【资金流入流出预测】baseline LSTM

最新推荐文章于 2024-01-18 19:58:55 发布

我叫陈叉叉叉叉

最新推荐文章于 2024-01-18 19:58:55 发布

阅读量857

点赞数

CC 4.0 BY-SA版权

分类专栏：数据挖掘-资金流入流出

本文链接：https://blog.youkuaiyun.com/wwqnmdhmp/article/details/108109202

数据挖掘-资金流入流出专栏收录该内容

3 篇文章

订阅专栏

import pandas as pd 
from sklearn.preprocessing import MinMaxScaler
import numpy as np

data = pd.read_csv('user_balance_table.csv')
data_1 = data.loc[:,['user_id','report_date','total_purchase_amt','total_redeem_amt']]
data_1 = data_1.groupby(by='report_date').sum()
data_1.reset_index(inplace=True)
data_1['date'] = pd.to_datetime(data_1['report_date'],format='%Y%m%d')
data = data_1[data_1['date'] >pd.to_datetime('2014-4-1')]

mm = MinMaxScaler()
data = mm.fit_transform(data.iloc[:,2:-1])

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\preprocessing\data.py:334: DataConversionWarning: Data with input dtype int64 were all converted to float64 by MinMaxScaler.
  return self.partial_fit(X, y)

def create_data(amt):
    mid_time = 50
    d = []
    for i in range(len(amt)-mid_time):
        x = amt[i:51+i]
        d.append((x.tolist()))
    amt_np = pd.DataFrame(d).values
    amt_np = amt_np.reshape((102,51,1))
    X_train ,y_train = amt_np[:,:50],amt_np[:,-1]
    return X_train,y_train

amt = data[:,0]
X_train,y_train = create_data(amt)

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-38-0ec22a5a2c78> in <module>
      1 amt = data[:,0]
----> 2 X_train,y_train = create_data(amt)


<ipython-input-15-10ca421a65bc> in create_data(amt)
      6         d.append((x.tolist()))
      7     amt_np = pd.DataFrame(d).values
----> 8     amt_np = amt_np.reshape((102,51,1))
      9     X_train ,y_train = amt_np[:,:50],amt_np[:,-1]
     10     return X_train,y_train


ValueError: cannot reshape array of size 0 into shape (102,51,1)

from keras.models import Sequential
from keras.layers import LSTM, TimeDistributed, Dense, Activation
from keras.optimizers import Adam

Using TensorFlow backend.

def create_model():
    model = Sequential()
    model.add(LSTM(units=256,input_shape=(None,1),return_sequences=True))
    model.add(LSTM(units=256))
    model.add(Dense(units=1))
    model.add(Activation('linear'))
    model.compile(loss='mse',optimizer='adam')
    return model

model = create_model()

model.fit(X_train, y_train, batch_size=20,epochs=100,validation_split=0.1)

WARNING:tensorflow:From C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.

Train on 91 samples, validate on 11 samples
Epoch 1/100
91/91 [==============================] - 3s 36ms/step - loss: 0.0927 - val_loss: 0.0359
Epoch 2/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0535 - val_loss: 0.0361
Epoch 3/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0550 - val_loss: 0.0367
Epoch 4/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0542 - val_loss: 0.0373
Epoch 5/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0514 - val_loss: 0.0364
Epoch 6/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0582 - val_loss: 0.0354
Epoch 7/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0557 - val_loss: 0.0386
Epoch 8/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0539 - val_loss: 0.0353
Epoch 9/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0510 - val_loss: 0.0362
Epoch 10/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0520 - val_loss: 0.0359
Epoch 11/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0503 - val_loss: 0.0342
Epoch 12/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0505 - val_loss: 0.0353
Epoch 13/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0508 - val_loss: 0.0336
Epoch 14/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0530 - val_loss: 0.0338
Epoch 15/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0495 - val_loss: 0.0376
Epoch 16/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0510 - val_loss: 0.0346
Epoch 17/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0490 - val_loss: 0.0332
Epoch 18/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0496 - val_loss: 0.0343
Epoch 19/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0519 - val_loss: 0.0345
Epoch 20/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0524 - val_loss: 0.0328
Epoch 21/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0511 - val_loss: 0.0374
Epoch 22/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0493 - val_loss: 0.0323
Epoch 23/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0489 - val_loss: 0.0322
Epoch 24/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0478 - val_loss: 0.0348
Epoch 25/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0475 - val_loss: 0.0323
Epoch 26/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0468 - val_loss: 0.0317
Epoch 27/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0478 - val_loss: 0.0313
Epoch 28/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0483 - val_loss: 0.0322
Epoch 29/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0504 - val_loss: 0.0313
Epoch 30/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0499 - val_loss: 0.0307
Epoch 31/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0482 - val_loss: 0.0333
Epoch 32/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0471 - val_loss: 0.0296
Epoch 33/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0452 - val_loss: 0.0287
Epoch 34/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0442 - val_loss: 0.0310
Epoch 35/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0449 - val_loss: 0.0274
Epoch 36/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0451 - val_loss: 0.0281
Epoch 37/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0451 - val_loss: 0.0239
Epoch 38/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0442 - val_loss: 0.0267
Epoch 39/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0394 - val_loss: 0.0215
Epoch 40/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0393 - val_loss: 0.0202
Epoch 41/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0361 - val_loss: 0.0210
Epoch 42/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0356 - val_loss: 0.0199
Epoch 43/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0343 - val_loss: 0.0210
Epoch 44/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0331 - val_loss: 0.0199
Epoch 45/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0326 - val_loss: 0.0208
Epoch 46/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0329 - val_loss: 0.0223
Epoch 47/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0315 - val_loss: 0.0195
Epoch 48/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0331 - val_loss: 0.0193
Epoch 49/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0355 - val_loss: 0.0247
Epoch 50/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0359 - val_loss: 0.0225
Epoch 51/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0336 - val_loss: 0.0207
Epoch 52/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0311 - val_loss: 0.0198
Epoch 53/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0305 - val_loss: 0.0197
Epoch 54/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0291 - val_loss: 0.0197
Epoch 55/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0281 - val_loss: 0.0196
Epoch 56/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0304 - val_loss: 0.0186
Epoch 57/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0304 - val_loss: 0.0215
Epoch 58/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0300 - val_loss: 0.0203
Epoch 59/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0272 - val_loss: 0.0187
Epoch 60/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0281 - val_loss: 0.0221
Epoch 61/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0262 - val_loss: 0.0191
Epoch 62/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0275 - val_loss: 0.0188
Epoch 63/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0247 - val_loss: 0.0196
Epoch 64/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0253 - val_loss: 0.0177
Epoch 65/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0234 - val_loss: 0.0172
Epoch 66/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0248 - val_loss: 0.0206
Epoch 67/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0277 - val_loss: 0.0183
Epoch 68/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0340 - val_loss: 0.0175
Epoch 69/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0248 - val_loss: 0.0419
Epoch 70/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0324 - val_loss: 0.0260
Epoch 71/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0348 - val_loss: 0.0230
Epoch 72/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0279 - val_loss: 0.0228
Epoch 73/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0271 - val_loss: 0.0205
Epoch 74/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0266 - val_loss: 0.0190
Epoch 75/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0253 - val_loss: 0.0238
Epoch 76/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0269 - val_loss: 0.0189
Epoch 77/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0264 - val_loss: 0.0207
Epoch 78/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0258 - val_loss: 0.0197
Epoch 79/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0248 - val_loss: 0.0212
Epoch 80/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0259 - val_loss: 0.0213
Epoch 81/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0281 - val_loss: 0.0180
Epoch 82/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0306 - val_loss: 0.0215
Epoch 83/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0229 - val_loss: 0.0169
Epoch 84/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0277 - val_loss: 0.0204
Epoch 85/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0265 - val_loss: 0.0204
Epoch 86/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0228 - val_loss: 0.0158
Epoch 87/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0229 - val_loss: 0.0232
Epoch 88/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0241 - val_loss: 0.0164
Epoch 89/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0258 - val_loss: 0.0194
Epoch 90/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0237 - val_loss: 0.0168
Epoch 91/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0213 - val_loss: 0.0170
Epoch 92/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0227 - val_loss: 0.0188
Epoch 93/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0216 - val_loss: 0.0181
Epoch 94/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0230 - val_loss: 0.0208
Epoch 95/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0230 - val_loss: 0.0233
Epoch 96/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0238 - val_loss: 0.0164
Epoch 97/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0233 - val_loss: 0.0218
Epoch 98/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0245 - val_loss: 0.0183
Epoch 99/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0239 - val_loss: 0.0173
Epoch 100/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0217 - val_loss: 0.0172





<keras.callbacks.callbacks.History at 0x2469b951208>

import matplotlib.pyplot as plt
%matplotlib inline
plt.plot(model.predict(X_train))
plt.plot(y_train)

[<matplotlib.lines.Line2D at 0x246badad400>]

在这里插入图片描述

X_test = X_train[-1:,]
for i in range (30):
    pre = model.predict(data)
    X_test = np.append(data,pre).reshape(1,-1,1)[:,-50:]

pre = data[:,-30:]

result = pd.DataFrame(pre.reshape(-1,1))

amt = data[:,1]
X_train,y_train = create_data(amt)

model.fit(X_train, y_train, batch_size=20,epochs=100,validation_split=0.1)

Train on 91 samples, validate on 11 samples
Epoch 1/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0420 - val_loss: 0.0217
Epoch 2/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0333 - val_loss: 0.0275
Epoch 3/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0326 - val_loss: 0.0266
Epoch 4/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0300 - val_loss: 0.0250
Epoch 5/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0294 - val_loss: 0.0213
Epoch 6/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0256 - val_loss: 0.0267
Epoch 7/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0312 - val_loss: 0.0229
Epoch 8/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0271 - val_loss: 0.0246
Epoch 9/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0275 - val_loss: 0.0232
Epoch 10/100
91/91 [==============================] - 1s 13ms/step - loss: 0.0283 - val_loss: 0.0187
Epoch 11/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0240 - val_loss: 0.0251
Epoch 12/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0269 - val_loss: 0.0238
Epoch 13/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0235 - val_loss: 0.0192
Epoch 14/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0261 - val_loss: 0.0215
Epoch 15/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0246 - val_loss: 0.0231
Epoch 16/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0234 - val_loss: 0.0194
Epoch 17/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0228 - val_loss: 0.0192
Epoch 18/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0234 - val_loss: 0.0201
Epoch 19/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0241 - val_loss: 0.0198
Epoch 20/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0250 - val_loss: 0.0207
Epoch 21/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0238 - val_loss: 0.0262
Epoch 22/100
91/91 [==============================] - 2s 27ms/step - loss: 0.0269 - val_loss: 0.0206
Epoch 23/100
91/91 [==============================] - 2s 20ms/step - loss: 0.0252 - val_loss: 0.0180
Epoch 24/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0201 - val_loss: 0.0269
Epoch 25/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0246 - val_loss: 0.0229
Epoch 26/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0221 - val_loss: 0.0204
Epoch 27/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0250 - val_loss: 0.0240
Epoch 28/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0228 - val_loss: 0.0250
Epoch 29/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0245 - val_loss: 0.0205
Epoch 30/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0209 - val_loss: 0.0220
Epoch 31/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0227 - val_loss: 0.0231
Epoch 32/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0229 - val_loss: 0.0268
Epoch 33/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0240 - val_loss: 0.0202
Epoch 34/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0221 - val_loss: 0.0249
Epoch 35/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0224 - val_loss: 0.0218
Epoch 36/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0217 - val_loss: 0.0193
Epoch 37/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0196 - val_loss: 0.0242
Epoch 38/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0214 - val_loss: 0.0224
Epoch 39/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0219 - val_loss: 0.0254
Epoch 40/100
91/91 [==============================] - 2s 19ms/step - loss: 0.0188 - val_loss: 0.0237
Epoch 41/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0180 - val_loss: 0.0222
Epoch 42/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0211 - val_loss: 0.0279
Epoch 43/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0199 - val_loss: 0.0256
Epoch 44/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0218 - val_loss: 0.0240
Epoch 45/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0196 - val_loss: 0.0211
Epoch 46/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0216 - val_loss: 0.0265
Epoch 47/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0187 - val_loss: 0.0253
Epoch 48/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0176 - val_loss: 0.0246
Epoch 49/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0170 - val_loss: 0.0274
Epoch 50/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0196 - val_loss: 0.0272
Epoch 51/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0231 - val_loss: 0.0238
Epoch 52/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0193 - val_loss: 0.0223
Epoch 53/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0298 - val_loss: 0.0241
Epoch 54/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0289 - val_loss: 0.0246
Epoch 55/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0292 - val_loss: 0.0247
Epoch 56/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0270 - val_loss: 0.0214
Epoch 57/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0229 - val_loss: 0.0197
Epoch 58/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0223 - val_loss: 0.0208
Epoch 59/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0187 - val_loss: 0.0229
Epoch 60/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0180 - val_loss: 0.0214
Epoch 61/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0203 - val_loss: 0.0228
Epoch 62/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0193 - val_loss: 0.0215
Epoch 63/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0173 - val_loss: 0.0273
Epoch 64/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0185 - val_loss: 0.0232
Epoch 65/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0188 - val_loss: 0.0211
Epoch 66/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0156 - val_loss: 0.0256
Epoch 67/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0157 - val_loss: 0.0234
Epoch 68/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0142 - val_loss: 0.0233
Epoch 69/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0161 - val_loss: 0.0252
Epoch 70/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0169 - val_loss: 0.0245
Epoch 71/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0150 - val_loss: 0.0271
Epoch 72/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0146 - val_loss: 0.0254
Epoch 73/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0150 - val_loss: 0.0268
Epoch 74/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0144 - val_loss: 0.0284
Epoch 75/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0134 - val_loss: 0.0296
Epoch 76/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0137 - val_loss: 0.0312
Epoch 77/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0148 - val_loss: 0.0279
Epoch 78/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0136 - val_loss: 0.0307
Epoch 79/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0153 - val_loss: 0.0283
Epoch 80/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0163 - val_loss: 0.0269
Epoch 81/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0148 - val_loss: 0.0299
Epoch 82/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0159 - val_loss: 0.0357
Epoch 83/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0157 - val_loss: 0.0307
Epoch 84/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0146 - val_loss: 0.0310
Epoch 85/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0137 - val_loss: 0.0322
Epoch 86/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0143 - val_loss: 0.0335
Epoch 87/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0131 - val_loss: 0.0321
Epoch 88/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0130 - val_loss: 0.0320
Epoch 89/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0132 - val_loss: 0.0348
Epoch 90/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0130 - val_loss: 0.0339
Epoch 91/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0145 - val_loss: 0.0317
Epoch 92/100
91/91 [==============================] - 2s 17ms/step - loss: 0.0112 - val_loss: 0.0383
Epoch 93/100
91/91 [==============================] - 2s 17ms/step - loss: 0.0120 - val_loss: 0.0357
Epoch 94/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0119 - val_loss: 0.0333
Epoch 95/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0129 - val_loss: 0.0350
Epoch 96/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0112 - val_loss: 0.0350
Epoch 97/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0120 - val_loss: 0.0323
Epoch 98/100
91/91 [==============================] - 1s 15ms/step - loss: 0.0111 - val_loss: 0.0334
Epoch 99/100
91/91 [==============================] - 1s 16ms/step - loss: 0.0133 - val_loss: 0.0308
Epoch 100/100
91/91 [==============================] - 1s 14ms/step - loss: 0.0108 - val_loss: 0.0327





