机器学习5-自己的第一个分类器

python 代码

# coding=utf-8
import random
from sklearn.datasets import load_iris

# 获取鸢尾数据
iris = load_iris()

X = iris.data
y = iris.target

# 评分公式
from sklearn.metrics import accuracy_score

# 乱写的一个分类器
# 评分大概
class MyClf():
    def fit(self,train_data,train_target):
        self.train_data = train_data
        self.train_target = train_target


    def predict(self,test_data):
        predictions = []
        for data in test_data:
            # 随机返回一个结果值
            target = random.choice(self.train_target)
            predictions.append(target)
        return predictions

# 使用k-neighbors原理写的分类器
# 此处为了简单，k取值1
from scipy.spatial import distance

def euc(a,b):
    return distance.euclidean(a,b)

class MyClf2():
    def fit(self,train_data,train_target):
        self.train_data = train_data
        self.train_target = train_target


    def predict(self,test_data):
        predictions = []
        for data in test_data:
            # 随机返回一个结果值
            target = self.closest(data)
            predictions.append(target)
        return predictions

    def closest(self,row):
        best_dis = euc(row,self.train_data[0])
        best_idx = 0

        for x in xrange(1,len(self.train_data)):
            curr_dis = euc(row,self.train_data[x])
            if best_dis>curr_dis:
                best_idx=x
                best_dis=curr_dis
                pass
        return self.train_target[best_idx]

# cross_validation 改成 model_selection
# 前者好像是版本问题，过期了
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=.3)

clf = MyClf()
clf.fit(X_train,y_train)
predictions = clf.predict(X_test)
# print predictions
# 评分大概在.3，因为target就3个值
print 'myclf score:',accuracy_score(y_test,predictions)


clf = MyClf2()
clf.fit(X_train,y_train)
predictions = clf.predict(X_test)
# print predictions
print 'myclf2 score:',accuracy_score(y_test,predictions)

截图

我们自己写的分类器的正确率到了97%