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': 50,
'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': 'AdamOptimizer',
'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])
In [5]:
output = np.load("output.npy")
output
Out[5]:
array([ 2.83628702e-04, 1.25220656e-01, 2.46496677e-01,
3.62098396e-01, 4.71018583e-01, 5.73093295e-01,
6.68254435e-01, 7.55321681e-01, 8.31420958e-01,
8.92778456e-01, 9.36342835e-01, 9.61099923e-01,
9.68107462e-01, 9.59291101e-01, 9.36133742e-01,
8.99040818e-01, 8.47349465e-01, 7.79820740e-01,
6.95699573e-01, 5.96313715e-01, 4.86185819e-01,
3.71985435e-01, 2.59565383e-01, 1.51709214e-01,
4.80490923e-02, -5.36487699e-02, -1.56006217e-01,
-2.60868192e-01, -3.68465126e-01, -4.76891696e-01,
-5.82098544e-01, -6.78666294e-01, -7.61285603e-01,
-8.26281726e-01, -8.72356117e-01, -9.00277674e-01,
-9.11976278e-01, -9.09641206e-01, -8.95137727e-01,
-8.69748294e-01, -8.34122002e-01, -7.88319170e-01,
-7.31931269e-01, -6.64238214e-01, -5.84427655e-01,
-4.91863847e-01, -3.86521637e-01, -2.69454122e-01,
-1.43157899e-01, -1.17858052e-02, 1.19671121e-01,
2.46818155e-01, 3.66988510e-01, 4.79326248e-01,
5.83918810e-01, 6.80491328e-01, 7.67520905e-01,
8.42176259e-01, 9.01080787e-01, 9.41686749e-01,
9.63451266e-01, 9.67714071e-01, 9.56425011e-01,
9.30925488e-01, 8.91438603e-01, 8.37164998e-01,
7.66863167e-01, 6.80017471e-01, 5.78454792e-01,
4.67203200e-01, 3.53019357e-01, 2.41342992e-01,
1.34380937e-01, 3.13458741e-02, -7.01583326e-02,
-1.72697991e-01, -2.77907431e-01, -3.85701716e-01,
-4.93822157e-01, -5.97936213e-01, -6.92539632e-01,
-7.72499263e-01, -8.34495723e-01, -8.77594173e-01,
-9.02802408e-01, -9.12136972e-01, -9.07769263e-01,
-8.91484439e-01, -8.64460051e-01, -8.27261269e-01,
-7.79893816e-01, -7.21895874e-01, -6.52494490e-01,
-5.70840597e-01, -4.76309240e-01, -3.69034111e-01,
-2.50574887e-01, -1.23953909e-01, 6.53201342e-03,
1.35919765e-01])
In [6]:
losses = np.load("losses.npy")
losses
Out[6]:
array([[ 1.00000000e+01, 6.10969737e-02],
[ 2.00000000e+01, 7.77162658e-03],
[ 3.00000000e+01, 5.52238105e-03],
[ 4.00000000e+01, 1.76544930e-03],
[ 5.00000000e+01, 1.60719675e-03],
[ 6.00000000e+01, 1.13896222e-03],
[ 7.00000000e+01, 4.38332325e-04],
[ 8.00000000e+01, 5.86728682e-04],
[ 9.00000000e+01, 5.89998439e-04],
[ 1.00000000e+02, 2.79696338e-04],
[ 1.10000000e+02, 2.95644713e-04],
[ 1.20000000e+02, 2.29450132e-04],
[ 1.30000000e+02, 2.56181287e-04],
[ 1.40000000e+02, 1.35044422e-04],
[ 1.50000000e+02, 9.05569832e-05],
[ 1.60000000e+02, 9.92824134e-05],
[ 1.70000000e+02, 8.34013335e-05],
[ 1.80000000e+02, 9.14113989e-05],
[ 1.90000000e+02, 1.08302695e-04],
[ 2.00000000e+02, 1.17158750e-04],
[ 2.10000000e+02, 1.10270797e-04],
[ 2.20000000e+02, 3.83183906e-05],
[ 2.30000000e+02, 4.02834303e-05],
[ 2.40000000e+02, 4.48412247e-05],
[ 2.50000000e+02, 1.75699854e-04],
[ 2.60000000e+02, 3.59078513e-05],
[ 2.70000000e+02, 3.58345787e-05],
[ 2.80000000e+02, 4.43954377e-05],
[ 2.90000000e+02, 2.94308829e-05],
[ 3.00000000e+02, 8.03085568e-05],
[ 3.10000000e+02, 2.07529793e-05],
[ 3.20000000e+02, 1.71598644e-04],
[ 3.30000000e+02, 4.65605408e-04],
[ 3.40000000e+02, 5.07283075e-05],
[ 3.50000000e+02, 2.03789386e-04],
[ 3.60000000e+02, 1.93025771e-05],
[ 3.70000000e+02, 4.25378967e-05],
[ 3.80000000e+02, 1.25800303e-04],
[ 3.90000000e+02, 2.28154331e-05],
[ 4.00000000e+02, 4.02827645e-05],
[ 4.10000000e+02, 4.57815004e-05],
[ 4.20000000e+02, 1.61580574e-05],
[ 4.30000000e+02, 3.01140899e-05],
[ 4.40000000e+02, 9.02587344e-05],
[ 4.50000000e+02, 3.33210221e-03],
[ 4.60000000e+02, 1.50356675e-03],
[ 4.70000000e+02, 7.84631848e-05],
[ 4.80000000e+02, 9.22413019e-05],
[ 4.90000000e+02, 1.81988740e-04],
[ 5.00000000e+02, 6.36586919e-05],
[ 5.10000000e+02, 4.42359415e-05],
[ 5.20000000e+02, 3.14874960e-05],
[ 5.30000000e+02, 6.59197322e-05],
[ 5.40000000e+02, 4.18465315e-05],
[ 5.50000000e+02, 2.90503867e-05],
[ 5.60000000e+02, 1.77055881e-05],
[ 5.70000000e+02, 5.37441301e-05],
[ 5.80000000e+02, 6.29912101e-05],
[ 5.90000000e+02, 8.94680416e-05],
[ 6.00000000e+02, 2.89067830e-05],
[ 6.10000000e+02, 1.01456491e-04],
[ 6.20000000e+02, 1.96453548e-05],
[ 6.30000000e+02, 3.45041044e-05],
[ 6.40000000e+02, 2.78717671e-05],
[ 6.50000000e+02, 1.77251659e-05],
[ 6.60000000e+02, 1.39132617e-05],
[ 6.70000000e+02, 3.81565405e-05],
[ 6.80000000e+02, 7.86456658e-05],
[ 6.90000000e+02, 2.08908823e-04],
[ 7.00000000e+02, 5.14062012e-05],
[ 7.10000000e+02, 5.21111033e-05],
[ 7.20000000e+02, 1.46123757e-05],
[ 7.30000000e+02, 6.78271681e-05],
[ 7.40000000e+02, 5.08984231e-05],
[ 7.50000000e+02, 2.30509577e-05],
[ 7.60000000e+02, 2.91194156e-05],
[ 7.70000000e+02, 1.86885991e-05],
[ 7.80000000e+02, 3.35167679e-05],
[ 7.90000000e+02, 2.27156183e-04],
[ 8.00000000e+02, 4.24601822e-05],
[ 8.10000000e+02, 6.19676546e-04],
[ 8.20000000e+02, 5.20430680e-04],
[ 8.30000000e+02, 5.20468457e-05],
[ 8.40000000e+02, 3.97397853e-05],
[ 8.50000000e+02, 5.15194697e-05],
[ 8.60000000e+02, 6.05165224e-05],
[ 8.70000000e+02, 2.51259335e-05],
[ 8.80000000e+02, 1.13653819e-04],
[ 8.90000000e+02, 7.12659443e-04],
[ 9.00000000e+02, 7.46952835e-04],
[ 9.10000000e+02, 3.31264164e-04],
[ 9.20000000e+02, 4.29162465e-05],
[ 9.30000000e+02, 1.68648767e-05],
[ 9.40000000e+02, 2.37524146e-05],
[ 9.50000000e+02, 1.86908619e-05],
[ 9.60000000e+02, 3.99018536e-05],
[ 9.70000000e+02, 1.84328484e-04],
[ 9.80000000e+02, 4.83773729e-05],
[ 9.90000000e+02, 7.37997616e-05],
[ 1.00000000e+03, 2.55007690e-05],
[ 1.01000000e+03, 4.05246064e-05],
[ 1.02000000e+03, 1.96581641e-05],
[ 1.03000000e+03, 3.71242699e-04],
[ 1.04000000e+03, 1.11877988e-03],
[ 1.05000000e+03, 1.08024338e-03],
[ 1.06000000e+03, 3.74444237e-04],
[ 1.07000000e+03, 3.51462404e-05],
[ 1.08000000e+03, 3.30660951e-05],
[ 1.09000000e+03, 1.70626416e-04],
[ 1.10000000e+03, 4.79441042e-05],
[ 1.11000000e+03, 3.75970740e-05],
[ 1.12000000e+03, 1.56329057e-04],
[ 1.13000000e+03, 1.35360287e-05],
[ 1.14000000e+03, 8.71407028e-05],
[ 1.15000000e+03, 9.54330972e-05],
[ 1.16000000e+03, 2.88726242e-05],
[ 1.17000000e+03, 2.01006933e-05],
[ 1.18000000e+03, 4.26631887e-05],
[ 1.19000000e+03, 1.99111219e-05],
[ 1.20000000e+03, 4.78418515e-05],
[ 1.21000000e+03, 3.48768299e-05],
[ 1.22000000e+03, 3.76810291e-04],
[ 1.23000000e+03, 1.40803648e-04],
[ 1.24000000e+03, 1.02131779e-03],
[ 1.25000000e+03, 1.20042961e-04],
[ 1.26000000e+03, 6.52319170e-04],
[ 1.27000000e+03, 3.97263910e-04],
[ 1.28000000e+03, 5.38318418e-04],
[ 1.29000000e+03, 7.37772425e-05],
[ 1.30000000e+03, 8.92243334e-05],
[ 1.31000000e+03, 2.74681715e-05],
[ 1.32000000e+03, 2.73687074e-05],
[ 1.33000000e+03, 9.33137926e-05],
[ 1.34000000e+03, 4.21714030e-05],
[ 1.35000000e+03, 3.78919176e-05],
[ 1.36000000e+03, 1.56807782e-05],
[ 1.37000000e+03, 3.31931806e-05],
[ 1.38000000e+03, 1.45089463e-04],
[ 1.39000000e+03, 8.85264380e-05],
[ 1.40000000e+03, 8.94753830e-05],
[ 1.41000000e+03, 6.12463409e-05],
[ 1.42000000e+03, 4.15983814e-05],
[ 1.43000000e+03, 2.18076493e-05],
[ 1.44000000e+03, 2.97649749e-05],
[ 1.45000000e+03, 9.18175283e-05],
[ 1.46000000e+03, 3.65466767e-05],
[ 1.47000000e+03, 4.56915332e-05],
[ 1.48000000e+03, 2.23563711e-05],
[ 1.49000000e+03, 1.75619498e-05],
[ 1.50000000e+03, 3.74899173e-05],
[ 1.51000000e+03, 9.88875545e-05],
[ 1.52000000e+03, 1.29086002e-05],
[ 1.53000000e+03, 1.14558454e-04],
[ 1.54000000e+03, 2.20962407e-04],
[ 1.55000000e+03, 1.96731067e-04],
[ 1.56000000e+03, 3.06505215e-04],
[ 1.57000000e+03, 4.14968294e-04],
[ 1.58000000e+03, 3.53203795e-05],
[ 1.59000000e+03, 2.74486316e-04],
[ 1.60000000e+03, 8.22234870e-05],
[ 1.61000000e+03, 1.48445310e-04],
[ 1.62000000e+03, 2.07026489e-04],
[ 1.63000000e+03, 3.43131542e-05],
[ 1.64000000e+03, 4.31808076e-05],
[ 1.65000000e+03, 3.01565924e-05],
[ 1.66000000e+03, 1.48747504e-05],
[ 1.67000000e+03, 1.90546307e-05],
[ 1.68000000e+03, 1.85402896e-05],
[ 1.69000000e+03, 2.98473082e-04],
[ 1.70000000e+03, 3.79519013e-04],
[ 1.71000000e+03, 5.43937786e-04],
[ 1.72000000e+03, 3.57387878e-04],
[ 1.73000000e+03, 9.88785250e-05],
[ 1.74000000e+03, 3.71587899e-04],
[ 1.75000000e+03, 1.02332662e-04],
[ 1.76000000e+03, 4.07013431e-05],
[ 1.77000000e+03, 4.03152226e-05],
[ 1.78000000e+03, 2.32265138e-05],
[ 1.79000000e+03, 2.16038843e-05],
[ 1.80000000e+03, 5.15775937e-05],
[ 1.81000000e+03, 3.19301580e-05],
[ 1.82000000e+03, 1.61456774e-05],
[ 1.83000000e+03, 1.89387683e-05],
[ 1.84000000e+03, 4.76303794e-05],
[ 1.85000000e+03, 2.07834964e-05],
[ 1.86000000e+03, 2.10150338e-05],
[ 1.87000000e+03, 1.23333484e-05],
[ 1.88000000e+03, 4.17010706e-05],
[ 1.89000000e+03, 3.82699618e-05],
[ 1.90000000e+03, 2.48225351e-05],
[ 1.91000000e+03, 2.45992778e-05],
[ 1.92000000e+03, 5.65225273e-05],
[ 1.93000000e+03, 7.30186512e-05],
[ 1.94000000e+03, 3.55231095e-05],
[ 1.95000000e+03, 6.28243142e-05],
[ 1.96000000e+03, 5.96105092e-05],
[ 1.97000000e+03, 2.35389125e-05],
[ 1.98000000e+03, 9.40761765e-06],
[ 1.99000000e+03, 8.98922553e-06],
[ 2.00000000e+03, 6.26939482e-06]])
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 0x10e62e908>
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 0x10e6016a0>
In [ ]:
Content source: nayutaya/tensorflow-rnn-sin
Similar notebooks: