Skip to content

Instantly share code, notes, and snippets.

@muhammed-kizilkaya

muhammed-kizilkaya/lstm_eeg.ipynb

Created June 15, 2021 11:47
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save muhammed-kizilkaya/9797bd25a28bb2e569dd897868d3241c to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save muhammed-kizilkaya/9797bd25a28bb2e569dd897868d3241c to your computer and use it in GitHub Desktop.
Download ZIP
LSTM_EEG.ipynb
Display the source blob
Display the rendered blob
Raw
lstm_eeg.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "LSTM_EEG.ipynb",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/muhammed-bayat/9797bd25a28bb2e569dd897868d3241c/lstm_eeg.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "QVkjoVU_uDK3",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "06377749-9b26-4e5b-8e99-fe5d579e4ac7"
},
"source": [
"pip install git+https://github.com/forrestbao/pyeeg.git"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting git+https://github.com/forrestbao/pyeeg.git\n",
" Cloning https://github.com/forrestbao/pyeeg.git to /tmp/pip-req-build-zxck6gwi\n",
" Running command git clone -q https://github.com/forrestbao/pyeeg.git /tmp/pip-req-build-zxck6gwi\n",
"Requirement already satisfied: numpy>=1.9.2 in /usr/local/lib/python3.7/dist-packages (from pyeeg==0.4.4) (1.19.5)\n",
"Building wheels for collected packages: pyeeg\n",
" Building wheel for pyeeg (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for pyeeg: filename=pyeeg-0.4.4-py2.py3-none-any.whl size=28133 sha256=6c9ebddcdedb39d0cf1936b61e3201e0e5c53b36f3200b2bf27cc9024b9fe930\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-4dnq2c_i/wheels/2d/3f/ad/106d4fc80b61d1ea1fc18e76e7439fd98aa043d83d58eae741\n",
"Successfully built pyeeg\n",
"Installing collected packages: pyeeg\n",
"Successfully installed pyeeg-0.4.4\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "5SPLfnVBY6LY"
},
"source": [
" import numpy as np\n",
"\n",
"import pickle as pickle\n",
"import pandas as pd\n",
"import pyeeg as pe"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "ez3vH_wWgM_p"
},
"source": [
"Her biri 40 müzik videosu izleyen 32 katılımcının EEG ve çevresel fizyolojik sinyalleri kaydedildi. Katılımcılar her videoyu uyarılma, değerlik, baskınlık ve beğeni düzeyleri açısından derecelendirdi. Veriler alt örneklendi (128 Hz'e kadar), önceden işlendi ve pickle Python formatlarında bölümlere ayrıldı."
]
},
{
"cell_type": "code",
"metadata": {
"id": "iq8EcwGxsgw4"
},
"source": [
"channel = [1,2,3,4,6,11,13,17,19,20,21,25,29,31] #14 Channels \n",
"band = [4,8,12,16,25,45] #5 bands\n",
"window_size = 256 #Averaging band power of 2 sec\n",
"step_size = 16 #Each 0.125 sec update once\n",
"sample_rate = 128 #Sampling rate of 128 Hz\n",
"## Load only 22/32 participants with frontal videos recorded\n",
"subjectList = ['01', '02', '03']\n",
"#List of subjects"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "K0dknWjUVpA-",
"outputId": "ba054316-1e59-4009-e8fd-a08c02a3faad"
},
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive/')"
],
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"text": [
"Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.activity.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fexperimentsandconfigs%20https%3a%2f%2fwww.googleapis.com%2fauth%2fphotos.native&response_type=code\n",
"\n",
"Enter your authorization code:\n",
"4/1AY0e-g4nj09snZnoxn95zVBO5CVt4Fx34_JbNRb2wepveBaaeZF0BLFQvMM\n",
"Mounted at /content/drive/\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "PLMSKXbch6TX"
},
"source": [
"from sklearn.preprocessing import normalize\n"
],
"execution_count": 8,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "BMHsERGylAEu"
},
"source": [
"def FFT_Processing (sub, channel, band, window_size, step_size, sample_rate):\n",
" '''\n",
" arguments: string subject\n",
" list channel indice\n",
" list band\n",
" int window size for FFT\n",
" int step size for FFT\n",
" int sample rate for FFT\n",
" return: void\n",
" '''\n",
" meta = []\n",
" with open('/content/drive/MyDrive/DEAP TEST CODE /data/s' + sub + '.dat', 'rb') as file:\n",
"\n",
" subject = pickle.load(file, encoding='latin1') #resolve the python 2 data problem by encoding : latin1\n",
"\n",
" for i in range (0,40):\n",
" # loop over 0-39 trails\n",
" data = subject[\"data\"][i]\n",
" labels = subject[\"labels\"][i]\n",
" start = 0;\n",
"\n",
" while start + window_size < data.shape[1]:\n",
" meta_array = []\n",
" meta_data = [] #meta vector for analysis\n",
" for j in channel:\n",
" X = data[j][start : start + window_size] #Slice raw data over 2 sec, at interval of 0.125 sec\n",
" Y = pe.bin_power(X, band, sample_rate) #FFT over 2 sec of channel j, in seq of theta, alpha, low beta, high beta, gamma\n",
" meta_data = meta_data + list(Y[0])\n",
"\n",
" meta_array.append(np.array(meta_data))\n",
" meta_array.append(labels)\n",
"\n",
" meta.append(np.array(meta_array)) \n",
" start = start + step_size\n",
" \n",
" meta = np.array(meta)\n",
" np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\s' + sub, meta, allow_pickle=True, fix_imports=True)\n",
"\n"
],
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "VzAJVGQBt-5v",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "23195af0-4798-481e-c6d0-0f3cd07bc8b9"
},
"source": [
"for subjects in subjectList:\n",
" FFT_Processing (subjects, channel, band, window_size, step_size, sample_rate)"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:33: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "uZGXiP2t2DFC",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 107
},
"outputId": "a668706f-0b2a-49e4-88f7-75e101ed2629"
},
"source": [
"\n",
"data_training = []\n",
"label_training = []\n",
"data_testing = []\n",
"label_testing = []\n",
"data_validation = []\n",
"label_validation = []\n",
"\n",
"for subjects in subjectList:\n",
" \n",
"\n",
" with open('/content/drive/MyDrive/DEAP TEST CODE /save\\s' + subjects + '.npy', 'rb') as file:\n",
" sub = np.load(file,allow_pickle=True)\n",
" for i in range (0,sub.shape[0]):\n",
" if i % 8 == 0:\n",
" data_testing.append(sub[i][0])\n",
" label_testing.append(sub[i][1])\n",
" \n",
" else:\n",
" data_training.append(sub[i][0])\n",
" label_training.append(sub[i][1])\n",
"\n",
"np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\data_training', np.array(data_training), allow_pickle=True, fix_imports=True)\n",
"np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\label_training', np.array(label_training), allow_pickle=True, fix_imports=True)\n",
"print(\"training dataset:\", np.array(data_training).shape, np.array(label_training).shape)\n",
"\n",
"\n",
"np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\data_testing', np.array(data_testing), allow_pickle=True, fix_imports=True)\n",
"np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\label_testing', np.array(label_testing), allow_pickle=True, fix_imports=True)\n",
"print(\"testing dataset:\", np.array(data_testing).shape, np.array(label_testing).shape)\n",
"\"\"\"\n",
"np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\data_validation', np.array(data_validation), allow_pickle=True, fix_imports=True)\n",
"np.save('/content/drive/MyDrive/DEAP TEST CODE /save\\label_validation', np.array(label_validation), allow_pickle=True, fix_imports=True)\n",
"print(\"validation dataset:\", np.array(data_validation).shape, np.array(label_validation).shape)\n",
"\"\"\""
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"training dataset: (51240, 70) (51240, 4)\n",
"testing dataset: (7320, 70) (7320, 4)\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
},
"text/plain": [
"'\\nnp.save(\\'/content/drive/MyDrive/DEAP TEST CODE /save\\\\data_validation\\', np.array(data_validation), allow_pickle=True, fix_imports=True)\\nnp.save(\\'/content/drive/MyDrive/DEAP TEST CODE /save\\\\label_validation\\', np.array(label_validation), allow_pickle=True, fix_imports=True)\\nprint(\"validation dataset:\", np.array(data_validation).shape, np.array(label_validation).shape)\\n'"
]
},
"metadata": {
"tags": []
},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "CFcayQrJ-h0I"
},
"source": [
"data= []\n",
"label = []\n",
"for subjects in subjectList:\n",
" \n",
"\n",
" with open('/content/drive/MyDrive/DEAP TEST CODE /save\\s' + subjects + '.npy', 'rb') as file:\n",
" sub = np.load(file,allow_pickle=True)\n",
