【python数据分析】数据建模之KNN分类

最近邻分类：在距离空间里，如果一个样本的最接近的k个邻居里，绝大多数属于某个类别，则该样本也属于这个类别。

KNN分类

案例分析：电影分类

from sklearn import neighbors  # 导入KNN分类模块

data = pd.DataFrame({'name':['北京遇上西雅图','喜欢你','疯狂动物城','战狼2','力王','敢死队'],                  'fight':[3,2,1,101,99,98],                  'kiss':[104,100,81,10,5,2],                  'type':['Romance','Romance','Romance','Action','Action','Action']})print(data)print('-------')
# 加载数据，构建KNN分类模型# 预测未知数据knn = neighbors.KNeighborsClassifier()   # 取得knn分类器knn.fit(data[['fight','kiss']], data['type'])# print('预测电影类型为:', knn.predict([18, 90]))
# 绘制图表plt.scatter(data[data['type'] == 'Romance']['fight'],data[data['type'] == 'Romance']['kiss'],color = 'r',marker = 'o',label = 'Romance')plt.scatter(data[data['type'] == 'Action']['fight'],data[data['type'] == 'Action']['kiss'],color = 'g',marker = 'o',label = 'Action')plt.grid()plt.legend()plt.scatter(18,90,color = 'r',marker = 'x',label = 'Romance')plt.ylabel('kiss')plt.xlabel('fight')plt.text(18,90,'《你的名字》',color = 'r')

# 给随机数据进行模拟预测
# 创建数据，并调用模型预测data2 = pd.DataFrame(np.random.randn(100,2)*50,columns = ['fight','kiss'])data2['type'] = knn.predict(data2)print(data2.head())print('------')
# 绘制图表plt.scatter(data[data['type'] == 'Romance']['fight'],data[data['type'] == 'Romance']['kiss'],color = 'r',marker = 'o',label = 'Romance')plt.scatter(data[data['type'] == 'Action']['fight'],data[data['type'] == 'Action']['kiss'],color = 'g',marker = 'o',label = 'Action')plt.grid()plt.scatter(data2[data2['type'] == 'Romance']['fight'],data2[data2['type'] == 'Romance']['kiss'],color = 'r',marker = 'x',label = 'Romance')plt.scatter(data2[data2['type'] == 'Action']['fight'],data2[data2['type'] == 'Action']['kiss'],color = 'g',marker = 'x',label = 'Action')plt.legend()plt.ylabel('kiss')plt.xlabel('fight')