In [10]:
from sklearn import datasets
iris = datasets.load_iris()
In [11]:
iris
Out[11]:
{'DESCR': 'Iris Plants Database\n====================\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',
'data': 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]]),
'feature_names': ['sepal length (cm)',
'sepal width (cm)',
'petal length (cm)',
'petal width (cm)'],
'target': 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]),
'target_names': array(['setosa', 'versicolor', 'virginica'],
dtype='<U10')}
In [15]:
iris.data
Out[15]:
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 [16]:
iris.target
Out[16]:
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 [12]:
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
In [17]:
gnb.fit(iris.data, iris.target)
Out[17]:
GaussianNB(priors=None)
In [18]:
print(gnb.fit)
<bound method GaussianNB.fit of GaussianNB(priors=None)>
In [14]:
y_pred = gnb.fit(iris.data, iris.target).predict(iris.data)
y_pred
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, 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 [22]:
import numpy as np
import pandas as pd
In [24]:
dict(pd.Series(iris.target).value_counts())
Out[24]:
{0: 50, 1: 50, 2: 50}
In [23]:
dict(pd.Series(y_pred).value_counts())
Out[23]:
{0: 50, 1: 50, 2: 50}
In [26]:
iris.data.shape
Out[26]:
(150, 4)
In [13]:
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 [40]:
from sklearn.metrics import confusion_matrix
In [41]:
cnf_matrix = confusion_matrix(iris.target, y_pred)
In [42]:
cnf_matrix
Out[42]:
array([[50, 0, 0],
[ 0, 47, 3],
[ 0, 3, 47]])
In [48]:
from sklearn.preprocessing import label_binarize
In [53]:
# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
y
Out[53]:
array([[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1]], dtype=int32)
In [54]:
y.shape
Out[54]:
(150, 3)
In [55]:
n_classes = y.shape[1]
n_classes
Out[55]:
3
In [56]:
y_pred = label_binarize(y_pred, classes=[0, 1, 2])
y_pred
Out[56]:
array([[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[1, 0, 0],
[0, 1, 0],
[0, 1, 0],
[0, 0, 1],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 0, 1],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 0, 1],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 1, 0],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 1, 0],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 1, 0],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 1, 0],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1],
[0, 0, 1]])
In [57]:
from sklearn.metrics import roc_curve, auc
In [58]:
# 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[:, i], y_pred[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
In [61]:
tpr
Out[61]:
{0: array([ 1., 1.]),
1: array([ 0. , 0.94, 1. ]),
2: array([ 0. , 0.94, 1. ])}
In [60]:
fpr
Out[60]:
{0: array([ 0., 1.]),
1: array([ 0. , 0.03, 1. ]),
2: array([ 0. , 0.03, 1. ])}
In [59]:
roc_auc
Out[59]:
{0: 1.0, 1: 0.95499999999999996, 2: 0.95499999999999996}
Content source: decisionstats/pythonfordatascience
Similar notebooks: