數據分析~KNN數據建模例子

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.neighbors import KNeighborsClassifier
%matplotlib inline

# 加載數據集
fruits_df = pd.read_table('fruit_data_with_colors.txt')

X = fruits_df[['mass', 'width', 'height', 'color_score']]
y = fruits_df['fruit_label']

# 分割數據集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=1/4, random_state=0)

# 創建模型
knn = KNeighborsClassifier(n_neighbors=5)

# 訓練模型
knn.fit(X_train, y_train)

# 驗證模型
y_pred = knn.predict(X_test)

acc = accuracy_score(y_test, y_pred)
print('準確率：', acc)

 

===================================

準確率： 0.533333333333