[ML] 1-3 마켓과 머신러닝

1-3 마켓과 머신러닝

In [ ]:

"""# 마켓과 머신러닝 """
"""## 생선 분류 문제 """
"""### 도미 데이터 준비하기 """

Out[ ]:

'### 도미 데이터 준비하기 '

In [ ]:

import matplotlib.pyplot as plt

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]

plt.scatter(bream_length, bream_weight)
plt.scatter(smelt_length, smelt_weight)
plt.xlabel('length')    # x축은 길이
plt.ylabel('weight')    # y축은 무게
plt.show()

 

In [ ]:

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

In [ ]:

print(fish_data)
print(fish_target)

 

[[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]]
[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]

In [ ]:

from sklearn.neighbors import KNeighborsClassifier

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

Out[ ]:

KNeighborsClassifier()

In [ ]:

kn.score(fish_data, fish_target)

Out[ ]:

1.0

In [ ]:

plt.scatter(bream_length, bream_weight)
plt.scatter(smelt_length, smelt_weight)
plt.scatter([30], [600])      # 새로운 데이터
plt.xlabel('length')    # x축은 길이
plt.ylabel('weight')    # y축은 무게
plt.show()

kn.predict([[30, 600]])       # 새로운 데이터

 

Out[ ]:

array([1])

In [ ]:

print(kn._fit_X)

In [ ]:

print(kn._y)

In [ ]:

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

Out[ ]:

0.7142857142857143

In [ ]:

print(35/49)

 

0.7142857142857143

In [ ]:

In [ ]:

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

for n in range(5, 50):
  kn.n_neighbors = n
  score = kn.score(fish_data, fish_target)
  if score < 1:
    print(n, score)
    break

 

18 0.9795918367346939

In [ ]: