In [1]:

    

from sklearn.datasets import load_iris
data = load_iris()
print(data)


    

    




{'target_names': array(['setosa', 'versicolor', 'virginica'], 
      dtype='|S10'), '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]]), '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]), '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', 'feature_names': ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']}

In [4]:

    

import numpy as np
import pandas as pd
from sklearn.datasets import load_iris

# save load_iris() sklearn dataset to iris
# if you'd like to check dataset type use: type(load_iris())
# if you'd like to view list of attributes use: dir(load_iris())
iris = load_iris()

# np.c_ is the numpy concatenate function
# which is used to concat iris['data'] and iris['target'] arrays 
# for pandas column argument: concat iris['feature_names'] list
# and string list (in this case one string); you can make this anything you'd like..  
# the original dataset would probably call this ['Species']
data1 = pd.DataFrame(data= np.c_[iris['data'], iris['target']],
                     columns= iris['feature_names'] + ['target'])

features = iris.feature_names
target = iris.target
print(max(target), min(target))
# mean hace la media de cada columna
print(np.mean(data1))

print(len(features))


    

    




(2, 0)
sepal length (cm)    5.843333
sepal width (cm)     3.054000
petal length (cm)    3.758667
petal width (cm)     1.198667
target               1.000000
dtype: float64
4

In [25]:

    

features = iris.feature_names

print(len(features))

print(features)

print(max(target), min(target))
# mean hace la media de cada columna
print(np.mean(data1))


    

    




4
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']
(2, 0)
sepal length (cm)    5.843333
sepal width (cm)     3.054000
petal length (cm)    3.758667
petal width (cm)     1.198667
target               1.000000
dtype: float64

In [30]:

    

data1[data1["petal width (cm)"] > 1.3]


    

    
Out[30]:






  

    

      

      
sepal length (cm)
      
sepal width (cm)
      
petal length (cm)
      
petal width (cm)
      
target
    
  
  

    

      
50
      
7.0
      
3.2
      
4.7
      
1.4
      
1.0
    
    

      
51
      
6.4
      
3.2
      
4.5
      
1.5
      
1.0
    
    

      
52
      
6.9
      
3.1
      
4.9
      
1.5
      
1.0
    
    

      
54
      
6.5
      
2.8
      
4.6
      
1.5
      
1.0
    
    

      
56
      
6.3
      
3.3
      
4.7
      
1.6
      
1.0
    
    

      
59
      
5.2
      
2.7
      
3.9
      
1.4
      
1.0
    
    

      
61
      
5.9
      
3.0
      
4.2
      
1.5
      
1.0
    
    

      
63
      
6.1
      
2.9
      
4.7
      
1.4
      
1.0
    
    

      
65
      
6.7
      
3.1
      
4.4
      
1.4
      
1.0
    
    

      
66
      
5.6
      
3.0
      
4.5
      
1.5
      
1.0
    
    

      
68
      
6.2
      
2.2
      
4.5
      
1.5
      
1.0
    
    

      
70
      
5.9
      
3.2
      
4.8
      
1.8
      
1.0
    
    

      
72
      
6.3
      
2.5
      
4.9
      
1.5
      
1.0
    
    

      
75
      
6.6
      
3.0
      
4.4
      
1.4
      
1.0
    
    

      
76
      
6.8
      
2.8
      
4.8
      
1.4
      
1.0
    
    

      
77
      
6.7
      
3.0
      
5.0
      
1.7
      
1.0
    
    

      
78
      
6.0
      
2.9
      
4.5
      
1.5
      
1.0
    
    

      
83
      
6.0
      
2.7
      
5.1
      
1.6
      
1.0
    
    

      
84
      
5.4
      
3.0
      
4.5
      
1.5
      
1.0
    
    

      
85
      
6.0
      
3.4
      
4.5
      
1.6
      
1.0
    
    

      
86
      
6.7
      
3.1
      
4.7
      
1.5
      
1.0
    
    

      
91
      
6.1
      
3.0
      
4.6
      
1.4
      
1.0
    
    

      
100
      
6.3
      
3.3
      
6.0
      
2.5
      
2.0
    
    

      
101
      
5.8
      
2.7
      
5.1
      
1.9
      
2.0
    
    

      
102
      
7.1
      
3.0
      
5.9
      
2.1
      
2.0
    
    

      
103
      
6.3
      
2.9
      
5.6
      
1.8
      
2.0
    
    

      
104
      
6.5
      
3.0
      
5.8
      
2.2
      
2.0
    
    

      
105
      
7.6
      
3.0
      
6.6
      
2.1
      
2.0
    
    

      
106
      
4.9
      
2.5
      
4.5
      
1.7
      
2.0
    
    

      
107
      
7.3
      
2.9
      
6.3
      
1.8
      
2.0
    
    

      
...
      
...
      
...
      
...
      
...
      
...
    
