In [1]:

    

import keras
import numpy as np
import pandas as pd

from keras.layers import Input, Dense
from keras.models import Model, Sequential


    

    




Using TensorFlow backend.

In [2]:

    

df = pd.read_csv("../housing-conditions-in-copenhagen/data.csv",sep="\s+")


    

In [3]:

    

df.head()


    

    
Out[3]:







  

    

      

      
housing
      
influence
      
contact_with_neighbours
      
satisfaction
      
n
    
  
  

    

      
1
      
1
      
1
      
1
      
1
      
21
    
    

      
2
      
1
      
1
      
1
      
2
      
21
    
    

      
3
      
1
      
1
      
1
      
3
      
28
    
    

      
4
      
1
      
1
      
2
      
1
      
14
    
    

      
5
      
1
      
1
      
2
      
2
      
19
    
  

In [4]:

    

df.describe()


    

    
Out[4]:







  

    

      

      
housing
      
influence
      
contact_with_neighbours
      
satisfaction
      
n
    
  
  

    

      
count
      
72.00000
      
72.000000
      
72.000000
      
72.000000
      
72.000000
    
    

      
mean
      
2.50000
      
2.000000
      
1.500000
      
2.000000
      
23.347222
    
    

      
std
      
1.12588
      
0.822226
      
0.503509
      
0.822226
      
17.666041
    
    

      
min
      
1.00000
      
1.000000
      
1.000000
      
1.000000
      
3.000000
    
    

      
25%
      
1.75000
      
1.000000
      
1.000000
      
1.000000
      
10.000000
    
    

      
50%
      
2.50000
      
2.000000
      
1.500000
      
2.000000
      
19.500000
    
    

      
75%
      
3.25000
      
3.000000
      
2.000000
      
3.000000
      
31.750000
    
    

      
max
      
4.00000
      
3.000000
      
2.000000
      
3.000000
      
86.000000
    
  

In [5]:

    

df_new = pd.concat([df,pd.get_dummies(df["housing"],prefix="housing")],axis=1).drop(["housing"],axis=1)
df_new = pd.concat([df_new,pd.get_dummies(df["influence"],prefix="influence")],axis=1).drop(["influence"],axis=1)
df_new = pd.concat([df_new,pd.get_dummies(df["satisfaction"],prefix="satisfaction")],axis=1).drop(["satisfaction"],axis=1)


    

In [6]:

    

df_new["contact_with_neighbours"] = df_new["contact_with_neighbours"].map(lambda v: 0 if v == 1 else 1)


    

In [13]:

    

df_new.head()


    

    
Out[13]:







  

    

      

      
contact_with_neighbours
      
n
      
housing_1
      
housing_2
      
housing_3
      
housing_4
      
influence_1
      
influence_2
      
influence_3
      
satisfaction_1
      
satisfaction_2
      
satisfaction_3
    
  
  

    

      
1
      
0
      
21
      
1
      
0
      
0
      
0
      
1
      
0
      
0
      
1
      
0
      
0
    
    

      
2
      
0
      
21
      
1
      
0
      
0
      
0
      
1
      
0
      
0
      
0
      
1
      
0
    
    

      
3
      
0
      
28
      
1
      
0
      
0
      
0
      
1
      
0
      
0
      
0
      
0
      
1
    
    

      
4
      
1
      
14
      
1
      
0
      
0
      
0
      
1
      
0
      
0
      
1
      
0
      
0
    
    

      
5
      
1
      
19
      
1
      
0
      
0
      
0
      
1
      
0
      
0
      
0
      
1
      
0
    
  

In [8]:

    

y = df_new["contact_with_neighbours"].values.reshape(-1,1)
X = df_new.drop(["contact_with_neighbours"], axis=1).values


    

In [9]:

    

y.shape, X.shape


    

    
Out[9]:





((72, 1), (72, 11))

In [10]:

    

indices = np.arange(72)
np.random.shuffle(indices)
num_validation_samples = int(0.2*72)

y = y[indices]
X = X[indices]

X_train = X[:-num_validation_samples]
y_train = y[:-num_validation_samples]
X_val = X[-num_validation_samples:]
y_val = y[-num_validation_samples:]


    

In [11]:

    

X_train.shape,y_train.shape,X_val.shape, y_val.shape


    

    
Out[11]:





((58, 11), (58, 1), (14, 11), (14, 1))

In [12]:

    

model = Sequential()
model.add(Dense(1, 
                activation='sigmoid', 
                input_dim=X.shape[1]))

rmsprop = keras.optimizers.RMSprop(lr=0.01)
model.compile(optimizer=rmsprop, loss='mse', metrics=['mse'])

early_stopping = keras.callbacks.EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=0, mode='auto')

model.fit(X, 
          y, 
          epochs=300, 
          validation_data=(X_val, y_val),
          callbacks = [early_stopping])


    

    




Train on 72 samples, validate on 14 samples
Epoch 1/300
72/72 [==============================] - 0s - loss: 0.4841 - mean_squared_error: 0.4841 - val_loss: 0.5723 - val_mean_squared_error: 0.5723
Epoch 2/300
72/72 [==============================] - 0s - loss: 0.4754 - mean_squared_error: 0.4754 - val_loss: 0.5702 - val_mean_squared_error: 0.5702
Epoch 3/300
72/72 [==============================] - 0s - loss: 0.4644 - mean_squared_error: 0.4644 - val_loss: 0.5651 - val_mean_squared_error: 0.5651
Epoch 4/300
72/72 [==============================] - 0s - loss: 0.4527 - mean_squared_error: 0.4527 - val_loss: 0.5474 - val_mean_squared_error: 0.5474
Epoch 5/300
72/72 [==============================] - 0s - loss: 0.4281 - mean_squared_error: 0.4281 - val_loss: 0.5112 - val_mean_squared_error: 0.5112
Epoch 6/300
72/72 [==============================] - 0s - loss: 0.3883 - mean_squared_error: 0.3883 - val_loss: 0.4228 - val_mean_squared_error: 0.4228
Epoch 7/300
72/72 [==============================] - 0s - loss: 0.3187 - mean_squared_error: 0.3187 - val_loss: 0.2956 - val_mean_squared_error: 0.2956
Epoch 8/300
72/72 [==============================] - 0s - loss: 0.2710 - mean_squared_error: 0.2710 - val_loss: 0.2641 - val_mean_squared_error: 0.2641
Epoch 9/300
72/72 [==============================] - 0s - loss: 0.2717 - mean_squared_error: 0.2717 - val_loss: 0.2575 - val_mean_squared_error: 0.2575
Epoch 10/300
72/72 [==============================] - 0s - loss: 0.2657 - mean_squared_error: 0.2657 - val_loss: 0.2420 - val_mean_squared_error: 0.2420
Epoch 11/300
72/72 [==============================] - 0s - loss: 0.2757 - mean_squared_error: 0.2757 - val_loss: 0.2439 - val_mean_squared_error: 0.2439
Epoch 12/300
72/72 [==============================] - 0s - loss: 0.2635 - mean_squared_error: 0.2635 - val_loss: 0.2357 - val_mean_squared_error: 0.2357
Epoch 13/300
72/72 [==============================] - 0s - loss: 0.2719 - mean_squared_error: 0.2719 - val_loss: 0.2336 - val_mean_squared_error: 0.2336
Epoch 14/300
72/72 [==============================] - 0s - loss: 0.2692 - mean_squared_error: 0.2692 - val_loss: 0.2338 - val_mean_squared_error: 0.2338
Epoch 15/300
72/72 [==============================] - 0s - loss: 0.2605 - mean_squared_error: 0.2605 - val_loss: 0.2557 - val_mean_squared_error: 0.2557
Epoch 16/300
72/72 [==============================] - 0s - loss: 0.2586 - mean_squared_error: 0.2586 - val_loss: 0.2461 - val_mean_squared_error: 0.2461
Epoch 17/300
72/72 [==============================] - 0s - loss: 0.2508 - mean_squared_error: 0.2508 - val_loss: 0.2407 - val_mean_squared_error: 0.2407
Epoch 18/300
72/72 [==============================] - 0s - loss: 0.2496 - mean_squared_error: 0.2496 - val_loss: 0.2806 - val_mean_squared_error: 0.2806
Epoch 19/300
72/72 [==============================] - 0s - loss: 0.2535 - mean_squared_error: 0.2535 - val_loss: 0.2430 - val_mean_squared_error: 0.2430






    
Out[12]:





<keras.callbacks.History at 0x7fd3e0748cc0>

In [ ]: