01. 기본 미션

a. 이 생선의 이름은 무엇인가요?

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]

import matplotlib.pyplot as plt
                
plt.scatter(bream_length, bream_weight)
plt.scatter(smelt_length, smelt_weight)
plt.xlabel('length')
plt.ylabel('weight')
plt.show()

length = bream_length+smelt_length
weight = bream_weight+smelt_weight

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

fish_target = [1]*35+[0]*14
print(fish_target)

from sklearn.neighbors import KNeighborsClassifier
kn = KNeighborsClassifier()

kn.fit(fish_data, fish_target)
kn.score(fish_data, fish_target)
kn.predict([[30,600]])

print(kn._fit_X)
print(kn._y)

kn49 = KNeighborsClassifier(n_neighbors=49)

kn49.fit(fish_data, fish_target)
kn49.score(fish_data, fish_target)

print(35/49)

b. 수상한 생선을 조심하라!

(1) 훈련 세트와 테스트 세트

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]

fish_data = [[l, w] for l, w in zip(fish_length, fish_weight)]
fish_target = [1]*35 + [0]*14

from sklearn.neighbors import KNeighborsClassifier

kn = KNeighborsClassifier()
print(fish_data[4])
print(fish_data[0:5])
print(fish_data[:5])
print(fish_data[44:])

train_input = fish_data[:35]
train_target = fish_target[:35]

test_input = fish_data[35:]
test_target = fish_target[35:]

kn.fit(train_input, train_target)
kn.score(test_input, test_target)

import numpy as np

input_arr = np.array(fish_data)
target_arr = np.array(fish_target)

print(input_arr)
print(input_arr.shape)

np.random.seed(42)
index = np.arange(49)
np.random.shuffle(index)

print(index)
print(input_arr[[1,3]])

train_input = input_arr[index[:35]]
train_target = target_arr[index[:35]]

print(input_arr[13], train_input[0])

test_input = input_arr[index[35:]]
test_target = target_arr[index[35:]]

import matplotlib.pyplot as plt

plt.scatter(train_input[:, 0], train_input[:, 1])
plt.scatter(test_input[:, 0], test_input[:, 1])
plt.xlabel('length')
plt.ylabel('weight')
plt.show()

kn.fit(train_input, train_target)
kn.score(test_input, test_target)
kn.predict(test_input)
test_target

(2) 데이터 전처리

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]

import numpy as np

np.column_stack(([1,2,3],[4,5,6]))
fish_data = np.column_stack((fish_length, fish_weight))

print(fish_data[:5])
print(np.ones(5))

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

from sklearn.model_selection import train_test_split

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

print(train_input.shape, test_input.shape)
print(train_target.shape, test_target.shape)
print(test_target)

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

print(test_target)