4/20/24, 8:54 PM MLlab 3/15/2024.
ipynb - Colab
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
dataset = pd.read_csv('https://raw.githubusercontent.com/mk-gurucharan/Classification/master/IrisDataset.csv')
X = dataset.iloc[:,:4].values
y = dataset['species'].values
dataset.head(5)
output sepal_length sepal_width petal_length petal_width species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, y_train)
▾ GaussianNB
GaussianNB()
y_pred = classifier.predict(X_test)
y_pred
array(['virginica', 'versicolor', 'versicolor', 'virginica', 'virginica',
'virginica', 'setosa', 'setosa', 'virginica', 'virginica',
'virginica', 'virginica', 'versicolor', 'versicolor', 'virginica',
'virginica', 'versicolor', 'setosa', 'versicolor', 'versicolor',
'virginica', 'versicolor', 'versicolor', 'versicolor', 'setosa',
'versicolor', 'setosa', 'setosa', 'virginica', 'virginica'],
dtype='<U10')
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
from sklearn.metrics import accuracy_score
print ("Accuracy : ", accuracy_score(y_test, y_pred))
cm
Accuracy : 1.0
array([[ 6, 0, 0],
[ 0, 11, 0],
[ 0, 0, 13]])
df_cm=pd.DataFrame(cm,columns =np.unique(y_test),index=np.unique(y_test))
df_cm.index.name='Actual'
df_cm.columns.name='Predicted'
sns.heatmap(df_cm, annot=True)
plt.show()
https://colab.research.google.com/drive/1qsQIG0ZIevF4iY_GXOjK3LWTRFwjnsXZ#printMode=true 1/3
4/20/24, 8:54 PM MLlab 3/15/2024.ipynb - Colab
df = pd.DataFrame({'Real Values':y_test, 'Predicted Values':y_pred})
df
Real Values Predicted Values
0 virginica virginica
1 setosa setosa
2 setosa setosa
3 versicolor versicolor
4 versicolor versicolor
5 virginica virginica
6 virginica virginica
7 setosa setosa
8 setosa setosa
9 virginica virginica
10 virginica virginica
11 versicolor versicolor
12 virginica virginica
13 setosa setosa
14 virginica versicolor
15 setosa setosa
16 virginica virginica
17 virginica virginica
18 versicolor versicolor
19 setosa setosa
20 virginica virginica
21 versicolor versicolor
22 virginica virginica
23 setosa setosa
24 virginica virginica
25 versicolor versicolor
26 setosa setosa
27 versicolor versicolor
28 setosa setosa
29 setosa setosa
https://colab.research.google.com/drive/1qsQIG0ZIevF4iY_GXOjK3LWTRFwjnsXZ#printMode=true 2/3
4/20/24, 8:54 PM MLlab 3/15/2024.ipynb - Colab
https://colab.research.google.com/drive/1qsQIG0ZIevF4iY_GXOjK3LWTRFwjnsXZ#printMode=true 3/3
