<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0">
<channel>
<title>Ask Ghassem - Recent questions tagged lstm</title>
<link>https://ask.ghassem.com/tag/lstm</link>
<description>Powered by Question2Answer</description>
<item>
<title>is impossible predict hours time series to minutes time series?</title>
<link>https://ask.ghassem.com/625/is-impossible-predict-hours-time-series-minutes-time-series</link>
<description>&lt;p&gt;&lt;a rel=&quot;nofollow&quot; href=&quot;https://stackoverflow.com/questions/55930051/is-impossible-predict-hours-time-series-to-minutes-time-series&quot;&gt;https://stackoverflow.com/questions/55930051/is-impossible-predict-hours-time-series-to-minutes-time-series&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;
&lt;p&gt;i want to this hours time series predict model to minute predict model&lt;/p&gt;</description>
<category>Deep Learning</category>
<guid isPermaLink="true">https://ask.ghassem.com/625/is-impossible-predict-hours-time-series-minutes-time-series</guid>
<pubDate>Wed, 01 May 2019 13:11:26 +0000</pubDate>
</item>
<item>
<title>model.predict is abnormal</title>
<link>https://ask.ghassem.com/590/model-predict-is-abnormal</link>
<description>&lt;p&gt;the code is&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;
&lt;pre&gt;
import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
from keras.layers.core import Dense, Activation, Dropout
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

def create_dataset(signal_data, look_back=1):
dataX, dataY = [], []
for i in range(len(signal_data) - look_back):
dataX.append(signal_data[i:(i + look_back), 0])
dataY.append(signal_data[i + look_back, 0])
return np.array(dataX), np.array(dataY)



look_back = 10

# 1. 데이터셋 생성하기
#signal_data = np.cos(np.arange(1600) * (20 * np.pi / 1000))[:, None]
df = pd.read_csv(&#039;test.csv&#039;)
signal_data = df.Close.values.astype(&#039;float32&#039;)
signal_data = signal_data.reshape(len(df), 1)

train_size = int(len(signal_data) * 0.80)
test_size = len(signal_data) - train_size
train, test = signal_data[0:train_size,:], signal_data[train_size:len(signal_data),:]

trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = np.reshape(testX, (testX.shape[0], testX.shape[1], 1 ))

model = Sequential()
model.add(LSTM(32, input_shape=(look_back, 1)))
model.add(Dropout(0.3))
model.add(Dense(1))

# 3. 모델 학습과정 설정하기
model.compile(loss=&#039;mean_squared_error&#039;, optimizer=&#039;adam&#039;)

# 4. 모델 학습시키기
hist = model.fit(trainX, trainY, epochs=10, batch_size=16)
plt.plot(testY)

p = model.predict(testX)
plt.plot(testY)
plt.plot(p)
plt.legend([&#039;testY&#039;, &#039;p&#039;], loc=&#039;upper right&#039;)
plt.show()
&lt;/pre&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;
&lt;p&gt;and test.csv is&lt;/p&gt;

&lt;p&gt;&lt;a rel=&quot;nofollow&quot; href=&quot;https://i.redd.it/qb3xjg1ff8n21.png&quot; target=&quot;_blank&quot;&gt;&lt;img alt=&quot;&quot; src=&quot;https://i.redd.it/qb3xjg1ff8n21.png&quot;&gt;&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;then&lt;/p&gt;

&lt;p&gt;i got&lt;/p&gt;

&lt;p&gt;&lt;a rel=&quot;nofollow&quot; href=&quot;https://i.redd.it/w4et2pqxe8n21.png&quot; target=&quot;_blank&quot;&gt;&lt;img alt=&quot;&quot; src=&quot;https://i.redd.it/w4et2pqxe8n21.png&quot;&gt;&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;i don&#039;t know what am i wrong...&lt;/p&gt;

&lt;p&gt;help me plz&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;
&lt;p&gt;test.csv is&amp;nbsp;&lt;a rel=&quot;nofollow&quot; href=&quot;https://docs.google.com/spreadsheets/d/13kvyiD7MRsneTiFv3Y6N2fWOPkI-VQ8XdK66fxB026Y/edit?usp=sharing&quot;&gt;https://docs.google.com/spreadsheets/d/13kvyiD7MRsneTiFv3Y6N2fWOPkI-VQ8XdK66fxB026Y/edit?usp=sharing&lt;/a&gt;&lt;/p&gt;</description>
<category>Machine Learning</category>
<guid isPermaLink="true">https://ask.ghassem.com/590/model-predict-is-abnormal</guid>
<pubDate>Wed, 20 Mar 2019 09:51:59 +0000</pubDate>
</item>
</channel>
</rss>