data1 # exploring the data

account_circle {'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, 0.2],
[5. , 3.2, 1.2, 0.2],
[5.5, 3.5, 1.3, 0.2],
[4.9, 3.6, 1.4, 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. ],

type(data1) # checking the type of the data

sklearn.utils._bunch.Bunch

data1.keys() # extracting all the keys of dictionary as data in the form of dictionary

dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])

data1['feature_names'] # selcecting feature names as name of column for SVM classification

['sepal length (cm)',

'sepal width (cm)',
'petal length (cm)',
'petal width (cm)']

data1['data'] # selecting data for four features

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, 0.2],
[5. , 3.2, 1.2, 0.2],
[5.5, 3.5, 1.3, 0.2],
[4.9, 3.6, 1.4, 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. ],

data1['target_names'] # selecting target names for for SVM classification

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

iris_data.head() # exploring the created iris dataset

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

0 5.1 3.5 1.4 0.2

1 4.9 3.0 1.4 0.2

2 4.7 3.2 1.3 0.2

3 4.6 3.1 1.5 0.2

4 5.0 3.6 1.4 0.2

iris_data.head() # checking first five rows of dataset

sepal length sepal width petal length petal width

Target
(cm) (cm) (cm) (cm)

0 5.1 3.5 1.4 0.2 0

1 4.9 3.0 1.4 0.2 0

2 4.7 3.2 1.3 0.2 0

3 4.6 3.1 1.5 0.2 0

4 5.0 3.6 1.4 0.2 0

data1.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])

data1.target_names

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

iris_data.tail() # checking last five rows of created iris dataset

sepal length sepal width petal length petal width Target

Target
(cm) (cm) (cm) (cm) name

145 6.7 3.0 5.2 2.3 2 virginica

146 6.3 2.5 5.0 1.9 2 virginica

147 6.5 3.0 5.2 2.0 2 virginica

148 6.2 3.4 5.4 2.3 2 virginica

149 5.9 3.0 5.1 1.8 2 virginica

iris_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 6 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 sepal length (cm) 150 non-null float64
1 sepal width (cm) 150 non-null float64
2 petal length (cm) 150 non-null float64
3 petal width (cm) 150 non-null float64
4 Target 150 non-null int64
5 Target name 150 non-null object
dtypes: float64(4), int64(1), object(1)
memory usage: 7.2+ KB

iris_data.describe() # describing all the numerical columns

sepal length sepal width petal length petal width

Target
(cm) (cm) (cm) (cm)

count 150.000000 150.000000 150.000000 150.000000 150.000000

mean 5.843333 3.057333 3.758000 1.199333 1.000000

std 0.828066 0.435866 1.765298 0.762238 0.819232

min 4.300000 2.000000 1.000000 0.100000 0.000000

25% 5.100000 2.800000 1.600000 0.300000 0.000000

50% 5.800000 3.000000 4.350000 1.300000 1.000000

75% 6.400000 3.300000 5.100000 1.800000 2.000000

max 7.900000 4.400000 6.900000 2.500000 2.000000

iris_data.groupby(['Target name']).mean() # taking maen of all numerical columns

sepal length sepal width petal length petal width

Target
(cm) (cm) (cm) (cm)

Target
name

sentosa 5.006 3.428 1.462 0.246 0.0

versicolor 5.936 2.770 4.260 1.326 1.0

X_train.shape # checking the shape of the training inputs

(120, 4)

from sklearn.neighbors import KNeighborsClassifier # importing KNN classifier from sklearn

knn = KNeighborsClassifier(n_neighbors=3) # making a KNN instance with 3 neighbors
knn.fit(X_train, y_train) # fitting KNN instance with traning data
 ▾ KNeighborsClassifier
KNeighborsClassifier(n_neighbors=3)

y_pred = knn.predict(X_test) # predicting the results on test data

y_pred

array(['virginica', 'versicolor', 'sentosa', 'virginica', 'sentosa',

'virginica', 'sentosa', 'versicolor', 'versicolor', 'versicolor',
'virginica', 'versicolor', 'versicolor', 'versicolor', 'virginica',
'sentosa', 'versicolor', 'versicolor', 'sentosa', 'sentosa',
'virginica', 'versicolor', 'sentosa', 'sentosa', 'virginica',
'sentosa', 'sentosa', 'versicolor', 'versicolor', 'sentosa'],
dtype=object)

print(f'Our model accuracy with k=3 is: {knn.score(X_test, y_test)}') # calculating the model's accuracy

Our model accuracy with k=3 is: 0.9666666666666667

print(classification_report(y_test, y_pred)) # generating the classification report

precision recall f1-score support

sentosa 1.00 1.00 1.00 13

versicolor 1.00 0.94 0.97 16
virginica 0.90 1.00 0.95 9

accuracy 0.97 38
macro avg 0.97 0.98 0.97 38
weighted avg 0.98 0.97 0.97 38

print(confusion_matrix(y_test, y_pred)) # printing the confusion matrix

[[13 0 0]
[ 0 15 1]
[ 0 0 9]]