Mon Apr 29 15:11:41 2019

hourly_wages:
  python version: 3.6.8
  keras version: 2.2.4
  Neural network to solve a multivariate regression problem.
  The data is read from an external file.

  Data contains 534 records with 10 features.
  Training data uses 450 records with 9 features.
  Test data uses 84 records with 9 features.
  train_data[0,0:9]:
[ 0.  8. 21. 35.  1.  1.  0.  1.  0.]
  train_targets[0]:
5.1

Training:

Train on 360 samples, validate on 90 samples
Epoch 1/30

 32/360 [=>............................] - ETA: 1s - loss: 36.5260
360/360 [==============================] - 0s 526us/step - loss: 33.9855 - val_loss: 43.1946
Epoch 2/30

 32/360 [=>............................] - ETA: 0s - loss: 18.9527
360/360 [==============================] - 0s 24us/step - loss: 30.1776 - val_loss: 38.5688
Epoch 3/30

 32/360 [=>............................] - ETA: 0s - loss: 28.5958
360/360 [==============================] - 0s 22us/step - loss: 27.4063 - val_loss: 31.7084
Epoch 4/30

 32/360 [=>............................] - ETA: 0s - loss: 16.1907
360/360 [==============================] - 0s 22us/step - loss: 24.2516 - val_loss: 29.0803
Epoch 5/30

 32/360 [=>............................] - ETA: 0s - loss: 55.2114
360/360 [==============================] - 0s 22us/step - loss: 22.8150 - val_loss: 26.5093
Epoch 6/30

 32/360 [=>............................] - ETA: 0s - loss: 26.3843
360/360 [==============================] - 0s 21us/step - loss: 21.8046 - val_loss: 24.8767
Epoch 7/30

 32/360 [=>............................] - ETA: 0s - loss: 61.3507
360/360 [==============================] - 0s 22us/step - loss: 21.5499 - val_loss: 24.7906
Epoch 8/30

 32/360 [=>............................] - ETA: 0s - loss: 61.7298
360/360 [==============================] - 0s 22us/step - loss: 21.1386 - val_loss: 24.0752
Epoch 9/30

 32/360 [=>............................] - ETA: 0s - loss: 54.9687
360/360 [==============================] - 0s 22us/step - loss: 20.7820 - val_loss: 23.6670
Epoch 10/30

 32/360 [=>............................] - ETA: 0s - loss: 25.1367
360/360 [==============================] - 0s 22us/step - loss: 20.5280 - val_loss: 23.5214
Epoch 11/30

 32/360 [=>............................] - ETA: 0s - loss: 54.0471
360/360 [==============================] - 0s 23us/step - loss: 20.3169 - val_loss: 23.7110
Epoch 12/30

 32/360 [=>............................] - ETA: 0s - loss: 10.1587
360/360 [==============================] - 0s 23us/step - loss: 20.1277 - val_loss: 23.5924
Epoch 13/30

 32/360 [=>............................] - ETA: 0s - loss: 17.1292
360/360 [==============================] - 0s 22us/step - loss: 19.8265 - val_loss: 22.8444
Epoch 14/30

 32/360 [=>............................] - ETA: 0s - loss: 12.6901
360/360 [==============================] - 0s 22us/step - loss: 19.7716 - val_loss: 23.1190
Epoch 15/30

 32/360 [=>............................] - ETA: 0s - loss: 8.4796
360/360 [==============================] - 0s 23us/step - loss: 19.6957 - val_loss: 23.0540
Epoch 16/30

 32/360 [=>............................] - ETA: 0s - loss: 8.6733
360/360 [==============================] - 0s 22us/step - loss: 19.6217 - val_loss: 22.5916
Epoch 17/30

 32/360 [=>............................] - ETA: 0s - loss: 10.9685
360/360 [==============================] - 0s 22us/step - loss: 19.5573 - val_loss: 23.1809
Epoch 18/30

 32/360 [=>............................] - ETA: 0s - loss: 13.5554
360/360 [==============================] - 0s 23us/step - loss: 19.4848 - val_loss: 22.2367
Epoch 19/30