" for i in range (0,sub.shape[0]):\n",
" data.append(sub[i][0])\n",
" label.append(sub[i][1])\n",
"np.save('data', np.array(data), allow_pickle=True, fix_imports=True)\n",
"np.save('label', np.array(label), allow_pickle=True, fix_imports=True)\n",
"\n"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "xBM9U5Kht73H"
},
"source": [
"df=pd.DataFrame(data=data)\n",
"df.to_csv(\"data.csv\",index=False)\n",
"\n",
"df1=pd.DataFrame(data=label)\n",
"df1.to_csv(\"label.csv\",index=False)\n"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "T3nEbmeVBikG"
},
"source": [
"\n",
"data1=pd.read_csv(\"/content/data.csv\")"
],
"execution_count": 14,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "oqaQzAAqBtud",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 444
},
"outputId": "3b7c5661-f4cf-408f-c260-8f8746d59681"
},
"source": [
"data1\n"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" <th>4</th>\n",
" <th>5</th>\n",
" <th>6</th>\n",
" <th>7</th>\n",
" <th>8</th>\n",
" <th>9</th>\n",
" <th>10</th>\n",
" <th>11</th>\n",
" <th>12</th>\n",
" <th>13</th>\n",
" <th>14</th>\n",
" <th>15</th>\n",
" <th>16</th>\n",
" <th>17</th>\n",
" <th>18</th>\n",
" <th>19</th>\n",
" <th>20</th>\n",
" <th>21</th>\n",
" <th>22</th>\n",
" <th>23</th>\n",
" <th>24</th>\n",
" <th>25</th>\n",
" <th>26</th>\n",
" <th>27</th>\n",
" <th>28</th>\n",
" <th>29</th>\n",
" <th>30</th>\n",
" <th>31</th>\n",
" <th>32</th>\n",
" <th>33</th>\n",
" <th>34</th>\n",
" <th>35</th>\n",
" <th>36</th>\n",
" <th>37</th>\n",
" <th>38</th>\n",
" <th>39</th>\n",
" <th>40</th>\n",
" <th>41</th>\n",
" <th>42</th>\n",
" <th>43</th>\n",
" <th>44</th>\n",
" <th>45</th>\n",
" <th>46</th>\n",
" <th>47</th>\n",
" <th>48</th>\n",
" <th>49</th>\n",
" <th>50</th>\n",
" <th>51</th>\n",
" <th>52</th>\n",
" <th>53</th>\n",
" <th>54</th>\n",
" <th>55</th>\n",
" <th>56</th>\n",
" <th>57</th>\n",
" <th>58</th>\n",
" <th>59</th>\n",
" <th>60</th>\n",
" <th>61</th>\n",
" <th>62</th>\n",
" <th>63</th>\n",
" <th>64</th>\n",
" <th>65</th>\n",
" <th>66</th>\n",
" <th>67</th>\n",
" <th>68</th>\n",
" <th>69</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>613.663621</td>\n",
" <td>914.264525</td>\n",
" <td>581.107620</td>\n",
" <td>1325.822606</td>\n",
" <td>1289.397695</td>\n",
" <td>839.213721</td>\n",
" <td>1020.221809</td>\n",
" <td>793.121658</td>\n",
" <td>1395.900243</td>\n",
" <td>1342.071643</td>\n",
" <td>890.226769</td>\n",
" <td>872.670620</td>\n",
" <td>649.000277</td>\n",
" <td>1160.705207</td>\n",
" <td>1055.468213</td>\n",
" <td>468.742832</td>\n",
" <td>767.808561</td>\n",
" <td>652.336315</td>\n",
" <td>909.577165</td>\n",
" <td>940.761742</td>\n",
" <td>754.402536</td>\n",
" <td>1432.087822</td>\n",
" <td>741.796243</td>\n",
" <td>1302.844506</td>\n",
" <td>974.411370</td>\n",
" <td>735.559657</td>\n",
" <td>1080.670160</td>\n",
" <td>709.279217</td>\n",
" <td>1154.020450</td>\n",
" <td>1642.844310</td>\n",
" <td>749.288840</td>\n",
" <td>1272.203633</td>\n",
" <td>599.541204</td>\n",
" <td>1135.773645</td>\n",
" <td>1761.775932</td>\n",
" <td>698.952176</td>\n",
" <td>724.674487</td>\n",
" <td>576.403629</td>\n",
" <td>1528.907210</td>\n",
" <td>1383.738897</td>\n",
" <td>890.303649</td>\n",
" <td>772.307962</td>\n",
" <td>724.554537</td>\n",
" <td>1566.141268</td>\n",
" <td>1292.462292</td>\n",
" <td>488.081594</td>\n",
" <td>997.251733</td>\n",
" <td>619.231972</td>\n",
" <td>1589.994461</td>\n",
" <td>1117.325669</td>\n",
" <td>500.749966</td>\n",
" <td>865.429606</td>\n",
" <td>533.323730</td>\n",
" <td>1371.979017</td>\n",
" <td>1129.393056</td>\n",
" <td>879.299890</td>\n",
" <td>1075.759978</td>\n",
" <td>715.708294</td>\n",
" <td>1501.934331</td>\n",
" <td>1261.149004</td>\n",
" <td>1040.334395</td>\n",
" <td>981.162284</td>\n",
" <td>783.241786</td>\n",
" <td>1227.575104</td>\n",
" <td>1263.204863</td>\n",
" <td>990.496924</td>\n",
" <td>1092.856450</td>\n",
" <td>937.054171</td>\n",
" <td>1249.394169</td>\n",
" <td>1051.721009</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>630.957834</td>\n",
" <td>855.122300</td>\n",
" <td>542.239450</td>\n",
" <td>1315.474230</td>\n",
" <td>1423.398476</td>\n",
" <td>814.348323</td>\n",
" <td>981.989919</td>\n",
" <td>691.537720</td>\n",
" <td>1299.173642</td>\n",
" <td>1397.736807</td>\n",
" <td>874.286869</td>\n",
" <td>803.679423</td>\n",
" <td>642.221040</td>\n",
" <td>1279.849432</td>\n",
" <td>1272.215925</td>\n",
" <td>409.709359</td>\n",
" <td>777.085724</td>\n",
" <td>582.751330</td>\n",
" <td>915.015730</td>\n",
" <td>926.135281</td>\n",
" <td>833.491387</td>\n",
" <td>1420.587771</td>\n",
" <td>781.428715</td>\n",
" <td>1283.356361</td>\n",
" <td>963.997530</td>\n",
" <td>750.579023</td>\n",
" <td>1135.894772</td>\n",
" <td>691.536337</td>\n",
" <td>1275.302319</td>\n",
" <td>1686.349601</td>\n",
" <td>772.415886</td>\n",
" <td>1380.323893</td>\n",
" <td>598.183302</td>\n",
" <td>1205.156108</td>\n",
" <td>1788.325540</td>\n",
" <td>695.817607</td>\n",
" <td>816.915328</td>\n",
" <td>622.665905</td>\n",
" <td>1461.146362</td>\n",
" <td>1416.627659</td>\n",
" <td>847.382668</td>\n",
" <td>846.996614</td>\n",
" <td>768.648277</td>\n",
" <td>1505.093816</td>\n",
" <td>1480.402636</td>\n",
" <td>622.061988</td>\n",
" <td>1020.240735</td>\n",
" <td>659.054210</td>\n",
" <td>1564.755039</td>\n",
" <td>1306.387102</td>\n",
" <td>604.827488</td>\n",
" <td>890.109422</td>\n",
" <td>538.045668</td>\n",
" <td>1343.579960</td>\n",
" <td>1140.542717</td>\n",
" <td>989.936032</td>\n",
" <td>1079.666797</td>\n",
" <td>738.119177</td>\n",
" <td>1414.556063</td>\n",
" <td>1241.151977</td>\n",
" <td>1067.913800</td>\n",
" <td>1035.706019</td>\n",
" <td>751.708067</td>\n",
" <td>1163.560098</td>\n",
" <td>1275.857565</td>\n",
" <td>960.486529</td>\n",
" <td>1096.329289</td>\n",
" <td>864.969378</td>\n",
" <td>1266.382407</td>\n",
" <td>1116.827476</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>669.998695</td>\n",
" <td>931.945086</td>\n",
" <td>599.149975</td>\n",
" <td>1314.559510</td>\n",
" <td>1264.353974</td>\n",
" <td>784.051992</td>\n",
" <td>937.734317</td>\n",
" <td>772.203595</td>\n",
" <td>1229.182154</td>\n",
" <td>1299.614647</td>\n",
" <td>925.468253</td>\n",
" <td>821.075664</td>\n",
" <td>769.610432</td>\n",
" <td>1220.592118</td>\n",
" <td>1074.246999</td>\n",
" <td>404.163680</td>\n",
" <td>680.885885</td>\n",
" <td>662.051356</td>\n",
" <td>827.506783</td>\n",
" <td>890.366925</td>\n",
" <td>874.067250</td>\n",
" <td>1443.024018</td>\n",
" <td>756.060284</td>\n",
" <td>1280.150905</td>\n",
" <td>983.346677</td>\n",
" <td>788.002953</td>\n",
" <td>1109.094870</td>\n",
" <td>672.529295</td>\n",
" <td>1197.685013</td>\n",
" <td>1697.140320</td>\n",
" <td>809.969366</td>\n",
" <td>1416.162713</td>\n",
" <td>565.771959</td>\n",
" <td>1161.236217</td>\n",
" <td>1726.311634</td>\n",
" <td>821.955456</td>\n",
" <td>904.630199</td>\n",
" <td>447.831709</td>\n",
" <td>1505.380963</td>\n",
" <td>1322.568616</td>\n",
" <td>923.233763</td>\n",
" <td>850.382449</td>\n",
" <td>730.986282</td>\n",
" <td>1460.750262</td>\n",
" <td>1269.859693</td>\n",
" <td>746.652042</td>\n",
" <td>1045.931493</td>\n",
" <td>595.349229</td>\n",
" <td>1465.766055</td>\n",
" <td>1161.269824</td>\n",
" <td>633.609655</td>\n",
" <td>872.511839</td>\n",
" <td>534.430652</td>\n",
" <td>1326.410604</td>\n",
" <td>1093.586060</td>\n",
" <td>991.097578</td>\n",
" <td>1087.236191</td>\n",
" <td>718.403704</td>\n",
" <td>1409.660979</td>\n",
" <td>1271.190295</td>\n",
" <td>1011.983315</td>\n",
" <td>905.245619</td>\n",
" <td>850.154988</td>\n",
" <td>1199.205576</td>\n",
" <td>1309.021453</td>\n",
" <td>1059.582178</td>\n",
" <td>1114.917138</td>\n",
" <td>972.796731</td>\n",
" <td>1298.654550</td>\n",
" <td>1047.062139</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>701.677561</td>\n",
" <td>959.023161</td>\n",
" <td>504.419961</td>\n",
" <td>1297.271930</td>\n",
" <td>1157.961176</td>\n",
" <td>726.590780</td>\n",
" <td>960.032416</td>\n",
" <td>612.783460</td>\n",
" <td>1211.140861</td>\n",
" <td>1244.118359</td>\n",
" <td>868.136120</td>\n",
" <td>825.324785</td>\n",
" <td>723.455190</td>\n",
" <td>1227.316054</td>\n",
" <td>1029.469831</td>\n",
" <td>394.244264</td>\n",
" <td>681.455648</td>\n",
" <td>607.480583</td>\n",
" <td>882.498939</td>\n",
" <td>904.584012</td>\n",
" <td>860.611560</td>\n",
" <td>1289.188142</td>\n",
" <td>689.857451</td>\n",
" <td>1320.002300</td>\n",
" <td>895.922258</td>\n",
" <td>729.304091</td>\n",
" <td>1063.806099</td>\n",
" <td>681.675317</td>\n",
" <td>1286.284291</td>\n",
" <td>1681.344923</td>\n",
" <td>837.176540</td>\n",
" <td>1432.926865</td>\n",
" <td>552.172927</td>\n",
" <td>1183.844763</td>\n",
" <td>1451.121614</td>\n",
" <td>824.171161</td>\n",
" <td>895.624556</td>\n",
" <td>447.339781</td>\n",
" <td>1470.414172</td>\n",
" <td>1197.901387</td>\n",
" <td>926.563662</td>\n",
" <td>822.458544</td>\n",
" <td>736.749506</td>\n",
" <td>1442.643272</td>\n",
" <td>1227.168627</td>\n",
" <td>807.937830</td>\n",
" <td>918.990956</td>\n",
" <td>569.182172</td>\n",
" <td>1445.601567</td>\n",
" <td>1169.888943</td>\n",
" <td>637.940252</td>\n",
" <td>818.582606</td>\n",
" <td>529.787818</td>\n",
" <td>1273.080231</td>\n",
" <td>972.307385</td>\n",
" <td>960.486325</td>\n",
" <td>1005.137615</td>\n",
" <td>705.395015</td>\n",
" <td>1380.459060</td>\n",
" <td>1226.123344</td>\n",
" <td>950.509981</td>\n",
" <td>815.561911</td>\n",
" <td>728.121910</td>\n",
" <td>1204.177302</td>\n",
" <td>1297.992213</td>\n",
" <td>1011.433771</td>\n",
" <td>1143.999877</td>\n",
" <td>816.408425</td>\n",
" <td>1282.611507</td>\n",
" <td>940.885261</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>652.078144</td>\n",
" <td>902.875458</td>\n",
" <td>499.707842</td>\n",
" <td>1321.872766</td>\n",
" <td>1206.565845</td>\n",
" <td>711.020676</td>\n",
" <td>889.252456</td>\n",
" <td>589.541464</td>\n",
" <td>1308.288598</td>\n",
" <td>1357.399305</td>\n",
" <td>779.699774</td>\n",
" <td>751.959416</td>\n",
" <td>696.787866</td>\n",
" <td>1242.254299</td>\n",
" <td>1082.721843</td>\n",
" <td>334.748091</td>\n",
" <td>681.383078</td>\n",
" <td>581.280463</td>\n",
" <td>832.981623</td>\n",
" <td>979.189044</td>\n",
" <td>844.632285</td>\n",
" <td>1357.829364</td>\n",
" <td>607.683382</td>\n",
" <td>1241.594864</td>\n",
" <td>917.629482</td>\n",
" <td>722.273848</td>\n",
" <td>1014.471592</td>\n",
" <td>687.007724</td>\n",
" <td>1166.021692</td>\n",
" <td>1652.283567</td>\n",
" <td>773.734355</td>\n",
" <td>1307.555841</td>\n",
" <td>560.615147</td>\n",
" <td>1138.430068</td>\n",
" <td>1658.743273</td>\n",
" <td>824.079011</td>\n",
" <td>890.289849</td>\n",
" <td>474.241487</td>\n",
" <td>1393.502569</td>\n",
" <td>1356.965862</td>\n",
" <td>826.962566</td>\n",
" <td>806.844113</td>\n",
" <td>720.674715</td>\n",
" <td>1442.072747</td>\n",
" <td>1263.643629</td>\n",
" <td>703.045858</td>\n",
" <td>839.117700</td>\n",
" <td>562.645030</td>\n",
" <td>1433.856817</td>\n",
" <td>1369.304803</td>\n",
" <td>644.136066</td>\n",
" <td>783.934251</td>\n",
" <td>510.922246</td>\n",
" <td>1286.035515</td>\n",
" <td>1105.490997</td>\n",
" <td>933.966920</td>\n",
" <td>999.857526</td>\n",
" <td>604.625284</td>\n",
" <td>1464.005908</td>\n",
" <td>1342.583131</td>\n",
" <td>901.191224</td>\n",
" <td>747.678356</td>\n",
" <td>714.336361</td>\n",
" <td>1205.249989</td>\n",
" <td>1256.259389</td>\n",
" <td>795.775421</td>\n",
" <td>1053.693925</td>\n",
" <td>794.931176</td>\n",
" <td>1267.562506</td>\n",
" <td>1080.441384</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58555</th>\n",
" <td>1214.383048</td>\n",
" <td>943.409365</td>\n",
" <td>361.336104</td>\n",
" <td>985.516996</td>\n",
" <td>1443.421766</td>\n",
" <td>659.131822</td>\n",
" <td>705.515407</td>\n",
" <td>408.516258</td>\n",
" <td>857.918490</td>\n",
" <td>852.594188</td>\n",
" <td>774.015985</td>\n",
" <td>557.838313</td>\n",
" <td>478.135525</td>\n",
" <td>1028.410565</td>\n",
" <td>1437.524942</td>\n",
" <td>2410.400223</td>\n",
" <td>1556.155614</td>\n",
" <td>1139.585672</td>\n",
" <td>2322.633224</td>\n",
" <td>5750.639416</td>\n",
" <td>3251.566277</td>\n",
" <td>2242.599010</td>\n",
" <td>1404.154185</td>\n",
" <td>3356.739618</td>\n",
" <td>8304.202129</td>\n",
" <td>1964.373846</td>\n",
" <td>1082.318252</td>\n",
" <td>1260.145505</td>\n",
" <td>2380.122404</td>\n",
" <td>5884.629536</td>\n",
" <td>930.857797</td>\n",
" <td>858.290324</td>\n",
" <td>513.623505</td>\n",
" <td>832.093403</td>\n",
" <td>1816.010974</td>\n",
" <td>983.798872</td>\n",
" <td>875.930942</td>\n",
" <td>495.233444</td>\n",
" <td>901.889623</td>\n",
" <td>1448.923272</td>\n",
" <td>1899.515966</td>\n",
" <td>1416.221849</td>\n",
" <td>617.591903</td>\n",
" <td>1387.364084</td>\n",
" <td>3051.373356</td>\n",
" <td>2087.759219</td>\n",
" <td>1322.725730</td>\n",
" <td>772.603088</td>\n",
" <td>1679.113831</td>\n",
" <td>4057.984139</td>\n",
" <td>2454.937789</td>\n",
" <td>1553.172994</td>\n",
" <td>863.302021</td>\n",
" <td>1971.382170</td>\n",
" <td>4883.328316</td>\n",
" <td>1626.396469</td>\n",
" <td>1113.027953</td>\n",
" <td>917.337427</td>\n",
" <td>1738.912537</td>\n",
" <td>4176.064283</td>\n",
" <td>874.523533</td>\n",
" <td>917.362054</td>\n",
" <td>635.754903</td>\n",
" <td>1218.815486</td>\n",
" <td>1623.484599</td>\n",
" <td>863.441919</td>\n",
" <td>920.345627</td>\n",
" <td>487.967250</td>\n",
" <td>992.311694</td>\n",
" <td>1973.814193</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58556</th>\n",
" <td>1246.594018</td>\n",
" <td>896.234868</td>\n",
" <td>372.728726</td>\n",
" <td>907.605870</td>\n",
" <td>1453.358657</td>\n",
" <td>663.142677</td>\n",
" <td>703.706040</td>\n",
" <td>415.169249</td>\n",
" <td>787.609809</td>\n",
" <td>815.832046</td>\n",
" <td>821.169350</td>\n",
" <td>540.320012</td>\n",
" <td>468.905602</td>\n",
" <td>970.890141</td>\n",
" <td>1542.258398</td>\n",
" <td>2437.833793</td>\n",
" <td>1337.928581</td>\n",
" <td>1198.070674</td>\n",
" <td>2252.124975</td>\n",
" <td>5692.757076</td>\n",
" <td>3190.241405</td>\n",
" <td>2038.497777</td>\n",
" <td>1503.419650</td>\n",
" <td>3260.743045</td>\n",
" <td>8126.139374</td>\n",
" <td>1857.265305</td>\n",
" <td>1045.972443</td>\n",
" <td>1296.665987</td>\n",
" <td>2268.572080</td>\n",
" <td>5773.899136</td>\n",
" <td>979.753131</td>\n",
" <td>879.757744</td>\n",
" <td>427.052454</td>\n",
" <td>786.428903</td>\n",
" <td>1812.541923</td>\n",
" <td>938.267229</td>\n",
" <td>880.224830</td>\n",
" <td>477.587246</td>\n",
" <td>890.670095</td>\n",
" <td>1440.579155</td>\n",
" <td>1937.127358</td>\n",
" <td>1368.585660</td>\n",
" <td>702.678551</td>\n",
" <td>1343.029694</td>\n",
" <td>2998.950578</td>\n",
" <td>2088.935424</td>\n",
" <td>1186.395216</td>\n",
" <td>822.348037</td>\n",
" <td>1645.559208</td>\n",
" <td>4010.211265</td>\n",
" <td>2449.076946</td>\n",
" <td>1384.803476</td>\n",
" <td>917.188617</td>\n",
" <td>1929.734078</td>\n",
" <td>4736.510673</td>\n",
" <td>1572.386220</td>\n",
" <td>1009.384891</td>\n",
" <td>1013.033666</td>\n",
" <td>1528.110550</td>\n",
" <td>4132.610290</td>\n",
" <td>963.722983</td>\n",
" <td>900.105897</td>\n",
" <td>626.333011</td>\n",
" <td>1281.467772</td>\n",
" <td>1611.434194</td>\n",
" <td>891.646559</td>\n",
" <td>914.147257</td>\n",
" <td>532.943915</td>\n",
" <td>1006.798739</td>\n",
" <td>2036.224335</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58557</th>\n",
" <td>1156.919684</td>\n",
" <td>928.939203</td>\n",
" <td>352.539310</td>\n",
" <td>882.238645</td>\n",
" <td>1537.577195</td>\n",
" <td>704.397673</td>\n",
" <td>742.780683</td>\n",
" <td>394.586309</td>\n",
" <td>836.618288</td>\n",
" <td>883.403197</td>\n",
" <td>826.177738</td>\n",
" <td>544.240938</td>\n",
" <td>553.014287</td>\n",
" <td>1081.949543</td>\n",
" <td>1723.808951</td>\n",
" <td>2404.844523</td>\n",
" <td>1733.814296</td>\n",
" <td>1311.418844</td>\n",
" <td>2584.353897</td>\n",
" <td>5722.728829</td>\n",
" <td>3174.696420</td>\n",
" <td>2496.954759</td>\n",
" <td>1784.646291</td>\n",
" <td>3745.977828</td>\n",
" <td>8281.981636</td>\n",
" <td>1969.529312</td>\n",
" <td>1660.490592</td>\n",
" <td>1510.860967</td>\n",
" <td>2554.933603</td>\n",
" <td>5968.011172</td>\n",
" <td>1012.070538</td>\n",
" <td>886.930816</td>\n",
" <td>377.859744</td>\n",
" <td>824.282567</td>\n",
" <td>1867.215397</td>\n",
" <td>1018.733589</td>\n",
" <td>865.427364</td>\n",
" <td>528.906952</td>\n",
" <td>983.027118</td>\n",
" <td>1515.707087</td>\n",
" <td>1842.225810</td>\n",
" <td>1384.723576</td>\n",
" <td>715.812364</td>\n",
" <td>1561.145829</td>\n",
" <td>3066.734187</td>\n",
" <td>2036.210618</td>\n",
" <td>1289.823753</td>\n",
" <td>906.664258</td>\n",
" <td>1673.960353</td>\n",
" <td>4123.033154</td>\n",
" <td>2403.751013</td>\n",
" <td>1548.189306</td>\n",
" <td>1059.607741</td>\n",
" <td>2173.825377</td>\n",
" <td>4880.310771</td>\n",
" <td>1565.627103</td>\n",
" <td>1388.316447</td>\n",
" <td>1059.144031</td>\n",
" <td>1881.066357</td>\n",
" <td>4162.733935</td>\n",
" <td>1067.345412</td>\n",
" <td>945.821422</td>\n",
" <td>541.800878</td>\n",
" <td>1236.251835</td>\n",
" <td>1676.581238</td>\n",
" <td>1006.731390</td>\n",
" <td>980.979614</td>\n",
" <td>497.149166</td>\n",
" <td>1017.721330</td>\n",
" <td>2226.500908</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58558</th>\n",
" <td>1124.560101</td>\n",
" <td>1029.136336</td>\n",
" <td>428.584173</td>\n",
" <td>932.356442</td>\n",
" <td>1530.088383</td>\n",
" <td>736.499741</td>\n",
" <td>722.729759</td>\n",
" <td>355.391541</td>\n",
" <td>812.585974</td>\n",
" <td>893.144363</td>\n",
" <td>972.873254</td>\n",
" <td>774.245505</td>\n",
" <td>468.330592</td>\n",
" <td>1103.195913</td>\n",
" <td>1633.090425</td>\n",
" <td>3111.023302</td>\n",
" <td>2290.162950</td>\n",
" <td>1474.036341</td>\n",
" <td>2617.167257</td>\n",
" <td>5824.283813</td>\n",
" <td>4647.885666</td>\n",
" <td>3549.926683</td>\n",
" <td>1907.301010</td>\n",
" <td>3813.859888</td>\n",
" <td>8380.120251</td>\n",
" <td>3153.079972</td>\n",
" <td>2034.593633</td>\n",
" <td>1575.906873</td>\n",
" <td>2527.761365</td>\n",
" <td>6052.243506</td>\n",
" <td>1047.135929</td>\n",
" <td>1020.767291</td>\n",
" <td>399.823131</td>\n",
" <td>948.118459</td>\n",
" <td>1913.746972</td>\n",
" <td>983.909315</td>\n",
" <td>956.150874</td>\n",
" <td>504.665107</td>\n",
" <td>917.954731</td>\n",
" <td>1494.374249</td>\n",
" <td>2131.862157</td>\n",
" <td>1594.447718</td>\n",
" <td>732.752686</td>\n",
" <td>1568.199685</td>\n",
" <td>3108.547453</td>\n",
" <td>2522.943660</td>\n",
" <td>1536.629241</td>\n",
" <td>1042.922695</td>\n",
" <td>1778.328728</td>\n",
" <td>4225.445463</td>\n",
" <td>3063.071759</td>\n",
" <td>1934.570679</td>\n",
" <td>1190.149711</td>\n",
" <td>2192.171714</td>\n",
" <td>4982.510483</td>\n",
" <td>2226.663717</td>\n",
" <td>1865.342515</td>\n",
" <td>1067.041633</td>\n",
" <td>1866.856669</td>\n",
" <td>4170.080117</td>\n",
" <td>1120.956944</td>\n",
" <td>1217.128927</td>\n",
" <td>601.302787</td>\n",
" <td>1272.315588</td>\n",
" <td>1693.655407</td>\n",
" <td>1024.292182</td>\n",
" <td>1123.799333</td>\n",
" <td>488.356273</td>\n",
" <td>1060.478027</td>\n",
" <td>2220.389943</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58559</th>\n",
" <td>1487.873695</td>\n",
" <td>924.787966</td>\n",
" <td>477.888200</td>\n",
" <td>1236.345039</td>\n",
" <td>1641.465755</td>\n",
" <td>873.227401</td>\n",
" <td>716.003156</td>\n",
" <td>350.080392</td>\n",
" <td>866.086584</td>\n",
" <td>960.934206</td>\n",
" <td>1018.046288</td>\n",
" <td>778.704834</td>\n",
" <td>470.106343</td>\n",
" <td>1089.297123</td>\n",
" <td>1695.824533</td>\n",
" <td>4746.388125</td>\n",
" <td>2511.089724</td>\n",
" <td>1660.147502</td>\n",
" <td>3355.088833</td>\n",
" <td>6077.601487</td>\n",
" <td>6731.792645</td>\n",
" <td>4246.054268</td>\n",
" <td>2352.627035</td>\n",
" <td>4873.856211</td>\n",
" <td>8375.907322</td>\n",
" <td>4468.615248</td>\n",
" <td>2274.026368</td>\n",
" <td>1746.482969</td>\n",
" <td>3025.968693</td>\n",
" <td>6073.876590</td>\n",
" <td>1200.426243</td>\n",
" <td>945.766271</td>\n",
" <td>432.604099</td>\n",
" <td>1090.040885</td>\n",
" <td>1954.037754</td>\n",
" <td>997.295945</td>\n",
" <td>863.982011</td>\n",
" <td>494.765361</td>\n",
" <td>918.286969</td>\n",
" <td>1596.864887</td>\n",
" <td>2661.059207</td>\n",
" <td>1578.642425</td>\n",
" <td>980.717044</td>\n",
" <td>1990.797181</td>\n",
" <td>3030.104900</td>\n",
" <td>3477.576774</td>\n",
" <td>1706.501853</td>\n",
" <td>1384.763751</td>\n",
" <td>2438.534643</td>\n",
" <td>4109.212271</td>\n",
" <td>4107.806515</td>\n",
" <td>2321.651069</td>\n",
" <td>1568.562819</td>\n",
" <td>2805.104242</td>\n",
" <td>4840.445674</td>\n",
" <td>3336.700252</td>\n",
" <td>1811.064596</td>\n",
" <td>1236.708820</td>\n",
" <td>2462.147869</td>\n",
" <td>4307.839775</td>\n",
" <td>1601.593521</td>\n",
" <td>1025.327001</td>\n",
" <td>642.765570</td>\n",
" <td>1555.167131</td>\n",
" <td>1925.954897</td>\n",
" <td>1214.317165</td>\n",
" <td>820.083239</td>\n",
" <td>549.951333</td>\n",
" <td>1298.066761</td>\n",
" <td>2486.505295</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>58560 rows × 70 columns</p>\n",
"</div>"
],
"text/plain": [
" 0 1 ... 68 69\n",
"0 613.663621 914.264525 ... 1249.394169 1051.721009\n",
"1 630.957834 855.122300 ... 1266.382407 1116.827476\n",
"2 669.998695 931.945086 ... 1298.654550 1047.062139\n",
"3 701.677561 959.023161 ... 1282.611507 940.885261\n",
"4 652.078144 902.875458 ... 1267.562506 1080.441384\n",
"... ... ... ... ... ...\n",
"58555 1214.383048 943.409365 ... 992.311694 1973.814193\n",
"58556 1246.594018 896.234868 ... 1006.798739 2036.224335\n",
"58557 1156.919684 928.939203 ... 1017.721330 2226.500908\n",
"58558 1124.560101 1029.136336 ... 1060.478027 2220.389943\n",
"58559 1487.873695 924.787966 ... 1298.066761 2486.505295\n",
"\n",
"[58560 rows x 70 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 12
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "6tjKhClBBvnB",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "4482583d-3f7a-47be-d015-f5aad7f55aa5"
},
"source": [
"label1=pd.read_csv(\"/content/label.csv\")\n",
"label1"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>7.71</td>\n",
" <td>7.60</td>\n",
" <td>6.90</td>\n",
" <td>7.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>7.71</td>\n",
" <td>7.60</td>\n",
" <td>6.90</td>\n",
" <td>7.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>7.71</td>\n",
" <td>7.60</td>\n",
" <td>6.90</td>\n",
" <td>7.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>7.71</td>\n",
" <td>7.60</td>\n",
" <td>6.90</td>\n",
" <td>7.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>7.71</td>\n",
" <td>7.60</td>\n",
" <td>6.90</td>\n",
" <td>7.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58555</th>\n",
" <td>5.38</td>\n",
" <td>4.33</td>\n",
" <td>5.67</td>\n",
" <td>5.29</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58556</th>\n",
" <td>5.38</td>\n",
" <td>4.33</td>\n",
" <td>5.67</td>\n",
" <td>5.29</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58557</th>\n",
" <td>5.38</td>\n",
" <td>4.33</td>\n",
" <td>5.67</td>\n",
" <td>5.29</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58558</th>\n",
" <td>5.38</td>\n",
" <td>4.33</td>\n",
" <td>5.67</td>\n",
" <td>5.29</td>\n",
" </tr>\n",
" <tr>\n",
" <th>58559</th>\n",
" <td>5.38</td>\n",
" <td>4.33</td>\n",
" <td>5.67</td>\n",
" <td>5.29</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>58560 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" 0 1 2 3\n",
"0 7.71 7.60 6.90 7.83\n",
"1 7.71 7.60 6.90 7.83\n",
"2 7.71 7.60 6.90 7.83\n",
"3 7.71 7.60 6.90 7.83\n",
"4 7.71 7.60 6.90 7.83\n",
"... ... ... ... ...\n",
"58555 5.38 4.33 5.67 5.29\n",
"58556 5.38 4.33 5.67 5.29\n",
"58557 5.38 4.33 5.67 5.29\n",
"58558 5.38 4.33 5.67 5.29\n",
"58559 5.38 4.33 5.67 5.29\n",
"\n",
"[58560 rows x 4 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 13
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "1vHNFxKNCzVA"
},
"source": [
"x=data1.values"
],
"execution_count": 17,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "KkOVzVQmDPw8",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "d2a1225f-f8e0-429a-bb4b-c01c70299805"
},
"source": [
"label1.isnull().sum()\n"
],
"execution_count": 18,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 0\n",
"1 0\n",
"2 0\n",
"3 0\n",
"dtype: int64"
]
},
"metadata": {
"tags": []
},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "t4K0sRcyD7v-"
},
"source": [
"y_val=label1.loc[:,'0']"
],
"execution_count": 19,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "JIvAMkCWCX93",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "93957730-dca4-45e4-e0b3-6bf54e846f19"
},
"source": [
"y_val.unique()"
],
"execution_count": 20,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([7.71, 8.1 , 8.58, 4.94, 6.96, 8.27, 7.44, 7.32, 4.04, 1.99, 2.99,\n",
" 2.71, 1.95, 4.18, 3.17, 6.81, 2.46, 7.23, 7.17, 8.26, 9. , 7.09,\n",
" 8.15, 7.04, 8.86, 7.28, 7.35, 3.88, 1.36, 2.08, 3.03, 2.28, 3.81,\n",
" 2.06, 2.9 , 2.31, 3.33, 3.24, 5.1 , 8.01, 6.05, 5.04, 5. , 4.96,\n",
" 4.99, 7.08, 8.94, 6. , 8.97, 1. , 4.06, 2.01, 4.87, 5.33, 7.21,\n",
" 7.55, 4.69, 6.92, 6.79, 5.45, 7.14, 7.33, 4.45, 7.94, 6.36, 7.91,\n",
" 7.29, 7.36, 7.15, 4.56, 7.1 , 8.14, 6.26, 3.65, 3.31, 3.45, 4.67,\n",
" 6.72, 5.59, 4.47, 3.87, 4.44, 5.17, 4.05, 4.72, 3.18, 5.01, 4.92,\n",
" 4.53, 4.33, 5.38])"
]
},
"metadata": {
"tags": []
},
"execution_count": 20
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "c9tQ8UKNfdtI",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "9e6f2dce-59f5-40e7-dd76-9f4102e6f715"
},
"source": [
"y_val"
],
"execution_count": 21,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0 7.71\n",
"1 7.71\n",
"2 7.71\n",
"3 7.71\n",
"4 7.71\n",
" ... \n",
"58555 5.38\n",
"58556 5.38\n",
"58557 5.38\n",
"58558 5.38\n",
"58559 5.38\n",
"Name: 0, Length: 58560, dtype: float64"
]
},
"metadata": {
"tags": []
},
"execution_count": 21
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "u6OfYsu5oina",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "b8ad5776-7fc0-4dfe-e571-55f055989dfb"
},
"source": [
"y_val.values"
],
"execution_count": 22,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([7.71, 7.71, 7.71, ..., 5.38, 5.38, 5.38])"
]
},
"metadata": {
"tags": []
},
"execution_count": 22
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "xGLKl-9Zfjaf",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "bfbcd60a-5894-4f21-c209-08a1f6dffba1"
},
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"scaler = StandardScaler()\n",
"scaler.fit(x)\n",
"x = scaler.transform(x)\n",
"\n",
"\n",
"from tensorflow.keras.utils import to_categorical\n",
"\n",
"y = to_categorical(y_val)\n",
"y"
],
"execution_count": 23,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[0., 0., 0., ..., 1., 0., 0.],\n",
" [0., 0., 0., ..., 1., 0., 0.],\n",
" [0., 0., 0., ..., 1., 0., 0.],\n",
" ...,\n",
" [0., 0., 0., ..., 0., 0., 0.],\n",
" [0., 0., 0., ..., 0., 0., 0.],\n",
" [0., 0., 0., ..., 0., 0., 0.]], dtype=float32)"
]
},
"metadata": {
"tags": []
},
"execution_count": 23
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "DQui7-n9Usd3",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "08f05825-b7ba-43f1-a2be-e593d1dd5d5f"
},
"source": [
"x"
],
"execution_count": 24,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[-0.5451585 , -0.53604247, -0.63340426, ..., 0.4137955 ,\n",
" 0.16243351, -1.19504867],\n",
" [-0.54434399, -0.54514193, -0.65045479, ..., 0.11147437,\n",
" 0.23369829, -1.09190271],\n",
" [-0.54250529, -0.53332219, -0.62548952, ..., 0.56369857,\n",
" 0.36907827, -1.20242955],\n",
" ...,\n",
" [-0.51957276, -0.53378467, -0.73367168, ..., -1.4311509 ,\n",
" -0.80942213, 0.66611502],\n",
" [-0.5210968 , -0.51836861, -0.70031263, ..., -1.46802799,\n",
" -0.63005999, 0.65643363],\n",
" [-0.50398581, -0.53442337, -0.67868414, ..., -1.20970044,\n",
" 0.36661253, 1.0780311 ]])"
]
},
"metadata": {
"tags": []
},
"execution_count": 0
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[-0.5451585 , -0.53604247, -0.63340426, ..., 0.4137955 ,\n",
" 0.16243351, -1.19504867],\n",
" [-0.54434399, -0.54514193, -0.65045479, ..., 0.11147437,\n",
" 0.23369829, -1.09190271],\n",
" [-0.54250529, -0.53332219, -0.62548952, ..., 0.56369857,\n",
" 0.36907827, -1.20242955],\n",
" ...,\n",
" [-0.51957276, -0.53378467, -0.73367168, ..., -1.4311509 ,\n",
" -0.80942213, 0.66611502],\n",
" [-0.5210968 , -0.51836861, -0.70031263, ..., -1.46802799,\n",
" -0.63005999, 0.65643363],\n",
" [-0.50398581, -0.53442337, -0.67868414, ..., -1.20970044,\n",
" 0.36661253, 1.0780311 ]])"
]
},
"metadata": {
"tags": []
},
"execution_count": 24
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "zru43-IYfvMO"
},
"source": [
"x = np.reshape(x, (x.shape[0],1,x.shape[1]))\n"
],
"execution_count": 28,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Sh3ai8VD1m1a",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "72c5fce7-4723-4024-beed-931a6407e385"
},
"source": [
"y.shape"
],
"execution_count": 29,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(58560, 10)"
]
},
"metadata": {
"tags": []
},
"execution_count": 29
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "1TQMW0F7nYL-",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "02d0d6c0-0ec7-4b55-9321-03e4ede26dd8"
},
"source": [
"y"
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([[0., 0., 0., ..., 1., 0., 0.],\n",
" [0., 0., 0., ..., 1., 0., 0.],\n",
" [0., 0., 0., ..., 1., 0., 0.],\n",
" ...,\n",
" [0., 0., 0., ..., 0., 0., 0.],\n",
" [0., 0., 0., ..., 0., 0., 0.],\n",
" [0., 0., 0., ..., 0., 0., 0.]], dtype=float32)"
]
},
"metadata": {
"tags": []
},
"execution_count": 24
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "EaKwv9nFgEX0"
},
"source": [
"from sklearn.model_selection import train_test_split\n",
"x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 4)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "FRJ5Fu1RmCdj",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "563ec19b-ad3c-49ac-818c-663897dd7473"
},
"source": [
"print(x_train.shape)\n",
"print(y_train.shape)\n",
"print(x_test.shape)\n",
"print(y_test.shape)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"(46848, 1, 70)\n",
"(46848, 10)\n",
"(11712, 1, 70)\n",
"(11712, 10)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "evd-F_sl3wPL"
},
"source": [
"import keras\n",
"\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense, Dropout\n",
"from keras.layers import LSTM,BatchNormalization,Activation\n",
"model = Sequential()\n",
"model.add(LSTM(512, batch_input_shape = (None, None, x.shape[2]),return_sequences=True))\n"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Yg55Y-9uYx02",
"outputId": "ff804aec-c98c-4f89-89eb-398becca2621"
},
"source": [
" x.shape\n",
" "
],
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(58560, 1, 70)"
]
},
"metadata": {
"tags": []
},
"execution_count": 28
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Ti2iT1O7YtxS",
"outputId": "811d662d-a4e1-4f8c-ea65-6592e303c9f5"
},
"source": [
"\n",
"model.add(BatchNormalization())\n",
"model.add(Dropout(0.3))\n",
"\n",
"model.add(LSTM(256,activation=\"relu\",return_sequences=True))\n",
"model.add(BatchNormalization())\n",
"model.add(Dropout(0.5))\n",
"\n",
"\n",
"model.add(LSTM(128,activation=\"relu\",return_sequences=True))\n",
"model.add(BatchNormalization())\n",
"model.add(Dropout(0.3))\n",
"\n",
"model.add(LSTM(64,activation=\"relu\",return_sequences=True))\n",
"model.add(BatchNormalization())\n",
"model.add(Dropout(0.3))\n",
"\n",
"\n",
"model.add(LSTM(32,activation=\"relu\"))\n",
"model.add(BatchNormalization())\n",
"model.add(Dropout(0.2))\n",
"\n",
"\n",
"model.add(Dense(1))\n",
"model.add(Activation('sigmoid'))\n",
"\n",
"rmsprop =keras.optimizers.RMSprop(lr=0.0001, rho=0.9, epsilon=1e-08)\n",
"model.compile(loss='mean_squared_error',\n",
" optimizer=rmsprop,\n",
" metrics=['accuracy'])\n",
"#adam = keras.optimizers.Adam(lr=0.5, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False)\n",
"#model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
"model.summary()"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Model: \"sequential\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"lstm (LSTM) (None, None, 512) 1193984 \n",
"_________________________________________________________________\n",
"batch_normalization (BatchNo (None, None, 512) 2048 \n",
"_________________________________________________________________\n",
"dropout (Dropout) (None, None, 512) 0 \n",
"_________________________________________________________________\n",
"lstm_1 (LSTM) (None, None, 256) 787456 \n",
"_________________________________________________________________\n",
"batch_normalization_1 (Batch (None, None, 256) 1024 \n",
"_________________________________________________________________\n",
"dropout_1 (Dropout) (None, None, 256) 0 \n",
"_________________________________________________________________\n",
"lstm_2 (LSTM) (None, None, 128) 197120 \n",
"_________________________________________________________________\n",
"batch_normalization_2 (Batch (None, None, 128) 512 \n",
"_________________________________________________________________\n",
"dropout_2 (Dropout) (None, None, 128) 0 \n",
"_________________________________________________________________\n",
"lstm_3 (LSTM) (None, None, 64) 49408 \n",
"_________________________________________________________________\n",
"batch_normalization_3 (Batch (None, None, 64) 256 \n",
"_________________________________________________________________\n",
"dropout_3 (Dropout) (None, None, 64) 0 \n",
"_________________________________________________________________\n",
"lstm_4 (LSTM) (None, 32) 12416 \n",
"_________________________________________________________________\n",
"batch_normalization_4 (Batch (None, 32) 128 \n",
"_________________________________________________________________\n",
"dropout_4 (Dropout) (None, 32) 0 \n",
"_________________________________________________________________\n",
"dense (Dense) (None, 1) 33 \n",
"_________________________________________________________________\n",
"activation (Activation) (None, 1) 0 \n",
"=================================================================\n",
"Total params: 2,244,385\n",
"Trainable params: 2,242,401\n",
"Non-trainable params: 1,984\n",
"_________________________________________________________________\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:375: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
" \"The `lr` argument is deprecated, use `learning_rate` instead.\")\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "6aNe2-s1gRTb",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "3968b7de-837f-4e74-f237-c26f810c2e78"
},
"source": [
"history = model.fit(x_train, y_train, epochs = 200, batch_size=512,validation_data= (x_test, y_test))\n"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Epoch 1/200\n",
"92/92 [==============================] - 54s 219ms/step - loss: 0.2792 - accuracy: 0.5354 - val_loss: 0.2284 - val_accuracy: 0.9000\n",
"Epoch 2/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.2494 - accuracy: 0.6452 - val_loss: 0.2006 - val_accuracy: 0.9000\n",
"Epoch 3/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.2280 - accuracy: 0.7379 - val_loss: 0.1751 - val_accuracy: 0.9000\n",
"Epoch 4/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.2100 - accuracy: 0.8008 - val_loss: 0.1586 - val_accuracy: 0.8997\n",
"Epoch 5/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.1929 - accuracy: 0.8281 - val_loss: 0.1510 - val_accuracy: 0.8898\n",
"Epoch 6/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.1781 - accuracy: 0.8442 - val_loss: 0.1527 - val_accuracy: 0.8786\n",
"Epoch 7/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.1643 - accuracy: 0.8560 - val_loss: 0.1488 - val_accuracy: 0.8773\n",
"Epoch 8/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.1502 - accuracy: 0.8668 - val_loss: 0.1410 - val_accuracy: 0.8775\n",
"Epoch 9/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1402 - accuracy: 0.8719 - val_loss: 0.1323 - val_accuracy: 0.8801\n",
"Epoch 10/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1304 - accuracy: 0.8768 - val_loss: 0.1252 - val_accuracy: 0.8805\n",
"Epoch 11/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1232 - accuracy: 0.8792 - val_loss: 0.1186 - val_accuracy: 0.8815\n",
"Epoch 12/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.1177 - accuracy: 0.8808 - val_loss: 0.1129 - val_accuracy: 0.8836\n",
"Epoch 13/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1123 - accuracy: 0.8842 - val_loss: 0.1080 - val_accuracy: 0.8859\n",
"Epoch 14/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1083 - accuracy: 0.8865 - val_loss: 0.1043 - val_accuracy: 0.8880\n",
"Epoch 15/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1056 - accuracy: 0.8875 - val_loss: 0.1017 - val_accuracy: 0.8894\n",
"Epoch 16/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.1028 - accuracy: 0.8890 - val_loss: 0.0990 - val_accuracy: 0.8914\n",
"Epoch 17/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.1015 - accuracy: 0.8896 - val_loss: 0.0976 - val_accuracy: 0.8926\n",
"Epoch 18/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.1005 - accuracy: 0.8900 - val_loss: 0.0962 - val_accuracy: 0.8936\n",
"Epoch 19/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0976 - accuracy: 0.8933 - val_loss: 0.0968 - val_accuracy: 0.8932\n",
"Epoch 20/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0977 - accuracy: 0.8928 - val_loss: 0.0967 - val_accuracy: 0.8932\n",
"Epoch 21/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0968 - accuracy: 0.8937 - val_loss: 0.0964 - val_accuracy: 0.8935\n",
"Epoch 22/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0968 - accuracy: 0.8938 - val_loss: 0.0947 - val_accuracy: 0.8953\n",
"Epoch 23/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.0967 - accuracy: 0.8938 - val_loss: 0.0945 - val_accuracy: 0.8956\n",
"Epoch 24/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0975 - accuracy: 0.8926 - val_loss: 0.0951 - val_accuracy: 0.8949\n",
"Epoch 25/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0966 - accuracy: 0.8938 - val_loss: 0.0945 - val_accuracy: 0.8954\n",
"Epoch 26/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0956 - accuracy: 0.8948 - val_loss: 0.0945 - val_accuracy: 0.8956\n",
"Epoch 27/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0953 - accuracy: 0.8952 - val_loss: 0.0940 - val_accuracy: 0.8961\n",
"Epoch 28/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.0963 - accuracy: 0.8940 - val_loss: 0.0943 - val_accuracy: 0.8957\n",
"Epoch 29/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.0956 - accuracy: 0.8947 - val_loss: 0.0939 - val_accuracy: 0.8962\n",
"Epoch 30/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0949 - accuracy: 0.8954 - val_loss: 0.0953 - val_accuracy: 0.8947\n",
"Epoch 31/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0951 - accuracy: 0.8952 - val_loss: 0.0947 - val_accuracy: 0.8953\n",
"Epoch 32/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0947 - accuracy: 0.8956 - val_loss: 0.0953 - val_accuracy: 0.8947\n",
"Epoch 33/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0943 - accuracy: 0.8962 - val_loss: 0.0934 - val_accuracy: 0.8966\n",
"Epoch 34/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.0945 - accuracy: 0.8958 - val_loss: 0.0942 - val_accuracy: 0.8958\n",
"Epoch 35/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0943 - accuracy: 0.8960 - val_loss: 0.0935 - val_accuracy: 0.8965\n",
"Epoch 36/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0944 - accuracy: 0.8959 - val_loss: 0.0940 - val_accuracy: 0.8960\n",
"Epoch 37/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0943 - accuracy: 0.8960 - val_loss: 0.0925 - val_accuracy: 0.8975\n",
"Epoch 38/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0940 - accuracy: 0.8960 - val_loss: 0.0934 - val_accuracy: 0.8966\n",
"Epoch 39/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0944 - accuracy: 0.8960 - val_loss: 0.0929 - val_accuracy: 0.8971\n",
"Epoch 40/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.0944 - accuracy: 0.8958 - val_loss: 0.0925 - val_accuracy: 0.8975\n",
"Epoch 41/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0937 - accuracy: 0.8966 - val_loss: 0.0929 - val_accuracy: 0.8972\n",
"Epoch 42/200\n",
"92/92 [==============================] - 17s 187ms/step - loss: 0.0935 - accuracy: 0.8967 - val_loss: 0.0929 - val_accuracy: 0.8971\n",
"Epoch 43/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0940 - accuracy: 0.8963 - val_loss: 0.0936 - val_accuracy: 0.8963\n",
"Epoch 44/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0937 - accuracy: 0.8966 - val_loss: 0.0927 - val_accuracy: 0.8974\n",
"Epoch 45/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0938 - accuracy: 0.8963 - val_loss: 0.0926 - val_accuracy: 0.8975\n",
"Epoch 46/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0939 - accuracy: 0.8964 - val_loss: 0.0936 - val_accuracy: 0.8964\n",
"Epoch 47/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0938 - accuracy: 0.8964 - val_loss: 0.0926 - val_accuracy: 0.8975\n",
"Epoch 48/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0939 - accuracy: 0.8963 - val_loss: 0.0923 - val_accuracy: 0.8978\n",
"Epoch 49/200\n",
"92/92 [==============================] - 17s 188ms/step - loss: 0.0934 - accuracy: 0.8967 - val_loss: 0.0929 - val_accuracy: 0.8971\n",
"Epoch 50/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0933 - accuracy: 0.8969 - val_loss: 0.0937 - val_accuracy: 0.8963\n",
"Epoch 51/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0934 - accuracy: 0.8969 - val_loss: 0.0925 - val_accuracy: 0.8975\n",
"Epoch 52/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0935 - accuracy: 0.8968 - val_loss: 0.0927 - val_accuracy: 0.8973\n",
"Epoch 53/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0931 - accuracy: 0.8971 - val_loss: 0.0924 - val_accuracy: 0.8976\n",
"Epoch 54/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0931 - accuracy: 0.8971 - val_loss: 0.0928 - val_accuracy: 0.8972\n",
"Epoch 55/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0929 - accuracy: 0.8973 - val_loss: 0.0928 - val_accuracy: 0.8973\n",
"Epoch 56/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0928 - accuracy: 0.8975 - val_loss: 0.0926 - val_accuracy: 0.8975\n",
"Epoch 57/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0927 - accuracy: 0.8976 - val_loss: 0.0925 - val_accuracy: 0.8975\n",
"Epoch 58/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0930 - accuracy: 0.8971 - val_loss: 0.0934 - val_accuracy: 0.8965\n",
"Epoch 59/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0926 - accuracy: 0.8976 - val_loss: 0.0931 - val_accuracy: 0.8969\n",
"Epoch 60/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0924 - accuracy: 0.8978 - val_loss: 0.0929 - val_accuracy: 0.8970\n",
"Epoch 61/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0925 - accuracy: 0.8978 - val_loss: 0.0923 - val_accuracy: 0.8977\n",
"Epoch 62/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0926 - accuracy: 0.8976 - val_loss: 0.0924 - val_accuracy: 0.8976\n",
"Epoch 63/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0923 - accuracy: 0.8979 - val_loss: 0.0927 - val_accuracy: 0.8973\n",
"Epoch 64/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0925 - accuracy: 0.8977 - val_loss: 0.0925 - val_accuracy: 0.8975\n",
"Epoch 65/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0922 - accuracy: 0.8979 - val_loss: 0.0923 - val_accuracy: 0.8977\n",
"Epoch 66/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0917 - accuracy: 0.8984 - val_loss: 0.0917 - val_accuracy: 0.8983\n",
"Epoch 67/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0916 - accuracy: 0.8986 - val_loss: 0.0921 - val_accuracy: 0.8978\n",
"Epoch 68/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0915 - accuracy: 0.8987 - val_loss: 0.0917 - val_accuracy: 0.8984\n",
"Epoch 69/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0916 - accuracy: 0.8986 - val_loss: 0.0909 - val_accuracy: 0.8991\n",
"Epoch 70/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0912 - accuracy: 0.8990 - val_loss: 0.0906 - val_accuracy: 0.8993\n",
"Epoch 71/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0910 - accuracy: 0.8992 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 72/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0910 - accuracy: 0.8992 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 73/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0910 - accuracy: 0.8993 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 74/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0908 - accuracy: 0.8994 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 75/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0907 - accuracy: 0.8996 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 76/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0908 - accuracy: 0.8994 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 77/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0908 - accuracy: 0.8995 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 78/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0908 - accuracy: 0.8994 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 79/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0908 - accuracy: 0.8994 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 80/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0908 - accuracy: 0.8995 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 81/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0906 - accuracy: 0.8997 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 82/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0906 - accuracy: 0.8997 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 83/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0907 - accuracy: 0.8996 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 84/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0907 - accuracy: 0.8996 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 85/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0905 - accuracy: 0.8997 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 86/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0905 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 87/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0905 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 88/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0905 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 89/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0905 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 90/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0905 - accuracy: 0.8997 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 91/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0905 - accuracy: 0.8997 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 92/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0905 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 93/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0904 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 94/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0904 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 95/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.9000 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 96/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.9000 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 97/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0904 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 98/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 99/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 100/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 101/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0904 - accuracy: 0.8997 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 102/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0904 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 103/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0904 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 104/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 105/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 106/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 107/200\n",
"92/92 [==============================] - 17s 189ms/step - loss: 0.0904 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 108/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0904 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 109/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 110/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 111/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 112/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 113/200\n",
"92/92 [==============================] - 18s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 114/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 115/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 116/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 117/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 118/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 119/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 120/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 121/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 122/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 123/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0903 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 124/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 125/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 126/200\n",
"92/92 [==============================] - 18s 190ms/step - loss: 0.0904 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 127/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 128/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 129/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 130/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 131/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 132/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0904 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 133/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 134/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 135/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 136/200\n",
"92/92 [==============================] - 17s 190ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 137/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 138/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 139/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 140/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 141/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 142/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0904 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 143/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 144/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 145/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 146/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 147/200\n",
"92/92 [==============================] - 18s 190ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 148/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0901 - val_accuracy: 0.9000\n",
"Epoch 149/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 150/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 151/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 152/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 153/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 154/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 155/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0904 - accuracy: 0.8997 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 156/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 157/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 158/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 159/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 160/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 161/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 162/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 163/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 164/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 165/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 166/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 167/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 168/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 169/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 170/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 171/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 172/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 173/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 174/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 175/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 176/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 177/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 178/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 179/200\n",
"92/92 [==============================] - 18s 191ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 180/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 181/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 182/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 183/200\n",
"92/92 [==============================] - 18s 193ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 184/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 185/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 186/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 187/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 188/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 189/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 190/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.8998 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 191/200\n",
"92/92 [==============================] - 18s 196ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 192/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 193/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 194/200\n",
"92/92 [==============================] - 18s 195ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 195/200\n",
"92/92 [==============================] - 18s 197ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 196/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0903 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 197/200\n",
"92/92 [==============================] - 18s 192ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 198/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.8999 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 199/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n",
"Epoch 200/200\n",
"92/92 [==============================] - 18s 194ms/step - loss: 0.0902 - accuracy: 0.9000 - val_loss: 0.0900 - val_accuracy: 0.9000\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "eNF8mZelgcis",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "af488bda-3dd1-4370-dae8-99cd30387e0a"
},
"source": [
" import keras\n",
"\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense, Dropout\n",
"from keras.layers import LSTM\n",
"model = Sequential()\n",
"model.add(LSTM(100, batch_input_shape = (None, None, x.shape[2]),return_sequences=True))\n",
"model.add(Dropout(0.2))\n",
"model.add(LSTM(50))\n",
"model.add(Dense(1, activation='softmax'))\n",
"\n",
"\n",
"rmsprop =keras.optimizers.RMSprop(lr=0.0001, rho=0.9, epsilon=1e-08)\n",
"model.compile(loss='mean_squared_error',\n",
" optimizer=rmsprop,\n",
" metrics=['accuracy'])\n",
"#adam = keras.optimizers.Adam(lr=0.5, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False)\n",
"#model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
"model.summary()"
],
"execution_count": 30,
"outputs": [
{
"output_type": "stream",
"text": [
"Model: \"sequential_5\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"lstm (LSTM) (None, None, 100) 68400 \n",
"_________________________________________________________________\n",
"dropout (Dropout) (None, None, 100) 0 \n",
"_________________________________________________________________\n",
"lstm_1 (LSTM) (None, 50) 30200 \n",
"_________________________________________________________________\n",
"dense (Dense) (None, 1) 51 \n",
"=================================================================\n",
"Total params: 98,651\n",
"Trainable params: 98,651\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:375: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.\n",
" \"The `lr` argument is deprecated, use `learning_rate` instead.\")\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "KRmWs2V1S4oL",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 313
},
"outputId": "64d50195-c9df-4788-ed3f-1aa2b53daa5a"
},
"source": [
"import matplotlib.pyplot as plt\n",
"print(history.history.keys())\n",
"# summarize history for accuracy\n",
"plt.plot(history.history['accuracy'])\n",
"plt.plot(history.history['val_accuracy'])\n",
"plt.title('model accuracy')\n",
"plt.ylabel('accuracy')\n",
"plt.xlabel('epoch')\n",
"plt.legend(['train', 'test'], loc='upper left')\n",
"plt.show()\n"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "7raPO9njE1_v",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 295
},
"outputId": "664af23c-0b48-4e6b-a739-6b520b34aa9f"
},
"source": [
"# summarize history for loss\n",
"plt.plot(history.history['loss'])\n",
"plt.plot(history.history['val_loss'])\n",
"plt.title('model loss')\n",
"plt.ylabel('loss')\n",
"plt.xlabel('epoch')\n",
"plt.legend(['train', 'test'], loc='upper left')\n",
"plt.show()"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "CGP-4LFxGBd8",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 295
},
"outputId": "6c449830-90f7-49bf-b10a-31cb5f50dc75"
},
"source": [
"plt.plot(history.history['val_accuracy'])\n",
"plt.plot(history.history['val_loss'])\n",
"plt.title('test model')\n",
"plt.ylabel('test accuracy')\n",
"plt.xlabel('test loss')\n",
"plt.show()"
],
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment