# 생선(도미)의 길이와 생선의 무게
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]
# 빙어 데이터
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]
import matplotlib.pylab as plt
plt.scatter(bream_length, bream_weight)
plt.xlabel('length')
plt.ylabel('weight')
plt.show()
plt.scatter(bream_length, bream_weight)
plt.scatter(smelt_length, smelt_weight)
plt.xlabel('length')
plt.ylabel('weight')
plt.show()
첫번째 머신러닝 프로그램
K-최근접 이웃
#리스트 합치기
length = bream_length + smelt_length
weight = bream_weight + smelt_weight
# 리스트 내포를 이용하여 2차원배열 생성
fish_data = [[l,w] for l,w in zip(length, weight)]
print(fish_data)
[[25.4, 242.0], [26.3, 290.0], [26.5, 340.0], [29.0, 363.0], [29.0, 430.0], [29.7, 450.0], [29.7, 500.0], [30.0, 390.0], [30.0, 450.0], [30.7, 500.0], [31.0, 475.0], [31.0, 500.0], [31.5, 500.0], [32.0, 340.0], [32.0, 600.0], [32.0, 600.0], [33.0, 700.0], [33.0, 700.0], [33.5, 610.0], [33.5, 650.0], [34.0, 575.0], [34.0, 685.0], [34.5, 620.0], [35.0, 680.0], [35.0, 700.0], [35.0, 725.0], [35.0, 720.0], [36.0, 714.0], [36.0, 850.0], [37.0, 1000.0], [38.5, 920.0], [38.5, 955.0], [39.5, 925.0], [41.0, 975.0], [41.0, 950.0], [9.8, 6.7], [10.5, 7.5], [10.6, 7.0], [11.0, 9.7], [11.2, 9.8], [11.3, 8.7], [11.8, 10.0], [11.8, 9.9], [12.0, 9.8], [12.2, 12.2], [12.4, 13.4], [13.0, 12.2], [14.3, 19.7], [15.0, 19.9]]
# 타겟 데이터 생성
fish_target = [1]*35 + [0]*14
print(fish_target)
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
import sklearn
from sklearn.neighbors import KNeighborsClassifier
model = sklearn.neighbors.KNeighborsClassifier()
kn = KNeighborsClassifier()
kn.fit(fish_data, fish_target)
kn.score(fish_data, fish_target)
kn.predict([[30,600]])
array([1])
# 특성 데이터
print(kn._fit_X)
[[ 25.4 242. ]
[ 26.3 290. ]
[ 26.5 340. ]
[ 29. 363. ]
[ 29. 430. ]
[ 29.7 450. ]
[ 29.7 500. ]
[ 30. 390. ]
[ 30. 450. ]
[ 30.7 500. ]
[ 31. 475. ]
[ 31. 500. ]
[ 31.5 500. ]
[ 32. 340. ]
[ 32. 600. ]
[ 32. 600. ]
[ 33. 700. ]
[ 33. 700. ]
[ 33.5 610. ]
[ 33.5 650. ]
[ 34. 575. ]
[ 34. 685. ]
[ 34.5 620. ]
[ 35. 680. ]
[ 35. 700. ]
[ 35. 725. ]
[ 35. 720. ]
[ 36. 714. ]
[ 36. 850. ]
[ 37. 1000. ]
[ 38.5 920. ]
[ 38.5 955. ]
[ 39.5 925. ]
[ 41. 975. ]
[ 41. 950. ]
[ 9.8 6.7]
[ 10.5 7.5]
[ 10.6 7. ]
[ 11. 9.7]
[ 11.2 9.8]
[ 11.3 8.7]
[ 11.8 10. ]
[ 11.8 9.9]
[ 12. 9.8]
[ 12.2 12.2]
[ 12.4 13.4]
[ 13. 12.2]
[ 14.3 19.7]
[ 15. 19.9]]
# 타겟 데이터 - 지도학습
print(kn._y)
[1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0
0 0 0 0 0 0 0 0 0 0 0 0]
# 도미, 빙어 그래프 + 샘플 데이터 추가
plt.scatter(bream_length, bream_weight)
plt.scatter(smelt_length, smelt_weight)
plt.scatter(30, 20)
plt.xlabel('length')
plt.ylabel('weight')
plt.show()
# 샘플데이터 예측하기
# kn.predict([[30,600]])
kn.predict([[30,20]])
array([0])
# 참고 데이터를 49개로 했을때 kn49 모델
kn49 = KNeighborsClassifier(n_neighbors=49)
kn49.fit(fish_data, fish_target)
kn49.score(fish_data, fish_target)
0.7142857142857143