<keras.callbacks.callbacks.History at 0x246c082e240>

import matplotlib.pyplot as plt
%matplotlib inline
plt.plot(model.predict(X_train))
plt.plot(y_train)

[<matplotlib.lines.Line2D at 0x246a0ec0630>]

在这里插入图片描述

X_test = X_train[-1:,]
for i in range (30):
    pre = model.predict(X_test)
    X_test = np.append(X_test,pre).reshape(1,-1,1)[:,-50:]

pre = X_test[:,-30:]

pre.reshape(-1,1)

array([[0.24009244],
       [0.46256679],
       [0.3980996 ],
       [0.33408886],
       [0.34861782],
       [0.3172265 ],
       [0.1568431 ],
       [0.06636516],
       [0.26820928],
       [0.36100432],
       [0.37124538],
       [0.43884429],
       [0.36251831],
       [0.13016453],
       [0.20833002],
       [0.69800997],
       [0.54660499],
       [0.36590093],
       [0.32258973],
       [0.31631702],
       [0.27021858],
       [0.24749132],
       [0.44507599],
       [0.60718513],
       [0.63579643],
       [0.56474674],
       [0.46380192],
       [0.30990487],
       [0.29024073],
       [0.49912572]])

result['1'] = pre.reshape(-1,1)

pd.DataFrame(mm.inverse_transform(result)).to_csv('result.csv')