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

# # 케라스로 만드는 회귀 예제
# 
# 매사추세츠 보스턴 지역의 주택 가격 예측하기

# [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/rickiepark/dl-illustrated/blob/master/notebooks/9-3.regression_in_keras.ipynb)

# #### 라이브러리를 적재합니다.

# In[1]:


import numpy as np
from tensorflow.keras.datasets import boston_housing
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout 
from tensorflow.keras.layers import BatchNormalization 


# #### 데이터를 적재합니다.

# In[2]:


(X_train, y_train), (X_valid, y_valid) = boston_housing.load_data()


# In[3]:


X_train.shape


# In[4]:


X_valid.shape


# In[5]:


X_train[0]


# In[6]:


y_train[0]


# #### 신경망을 만듭니다.

# In[7]:


model = Sequential()

model.add(Dense(32, input_dim=13, activation='relu'))
model.add(BatchNormalization())

model.add(Dense(16, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.2))

model.add(Dense(1, activation='linear'))


# In[8]:


model.summary()


# #### 모델을 설정합니다.

# In[9]:


model.compile(loss='mean_squared_error', optimizer='adam')


# #### 훈련!

# In[10]:


model.fit(X_train, y_train, 
          batch_size=8, epochs=32, verbose=1, 
          validation_data=(X_valid, y_valid))


# In[11]:


X_valid[42]


# In[12]:


y_valid[42]


# In[13]:


model.predict(np.reshape(X_valid[42], [1, 13]))