Gaussian Naive Bayes ile Iris Veriseti Sınıflandırması

In [1]:
import matplotlib.pyplot as plt
import numpy as np
from IPython.display import Image,HTML
from sklearn import datasets
HTML("""<style>
.output_png {text-align: center;}
</style>""")

Out[1]:
In [2]:
Image(filename="C:\\Users\\ceakn\\Desktop\\1-site-resimler\\iris.png")

Out[2]:
In [3]:
print(iris.feature_names)

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

In [4]:
print(iris.target_names)

['setosa' 'versicolor' 'virginica']

In [5]:
iris.data

Out[5]:
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,  0.1],
[ 5. ,  3.2,  1.2,  0.2],
[ 5.5,  3.5,  1.3,  0.2],
[ 4.9,  3.1,  1.5,  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. ],
[ 6.6,  2.9,  4.6,  1.3],
[ 5.2,  2.7,  3.9,  1.4],
[ 5. ,  2. ,  3.5,  1. ],
[ 5.9,  3. ,  4.2,  1.5],
[ 6. ,  2.2,  4. ,  1. ],
[ 6.1,  2.9,  4.7,  1.4],
[ 5.6,  2.9,  3.6,  1.3],
[ 6.7,  3.1,  4.4,  1.4],
[ 5.6,  3. ,  4.5,  1.5],
[ 5.8,  2.7,  4.1,  1. ],
[ 6.2,  2.2,  4.5,  1.5],
[ 5.6,  2.5,  3.9,  1.1],
[ 5.9,  3.2,  4.8,  1.8],
[ 6.1,  2.8,  4. ,  1.3],
[ 6.3,  2.5,  4.9,  1.5],
[ 6.1,  2.8,  4.7,  1.2],
[ 6.4,  2.9,  4.3,  1.3],
[ 6.6,  3. ,  4.4,  1.4],
[ 6.8,  2.8,  4.8,  1.4],
[ 6.7,  3. ,  5. ,  1.7],
[ 6. ,  2.9,  4.5,  1.5],
[ 5.7,  2.6,  3.5,  1. ],
[ 5.5,  2.4,  3.8,  1.1],
[ 5.5,  2.4,  3.7,  1. ],
[ 5.8,  2.7,  3.9,  1.2],
[ 6. ,  2.7,  5.1,  1.6],
[ 5.4,  3. ,  4.5,  1.5],
[ 6. ,  3.4,  4.5,  1.6],
[ 6.7,  3.1,  4.7,  1.5],
[ 6.3,  2.3,  4.4,  1.3],
[ 5.6,  3. ,  4.1,  1.3],
[ 5.5,  2.5,  4. ,  1.3],
[ 5.5,  2.6,  4.4,  1.2],
[ 6.1,  3. ,  4.6,  1.4],
[ 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]])
In [6]:
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]

In [7]:
print(type(iris.data))
print(type(iris.target))
print(type(iris))
print(iris.data.shape)

<class 'numpy.ndarray'>
<class 'numpy.ndarray'>
<class 'sklearn.datasets.base.Bunch'>
(150, 4)

In [8]:
np.isnan(iris.data).any()
np.isnan(iris.target).any()

Out[8]:
False
In [9]:
X = iris.data
y = iris.target


Gerekli Kütüphanenin İçe Aktarılması

In [10]:
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()

In [11]:
classifier.fit(X,y)

Out[11]:
GaussianNB(priors=None)

Eğitim ve Test Kümelerine Ayırma (Train/Test split)

In [12]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=4)

In [13]:
print(X_train.shape ,X_test.shape)

(100, 4) (50, 4)

In [14]:
print(y_train.shape ,y_test.shape)

(100,) (50,)

In [15]:
y_pred = classifier.predict(X_test)


Hata Oranını Bulalım

In [16]:
from sklearn.metrics import accuracy_score

In [17]:
print(accuracy_score(y_test, y_pred))

0.98

In [18]:
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
cm

Out[18]:
array([[23,  0,  0],
[ 0, 12,  0],
[ 0,  1, 14]])

1 hatalı sonucumuz varmış