Machine-Learning/lab_sheet_3.py at main · samadhiy/Machine-Learning · GitHub

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
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
# -*- coding: utf-8 -*-
"""Lab Sheet 3.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1h-REPmmItYJLrAlYVAKivMUbYNdLmLnU

Mini Project: Iris Flower Classification using KNN

1.Import Required Libraries
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

"""2.Load the Iris Dataset"""

data = pd.read_csv("iris.csv")
data.head()

"""3.Dataset Information"""

data.info()

"""4.Statistical Summary"""

data.describe()

"""5.Separate Features and Target"""

X = data.drop("species", axis=1)
y = data["species"]

"""6.Train–Test Split"""

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

"""7.Feature Scaling

"""

scaler = StandardScaler()

X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

"""8.Build KNN Model (k = 5)"""

knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train_scaled, y_train)

"""9.Make Predictions"""

y_pred = knn.predict(X_test_scaled)
y_pred

"""10.Model Accuracy"""

accuracy = accuracy_score(y_test, y_pred)
accuracy

"""11.Confusion Matrix"""

cm = confusion_matrix(y_test, y_pred)
cm

"""12.Classification Report"""

print(classification_report(y_test, y_pred))

"""13.Effect of Different k Values"""

accuracy_list = []

k_values = range(1, 21)

for k in k_values:
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train_scaled, y_train)
    y_pred = knn.predict(X_test_scaled)
    accuracy_list.append(accuracy_score(y_test, y_pred))

"""14.Plot Accuracy vs k"""

plt.plot(k_values, accuracy_list, marker='o')
plt.xlabel("Value of k")
plt.ylabel("Accuracy")
plt.title("KNN Accuracy for Different k Values")
plt.show()

"""15.Best k Value"""

best_k = k_values[accuracy_list.index(max(accuracy_list))]
best_k