5/6/2021 Cross Validation Presentation - Jupyter Notebook

In [7]:

#K-fold

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sn
import statsmodels.api as sm
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold

ipl_df=pd.read_csv(r'M:\MCA\Sem 4\ML(PREETI MAM)\p1\IPL IMB381IPL2013.csv')

#spliting dataset into train and test set

X=ipl_df['BASE PRICE']
y=ipl_df['SOLD PRICE']

kf = KFold(n_splits=2)

for train_index, test_index in kf.split(X):

print("TRAIN:", train_index)
print("TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]

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

localhost:8888/notebooks/Cross Validation Presentation.ipynb 1/4

5/6/2021 Cross Validation Presentation - Jupyter Notebook

In [15]:

from sklearn.model_selection import LeaveOneOut

loo = LeaveOneOut()

for train_index, test_index in loo.split(X):

print("TRAIN:", train_index)
print("TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]

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

localhost:8888/notebooks/Cross Validation Presentation.ipynb 2/4

5/6/2021 Cross Validation Presentation - Jupyter Notebook

In [14]:

import numpy as np
from sklearn.model_selection import StratifiedKFold

skf = StratifiedKFold(n_splits=2)

for train_index, test_index in skf.split(X, y):

print("TRAIN:", train_index)
print("TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]

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

C:\Users\DV\anaconda3\lib\site-packages\sklearn\model_selection\_split.py:67
0: UserWarning: The least populated class in y has only 1 members, which is
less than n_splits=2.
warnings.warn(("The least populated class in y has only %d"

localhost:8888/notebooks/Cross Validation Presentation.ipynb 3/4

5/6/2021 Cross Validation Presentation - Jupyter Notebook

In [12]:

#Leave-p-out

import numpy as np
from sklearn.model_selection import LeavePOut

lpo = LeavePOut(2)

for train_index, test_index in lpo.split(X):

print("TRAIN:", train_index)
print("TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]

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

localhost:8888/notebooks/Cross Validation Presentation.ipynb 4/4