[ML] 2-2 데이터 전처리

In [ ]:

fish_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, 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]
fish_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, 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]

In [ ]:

import numpy as np

In [ ]:

fish_data = np.column_stack((fish_length, fish_weight))

In [ ]:

fish_target = np.concatenate((np.ones(35), np.zeros(14)))

In [ ]:

from sklearn.model_selection import train_test_split

In [ ]:

train_input, test_input, train_target, test_target = train_test_split(fish_data, fish_target, random_state=42)
print(test_target)

[1. 0. 0. 0. 1. 1. 1. 1. 1. 1. 1. 1. 1.]

In [ ]:

# 샘플링 편항을 해결하기 위한 stratify 매개변수 사용
train_input, test_input, train_target, test_target = train_test_split(fish_data, fish_target, stratify=fish_target, random_state=42)
print(test_target)

[0. 0. 1. 0. 1. 0. 1. 1. 1. 1. 1. 1. 1.]

In [ ]:

from sklearn.neighbors import KNeighborsClassifier
kn = KNeighborsClassifier()
kn.fit(train_input, train_target)
kn.score(test_input, test_target)

Out[ ]:

1.0

In [ ]:

print(kn.predict([[25, 150]]))

[0.]

In [ ]:

import matplotlib.pyplot as plt
plt.scatter(train_input[:,0], train_input[:,1])
plt.scatter(25, 150, marker='^')
plt.xlabel('length')
plt.ylabel('weight')
plt.show()

In [ ]:

distances, indexes = kn.kneighbors([[25, 150]])

In [ ]:

plt.scatter(train_input[:,0], train_input[:,1])
plt.scatter(25, 150, marker='^')
plt.scatter(train_input[indexes, 0], train_input[indexes, 1], marker='D')
plt.xlabel('length')
plt.ylabel('weight')
plt.show()

In [ ]:

print(train_input[indexes])

[[[ 25.4 242. ]
  [ 15.   19.9]
  [ 14.3  19.7]
  [ 13.   12.2]
  [ 12.2  12.2]]]

In [ ]:

print(train_target[indexes])

[[1. 0. 0. 0. 0.]]

In [ ]:

print(distances)

[[ 92.00086956 130.48375378 130.73859415 138.32150953 138.39320793]]

In [ ]:

# xlim(), ylim() 함수 : 맷플롯립에서 x, y축 범위를 지정
plt.scatter(train_input[:,0], train_input[:,1])
plt.scatter(25, 150, marker='^')
plt.scatter(train_input[indexes, 0], train_input[indexes, 1], marker='D')
plt.xlim((0, 1000))
plt.xlabel('length')
plt.ylabel('weight')
plt.show()

In [ ]:

# 데이터 전처리(data preprocessing)

In [ ]:

# 평균, 표준편차
mean = np.mean(train_input, axis=0)
std = np.std(train_input, axis=0)

In [ ]:

print(mean, std)

[ 27.29722222 454.09722222] [  9.98244253 323.29893931]

In [ ]:

# 훈련 세트 표준점수로 변환
train_scaled = (train_input - mean) / std

In [ ]:

# 새로운 데이터도 표준점수로 변환
new = [25, 150]
new_scaled = (new - mean) / std
# 새로운 데이터와 함께 산점도 그래프 출력
plt.scatter(train_scaled[:,0], train_scaled[:,1])
plt.scatter(new_scaled[0], new_scaled[1], marker='^')
plt.xlabel('length')
plt.ylabel('weight')
plt.show()

In [ ]:

# 표준점수로 변환된 훈련 세트로 훈련
kn.fit(train_scaled, train_target)
# 테스트 세트도 표준점수로 변환
test_scaled = (test_input - mean) / std
kn.score(test_scaled, test_target)

Out[ ]:

1.0

In [ ]:

# 새로운 데이터를 다시 예측
print(kn.predict([new]))

[1.]

In [ ]: