#!/usr/bin/env python
# coding: utf-8

# # 마켓과 머신러닝

# <table align="left">
#   <td>
#     <a target="_blank" href="https://colab.research.google.com/github/rickiepark/hg-mldl/blob/master/1-3.ipynb"><img src="https://www.tensorflow.org/images/colab_logo_32px.png" />구글 코랩에서 실행하기</a>
#   </td>
# </table>

# ## 생선 분류 문제

# ### 도미 데이터 준비하기

# In[1]:


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]


# In[2]:


import matplotlib.pyplot as plt

plt.scatter(bream_length, bream_weight)
plt.xlabel('length')
plt.ylabel('weight')
plt.show()


# ### 빙어 데이터 준비하기

# In[3]:


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]


# In[4]:


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


# ## 첫 번째 머신러닝 프로그램

# In[5]:


length = bream_length+smelt_length
weight = bream_weight+smelt_weight


# In[6]:


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

print(fish_data)


# In[7]:


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


# In[8]:


from sklearn.neighbors import KNeighborsClassifier


# In[9]:


kn = KNeighborsClassifier()


# In[10]:


kn.fit(fish_data, fish_target)


# In[11]:


kn.score(fish_data, fish_target)


# ### k-최근접 이웃 알고리즘

# In[12]:


plt.scatter(bream_length, bream_weight)
plt.scatter(smelt_length, smelt_weight)
plt.scatter(30, 600, marker='^')
plt.xlabel('length')
plt.ylabel('weight')
plt.show()


# In[13]:


kn.predict([[30, 600]])


# In[14]:


print(kn._fit_X)


# In[15]:


print(kn._y)


# In[16]:


kn49 = KNeighborsClassifier(n_neighbors=49)


# In[17]:


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


# In[18]:


print(35/49)


# ### 확인 문제

# In[19]:


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

for n in range(5, 50):
    # 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(n, score)
        break