In [3]:

    

from pandas import DataFrame, concat


    

In [1]:

    

# create sequence
length = 10
sequence = [i / float(length) for i in range(length)]


    

In [10]:

    

df = DataFrame(sequence)
df = concat([df.shift(1), df], axis=1)
df.dropna(inplace=True)

values = df.values
X, y = values[:, 0], values[:, 1]


    

In [11]:

    

df


    

    
Out[11]:







  

    

      

      
0
      
0
    
  
  

    

      
1
      
0.0
      
0.1
    
    

      
2
      
0.1
      
0.2
    
    

      
3
      
0.2
      
0.3
    
    

      
4
      
0.3
      
0.4
    
    

      
5
      
0.4
      
0.5
    
    

      
6
      
0.5
      
0.6
    
    

      
7
      
0.6
      
0.7
    
    

      
8
      
0.7
      
0.8
    
    

      
9
      
0.8
      
0.9
    
  

In [12]:

    

X


    

    
Out[12]:





array([ 0. ,  0.1,  0.2,  0.3,  0.4,  0.5,  0.6,  0.7,  0.8])

In [13]:

    

y


    

    
Out[13]:





array([ 0.1,  0.2,  0.3,  0.4,  0.5,  0.6,  0.7,  0.8,  0.9])

In [18]:

    

from keras.models import Sequential
from keras.layers import Dense
from sklearn.metrics import mean_squared_error

def fit_model(X, y):
    model = Sequential()
    model.add(Dense(10, input_dim=1))
    model.add(Dense(1))
    model.compile(loss='mean_squared_error', optimizer='adam')
    model.fit(X, y, epochs=100, batch_size=len(X), verbose=0)
    yhat = model.predict(X, verbose=0)
    print(mean_squared_error(y, yhat[:, 0]))


    

In [23]:

    

import numpy as np
from tensorflow import set_random_seed
np.random.seed(1)
set_random_seed(2)

# repeat experiment
repeats = 10
for _ in range(repeats):
    fit_model(X, y)


    

    




0.224562145077
0.00151052173366
0.00386903845727
0.0291074615536
0.00945919807316
0.0132488233332
0.0204295457932
0.0358127851784
0.00440309365743
0.299993946751

In [ ]: