Scribd
Upload
17 views

Exp 07 (ML)

This document loads and analyzes the iris dataset using various machine learning algorithms like KNN. It loads the iris data, explores various attributes, performs train-test split and analyzes the accuracy of KNN for different values of K.

Uploaded by

DSE 04. Chetana Bhoir
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
17 views

Exp 07 (ML)

This document loads and analyzes the iris dataset using various machine learning algorithms like KNN. It loads the iris data, explores various attributes, performs train-test split and analyzes the accuracy of KNN for different values of K.

Uploaded by

DSE 04. Chetana Bhoir
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

8/20/23, 12:14 AM EXP_07(ML).

ipynb - Colaboratory

Name -: Chetana Bhoir

Roll_No -: 12

%matplotlib inline
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris

iris = load_iris()
type(iris)

sklearn.utils._bunch.Bunch

iris.data

[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]])

print(iris.feature_names)

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

( )
https://colab.research.google.com/drive/1IYOHvE58f1fP_UQDmsVF4QQ0KvQkTCF6#scrollTo=KZsMYwNaOvCF&printMode=true 1/5
8/20/23, 12:14 AM EXP_07(ML).ipynb - Colaboratory
print(iris.target)

[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]

print(iris.target_names)

['setosa' 'versicolor' 'virginica']

plt.scatter(iris.data[:,1],iris.data[:,2],c=iris.target, cmap=plt.cm.Paired)
plt.xlabel(iris.feature_names[1])
plt.ylabel(iris.feature_names[2])
plt.show()

plt.scatter(iris.data[:,0],iris.data[:,3],c=iris.target, cmap=plt.cm.Paired)
plt.xlabel(iris.feature_names[0])
plt.ylabel(iris.feature_names[3])
plt.show()

p = iris.data
q = iris.target

print(p.shape)
print(q.shape)

https://colab.research.google.com/drive/1IYOHvE58f1fP_UQDmsVF4QQ0KvQkTCF6#scrollTo=KZsMYwNaOvCF&printMode=true 2/5
8/20/23, 12:14 AM EXP_07(ML).ipynb - Colaboratory

(150, 4)
(150,)

!pip install matplotlib-venn


# https://pypi.python.org/pypi/libarchive

Requirement already satisfied: matplotlib-venn in /usr/local/lib/python3.10/dist-packages (0.11.9)


Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from matplotlib-venn) (3.7.1)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from matplotlib-venn) (1.23.5)
Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from matplotlib-venn) (1.10.1)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (1.1.0)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (4.42.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (1.4.4)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (23.1)
Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (9.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (3.1.1)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (2.8.2
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib->matplotlib-ve

!pip install matplotlib-venn


!apt-get -qq install -y libfluidsynth1

Requirement already satisfied: matplotlib-venn in /usr/local/lib/python3.10/dist-packages (0.11.9)


Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from matplotlib-venn) (3.7.1)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from matplotlib-venn) (1.23.5)
Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from matplotlib-venn) (1.10.1)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (1.1.0)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (4.42.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (1.4.4)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (23.1)
Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (9.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (3.1.1)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib->matplotlib-venn) (2.8.2
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib->matplotlib-ve
E: Package 'libfluidsynth1' has no installation candidate

from sklearn.model_selection import train_test_split


p_train,p_test,q_train,q_test = train_test_split(p,q,test_size=0.2,random_state=4)

print(p_train.shape)
print(p_test.shape)

(120, 4)
(30, 4)

print(q_train.shape)
print(q_test.shape)

(120,)
(30,)

from sklearn.neighbors import KNeighborsClassifier

from sklearn import metrics

k_range = range(1,26)
scores = {}
scores_list = []
for k in k_range:
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(p_train,q_train)
q_pred=knn.predict(p_test)
scores[k] = metrics.accuracy_score(q_test,q_pred)
scores_list.append(metrics.accuracy_score(q_test,q_pred))

scores

{1: 0.9333333333333333,
2: 0.9333333333333333,

https://colab.research.google.com/drive/1IYOHvE58f1fP_UQDmsVF4QQ0KvQkTCF6#scrollTo=KZsMYwNaOvCF&printMode=true 3/5
8/20/23, 12:14 AM EXP_07(ML).ipynb - Colaboratory
3: 0.9666666666666667,
4: 0.9666666666666667,
5: 0.9666666666666667,
6: 0.9666666666666667,
7: 0.9666666666666667,
8: 0.9666666666666667,
9: 0.9666666666666667,
10: 0.9666666666666667,
11: 0.9666666666666667,
12: 0.9666666666666667,
13: 0.9666666666666667,
14: 0.9666666666666667,
15: 0.9666666666666667,
16: 0.9666666666666667,
17: 0.9666666666666667,
18: 0.9666666666666667,
19: 0.9666666666666667,
20: 0.9333333333333333,
21: 0.9666666666666667,
22: 0.9333333333333333,
23: 0.9666666666666667,
24: 0.9666666666666667,
25: 0.9666666666666667}

#plot the relationship between K and the testing accuracy


plt.plot(k_range,scores_list)
plt.xlabel('Value of K for KNN')
plt.ylabel('Testing Accuracy')

Text(0, 0.5, 'Testing Accuracy')

knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(p,q)

▾ KNeighborsClassifier
KNeighborsClassifier()

#0 = setosa, 1=versicolor, 2=virginica


classes = {0:'setosa',1:'versicolor',2:'virginica'}

x_new = [[3,4,5,2],
[5,4,2,2]]
y_predict = knn.predict(x_new)

print(classes[y_predict[0]])
print(classes[y_predict[1]])

versicolor
setosa

https://colab.research.google.com/drive/1IYOHvE58f1fP_UQDmsVF4QQ0KvQkTCF6#scrollTo=KZsMYwNaOvCF&printMode=true 4/5

You might also like