 32/360 [=>............................] - ETA: 0s - loss: 11.6552
360/360 [==============================] - 0s 23us/step - loss: 19.4093 - val_loss: 22.5820
Epoch 20/30

 32/360 [=>............................] - ETA: 0s - loss: 9.2920
360/360 [==============================] - 0s 23us/step - loss: 19.4535 - val_loss: 22.5006
Epoch 21/30

 32/360 [=>............................] - ETA: 0s - loss: 16.1311
360/360 [==============================] - 0s 23us/step - loss: 19.3585 - val_loss: 21.9781
Epoch 22/30

 32/360 [=>............................] - ETA: 0s - loss: 9.6522
360/360 [==============================] - 0s 23us/step - loss: 19.3029 - val_loss: 22.2624
Epoch 23/30

 32/360 [=>............................] - ETA: 0s - loss: 14.5235
360/360 [==============================] - 0s 22us/step - loss: 19.2317 - val_loss: 22.4516
Epoch 24/30

 32/360 [=>............................] - ETA: 0s - loss: 14.5170
360/360 [==============================] - 0s 22us/step - loss: 19.1656 - val_loss: 22.4065

Testing:

  0: 8.613173  10.280000
  1: 10.327003  15.000000
  2: 12.371456  12.000000
  3: 9.502140  10.580000
  4: 10.768035  5.850000
  5: 12.993261  11.220000
  6: 9.719757  8.560000
  7: 10.818596  13.890000
  8: 9.499022  5.710000
  9: 9.899394  15.790000
  10: 11.727979  7.500000
  11: 8.891652  11.250000
  12: 10.935744  6.150000
  13: 11.074924  13.450000
  14: 8.605358  6.250000
  15: 8.276031  6.500000
  16: 8.255935  12.000000
  17: 8.997073  8.500000
  18: 13.459388  8.000000
  19: 8.538110  5.750000
  20: 8.192931  15.730000
  21: 10.410794  9.860000
  22: 11.661864  13.510000
  23: 9.378822  5.400000
  24: 11.283679  6.250000
  25: 11.695477  5.500000
  26: 7.074957  5.000000
  27: 13.641491  6.250000
  28: 6.797038  5.750000
  29: 10.551037  20.500000
  30: 6.773502  5.000000
  31: 13.478882  7.000000
  32: 11.451565  18.000000
  33: 12.089472  12.000000
  34: 8.300384  20.400000
  35: 12.392324  22.200000
  36: 10.553313  16.420000
  37: 7.161630  8.630000
  38: 9.636646  19.380000
  39: 10.925756  14.000000
  40: 11.079876  10.000000
  41: 10.475279  15.950000
  42: 11.245818  20.000000
  43: 9.378822  10.000000
  44: 7.689336  24.980000
  45: 8.368313  11.250000
  46: 12.085558  22.830000
  47: 12.517554  10.200000
  48: 7.411417  10.000000
  49: 12.836534  14.000000
  50: 10.455183  12.500000
  51: 9.533056  5.790000
  52: 12.390264  24.980000
  53: 6.193356  4.350000
  54: 9.744098  11.250000
  55: 9.356634  6.670000
  56: 11.183578  8.000000
  57: 9.899394  18.160000
  58: 10.410112  12.000000
  59: 11.836884  8.890000
  60: 10.755291  9.500000
  61: 10.240329  13.650000
  62: 13.581266  12.000000
  63: 9.794769  15.000000
  64: 11.271618  12.670000
  65: 9.933876  7.380000
  66: 10.002602  15.560000
  67: 8.209909  7.450000
  68: 9.204113  6.250000
  69: 8.184885  6.250000
  70: 9.511932  9.370000
  71: 11.544620  22.500000
  72: 9.940220  7.500000
  73: 7.844634  7.000000
  74: 7.415190  5.750000
  75: 9.291468  7.670000
  76: 9.657424  12.500000
  77: 8.696967  16.000000
  78: 8.325346  11.790000
  79: 9.403848  11.360000
  80: 8.798800  6.100000
  81: 12.544653  23.250000
  82: 8.912503  19.880000
  83: 11.742251  15.380000