09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.

ipynb - Colab

import pandas as pd

from sklearn.datasets import load_iris

iris = load_iris()

iris.feature_names

['sepal length (cm)',

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

Double-click (or enter) to edit

iris.target_names

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

df = pd.DataFrame(iris.data, columns=iris.feature_names)
df.head()

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 1/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab

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

df.shape

(150, 4)

df['target'] = iris.target
df.head()

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

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

df[df.target == 1].head()

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

50 7.0 3.2 4.7 1.4 1

51 6.4 3.2 4.5 1.5 1

52 6.9 3.1 4.9 1.5 1

53 5.5 2.3 4.0 1.3 1

54 6.5 2.8 4.6 1.5 1

df[df.target == 2].head()

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 2/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab

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

100 6.3 3.3 6.0 2.5 2

101 5.8 2.7 5.1 1.9 2

102 7.1 3.0 5.9 2.1 2

103 6.3 2.9 5.6 1.8 2

104 6.5 3.0 5.8 2.2 2

df['flower_name'] = df.target.apply(lambda x: iris.target_names[x])

df.head()

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

0 5.1 3.5 1.4 0.2 0 setosa

1 4.9 3.0 1.4 0.2 0 setosa

2 4.7 3.2 1.3 0.2 0 setosa

3 4.6 3.1 1.5 0.2 0 setosa

4 5.0 3.6 1.4 0.2 0 setosa

df[45:55]

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

45 4.8 3.0 1.4 0.3 0 setosa

46 5.1 3.8 1.6 0.2 0 setosa

47 4.6 3.2 1.4 0.2 0 setosa

48 5.3 3.7 1.5 0.2 0 setosa

49 5.0 3.3 1.4 0.2 0 setosa

50 7.0 3.2 4.7 1.4 1 versicolor

51 6.4 3.2 4.5 1.5 1 versicolor

52 6.9 3.1 4.9 1.5 1 versicolor

53 5.5 2.3 4.0 1.3 1 versicolor

54 6.5 2.8 4.6 1.5 1 versicolor

df0 = df[:50]
df1 = df[50:100]
df2 = df[100:]

import matplotlib.pyplot as plt

%matplotlib inline

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 3/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab

plt.xlabel('Sepal Length')
plt.ylabel('Sepal Width')
plt.scatter(df0['sepal length (cm)'], df0['sepal width (cm)'],color="green",marker='+')
plt.scatter(df1['sepal length (cm)'], df1['sepal width (cm)'],color="blue",marker='*')

<matplotlib.collections.PathCollection at 0x78d7e90c9270>

plt.xlabel('Petal Length')
plt.ylabel('Petal Width')
plt.scatter(df0['petal length (cm)'], df0['petal width (cm)'],color="green",marker='+')
plt.scatter(df1['petal length (cm)'], df1['petal width (cm)'],color="blue",marker='*')

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 4/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab
<matplotlib.collections.PathCollection at 0x78d7e869e710>

from sklearn.model_selection import train_test_split

x = df.drop(['target','flower_name'], axis='columns')
y = df.target

x_train, x_test, y_train, y_test = train_test_split(x,y, test_size=0.4, random_state=1)

len(x_train)

90

len(x_test)

60

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier (n_neighbors=55)

knn.fit(x_train, y_train)

▾ KNeighborsClassifier i ?

KNeighborsClassifier(n_neighbors=55)

knn.score(x_test, y_test)

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 5/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab
0.8833333333333333

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay

y_pred = knn.predict(x_test)

# Compute confusion matrix

cm = confusion_matrix(y_test, y_pred)

# Display confusion matrix in text form

print("Confusion Matrix:\n", cm)

# Plot confusion matrix

disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=knn.classes_)
disp.plot(cmap="Blues")

Confusion Matrix:
[[19 0 0]
[ 1 14 6]
[ 0 0 20]]
<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x78d7e7e40bb0>

print(f"\nTotal number of data points in test set: {len(y_test)}")

print(f"Total number of predictions made: {total_predictions}")

Total number of data points in test set: 60

Total number of predictions made: 60

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 6/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay

# Compute confusion matrix

cm = confusion_matrix(y_test, y_pred)

# Calculate total test set predictions

total_predictions = cm.sum()

# Display confusion matrix in text form

print("Confusion Matrix:")
print(cm)

# Display class labels and confusion matrix summary

class_labels = knn.classes_
print("\nClass Labels:")
for i, label in enumerate(class_labels):
print(f"Class {i}: {label}")

print(f"\nTotal number of data points in test set: {len(y_test)}")

print(f"Total number of predictions made: {total_predictions}")

# Plot confusion matrix with class labels

disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=class_labels)
disp.plot(cmap="Blues")

# Show the plot

import matplotlib.pyplot as plt
plt.show()

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 7/8
09/12/2024, 22:49 LAB # 07 KNN_Iris Dataset.ipynb - Colab
Confusion Matrix:
[[11 0 0]
[ 1 10 2]
[ 0 0 6]]

Class Labels:
Class 0: 0

keyboard_arrow_down Load digits dataset from sklearn, and use knn classifier for classification of digits
Class 1: 1
Class 2: 2

Total number of data points in test set: 30

Total number of predictions made: 30
from sklearn.datasets import load_digits
digits = load_digits()
print(digits.data.shape)
(1797, 64)
import matplotlib.pyplot as plt
plt.gray()
plt.matshow(digits.images[2])
plt.show()

(1797, 64)
<Figure size 640x480 with 0 Axes>

https://colab.research.google.com/drive/1Rql8Pw86rMXQ20F3wSkyUjHGyECJtjPv#printMode=true 8/8