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

# # 결정 트리

# <table align="left">
#   <td>
#     <a target="_blank" href="https://colab.research.google.com/github/rickiepark/hg-mldl/blob/master/5-1.ipynb"><img src="https://www.tensorflow.org/images/colab_logo_32px.png" />구글 코랩에서 실행하기</a>
#   </td>
# </table>

# ## 로지스틱 회귀로 와인 분류하기

# In[1]:


import pandas as pd

wine = pd.read_csv('https://bit.ly/wine_csv_data')


# In[2]:


wine.head()


# In[3]:


wine.info()


# In[4]:


wine.describe()


# In[5]:


data = wine[['alcohol', 'sugar', 'pH']].to_numpy()
target = wine['class'].to_numpy()


# In[6]:


from sklearn.model_selection import train_test_split

train_input, test_input, train_target, test_target = train_test_split(
    data, target, test_size=0.2, random_state=42)


# In[7]:


print(train_input.shape, test_input.shape)


# In[8]:


from sklearn.preprocessing import StandardScaler

ss = StandardScaler()
ss.fit(train_input)

train_scaled = ss.transform(train_input)
test_scaled = ss.transform(test_input)


# In[9]:


from sklearn.linear_model import LogisticRegression

lr = LogisticRegression()
lr.fit(train_scaled, train_target)

print(lr.score(train_scaled, train_target))
print(lr.score(test_scaled, test_target))


# ### 설명하기 쉬운 모델과 어려운 모델

# In[10]:


print(lr.coef_, lr.intercept_)


# ## 결정 트리

# In[11]:


from sklearn.tree import DecisionTreeClassifier

dt = DecisionTreeClassifier(random_state=42)
dt.fit(train_scaled, train_target)

print(dt.score(train_scaled, train_target))
print(dt.score(test_scaled, test_target))


# In[12]:


import matplotlib.pyplot as plt
from sklearn.tree import plot_tree

plt.figure(figsize=(10,7))
plot_tree(dt)
plt.show()


# In[13]:


plt.figure(figsize=(10,7))
plot_tree(dt, max_depth=1, filled=True, feature_names=['alcohol', 'sugar', 'pH'])
plt.show()


# ### 가지치기

# In[14]:


dt = DecisionTreeClassifier(max_depth=3, random_state=42)
dt.fit(train_scaled, train_target)

print(dt.score(train_scaled, train_target))
print(dt.score(test_scaled, test_target))


# In[15]:


plt.figure(figsize=(20,15))
plot_tree(dt, filled=True, feature_names=['alcohol', 'sugar', 'pH'])
plt.show()


# In[16]:


dt = DecisionTreeClassifier(max_depth=3, random_state=42)
dt.fit(train_input, train_target)

print(dt.score(train_input, train_target))
print(dt.score(test_input, test_target))


# In[17]:


plt.figure(figsize=(20,15))
plot_tree(dt, filled=True, feature_names=['alcohol', 'sugar', 'pH'])
plt.show()


# In[18]:


print(dt.feature_importances_)


# ## 확인문제

# In[19]:


dt = DecisionTreeClassifier(min_impurity_decrease=0.0005, random_state=42)
dt.fit(train_input, train_target)

print(dt.score(train_input, train_target))
print(dt.score(test_input, test_target))


# In[20]:


plt.figure(figsize=(20,15))
plot_tree(dt, filled=True, feature_names=['alcohol', 'sugar', 'pH'])
plt.show()