In [1]:
import pandas as pd
import numpy as np
import yaml
%matplotlib inline
In [2]:
with open("param.yaml", "r") as file:
param = yaml.load(file.read())
param
Out[2]:
{'forget_bias': 1.0,
'learning_rate': 0.1,
'length_of_sequences': 60,
'num_of_hidden_nodes': 2,
'num_of_input_nodes': 1,
'num_of_output_nodes': 1,
'num_of_prediction_epochs': 100,
'num_of_training_epochs': 2000,
'optimizer': 'GradientDescentOptimizer',
'seed': 0,
'size_of_mini_batch': 100,
'train_data_path': '../train_data/normal.npy'}
In [3]:
train = np.load(param["train_data_path"])
train
Out[3]:
array([[ 0.00000000e+00, 1.25333234e-01],
[ 1.25333234e-01, 2.48689887e-01],
[ 2.48689887e-01, 3.68124553e-01],
...,
[ -3.68124553e-01, -2.48689887e-01],
[ -2.48689887e-01, -1.25333234e-01],
[ -1.25333234e-01, 3.92877345e-15]])
In [4]:
initial = np.load("initial.npy")
initial
Out[4]:
array([ 0.00000000e+00, 1.25333234e-01, 2.48689887e-01,
3.68124553e-01, 4.81753674e-01, 5.87785252e-01,
6.84547106e-01, 7.70513243e-01, 8.44327926e-01,
9.04827052e-01, 9.51056516e-01, 9.82287251e-01,
9.98026728e-01, 9.98026728e-01, 9.82287251e-01,
9.51056516e-01, 9.04827052e-01, 8.44327926e-01,
7.70513243e-01, 6.84547106e-01, 5.87785252e-01,
4.81753674e-01, 3.68124553e-01, 2.48689887e-01,
1.25333234e-01, -3.21624530e-16, -1.25333234e-01,
-2.48689887e-01, -3.68124553e-01, -4.81753674e-01,
-5.87785252e-01, -6.84547106e-01, -7.70513243e-01,
-8.44327926e-01, -9.04827052e-01, -9.51056516e-01,
-9.82287251e-01, -9.98026728e-01, -9.98026728e-01,
-9.82287251e-01, -9.51056516e-01, -9.04827052e-01,
-8.44327926e-01, -7.70513243e-01, -6.84547106e-01,
-5.87785252e-01, -4.81753674e-01, -3.68124553e-01,
-2.48689887e-01, -1.25333234e-01, 6.43249060e-16,
1.25333234e-01, 2.48689887e-01, 3.68124553e-01,
4.81753674e-01, 5.87785252e-01, 6.84547106e-01,
7.70513243e-01, 8.44327926e-01, 9.04827052e-01])
In [5]:
output = np.load("output.npy")
output
Out[5]:
array([ 0.97054219, 0.99542677, 0.99664259, 0.97980571, 0.94903433,
0.90724421, 0.85622942, 0.79683995, 0.72917295, 0.65274036,
0.56663024, 0.46971533, 0.360993 , 0.24014762, 0.1083529 ,
-0.0309262 , -0.17179006, -0.3071579 , -0.43118346, -0.5411582 ,
-0.63743806, -0.72183192, -0.79586411, -0.85972786, -0.9121083 ,
-0.95087218, -0.97426164, -0.98175704, -0.974038 , -0.95231724,
-0.91766751, -0.87065327, -0.8112452 , -0.73892903, -0.65298265,
-0.55295956, -0.43940848, -0.3146871 , -0.18339175, -0.05171674,
0.07443893, 0.19164547, 0.29994646, 0.40220353, 0.50240505,
0.60358119, 0.70556152, 0.80333221, 0.88798857, 0.95103145,
0.98856533, 1.00176418, 0.99455345, 0.97127593, 0.93548083,
0.88959348, 0.83499062, 0.7721864 , 0.70101511, 0.6207912 ,
0.53047967, 0.42894408, 0.31536409, 0.18989888, 0.05454114,
-0.08623961, -0.22583987, -0.35735172, -0.47602576, -0.58048177,
-0.67187834, -0.75209439, -0.82221299, -0.88180852, -0.92912066,
-0.96201837, -0.97917163, -0.98058474, -0.96723819, -0.94035602,
-0.90083849, -0.84901559, -0.78464675, -0.707093 , -0.61566848,
-0.51021785, -0.39190477, -0.26395342, -0.13173604, -0.00160569,
0.12127978, 0.23482224, 0.34031877, 0.44130209, 0.54164779,
0.64340353, 0.74461508, 0.8384285 , 0.91547823, 0.96872914])
In [6]:
losses = np.load("losses.npy")
losses
Out[6]:
array([[ 1.00000000e+01, 5.06403089e-01],
[ 2.00000000e+01, 4.65100288e-01],
[ 3.00000000e+01, 4.53504324e-01],
[ 4.00000000e+01, 4.30691004e-01],
[ 5.00000000e+01, 4.28720653e-01],
[ 6.00000000e+01, 2.52964824e-01],
[ 7.00000000e+01, 1.28045768e-01],
[ 8.00000000e+01, 9.34872925e-02],
[ 9.00000000e+01, 6.41007647e-02],
[ 1.00000000e+02, 5.14015183e-02],
[ 1.10000000e+02, 4.26473096e-02],
[ 1.20000000e+02, 3.38089503e-02],
[ 1.30000000e+02, 2.28780098e-02],
[ 1.40000000e+02, 1.59108117e-02],
[ 1.50000000e+02, 1.17567368e-02],
[ 1.60000000e+02, 7.27781793e-03],
[ 1.70000000e+02, 5.79333678e-03],
[ 1.80000000e+02, 4.57283249e-03],
[ 1.90000000e+02, 4.75384993e-03],
[ 2.00000000e+02, 3.71356611e-03],
[ 2.10000000e+02, 3.90847493e-03],
[ 2.20000000e+02, 2.94273742e-03],
[ 2.30000000e+02, 3.27187241e-03],
[ 2.40000000e+02, 3.23887938e-03],
[ 2.50000000e+02, 2.81045493e-03],
[ 2.60000000e+02, 2.46776524e-03],
[ 2.70000000e+02, 2.72319233e-03],
[ 2.80000000e+02, 2.48362566e-03],
[ 2.90000000e+02, 2.16595759e-03],
[ 3.00000000e+02, 2.25789077e-03],
[ 3.10000000e+02, 2.25824770e-03],
[ 3.20000000e+02, 2.17676419e-03],
[ 3.30000000e+02, 1.99272204e-03],
[ 3.40000000e+02, 1.86030532e-03],
[ 3.50000000e+02, 1.56256172e-03],
[ 3.60000000e+02, 1.55303883e-03],
[ 3.70000000e+02, 1.69490988e-03],
[ 3.80000000e+02, 1.58757810e-03],
[ 3.90000000e+02, 1.67618145e-03],
[ 4.00000000e+02, 1.47449540e-03],
[ 4.10000000e+02, 1.27437117e-03],
[ 4.20000000e+02, 1.17170962e-03],
[ 4.30000000e+02, 1.23217446e-03],
[ 4.40000000e+02, 1.24156335e-03],
[ 4.50000000e+02, 1.32552418e-03],
[ 4.60000000e+02, 1.12539809e-03],
[ 4.70000000e+02, 1.28757383e-03],
[ 4.80000000e+02, 1.25204073e-03],
[ 4.90000000e+02, 1.16147427e-03],
[ 5.00000000e+02, 9.60597245e-04],
[ 5.10000000e+02, 7.29211257e-04],
[ 5.20000000e+02, 1.06216129e-03],
[ 5.30000000e+02, 9.32767813e-04],
[ 5.40000000e+02, 9.26595356e-04],
[ 5.50000000e+02, 9.56396339e-04],
[ 5.60000000e+02, 7.88826321e-04],
[ 5.70000000e+02, 1.00343931e-03],
[ 5.80000000e+02, 1.00611302e-03],
[ 5.90000000e+02, 9.82254161e-04],
[ 6.00000000e+02, 6.86758547e-04],
[ 6.10000000e+02, 7.12899957e-04],
[ 6.20000000e+02, 7.27548904e-04],
[ 6.30000000e+02, 7.64576369e-04],
[ 6.40000000e+02, 7.58014037e-04],
[ 6.50000000e+02, 7.47552665e-04],
[ 6.60000000e+02, 8.14763305e-04],
[ 6.70000000e+02, 7.39449926e-04],
[ 6.80000000e+02, 8.02603085e-04],
[ 6.90000000e+02, 7.19150470e-04],
[ 7.00000000e+02, 7.02608202e-04],
[ 7.10000000e+02, 6.08150032e-04],
[ 7.20000000e+02, 7.03473983e-04],
[ 7.30000000e+02, 7.08433217e-04],
[ 7.40000000e+02, 7.24861457e-04],
[ 7.50000000e+02, 5.37842978e-04],
[ 7.60000000e+02, 6.41418563e-04],
[ 7.70000000e+02, 5.75507409e-04],
[ 7.80000000e+02, 6.03403838e-04],
[ 7.90000000e+02, 6.54002884e-04],
[ 8.00000000e+02, 5.54654165e-04],
[ 8.10000000e+02, 4.99101589e-04],
[ 8.20000000e+02, 6.56683056e-04],
[ 8.30000000e+02, 5.56540850e-04],
[ 8.40000000e+02, 6.25622924e-04],
[ 8.50000000e+02, 4.45001177e-04],
[ 8.60000000e+02, 5.40971174e-04],
[ 8.70000000e+02, 5.67872601e-04],
[ 8.80000000e+02, 4.75532404e-04],
[ 8.90000000e+02, 4.92830703e-04],
[ 9.00000000e+02, 5.90068870e-04],
[ 9.10000000e+02, 5.11613616e-04],
[ 9.20000000e+02, 4.64697456e-04],
[ 9.30000000e+02, 4.30622429e-04],
[ 9.40000000e+02, 5.59505192e-04],
[ 9.50000000e+02, 5.31189842e-04],
[ 9.60000000e+02, 5.05464501e-04],
[ 9.70000000e+02, 3.56924895e-04],
[ 9.80000000e+02, 4.99868009e-04],
[ 9.90000000e+02, 3.87771142e-04],
[ 1.00000000e+03, 4.41522920e-04],
[ 1.01000000e+03, 4.31795575e-04],
[ 1.02000000e+03, 5.34437015e-04],
[ 1.03000000e+03, 4.28901461e-04],
[ 1.04000000e+03, 3.87969078e-04],
[ 1.05000000e+03, 3.35424847e-04],
[ 1.06000000e+03, 4.73805732e-04],
[ 1.07000000e+03, 4.10100678e-04],
[ 1.08000000e+03, 3.57456418e-04],
[ 1.09000000e+03, 3.90132511e-04],
[ 1.10000000e+03, 4.39921481e-04],
[ 1.11000000e+03, 3.61111946e-04],
[ 1.12000000e+03, 3.77521355e-04],
[ 1.13000000e+03, 4.22277371e-04],
[ 1.14000000e+03, 4.74101602e-04],
[ 1.15000000e+03, 3.80392885e-04],
[ 1.16000000e+03, 3.88564164e-04],
[ 1.17000000e+03, 3.65295477e-04],
[ 1.18000000e+03, 3.40796338e-04],
[ 1.19000000e+03, 3.56410659e-04],
[ 1.20000000e+03, 4.02213162e-04],
[ 1.21000000e+03, 3.43823718e-04],
[ 1.22000000e+03, 3.85664112e-04],
[ 1.23000000e+03, 3.88184446e-04],
[ 1.24000000e+03, 4.04180726e-04],
[ 1.25000000e+03, 3.86747182e-04],
[ 1.26000000e+03, 3.41747858e-04],
[ 1.27000000e+03, 3.48885718e-04],
[ 1.28000000e+03, 3.13018973e-04],
[ 1.29000000e+03, 3.07582028e-04],
[ 1.30000000e+03, 3.73672869e-04],
[ 1.31000000e+03, 3.87388834e-04],
[ 1.32000000e+03, 4.19116666e-04],
[ 1.33000000e+03, 3.27760878e-04],
[ 1.34000000e+03, 3.08957970e-04],
[ 1.35000000e+03, 3.30988230e-04],
[ 1.36000000e+03, 3.46238434e-04],
[ 1.37000000e+03, 3.44896660e-04],
[ 1.38000000e+03, 3.70746973e-04],
[ 1.39000000e+03, 3.50284274e-04],
[ 1.40000000e+03, 3.14876030e-04],
[ 1.41000000e+03, 3.73970484e-04],
[ 1.42000000e+03, 3.45496956e-04],
[ 1.43000000e+03, 3.40876257e-04],
[ 1.44000000e+03, 3.22644337e-04],
[ 1.45000000e+03, 3.35026300e-04],
[ 1.46000000e+03, 2.88841547e-04],
[ 1.47000000e+03, 3.12957622e-04],
[ 1.48000000e+03, 3.08143673e-04],
[ 1.49000000e+03, 2.95434991e-04],
[ 1.50000000e+03, 2.98283383e-04],
[ 1.51000000e+03, 3.24022199e-04],
[ 1.52000000e+03, 2.56367523e-04],
[ 1.53000000e+03, 2.77088810e-04],
[ 1.54000000e+03, 3.02627857e-04],
[ 1.55000000e+03, 2.72747478e-04],
[ 1.56000000e+03, 3.06661386e-04],
[ 1.57000000e+03, 2.64829258e-04],
[ 1.58000000e+03, 2.76857172e-04],
[ 1.59000000e+03, 2.81696732e-04],
[ 1.60000000e+03, 3.00184474e-04],
[ 1.61000000e+03, 2.55607971e-04],
[ 1.62000000e+03, 2.76382896e-04],
[ 1.63000000e+03, 2.35493426e-04],
[ 1.64000000e+03, 2.48022145e-04],
[ 1.65000000e+03, 3.01513704e-04],
[ 1.66000000e+03, 2.66833609e-04],
[ 1.67000000e+03, 2.71970814e-04],
[ 1.68000000e+03, 2.68793898e-04],
[ 1.69000000e+03, 2.41466987e-04],
[ 1.70000000e+03, 2.77868385e-04],
[ 1.71000000e+03, 2.94675818e-04],
[ 1.72000000e+03, 2.45844160e-04],
[ 1.73000000e+03, 2.50226178e-04],
[ 1.74000000e+03, 2.61309848e-04],
[ 1.75000000e+03, 2.67283089e-04],
[ 1.76000000e+03, 2.87918781e-04],
[ 1.77000000e+03, 2.88327225e-04],
[ 1.78000000e+03, 2.44195980e-04],
[ 1.79000000e+03, 2.75243481e-04],
[ 1.80000000e+03, 2.20340080e-04],
[ 1.81000000e+03, 2.81056040e-04],
[ 1.82000000e+03, 2.27521130e-04],
[ 1.83000000e+03, 2.58146698e-04],
[ 1.84000000e+03, 2.18406873e-04],
[ 1.85000000e+03, 2.33469735e-04],
[ 1.86000000e+03, 2.25574753e-04],
[ 1.87000000e+03, 2.32736464e-04],
[ 1.88000000e+03, 2.42906332e-04],
[ 1.89000000e+03, 2.63917493e-04],
[ 1.90000000e+03, 2.74311577e-04],
[ 1.91000000e+03, 2.39641056e-04],
[ 1.92000000e+03, 1.75235909e-04],
[ 1.93000000e+03, 3.02739878e-04],
[ 1.94000000e+03, 2.05147531e-04],
[ 1.95000000e+03, 2.08231912e-04],
[ 1.96000000e+03, 2.31014754e-04],
[ 1.97000000e+03, 2.28317673e-04],
[ 1.98000000e+03, 2.48514290e-04],
[ 1.99000000e+03, 2.36065680e-04],
[ 2.00000000e+03, 2.02242474e-04]])
In [7]:
train_df = pd.DataFrame(train[:len(initial) + len(output), 0], columns=["train"])
initial_df = pd.DataFrame(initial, columns=["initial"])
output_df = pd.DataFrame(output, columns=["output"], index=range(len(initial), len(initial) + len(output)))
merged = pd.concat([train_df, initial_df, output_df])
merged.plot(figsize=(15, 5), grid=True, style=["-", "-", "k--"])
Out[7]:
<matplotlib.axes._subplots.AxesSubplot at 0x112980940>
In [8]:
losses_df = pd.DataFrame(losses, columns=["epoch", "loss"])
losses_df.plot(figsize=(15, 5), grid=True, logy=True, x="epoch")
Out[8]:
<matplotlib.axes._subplots.AxesSubplot at 0x1129525f8>
In [ ]:
Content source: nayutaya/tensorflow-rnn-sin
Similar notebooks: