도미 데이터 머신러닝(KNN)-1

# -*- coding: utf-8 -*-
"""
#데이터 준비하기
"""

bream_length = [25.4, 26.3, 26.5, 29.0, 29.0, 29.7, 29.7, 30.0, 30.0, 30.7, 31.0, 31.0, 
                31.5, 32.0, 32.0, 32.0, 33.0, 33.0, 33.5, 33.5, 34.0, 34.0, 34.5, 35.0, 
                35.0, 35.0, 35.0, 36.0, 36.0, 37.0, 38.5, 38.5, 39.5, 41.0, 41.0]
bream_weight = [242.0, 290.0, 340.0, 363.0, 430.0, 450.0, 500.0, 390.0, 450.0, 500.0, 475.0, 500.0, 
                500.0, 340.0, 600.0, 600.0, 700.0, 700.0, 610.0, 650.0, 575.0, 685.0, 620.0, 680.0, 
                700.0, 725.0, 720.0, 714.0, 850.0, 1000.0, 920.0, 955.0, 925.0, 975.0, 950.0]

smelt_length = [9.8, 10.5, 10.6, 11.0, 11.2, 11.3, 11.8, 11.8, 12.0, 12.2, 12.4, 13.0, 14.3, 15.0]
smelt_weight = [6.7, 7.5, 7.0, 9.7, 9.8, 8.7, 10.0, 9.9, 9.8, 12.2, 13.4, 12.2, 19.7, 19.9]

length = bream_length + smelt_length
weight = bream_weight + smelt_weight

fish_data = [(l,w) for l,w in zip(length, weight)]

fish_target = [1]*35 + [0]*14
#도미: 35개, 빙어:14개

len(fish_data)

len(fish_target)

"""#훈련하기"""

from sklearn.neighbors import KNeighborsClassifier

kn = KNeighborsClassifier()

kn.fit(fish_data, fish_target)  #kn이라는 객체 안에 학습된 데이터가 있어야 한다.
#KNN classifier 구현체 -> 학습이 없다.

kn.effective_metric_

kn._fit_X.shape

attrs = dir(kn)

x,y=2,3
x+y

# _는 마지막 결과를 저장한다.
_

result = 0
for i in range(1,6):
  result+=i
result

class MyClass(object):
  def __init__(self):
    pass  #객체를 초기화할때
  def test_method(self):
    pass
my_obj = MyClass()
my_obj.test_method()

1000000

1_000_000
#자릿수

import re
#*:0이상, 1이상(0이면 없어도 된다.)
p=re.compile('_[a-zA-Z0-9]*')
for attr in attrs:
  if p.match(attr):
    print(attr)

kn.predict([[30,500]])

kn.predict([[30,500],[25,100],[29,50],[32,70]])

kn.score(fish_data,fish_target)
#결과값이 1.0이면 다 맞췄다.

kn3 = KNeighborsClassifier(n_neighbors=3)
kn3.fit(fish_data, fish_target)

kn49 = KNeighborsClassifier(n_neighbors=49)
kn49.fit(fish_data, fish_target)

kn3.score(fish_data,fish_target)

kn49.score(fish_data, fish_target)

35/49
#35:더미, 49:전체

from sklearn.metrics import accuracy_score

accuracy_score(fish_target, kn.predict(fish_data))

"""#연습

"""

kn = KNeighborsClassifier()
kn.fit(fish_data, fish_target) 

for n in range(5,50):
  #k-최근접 이웃 개수 설정
  kn.n_neighbors = n
  #점수 계산
  score = kn.score(fish_data, fish_target)
  #100% 정확도에 미치지 못하는 이웃 개수 출력
  if score<1:
    print(f'n:{n}->{score}')
    break