notebook.community

Edit and run

We can split a dataset in three ways- 1) Using indices from top to bottom 2) Using indices using random numbers using numpy 3) Using text_train split in scikit learn





In [17]:



    


import pandas as pd



    











In [18]:



    


iris=pd.read_csv("https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/iris.csv")



    











In [19]:



    


iris.head()



    


















    
Out[19]:











  
    

      
      Unnamed: 0
      Sepal.Length
      Sepal.Width
      Petal.Length
      Petal.Width
      Species
    

  
  
    

      0
      1
      5.1
      3.5
      1.4
      0.2
      setosa
    

    

      1
      2
      4.9
      3.0
      1.4
      0.2
      setosa
    

    

      2
      3
      4.7
      3.2
      1.3
      0.2
      setosa
    

    

      3
      4
      4.6
      3.1
      1.5
      0.2
      setosa
    

    

      4
      5
      5.0
      3.6
      1.4
      0.2
      setosa
    

  




















In [22]:



    


iris.shape



    


















    
Out[22]:








(150, 6)

















In [23]:



    


iris=iris.iloc[:,1:]



    











In [24]:



    


iris.head()



    


















    
Out[24]:











  
    

      
      Sepal.Length
      Sepal.Width
      Petal.Length
      Petal.Width
      Species
    

  
  
    

      0
      5.1
      3.5
      1.4
      0.2
      setosa
    

    

      1
      4.9
      3.0
      1.4
      0.2
      setosa
    

    

      2
      4.7
      3.2
      1.3
      0.2
      setosa
    

    

      3
      4.6
      3.1
      1.5
      0.2
      setosa
    

    

      4
      5.0
      3.6
      1.4
      0.2
      setosa
    

  




















In [25]:



    


iris.shape



    


















    
Out[25]:








(150, 5)

















In [26]:



    


import numpy as np



    











In [27]:



    


len(iris)



    


















    
Out[27]:








150

















In [29]:



    


indices = np.random.permutation(len(iris))



    











In [30]:



    


indices



    


















    
Out[30]:








array([ 70,  47, 123,   3,  14, 141,   5, 136,  89,  79,  62, 117,   2,
       135,  40, 109, 145, 137,  87, 102,  23,  39,   0, 142,  54,  33,
        61, 125,  51,  74,  76,  12,  59,  75,  42,  90,   9, 106,  50,
        72, 110,  21,  43,  71,  20, 118, 126,  48,  24,  22,  37,  36,
        98,  69,  60,   7,  57, 113,  92, 129,  63,  38, 133,  82,  11,
       104, 146,  93, 116, 131,   4, 103, 127, 107,  94,  58,  80,  77,
        19,  99,  78,  86, 130,  73,  96,  52,  85, 140,  31,  26,  27,
        35,  97,   1, 111,  16,  34,  68,  49,  81, 128,  55, 120,  17,
        65,  83,  32, 144,  10,  84, 139,  44, 112, 124, 105,  88, 138,
        53,  30,  66,  15, 148,  64, 114,  45,  29,  67,  91, 147, 122,
        18,   6, 115,  41, 121,  95,  56,   8, 108,  13, 100,  28, 101,
        46, 149, 134,  25, 119, 143, 132])

















In [35]:



    


from sklearn.linear_model import LogisticRegression



    











In [38]:



    


from sklearn import datasets



    











In [39]:



    


iris = datasets.load_iris()



    











In [40]:



    


x,y=iris.data,iris.target



    











In [42]:



    


x



    


















    
Out[42]:








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 [43]:



    


y



    


















    
Out[43]:








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 [45]:



    


from sklearn.cross_validation import train_test_split



    


















    






C:\Users\KOGENTIX\Anaconda3\lib\site-packages\sklearn\cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)

















In [46]:



    


X_train,X_test,y_train,y_test=train_test_split(x,y,test_size=0.8)



    











In [61]:



    


iris_X_train2 = iris.data[:-30]
iris_X_test2  = iris.data[-30:]
iris_y_train2 = iris.target[:-30]
iris_y_test2  = iris.target[-30:]



    











In [62]:



    


iris_X_train2.shape



    


















    
Out[62]:








(120, 4)

















In [63]:



    


iris_X_train2



    


















    
Out[63]:








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]])

















In [64]:



    


X_train



    


















    
Out[64]:








array([[ 5.2,  2.7,  3.9,  1.4],
       [ 4.9,  2.4,  3.3,  1. ],
       [ 7.7,  2.6,  6.9,  2.3],
       [ 5.8,  2.8,  5.1,  2.4],
       [ 7.3,  2.9,  6.3,  1.8],
       [ 7.7,  3.8,  6.7,  2.2],
       [ 6.2,  2.2,  4.5,  1.5],
       [ 6.1,  3. ,  4.9,  1.8],
       [ 5.1,  3.8,  1.5,  0.3],
       [ 6.3,  2.3,  4.4,  1.3],
       [ 5.7,  4.4,  1.5,  0.4],
       [ 5.5,  2.4,  3.8,  1.1],
       [ 6.5,  3. ,  5.2,  2. ],
       [ 7.2,  3.6,  6.1,  2.5],
       [ 6. ,  2.2,  5. ,  1.5],
       [ 5.6,  3. ,  4.5,  1.5],
       [ 5. ,  3.6,  1.4,  0.2],
       [ 4.8,  3. ,  1.4,  0.3],
       [ 6.2,  2.9,  4.3,  1.3],
       [ 5.9,  3. ,  5.1,  1.8],
       [ 5.4,  3.7,  1.5,  0.2],
       [ 5. ,  3.2,  1.2,  0.2],
       [ 5.4,  3.4,  1.7,  0.2],
       [ 6.7,  3.3,  5.7,  2.5],
       [ 5. ,  2.3,  3.3,  1. ],
       [ 6. ,  3.4,  4.5,  1.6],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5.7,  3.8,  1.7,  0.3],
       [ 5.5,  2.4,  3.7,  1. ],
       [ 6.3,  2.5,  4.9,  1.5]])

















In [65]:



    


X_train.shape



    


















    
Out[65]:








(30, 4)

















In [66]:



    


X_train.shape



    


















    
Out[66]:








(30, 4)

















In [67]:



    


X_test.shape



    


















    
Out[67]:








(120, 4)

















In [68]:



    


y_train.shape



    


















    
Out[68]:








(30,)

















In [69]:



    


y_test.shape



    


















    
Out[69]:








(120,)

















In [70]:



    


np.random.seed(0)
indices = np.random.permutation(len(iris))



    











In [71]:



    


iris_X_train = iris.data[indices[:-30]]



    











In [72]:



    


iris_y_train = iris.data[indices[:-30]]
iris_X_test  = iris.data[indices[-30:]]
iris_y_test  = iris.target[indices[-30:]]



    











In [ ]:

Content source: decisionstats/pythonfordatascience

Similar notebooks:

notebook.community | gallery | about