [ 5. ,  3.5,  1.6,  0.6],
       [ 5.1,  3.8,  1.9,  0.4],
       [ 4.8,  3. ,  1.4,  0.3],
       [ 5.1,  3.8,  1.6,  0.2],
       [ 4.6,  3.2,  1.4,  0.2],
       [ 5.3,  3.7,  1.5,  0.2],
       [ 5. ,  3.3,  1.4,  0.2],
       [ 7. ,  3.2,  4.7,  1.4],
       [ 6.4,  3.2,  4.5,  1.5],
       [ 6.9,  3.1,  4.9,  1.5],
       [ 5.5,  2.3,  4. ,  1.3],
       [ 6.5,  2.8,  4.6,  1.5],
       [ 5.7,  2.8,  4.5,  1.3],
       [ 6.3,  3.3,  4.7,  1.6],
       [ 4.9,  2.4,  3.3,  1. ],
       [ 6.6,  2.9,  4.6,  1.3],
       [ 5.2,  2.7,  3.9,  1.4],
       [ 5. ,  2. ,  3.5,  1. ],
       [ 5.9,  3. ,  4.2,  1.5],
       [ 6. ,  2.2,  4. ,  1. ],
       [ 6.1,  2.9,  4.7,  1.4],
       [ 5.6,  2.9,  3.6,  1.3],
       [ 6.7,  3.1,  4.4,  1.4],
       [ 5.6,  3. ,  4.5,  1.5],
       [ 5.8,  2.7,  4.1,  1. ],
       [ 6.2,  2.2,  4.5,  1.5],
       [ 5.6,  2.5,  3.9,  1.1],
       [ 5.9,  3.2,  4.8,  1.8],
       [ 6.1,  2.8,  4. ,  1.3],
       [ 6.3,  2.5,  4.9,  1.5],
       [ 6.1,  2.8,  4.7,  1.2],
       [ 6.4,  2.9,  4.3,  1.3],
       [ 6.6,  3. ,  4.4,  1.4],
       [ 6.8,  2.8,  4.8,  1.4],
       [ 6.7,  3. ,  5. ,  1.7],
       [ 6. ,  2.9,  4.5,  1.5],
       [ 5.7,  2.6,  3.5,  1. ],
       [ 5.5,  2.4,  3.8,  1.1],
       [ 5.5,  2.4,  3.7,  1. ],
       [ 5.8,  2.7,  3.9,  1.2],
       [ 6. ,  2.7,  5.1,  1.6],
       [ 5.4,  3. ,  4.5,  1.5],
       [ 6. ,  3.4,  4.5,  1.6],
       [ 6.7,  3.1,  4.7,  1.5],
       [ 6.3,  2.3,  4.4,  1.3],
       [ 5.6,  3. ,  4.1,  1.3],
       [ 5.5,  2.5,  4. ,  1.3],
       [ 5.5,  2.6,  4.4,  1.2],
       [ 6.1,  3. ,  4.6,  1.4],
       [ 5.8,  2.6,  4. ,  1.2],
       [ 5. ,  2.3,  3.3,  1. ],
       [ 5.6,  2.7,  4.2,  1.3],
       [ 5.7,  3. ,  4.2,  1.2],
       [ 5.7,  2.9,  4.2,  1.3],
       [ 6.2,  2.9,  4.3,  1.3],
       [ 5.1,  2.5,  3. ,  1.1],
       [ 5.7,  2.8,  4.1,  1.3],
       [ 6.3,  3.3,  6. ,  2.5],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 7.1,  3. ,  5.9,  2.1],
       [ 6.3,  2.9,  5.6,  1.8],
       [ 6.5,  3. ,  5.8,  2.2],
       [ 7.6,  3. ,  6.6,  2.1],
       [ 4.9,  2.5,  4.5,  1.7],
       [ 7.3,  2.9,  6.3,  1.8],
       [ 6.7,  2.5,  5.8,  1.8],
       [ 7.2,  3.6,  6.1,  2.5],
       [ 6.5,  3.2,  5.1,  2. ],
       [ 6.4,  2.7,  5.3,  1.9],
       [ 6.8,  3. ,  5.5,  2.1],
       [ 5.7,  2.5,  5. ,  2. ],
       [ 5.8,  2.8,  5.1,  2.4],
       [ 6.4,  3.2,  5.3,  2.3],
       [ 6.5,  3. ,  5.5,  1.8],
       [ 7.7,  3.8,  6.7,  2.2],
       [ 7.7,  2.6,  6.9,  2.3],
       [ 6. ,  2.2,  5. ,  1.5],
       [ 6.9,  3.2,  5.7,  2.3],
       [ 5.6,  2.8,  4.9,  2. ],
       [ 7.7,  2.8,  6.7,  2. ],
       [ 6.3,  2.7,  4.9,  1.8],
       [ 6.7,  3.3,  5.7,  2.1],
       [ 7.2,  3.2,  6. ,  1.8],
       [ 6.2,  2.8,  4.8,  1.8],
       [ 6.1,  3. ,  4.9,  1.8],
       [ 6.4,  2.8,  5.6,  2.1],
       [ 7.2,  3. ,  5.8,  1.6],
       [ 7.4,  2.8,  6.1,  1.9],
       [ 7.9,  3.8,  6.4,  2. ],
       [ 6.4,  2.8,  5.6,  2.2],
       [ 6.3,  2.8,  5.1,  1.5],
       [ 6.1,  2.6,  5.6,  1.4],
       [ 7.7,  3. ,  6.1,  2.3],
       [ 6.3,  3.4,  5.6,  2.4],
       [ 6.4,  3.1,  5.5,  1.8],
       [ 6. ,  3. ,  4.8,  1.8],
       [ 6.9,  3.1,  5.4,  2.1],
       [ 6.7,  3.1,  5.6,  2.4],
       [ 6.9,  3.1,  5.1,  2.3],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 6.8,  3.2,  5.9,  2.3],
       [ 6.7,  3.3,  5.7,  2.5],
       [ 6.7,  3. ,  5.2,  2.3],
       [ 6.3,  2.5,  5. ,  1.9],
       [ 6.5,  3. ,  5.2,  2. ],
       [ 6.2,  3.4,  5.4,  2.3],
       [ 5.9,  3. ,  5.1,  1.8]])

In [14]:
iris.target


Out[14]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [46]:
clf.fit(digits.data[:-1], digits.target[:-1])


Out[46]:
SVC(C=100.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma=0.001, kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [47]:
clf.predict(digits.data[-1:])


Out[47]:
array([8])

In [48]:
clf = svm.SVC()
iris = datasets.load_iris()
X, y = iris.data, iris.target
clf.fit(X, y)


Out[48]:
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [49]:
import pickle
s = pickle.dumps(clf)
clf2 = pickle.loads(s)
clf2.predict(X[0:1])


Out[49]:
array([0])

In [19]:
y[0]


Out[19]:
0

In [20]:
y


Out[20]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [21]:
clf2.predict(X)


Out[21]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [22]:
(clf2.predict(X) != y).sum()


Out[22]:
2

In [50]:
from sklearn import tree
from sklearn.datasets import load_iris

In [51]:
iris.target


Out[51]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [52]:
clf = tree.DecisionTreeClassifier()
clf = clf.fit(iris.data, iris.target)

In [ ]:
X, y = iris.data, iris.target

In [53]:
names=['sepal length', 'sepal width', 'petal length', 'petal width','species']

In [54]:
clf


Out[54]:
DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            presort=False, random_state=None, splitter='best')

In [55]:
clf.predict(X)


Out[55]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [29]:
iris.target


Out[29]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [56]:
(clf.predict(X)!=iris.target).sum()


Out[56]:
0

In [57]:
! pip install pydotplus


Requirement already satisfied: pydotplus in c:\users\dell\anaconda3\lib\site-packages
Requirement already satisfied: pyparsing>=2.0.1 in c:\users\dell\anaconda3\lib\site-packages (from pydotplus)

In [58]:
import pydotplus as pydot

from IPython.display import Image

from sklearn.externals.six import StringIO

In [59]:
dot_data = StringIO()

In [60]:
tree.export_graphviz(clf, out_file=dot_data,feature_names=names[:-1])

In [61]:
graph = pydot.graph_from_dot_data(dot_data.getvalue())

In [62]:
Image(graph.create_png())


Out[62]:

In [37]:
import matplotlib.pyplot as plt
%matplotlib  inline
from collections import OrderedDict
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier

In [38]:
# Author: Kian Ho <hui.kian.ho@gmail.com>
#         Gilles Louppe <g.louppe@gmail.com>
#         Andreas Mueller <amueller@ais.uni-bonn.de>
#
# License: BSD 3 Clause

print(__doc__)

RANDOM_STATE = 123

# Generate a binary classification dataset.
X, y = make_classification(n_samples=500, n_features=25,
                           n_clusters_per_class=1, n_informative=15,
                           random_state=RANDOM_STATE)

# NOTE: Setting the `warm_start` construction parameter to `True` disables
# support for parallelized ensembles but is necessary for tracking the OOB
# error trajectory during training.
ensemble_clfs = [
    ("RandomForestClassifier, max_features='sqrt'",
        RandomForestClassifier(warm_start=True, oob_score=True,
                               max_features="sqrt",
                               random_state=RANDOM_STATE)),
    ("RandomForestClassifier, max_features='log2'",
        RandomForestClassifier(warm_start=True, max_features='log2',
                               oob_score=True,
                               random_state=RANDOM_STATE)),
    ("RandomForestClassifier, max_features=None",
        RandomForestClassifier(warm_start=True, max_features=None,
                               oob_score=True,
                               random_state=RANDOM_STATE))
]

# Map a classifier name to a list of (<n_estimators>, <error rate>) pairs.
error_rate = OrderedDict((label, []) for label, _ in ensemble_clfs)

# Range of `n_estimators` values to explore.
min_estimators = 15
max_estimators = 175

for label, clf in ensemble_clfs:
    for i in range(min_estimators, max_estimators + 1):
        clf.set_params(n_estimators=i)
        clf.fit(X, y)

        # Record the OOB error for each `n_estimators=i` setting.
        oob_error = 1 - clf.oob_score_
        error_rate[label].append((i, oob_error))

# Generate the "OOB error rate" vs. "n_estimators" plot.
for label, clf_err in error_rate.items():
    xs, ys = zip(*clf_err)


Automatically created module for IPython interactive environment

In [39]:
plt.plot(xs, ys, label=label)
plt.xlim(min_estimators, max_estimators)
plt.xlabel("n_estimators")
plt.ylabel("OOB error rate")
plt.legend(loc="upper right")
plt.show()



In [63]:
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression

X, y = make_classification(n_samples=10000, n_features=10, n_classes=2, n_informative=5)
Xtrain = X[:9000]
Xtest = X[9000:]
ytrain = y[:9000]
ytest = y[9000:]

In [64]:
clf = LogisticRegression()
clf.fit(Xtrain, ytrain)
from sklearn import metrics
import pandas as pd
from ggplot import *

preds = clf.predict_proba(Xtest)[:,1]
fpr, tpr, _ = metrics.roc_curve(ytest, preds)

df = pd.DataFrame(dict(fpr=fpr, tpr=tpr))
ggplot(df, aes(x='fpr', y='tpr')) +\
    geom_line() +\
    geom_abline(linetype='dashed')


Out[64]:
<ggplot: (14069326)>

In [66]:
print(__doc__)

import numpy as np
import matplotlib.pyplot as plt
from itertools import cycle

from sklearn import svm, datasets
from sklearn.metrics import roc_curve, auc
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier
from scipy import interp

# Import some data to play with
iris = datasets.load_iris()
X = iris.data
y = iris.target

# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]

# Add noisy features to make the problem harder
random_state = np.random.RandomState(0)
n_samples, n_features = X.shape
X = np.c_[X, random_state.randn(n_samples, 200 * n_features)]

# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5,
                                                    random_state=0)

# Learn to predict each class against the other
classifier = OneVsRestClassifier(svm.SVC(kernel='linear', probability=True,
                                 random_state=random_state))
y_score = classifier.fit(X_train, y_train).decision_function(X_test)

# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
    fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
    roc_auc[i] = auc(fpr[i], tpr[i])

# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])


Automatically created module for IPython interactive environment

In [67]:
# Compute macro-average ROC curve and ROC area

# First aggregate all false positive rates
all_fpr = np.unique(np.concatenate([fpr[i] for i in range(n_classes)]))

# Then interpolate all ROC curves at this points
mean_tpr = np.zeros_like(all_fpr)
for i in range(n_classes):
    mean_tpr += interp(all_fpr, fpr[i], tpr[i])

# Finally average it and compute AUC
mean_tpr /= n_classes

fpr["macro"] = all_fpr
tpr["macro"] = mean_tpr
roc_auc["macro"] = auc(fpr["macro"], tpr["macro"])

# Plot all ROC curves
plt.figure()
plt.plot(fpr["micro"], tpr["micro"],
         label='micro-average ROC curve (area = {0:0.2f})'
               ''.format(roc_auc["micro"]),
         color='deeppink', linestyle=':', linewidth=4)

plt.plot(fpr["macro"], tpr["macro"],
         label='macro-average ROC curve (area = {0:0.2f})'
               ''.format(roc_auc["macro"]),
         color='navy', linestyle=':', linewidth=4)

colors = cycle(['aqua', 'darkorange', 'cornflowerblue'])
for i, color in zip(range(n_classes), colors):
    plt.plot(fpr[i], tpr[i], color=color, lw=lw,
             label='ROC curve of class {0} (area = {1:0.2f})'
             ''.format(i, roc_auc[i]))

plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Some extension of Receiver operating characteristic to multi-class')
plt.legend(loc="lower right")
plt.show()


---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-67-ecc63baa3f6c> in <module>()
     30 colors = cycle(['aqua', 'darkorange', 'cornflowerblue'])
     31 for i, color in zip(range(n_classes), colors):
---> 32     plt.plot(fpr[i], tpr[i], color=color, lw=lw,
     33              label='ROC curve of class {0} (area = {1:0.2f})'
     34              ''.format(i, roc_auc[i]))

NameError: name 'lw' is not defined

In [69]:
iris.target_names


Out[69]:
array(['setosa', 'versicolor', 'virginica'], 
      dtype='<U10')

In [70]:
from sklearn.linear_model import LogisticRegression

In [71]:
logreg=LogisticRegression()

In [74]:
x,y=iris.data,iris.target

In [75]:
logreg.fit(x,y)


Out[75]:
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=None, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

In [76]:
x_new=[[3,5,4,2],[5,4,3,2]]

In [77]:
logreg.predict(x_new)


Out[77]:
array([2, 0])

In [ ]:
X_train,X_test,y_train,y_test=train_test_split(x,y,test_size=0.8)

In [ ]:
iris_X_train2 = iris.data[:-20]
iris_X_test2  = iris.data[-20:]
iris_y_train2 = iris.target[:-20]
iris_y_test2  = iris.target[-20:]

In [ ]:
np.random.seed(0)
indices = np.random.permutation(len(iris))

In [ ]:
iris_X_train = iris_X[indices[:-10]]
iris_y_train = iris_y[indices[:-10]]
iris_X_test  = iris_X[indices[-10:]]
iris_y_test  = iris_y[indices[-10:]]