KNN classification - iris

데이터셋 불러오기

 

# seaborn 라이브러리 사용

import seaborn as sns
iris = sns.load_dataset('iris')
X =  iris.drop('species', axis = 1)
y = iris['species']

#sklearn 라이브러리 사용

from sklearn.datasets import load_iris
iris = load_iris()

<seaborn.load_dataset>

manual: seaborn.pydata.org/generated/seaborn.load_dataset.html?highlight=load_dataset#seaborn.load_dataset

seaborn.load_dataset — seaborn 0.11.0 documentation

<sklearn.datasets.load_iris>

manual: scikit-learn.org/stable/modules/classes.html?highlight=datasets#module-sklearn.datasets

API Reference — scikit-learn 0.23.2 documentation

 

카테고리의 실수화

class name이 실수가 아니기 때문에 실수로 바꿔 줌

from sklearn.preprocessing import LabelEncoder
import numpy as np
classle = LabelEncoder()
y = classle.fit_transform(iris['species'].values)

yo = classle.inverse_transform(y)

 

데이터 분할

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 1, stratify = y)

 

학습

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=5, p=2)
knn.fit(X_train, y_train)

y_train_pred = knn.predict(X_train)
y_test_pred = kbb.predict(X_test)

from sklearn.metrics import accuracy_score
print(accuracy_score(y_test, y_test_pred))