    

      
120
      
6.9
      
3.2
      
5.7
      
2.3
      
2.0
    
    

      
121
      
5.6
      
2.8
      
4.9
      
2.0
      
2.0
    
    

      
122
      
7.7
      
2.8
      
6.7
      
2.0
      
2.0
    
    

      
123
      
6.3
      
2.7
      
4.9
      
1.8
      
2.0
    
    

      
124
      
6.7
      
3.3
      
5.7
      
2.1
      
2.0
    
    

      
125
      
7.2
      
3.2
      
6.0
      
1.8
      
2.0
    
    

      
126
      
6.2
      
2.8
      
4.8
      
1.8
      
2.0
    
    

      
127
      
6.1
      
3.0
      
4.9
      
1.8
      
2.0
    
    

      
128
      
6.4
      
2.8
      
5.6
      
2.1
      
2.0
    
    

      
129
      
7.2
      
3.0
      
5.8
      
1.6
      
2.0
    
    

      
130
      
7.4
      
2.8
      
6.1
      
1.9
      
2.0
    
    

      
131
      
7.9
      
3.8
      
6.4
      
2.0
      
2.0
    
    

      
132
      
6.4
      
2.8
      
5.6
      
2.2
      
2.0
    
    

      
133
      
6.3
      
2.8
      
5.1
      
1.5
      
2.0
    
    

      
134
      
6.1
      
2.6
      
5.6
      
1.4
      
2.0
    
    

      
135
      
7.7
      
3.0
      
6.1
      
2.3
      
2.0
    
    

      
136
      
6.3
      
3.4
      
5.6
      
2.4
      
2.0
    
    

      
137
      
6.4
      
3.1
      
5.5
      
1.8
      
2.0
    
    

      
138
      
6.0
      
3.0
      
4.8
      
1.8
      
2.0
    
    

      
139
      
6.9
      
3.1
      
5.4
      
2.1
      
2.0
    
    

      
140
      
6.7
      
3.1
      
5.6
      
2.4
      
2.0
    
    

      
141
      
6.9
      
3.1
      
5.1
      
2.3
      
2.0
    
    

      
142
      
5.8
      
2.7
      
5.1
      
1.9
      
2.0
    
    

      
143
      
6.8
      
3.2
      
5.9
      
2.3
      
2.0
    
    

      
144
      
6.7
      
3.3
      
5.7
      
2.5
      
2.0
    
    

      
145
      
6.7
      
3.0
      
5.2
      
2.3
      
2.0
    
    

      
146
      
6.3
      
2.5
      
5.0
      
1.9
      
2.0
    
    

      
147
      
6.5
      
3.0
      
5.2
      
2.0
      
2.0
    
    

      
148
      
6.2
      
3.4
      
5.4
      
2.3
      
2.0
    
    

      
149
      
5.9
      
3.0
      
5.1
      
1.8
      
2.0
    
  

72 rows × 5 columns

In [50]:

    

#print(max(data1["sepal length (cm)"] data1[target == 0]))
a = data1["sepal length (cm)"]
print(max(a[target == 2]))


    

    




7.9

In [71]:

    

# argmin: funcion que devuelve el indice del min
indice = data1["sepal length (cm)"].argmin()


    

In [74]:

    

data1.corr(method='kendall')


    

    
Out[74]:






  

    

      

      
sepal length (cm)
      
sepal width (cm)
      
petal length (cm)
      
petal width (cm)
      
target
    
  
  

    

      
sepal length (cm)
      
1.000000
      
-0.072112
      
0.717624
      
0.654960
      
0.670444
    
    

      
sepal width (cm)
      
-0.072112
      
1.000000
      
-0.182391
      
-0.146988
      
-0.333435
    
    

      
petal length (cm)
      
0.717624
      
-0.182391
      
1.000000
      
0.803014
      
0.822949
    
    

      
petal width (cm)
      
0.654960
      
-0.146988
      
0.803014
      
1.000000
      
0.838757
    
    

      
target
      
0.670444
      
-0.333435
      
0.822949
      
0.838757
      
1.000000
    
  

In [14]:

    

# Sirve para poder visualizar las graficas online
%matplotlib inline
# libreria para usar las graficas
import seaborn as sns; sns.set(style="ticks", color_codes=True)
# Mostramos la grafica y pintamos los puntos segun el target
sns.pairplot(data1, hue="target")


    

    




<seaborn.axisgrid.PairGrid object at 0x7fafa99f1fd0>






    

In [21]:

    

from sklearn.model_selection import train_test_split
X = data1[iris['feature_names']]
y = data1[iris['target']]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)

from sklearn.neighbors import KNeighborsClassifier
neigh = KNeighborsClassifier()
neigh.fit(X_train, y_train)
'''from sklearn.neighbors import KNeighborsClassifier
neigh = KNeighborsClassifier()
neigh.fit(X_train, y_train)
print(neigh.predict([[1,3,5,6]]))
'''
#print(y_train)
#print(x)


    

    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-21-8421e02580e1> in <module>()
      6 from sklearn.neighbors import KNeighborsClassifier
      7 neigh = KNeighborsClassifier()
----> 8 neigh.fit(X_train, y_train)
      9 '''from sklearn.neighbors import KNeighborsClassifier
     10 neigh = KNeighborsClassifier()

/home/hlocal/.conda/envs/EJE1/lib/python2.7/site-packages/sklearn/neighbors/base.pyc in fit(self, X, y)
    773             self.outputs_2d_ = True
    774 
--> 775         check_classification_targets(y)
    776         self.classes_ = []
    777         self._y = np.empty(y.shape, dtype=np.int)

/home/hlocal/.conda/envs/EJE1/lib/python2.7/site-packages/sklearn/utils/multiclass.pyc in check_classification_targets(y)
    170     if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
    171             'multilabel-indicator', 'multilabel-sequences']:
--> 172         raise ValueError("Unknown label type: %r" % y_type)
    173 
    174 

ValueError: Unknown label type: 'continuous-multioutput'

In [ ]:

    




    

In [ ]: