Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
TimeSerieser
GitHub Repository: TimeSerieser/How-to-Guess-Accurately-3-Lottery-Numbers-Out-of-6-using-LSTM
 Path: blob/main/Israeli Lottery.ipynb
108 views
Kernel: Python 3
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler

df = pd.read_csv("IsraeliLottery.csv")

df.head()

df.tail()

df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 4047 entries, 0 to 4046 Data columns (total 8 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Game 4047 non-null int64 1 Date 4047 non-null object 2 A 4047 non-null int64 3 B 4047 non-null int64 4 C 4047 non-null int64 5 D 4047 non-null int64 6 E 4047 non-null int64 7 F 4047 non-null int64 dtypes: int64(7), object(1) memory usage: 253.1+ KB 
df.describe()

df.drop(['Game', 'Date'], axis=1, inplace=True)

df.head()

scaler = StandardScaler().fit(df.values)
transformed_dataset = scaler.transform(df.values)
transformed_df = pd.DataFrame(data=transformed_dataset, index=df.index)

transformed_df.head()

# All our games
number_of_rows = df.values.shape[0]
number_of_rows
4047
# Amount of games we need to take into consideration for prediction
window_length = 7
window_length
7
# Balls counts
number_of_features = df.values.shape[1]
number_of_features
6
X = np.empty([ number_of_rows - window_length, window_length, number_of_features], dtype=float)
X
array([[[0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], ..., [2.19987190e-152, 6.01099881e+175, 9.03082937e-090, 4.82336277e+228, 5.04533095e+223, 2.35567712e+251], [1.27640997e-152, 5.04620669e+180, 4.95241270e+223, 5.71606413e+180, 1.06314419e+248, 9.08367206e+223], [1.55541130e+161, 6.32672135e+180, 2.45652619e+198, 1.27989698e-152, 4.08841057e+233, 5.02065932e+276]], [[9.10580156e+102, 1.14503156e+243, 3.68065911e+180, 1.69375611e+190, 1.99722753e+161, 5.53083643e-311], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], ..., [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000]], [[0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], ..., [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000], [0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000, 0.00000000e+000]], ..., [[4.17649570e-316, 4.17649580e-316, 4.17649589e-316, 4.17649599e-316, 4.17649614e-316, 4.17649629e-316], [4.17649644e-316, 4.17649669e-316, 4.17649723e-316, 4.17649738e-316, 4.17649753e-316, 4.17649767e-316], [4.17649782e-316, 4.17649797e-316, 4.17649812e-316, 4.17649836e-316, 4.17649891e-316, 4.17649901e-316], ..., [4.17650054e-316, 4.17650064e-316, 4.17650079e-316, 4.17650093e-316, 4.17650108e-316, 4.17650123e-316], [4.17650138e-316, 4.17650163e-316, 4.17650217e-316, 4.17650232e-316, 4.17650247e-316, 4.17650261e-316], [4.17650276e-316, 4.17650291e-316, 4.17650306e-316, 4.17650331e-316, 4.17650385e-316, 4.17650395e-316]], [[4.17650410e-316, 4.17650424e-316, 4.17650439e-316, 4.17650454e-316, 4.17650469e-316, 4.17650494e-316], [4.17650548e-316, 4.17650563e-316, 4.17650578e-316, 4.17650592e-316, 4.17650607e-316, 4.17650622e-316], [4.17650637e-316, 4.17650662e-316, 4.17650716e-316, 4.17650731e-316, 4.17650746e-316, 4.17650760e-316], ..., [4.17650914e-316, 4.17650928e-316, 4.17650943e-316, 4.17650958e-316, 4.17650973e-316, 4.17650998e-316], [4.17651052e-316, 4.17651062e-316, 4.17651072e-316, 4.17651086e-316, 4.17651101e-316, 4.17651116e-316], [4.17651131e-316, 4.17651156e-316, 4.17651210e-316, 4.17651220e-316, 4.17651230e-316, 4.17651245e-316]], [[4.17651259e-316, 4.17651274e-316, 4.17651289e-316, 4.17651314e-316, 4.17651368e-316, 4.17651378e-316], [4.17651393e-316, 4.17651408e-316, 4.17651422e-316, 4.17651437e-316, 4.17651452e-316, 4.17651477e-316], [4.17651531e-316, 4.17651541e-316, 4.17651556e-316, 4.17651571e-316, 4.17651585e-316, 4.17651600e-316], ..., [4.17651749e-316, 4.17651763e-316, 4.17651778e-316, 4.17651803e-316, 4.17651857e-316, 4.17651872e-316], [4.17651887e-316, 4.17651902e-316, 4.17651917e-316, 4.17651931e-316, 4.17651946e-316, 4.17651971e-316], [4.17652025e-316, 4.17652040e-316, 4.17652055e-316, 4.17652070e-316, 4.17652084e-316, 4.17652099e-316]]])
y = np.empty([ number_of_rows - window_length, number_of_features], dtype=float)
y
array([[ 0. , 53.31128703, 5.29670833, 22.07629815, 22.07629815, 1.69379259], [ 22.07629815, 13.67921389, 7.28212963, 13.67921389, 0.48796111, 13.67921389], [ 7.28212963, 0.48796111, 10.89962407, 28.10545555, 39.70837129, 7.28212963], ..., [ 2.67415833, 2.67415833, 2.67415833, 13.21529991, 5.59187516, 5.59187516], [135.37986626, 0.40358754, 13.21529991, 2.67415833, 0.40358754, 1.86244595], [ 1.86244595, 5.59187516, 31.7564415 , 0.40358754, 1.86244595, 0.40358754]])
for i in range(0, number_of_rows-window_length):
    X[i] = transformed_df.iloc[i : i+window_length, 0 : number_of_features]
    y[i] = transformed_df.iloc[i+window_length : i+window_length+1, 0 : number_of_features]

X.shape
(4040, 7, 6)
y.shape
(4040, 6)
X[0]
array([[-0.58223113, 0.429455 , 0.1300936 , -0.13906023, -0.57371015, -0.27670816], [ 1.57534546, 1.43157169, 0.87667445, 0.88736948, 0.4844041 , -0.10749723], [ 0.49655716, 0.0954161 , 1.32462296, 0.59410385, 0.78672246, 0.56934648], [-1.01374645, 0.429455 , -0.01922257, 0.44747103, 0.93788164, 0.7385574 ], [-1.01374645, -0.73968114, -1.36306809, -2.04528682, -2.68993865, -0.78434094], [ 0.2807995 , -0.40564224, -1.06443575, -0.8722243 , -0.87602851, -0.10749723], [-1.01374645, -0.90670059, 0.87667445, 0.88736948, 0.63556328, -0.10749723]])
X[1]
array([[ 1.57534546, 1.43157169, 0.87667445, 0.88736948, 0.4844041 , -0.10749723], [ 0.49655716, 0.0954161 , 1.32462296, 0.59410385, 0.78672246, 0.56934648], [-1.01374645, 0.429455 , -0.01922257, 0.44747103, 0.93788164, 0.7385574 ], [-1.01374645, -0.73968114, -1.36306809, -2.04528682, -2.68993865, -0.78434094], [ 0.2807995 , -0.40564224, -1.06443575, -0.8722243 , -0.87602851, -0.10749723], [-1.01374645, -0.90670059, 0.87667445, 0.88736948, 0.63556328, -0.10749723], [-0.79798879, 0.26243555, 0.42872594, 0.1542054 , -0.57371015, -1.29197372]])
y[0]
array([-0.79798879, 0.26243555, 0.42872594, 0.1542054 , -0.57371015, -1.29197372])
y[1]
array([-0.58223113, -0.40564224, 1.32462296, 1.32726792, 0.78672246, 0.23092462])
# Recurrent Neural Netowrk (RNN) with Long Short Term Memory (LSTM)
# Importing the Keras libraries and packages
from keras.models import Sequential
from keras.layers import LSTM, Dense, Bidirectional, Dropout
batch_size = 100

# Initialising the RNN
model = Sequential()
# Adding the input layer and the LSTM layer
model.add(Bidirectional(LSTM(240,
                        input_shape = (window_length, number_of_features),
                        return_sequences = True)))
# Adding a first Dropout layer
model.add(Dropout(0.2))
# Adding a second LSTM layer
model.add(Bidirectional(LSTM(240,
                        input_shape = (window_length, number_of_features),
                        return_sequences = True)))
# Adding a second Dropout layer
model.add(Dropout(0.2))
# Adding a third LSTM layer
model.add(Bidirectional(LSTM(240,
                        input_shape = (window_length, number_of_features),
                        return_sequences = True)))
# Adding a fourth LSTM layer
model.add(Bidirectional(LSTM(240,
                        input_shape = (window_length, number_of_features),
                        return_sequences = False)))
# Adding a fourth Dropout layer
model.add(Dropout(0.2))
# Adding the first output layer
model.add(Dense(59))
# Adding the last output layer
model.add(Dense(number_of_features))

from tensorflow import keras
from tensorflow.keras.optimizers import Adam
model.compile(optimizer=Adam(learning_rate=0.0001), loss ='mse', metrics=['accuracy'])

model.fit(x=X, y=y, batch_size=100, epochs=300, verbose=2)
Epoch 1/300 41/41 - 12s - loss: 0.0094 - accuracy: 0.9245 - 12s/epoch - 285ms/step Epoch 2/300 41/41 - 1s - loss: 0.0081 - accuracy: 0.9339 - 637ms/epoch - 16ms/step Epoch 3/300 41/41 - 1s - loss: 0.0077 - accuracy: 0.9354 - 633ms/epoch - 15ms/step Epoch 4/300 41/41 - 1s - loss: 0.0072 - accuracy: 0.9401 - 629ms/epoch - 15ms/step Epoch 5/300 41/41 - 1s - loss: 0.0070 - accuracy: 0.9342 - 644ms/epoch - 16ms/step Epoch 6/300 41/41 - 1s - loss: 0.0066 - accuracy: 0.9351 - 652ms/epoch - 16ms/step Epoch 7/300 41/41 - 1s - loss: 0.0067 - accuracy: 0.9349 - 619ms/epoch - 15ms/step Epoch 8/300 41/41 - 1s - loss: 0.0066 - accuracy: 0.9374 - 638ms/epoch - 16ms/step Epoch 9/300 41/41 - 1s - loss: 0.0062 - accuracy: 0.9394 - 639ms/epoch - 16ms/step Epoch 10/300 41/41 - 1s - loss: 0.0061 - accuracy: 0.9391 - 630ms/epoch - 15ms/step Epoch 11/300 41/41 - 1s - loss: 0.0061 - accuracy: 0.9381 - 637ms/epoch - 16ms/step Epoch 12/300 41/41 - 1s - loss: 0.0062 - accuracy: 0.9356 - 638ms/epoch - 16ms/step Epoch 13/300 41/41 - 1s - loss: 0.0061 - accuracy: 0.9356 - 630ms/epoch - 15ms/step Epoch 14/300 41/41 - 1s - loss: 0.0060 - accuracy: 0.9413 - 637ms/epoch - 16ms/step Epoch 15/300 41/41 - 1s - loss: 0.0061 - accuracy: 0.9418 - 629ms/epoch - 15ms/step Epoch 16/300 41/41 - 1s - loss: 0.0059 - accuracy: 0.9381 - 641ms/epoch - 16ms/step Epoch 17/300 41/41 - 1s - loss: 0.0059 - accuracy: 0.9369 - 634ms/epoch - 15ms/step Epoch 18/300 41/41 - 1s - loss: 0.0059 - accuracy: 0.9436 - 632ms/epoch - 15ms/step Epoch 19/300 41/41 - 1s - loss: 0.0057 - accuracy: 0.9384 - 631ms/epoch - 15ms/step Epoch 20/300 41/41 - 1s - loss: 0.0057 - accuracy: 0.9413 - 627ms/epoch - 15ms/step Epoch 21/300 41/41 - 1s - loss: 0.0057 - accuracy: 0.9426 - 630ms/epoch - 15ms/step Epoch 22/300 41/41 - 1s - loss: 0.0058 - accuracy: 0.9426 - 642ms/epoch - 16ms/step Epoch 23/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9384 - 625ms/epoch - 15ms/step Epoch 24/300 41/41 - 1s - loss: 0.0057 - accuracy: 0.9349 - 635ms/epoch - 15ms/step Epoch 25/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9473 - 628ms/epoch - 15ms/step Epoch 26/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9431 - 626ms/epoch - 15ms/step Epoch 27/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9394 - 633ms/epoch - 15ms/step Epoch 28/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9408 - 624ms/epoch - 15ms/step Epoch 29/300 41/41 - 1s - loss: 0.0057 - accuracy: 0.9428 - 632ms/epoch - 15ms/step Epoch 30/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9483 - 634ms/epoch - 15ms/step Epoch 31/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9374 - 636ms/epoch - 16ms/step Epoch 32/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9488 - 643ms/epoch - 16ms/step Epoch 33/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9369 - 636ms/epoch - 16ms/step Epoch 34/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9470 - 630ms/epoch - 15ms/step Epoch 35/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9399 - 648ms/epoch - 16ms/step Epoch 36/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9431 - 657ms/epoch - 16ms/step Epoch 37/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9450 - 656ms/epoch - 16ms/step Epoch 38/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9411 - 639ms/epoch - 16ms/step Epoch 39/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9480 - 629ms/epoch - 15ms/step Epoch 40/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9455 - 641ms/epoch - 16ms/step Epoch 41/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9441 - 634ms/epoch - 15ms/step Epoch 42/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9401 - 628ms/epoch - 15ms/step Epoch 43/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9448 - 637ms/epoch - 16ms/step Epoch 44/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9406 - 629ms/epoch - 15ms/step Epoch 45/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9448 - 636ms/epoch - 16ms/step Epoch 46/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9468 - 631ms/epoch - 15ms/step Epoch 47/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9431 - 631ms/epoch - 15ms/step Epoch 48/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9436 - 645ms/epoch - 16ms/step Epoch 49/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9421 - 636ms/epoch - 16ms/step Epoch 50/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9455 - 615ms/epoch - 15ms/step Epoch 51/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9465 - 630ms/epoch - 15ms/step Epoch 52/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9344 - 637ms/epoch - 16ms/step Epoch 53/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9443 - 628ms/epoch - 15ms/step Epoch 54/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9436 - 644ms/epoch - 16ms/step Epoch 55/300 41/41 - 1s - loss: 0.0056 - accuracy: 0.9384 - 637ms/epoch - 16ms/step Epoch 56/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9433 - 634ms/epoch - 15ms/step Epoch 57/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9470 - 635ms/epoch - 15ms/step Epoch 58/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9413 - 628ms/epoch - 15ms/step Epoch 59/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9416 - 628ms/epoch - 15ms/step Epoch 60/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9460 - 629ms/epoch - 15ms/step Epoch 61/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9401 - 622ms/epoch - 15ms/step Epoch 62/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9374 - 622ms/epoch - 15ms/step Epoch 63/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9421 - 622ms/epoch - 15ms/step Epoch 64/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9433 - 642ms/epoch - 16ms/step Epoch 65/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9403 - 628ms/epoch - 15ms/step Epoch 66/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9450 - 627ms/epoch - 15ms/step Epoch 67/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9436 - 629ms/epoch - 15ms/step Epoch 68/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9376 - 627ms/epoch - 15ms/step Epoch 69/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9438 - 611ms/epoch - 15ms/step Epoch 70/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9413 - 629ms/epoch - 15ms/step Epoch 71/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9426 - 639ms/epoch - 16ms/step Epoch 72/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9473 - 621ms/epoch - 15ms/step Epoch 73/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9411 - 635ms/epoch - 15ms/step Epoch 74/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9515 - 629ms/epoch - 15ms/step Epoch 75/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9473 - 631ms/epoch - 15ms/step Epoch 76/300 41/41 - 1s - loss: 0.0055 - accuracy: 0.9475 - 627ms/epoch - 15ms/step Epoch 77/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9460 - 620ms/epoch - 15ms/step Epoch 78/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9480 - 627ms/epoch - 15ms/step Epoch 79/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9450 - 621ms/epoch - 15ms/step Epoch 80/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9423 - 641ms/epoch - 16ms/step Epoch 81/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9413 - 627ms/epoch - 15ms/step Epoch 82/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9480 - 648ms/epoch - 16ms/step Epoch 83/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9403 - 625ms/epoch - 15ms/step Epoch 84/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9399 - 676ms/epoch - 16ms/step Epoch 85/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9490 - 631ms/epoch - 15ms/step Epoch 86/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9408 - 625ms/epoch - 15ms/step Epoch 87/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9455 - 646ms/epoch - 16ms/step Epoch 88/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9418 - 628ms/epoch - 15ms/step Epoch 89/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9512 - 629ms/epoch - 15ms/step Epoch 90/300 41/41 - 1s - loss: 0.0054 - accuracy: 0.9443 - 618ms/epoch - 15ms/step Epoch 91/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9455 - 622ms/epoch - 15ms/step Epoch 92/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9455 - 634ms/epoch - 15ms/step Epoch 93/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9423 - 619ms/epoch - 15ms/step Epoch 94/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9460 - 625ms/epoch - 15ms/step Epoch 95/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9448 - 624ms/epoch - 15ms/step Epoch 96/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9470 - 630ms/epoch - 15ms/step Epoch 97/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9431 - 632ms/epoch - 15ms/step Epoch 98/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9473 - 622ms/epoch - 15ms/step Epoch 99/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9436 - 624ms/epoch - 15ms/step Epoch 100/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9389 - 639ms/epoch - 16ms/step Epoch 101/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9416 - 631ms/epoch - 15ms/step Epoch 102/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9421 - 623ms/epoch - 15ms/step Epoch 103/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9483 - 636ms/epoch - 16ms/step Epoch 104/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9455 - 619ms/epoch - 15ms/step Epoch 105/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9473 - 633ms/epoch - 15ms/step Epoch 106/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9431 - 624ms/epoch - 15ms/step Epoch 107/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9416 - 650ms/epoch - 16ms/step Epoch 108/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9500 - 633ms/epoch - 15ms/step Epoch 109/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9483 - 625ms/epoch - 15ms/step Epoch 110/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9379 - 636ms/epoch - 16ms/step Epoch 111/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9473 - 628ms/epoch - 15ms/step Epoch 112/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9470 - 628ms/epoch - 15ms/step Epoch 113/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9401 - 630ms/epoch - 15ms/step Epoch 114/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9485 - 620ms/epoch - 15ms/step Epoch 115/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9446 - 620ms/epoch - 15ms/step Epoch 116/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9418 - 629ms/epoch - 15ms/step Epoch 117/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9436 - 621ms/epoch - 15ms/step Epoch 118/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9436 - 629ms/epoch - 15ms/step Epoch 119/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9411 - 635ms/epoch - 15ms/step Epoch 120/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9433 - 624ms/epoch - 15ms/step Epoch 121/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9441 - 633ms/epoch - 15ms/step Epoch 122/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9438 - 619ms/epoch - 15ms/step Epoch 123/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9438 - 629ms/epoch - 15ms/step Epoch 124/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9421 - 615ms/epoch - 15ms/step Epoch 125/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9468 - 619ms/epoch - 15ms/step Epoch 126/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9418 - 636ms/epoch - 16ms/step Epoch 127/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9443 - 630ms/epoch - 15ms/step Epoch 128/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9453 - 632ms/epoch - 15ms/step Epoch 129/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9401 - 632ms/epoch - 15ms/step Epoch 130/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9468 - 631ms/epoch - 15ms/step Epoch 131/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9463 - 643ms/epoch - 16ms/step Epoch 132/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9423 - 676ms/epoch - 16ms/step Epoch 133/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9485 - 659ms/epoch - 16ms/step Epoch 134/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9468 - 648ms/epoch - 16ms/step Epoch 135/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9446 - 637ms/epoch - 16ms/step Epoch 136/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9453 - 655ms/epoch - 16ms/step Epoch 137/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9436 - 650ms/epoch - 16ms/step Epoch 138/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9443 - 818ms/epoch - 20ms/step Epoch 139/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9428 - 708ms/epoch - 17ms/step Epoch 140/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9389 - 653ms/epoch - 16ms/step Epoch 141/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9431 - 647ms/epoch - 16ms/step Epoch 142/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9438 - 662ms/epoch - 16ms/step Epoch 143/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9423 - 647ms/epoch - 16ms/step Epoch 144/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9438 - 629ms/epoch - 15ms/step Epoch 145/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9473 - 636ms/epoch - 16ms/step Epoch 146/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9453 - 642ms/epoch - 16ms/step Epoch 147/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9421 - 638ms/epoch - 16ms/step Epoch 148/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9443 - 661ms/epoch - 16ms/step Epoch 149/300 41/41 - 1s - loss: 0.0053 - accuracy: 0.9431 - 649ms/epoch - 16ms/step Epoch 150/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9458 - 969ms/epoch - 24ms/step Epoch 151/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9441 - 632ms/epoch - 15ms/step Epoch 152/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9423 - 640ms/epoch - 16ms/step Epoch 153/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9428 - 635ms/epoch - 15ms/step Epoch 154/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9478 - 646ms/epoch - 16ms/step Epoch 155/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9448 - 645ms/epoch - 16ms/step Epoch 156/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9416 - 613ms/epoch - 15ms/step Epoch 157/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9500 - 635ms/epoch - 15ms/step Epoch 158/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9438 - 629ms/epoch - 15ms/step Epoch 159/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9465 - 620ms/epoch - 15ms/step Epoch 160/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9416 - 617ms/epoch - 15ms/step Epoch 161/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9413 - 631ms/epoch - 15ms/step Epoch 162/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9475 - 632ms/epoch - 15ms/step Epoch 163/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9453 - 657ms/epoch - 16ms/step Epoch 164/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9438 - 899ms/epoch - 22ms/step Epoch 165/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9500 - 625ms/epoch - 15ms/step Epoch 166/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9396 - 639ms/epoch - 16ms/step Epoch 167/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9455 - 636ms/epoch - 16ms/step Epoch 168/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9478 - 633ms/epoch - 15ms/step Epoch 169/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9448 - 652ms/epoch - 16ms/step Epoch 170/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9495 - 644ms/epoch - 16ms/step Epoch 171/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9394 - 640ms/epoch - 16ms/step Epoch 172/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9488 - 634ms/epoch - 15ms/step Epoch 173/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9453 - 634ms/epoch - 15ms/step Epoch 174/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9450 - 633ms/epoch - 15ms/step Epoch 175/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9483 - 633ms/epoch - 15ms/step Epoch 176/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9411 - 622ms/epoch - 15ms/step Epoch 177/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9455 - 673ms/epoch - 16ms/step Epoch 178/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9433 - 855ms/epoch - 21ms/step Epoch 179/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9465 - 641ms/epoch - 16ms/step Epoch 180/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9505 - 639ms/epoch - 16ms/step Epoch 181/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9483 - 639ms/epoch - 16ms/step Epoch 182/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9478 - 625ms/epoch - 15ms/step Epoch 183/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9488 - 650ms/epoch - 16ms/step Epoch 184/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9480 - 629ms/epoch - 15ms/step Epoch 185/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9460 - 642ms/epoch - 16ms/step Epoch 186/300 41/41 - 1s - loss: 0.0052 - accuracy: 0.9408 - 631ms/epoch - 15ms/step Epoch 187/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9428 - 626ms/epoch - 15ms/step Epoch 188/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9495 - 675ms/epoch - 16ms/step Epoch 189/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9453 - 690ms/epoch - 17ms/step Epoch 190/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9438 - 699ms/epoch - 17ms/step Epoch 191/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9394 - 711ms/epoch - 17ms/step Epoch 192/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9485 - 705ms/epoch - 17ms/step Epoch 193/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9413 - 705ms/epoch - 17ms/step Epoch 194/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9438 - 686ms/epoch - 17ms/step Epoch 195/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9475 - 702ms/epoch - 17ms/step Epoch 196/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9418 - 678ms/epoch - 17ms/step Epoch 197/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9463 - 688ms/epoch - 17ms/step Epoch 198/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9517 - 767ms/epoch - 19ms/step Epoch 199/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9450 - 688ms/epoch - 17ms/step Epoch 200/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9443 - 687ms/epoch - 17ms/step Epoch 201/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9480 - 674ms/epoch - 16ms/step Epoch 202/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9426 - 668ms/epoch - 16ms/step Epoch 203/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9468 - 651ms/epoch - 16ms/step Epoch 204/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9438 - 653ms/epoch - 16ms/step Epoch 205/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9460 - 636ms/epoch - 16ms/step Epoch 206/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9431 - 628ms/epoch - 15ms/step Epoch 207/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9428 - 631ms/epoch - 15ms/step Epoch 208/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9480 - 627ms/epoch - 15ms/step Epoch 209/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9465 - 637ms/epoch - 16ms/step Epoch 210/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9418 - 634ms/epoch - 15ms/step Epoch 211/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9475 - 613ms/epoch - 15ms/step Epoch 212/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9413 - 628ms/epoch - 15ms/step Epoch 213/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9478 - 632ms/epoch - 15ms/step Epoch 214/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9431 - 648ms/epoch - 16ms/step Epoch 215/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9465 - 642ms/epoch - 16ms/step Epoch 216/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9488 - 626ms/epoch - 15ms/step Epoch 217/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9500 - 630ms/epoch - 15ms/step Epoch 218/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9458 - 639ms/epoch - 16ms/step Epoch 219/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9446 - 621ms/epoch - 15ms/step Epoch 220/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9448 - 631ms/epoch - 15ms/step Epoch 221/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9428 - 626ms/epoch - 15ms/step Epoch 222/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9446 - 641ms/epoch - 16ms/step Epoch 223/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9478 - 637ms/epoch - 16ms/step Epoch 224/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9493 - 656ms/epoch - 16ms/step Epoch 225/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9450 - 674ms/epoch - 16ms/step Epoch 226/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9428 - 637ms/epoch - 16ms/step Epoch 227/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9396 - 627ms/epoch - 15ms/step Epoch 228/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9455 - 636ms/epoch - 16ms/step Epoch 229/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9458 - 631ms/epoch - 15ms/step Epoch 230/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9507 - 644ms/epoch - 16ms/step Epoch 231/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9443 - 651ms/epoch - 16ms/step Epoch 232/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9416 - 649ms/epoch - 16ms/step Epoch 233/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9480 - 623ms/epoch - 15ms/step Epoch 234/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9475 - 633ms/epoch - 15ms/step Epoch 235/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9468 - 625ms/epoch - 15ms/step Epoch 236/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9483 - 637ms/epoch - 16ms/step Epoch 237/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9446 - 674ms/epoch - 16ms/step Epoch 238/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9470 - 621ms/epoch - 15ms/step Epoch 239/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9488 - 642ms/epoch - 16ms/step Epoch 240/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9478 - 644ms/epoch - 16ms/step Epoch 241/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9448 - 640ms/epoch - 16ms/step Epoch 242/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9485 - 639ms/epoch - 16ms/step Epoch 243/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9488 - 642ms/epoch - 16ms/step Epoch 244/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9436 - 627ms/epoch - 15ms/step Epoch 245/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9408 - 628ms/epoch - 15ms/step Epoch 246/300 41/41 - 1s - loss: 0.0051 - accuracy: 0.9441 - 640ms/epoch - 16ms/step Epoch 247/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9493 - 627ms/epoch - 15ms/step Epoch 248/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9500 - 627ms/epoch - 15ms/step Epoch 249/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9386 - 626ms/epoch - 15ms/step Epoch 250/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9426 - 631ms/epoch - 15ms/step Epoch 251/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9453 - 627ms/epoch - 15ms/step Epoch 252/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9448 - 616ms/epoch - 15ms/step Epoch 253/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9443 - 629ms/epoch - 15ms/step Epoch 254/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9376 - 622ms/epoch - 15ms/step Epoch 255/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9515 - 630ms/epoch - 15ms/step Epoch 256/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9483 - 638ms/epoch - 16ms/step Epoch 257/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9535 - 622ms/epoch - 15ms/step Epoch 258/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9522 - 626ms/epoch - 15ms/step Epoch 259/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9483 - 627ms/epoch - 15ms/step Epoch 260/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9441 - 618ms/epoch - 15ms/step Epoch 261/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9490 - 642ms/epoch - 16ms/step Epoch 262/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9490 - 639ms/epoch - 16ms/step Epoch 263/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9468 - 625ms/epoch - 15ms/step Epoch 264/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9478 - 628ms/epoch - 15ms/step Epoch 265/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9446 - 625ms/epoch - 15ms/step Epoch 266/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9465 - 622ms/epoch - 15ms/step Epoch 267/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9438 - 619ms/epoch - 15ms/step Epoch 268/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9470 - 629ms/epoch - 15ms/step Epoch 269/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9517 - 637ms/epoch - 16ms/step Epoch 270/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9438 - 619ms/epoch - 15ms/step Epoch 271/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9483 - 631ms/epoch - 15ms/step Epoch 272/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9421 - 649ms/epoch - 16ms/step Epoch 273/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9436 - 662ms/epoch - 16ms/step Epoch 274/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9436 - 633ms/epoch - 15ms/step Epoch 275/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9465 - 635ms/epoch - 15ms/step Epoch 276/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9443 - 620ms/epoch - 15ms/step Epoch 277/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9498 - 672ms/epoch - 16ms/step Epoch 278/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9446 - 649ms/epoch - 16ms/step Epoch 279/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9450 - 630ms/epoch - 15ms/step Epoch 280/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9431 - 629ms/epoch - 15ms/step Epoch 281/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9443 - 632ms/epoch - 15ms/step Epoch 282/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9530 - 634ms/epoch - 15ms/step Epoch 283/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9416 - 633ms/epoch - 15ms/step Epoch 284/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9465 - 620ms/epoch - 15ms/step Epoch 285/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9458 - 627ms/epoch - 15ms/step Epoch 286/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9460 - 623ms/epoch - 15ms/step Epoch 287/300 41/41 - 1s - loss: 0.0050 - accuracy: 0.9473 - 636ms/epoch - 16ms/step Epoch 288/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9433 - 640ms/epoch - 16ms/step Epoch 289/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9455 - 627ms/epoch - 15ms/step Epoch 290/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9453 - 631ms/epoch - 15ms/step Epoch 291/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9463 - 650ms/epoch - 16ms/step Epoch 292/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9483 - 619ms/epoch - 15ms/step Epoch 293/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9490 - 624ms/epoch - 15ms/step Epoch 294/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9453 - 644ms/epoch - 16ms/step Epoch 295/300 41/41 - 1s - loss: 0.0048 - accuracy: 0.9460 - 628ms/epoch - 15ms/step Epoch 296/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9455 - 636ms/epoch - 16ms/step Epoch 297/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9510 - 630ms/epoch - 15ms/step Epoch 298/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9460 - 630ms/epoch - 15ms/step Epoch 299/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9441 - 634ms/epoch - 15ms/step Epoch 300/300 41/41 - 1s - loss: 0.0049 - accuracy: 0.9525 - 622ms/epoch - 15ms/step
<keras.callbacks.History at 0x7faa82146350>
to_predict = df.tail(8)
to_predict.drop([to_predict.index[-1]],axis=0, inplace=True)
to_predict
/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py:4913: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy errors=errors, 
to_predict = np.array(to_predict)
to_predict
array([[ 1, 14, 15, 17, 28, 37], [ 3, 13, 21, 24, 27, 35], [17, 19, 21, 23, 25, 34], [ 9, 16, 17, 21, 26, 29], [ 1, 4, 5, 24, 31, 32], [ 1, 8, 18, 25, 29, 30], [ 3, 4, 5, 15, 24, 33]])
scaled_to_predict = scaler.transform(to_predict)

y_pred = model.predict(np.array([scaled_to_predict]))
print("The predicted numbers in the last lottery game are:", scaler.inverse_transform(y_pred).astype(int)[0])
The predicted numbers in the last lottery game are: [ 5 9 12 20 23 35] 
prediction = df.tail(1)
prediction = np.array(prediction)
print("The actual numbers in the last lottery game were:", prediction[0])
The actual numbers in the last lottery game were: [ 6 10 13 20 23 35]