Skip to content

Instantly share code, notes, and snippets.

@Radi4

Radi4/Leader board

Created February 4, 2018 17:01
Show Gist options
  • Save Radi4/25c7ad8e5d76833da2300125f811f41b to your computer and use it in GitHub Desktop.
Save Radi4/25c7ad8e5d76833da2300125f811f41b to your computer and use it in GitHub Desktop.
Download ZIP
Raw
Leader board
{
"cells": [
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"from keras.models import Model\n",
"from keras.layers import Dense, Input\n",
"import numpy as np\n",
"import mne\n",
"import os\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.model_selection import train_test_split\n",
"import h5py\n",
"from sklearn.metrics import mean_squared_error"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"eeg_dir = \"./data/new_data/\"\n",
"eeg_names = [x for x in os.listdir(eeg_dir) \n",
" if x[-5:] == \".vhdr\"]"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting parameters from ./data/new_data/0311_pre_eeg_popova.vhdr...\n",
"Setting channel info structure...\n",
"Extracting parameters from ./data/new_data/2509_post_eeg_rinata.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 601549 = 0.000 ... 601.549 secs...\n",
"Extracting parameters from ./data/new_data/2510_post_eeg_osipova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602949 = 0.000 ... 602.949 secs...\n",
"Extracting parameters from ./data/new_data/0311_post_eeg_mazurova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603349 = 0.000 ... 603.349 secs...\n",
"Extracting parameters from ./data/new_data/3111_post_eeg_popova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 612499 = 0.000 ... 612.499 secs...\n",
"Extracting parameters from ./data/new_data/1909_pre_eeg_eliseev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 608399 = 0.000 ... 608.399 secs...\n",
"Extracting parameters from ./data/new_data/14071200_limanskaya_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604549 = 0.000 ... 604.549 secs...\n",
"Extracting parameters from ./data/new_data/3010_pre_eeg_suhareva.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 609899 = 0.000 ... 609.899 secs...\n",
"Extracting parameters from ./data/new_data/2809_pre_eeg_lukyanov.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 615899 = 0.000 ... 615.899 secs...\n",
"Extracting parameters from ./data/new_data/1207_shevchenko_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602849 = 0.000 ... 602.849 secs...\n",
"Extracting parameters from ./data/new_data/0708_pre_eeg_krasovskaya.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604049 = 0.000 ... 604.049 secs...\n",
"Extracting parameters from ./data/new_data/1207_shevchenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2132749 = 0.000 ... 2132.749 secs...\n",
"Extracting parameters from ./data/new_data/0311_eeg_mazurova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2048799 = 0.000 ... 2048.799 secs...\n",
"Extracting parameters from ./data/new_data/3010_post_eeg_suhareva.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 605799 = 0.000 ... 605.799 secs...\n",
"Extracting parameters from ./data/new_data/2809_lukyanov.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2085449 = 0.000 ... 2085.449 secs...\n",
"Extracting parameters from ./data/new_data/1608_post_eeg_polshina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 632899 = 0.000 ... 632.899 secs...\n",
"Extracting parameters from ./data/new_data/17_11_pre_eeg_bachurina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602149 = 0.000 ... 602.149 secs...\n",
"Extracting parameters from ./data/new_data/3110_maistrenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1914399 = 0.000 ... 1914.399 secs...\n",
"Extracting parameters from ./data/new_data/1509_pre_eeg_zvyagincev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 606799 = 0.000 ... 606.799 secs...\n",
"Extracting parameters from ./data/new_data/2306_patrakeeva_post_eeg_rest.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 605199 = 0.000 ... 605.199 secs...\n",
"Extracting parameters from ./data/new_data/3010_eeg_suhareva.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1572349 = 0.000 ... 1572.349 secs...\n",
"Extracting parameters from ./data/new_data/1909_eliseev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2093299 = 0.000 ... 2093.299 secs...\n",
"Extracting parameters from ./data/new_data/1909_post_eeg_eliseev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 842249 = 0.000 ... 842.249 secs...\n",
"Extracting parameters from ./data/new_data/0307_STRELKOVA.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2103349 = 0.000 ... 2103.349 secs...\n",
"Extracting parameters from ./data/new_data/3110_post_eeg_maistrenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 620899 = 0.000 ... 620.899 secs...\n",
"Extracting parameters from ./data/new_data/2606_patrakeeva_main_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2106049 = 0.000 ... 2106.049 secs...\n",
"Extracting parameters from ./data/new_data/1608_rpre_eeg_polshina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 629449 = 0.000 ... 629.449 secs...\n",
"Extracting parameters from ./data/new_data/2510_pre_eeg_osipova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604099 = 0.000 ... 604.099 secs...\n",
"Extracting parameters from ./data/new_data/0311_eeg_popova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1977699 = 0.000 ... 1977.699 secs...\n",
"Extracting parameters from ./data/new_data/0708_post_eeg_krasovskaya.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 614349 = 0.000 ... 614.349 secs...\n",
"Extracting parameters from ./data/new_data/14071200_limaskaya_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604849 = 0.000 ... 604.849 secs...\n",
"Extracting parameters from ./data/new_data/2510_osipova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1958699 = 0.000 ... 1958.699 secs...\n",
"Extracting parameters from ./data/new_data/2809_post_eeg_lukyanov.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602149 = 0.000 ... 602.149 secs...\n",
"Extracting parameters from ./data/new_data/1207_shevchenko_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 614199 = 0.000 ... 614.199 secs...\n",
"Extracting parameters from ./data/new_data/0708_eeg_krasovskaya.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2023149 = 0.000 ... 2023.149 secs...\n",
"Extracting parameters from ./data/new_data/2306_patrakeeva_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Extracting parameters from ./data/new_data/0307_POST_EEG_sTRELKOVA.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602149 = 0.000 ... 602.149 secs...\n",
"Extracting parameters from ./data/new_data/2509_eeg_rinata.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2129299 = 0.000 ... 2129.299 secs...\n",
"Extracting parameters from ./data/new_data/2509-pre_eeg_rinata.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 724899 = 0.000 ... 724.899 secs...\n",
"Extracting parameters from ./data/new_data/17_11_post_eeg_bachurina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 610499 = 0.000 ... 610.499 secs...\n",
"Extracting parameters from ./data/new_data/1608_eeg_polshina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1961799 = 0.000 ... 1961.799 secs...\n",
"Extracting parameters from ./data/new_data/311_pre_eeg_mazurova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604349 = 0.000 ... 604.349 secs...\n",
"Extracting parameters from ./data/new_data/1509_zvyagincev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1910849 = 0.000 ... 1910.849 secs...\n",
"Extracting parameters from ./data/new_data/1407_limanskaya_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2406349 = 0.000 ... 2406.349 secs...\n",
"Extracting parameters from ./data/new_data/3110_pre_eeg_maistrenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 663199 = 0.000 ... 663.199 secs...\n",
"Extracting parameters from ./data/new_data/17_11_bachurina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1979549 = 0.000 ... 1979.549 secs...\n",
"Extracting parameters from ./data/new_data/0307_STRELKOVA_PRE_EEG.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 601999 = 0.000 ... 601.999 secs...\n",
"2\n"
]
}
],
"source": [
"data = np.zeros((0,61))\n",
"\n",
"fail_count = 0\n",
"\n",
"for eeg_name in eeg_names:\n",
" try:\n",
" eeg_data = mne.io.read_raw_brainvision(eeg_dir + eeg_name, preload=True).get_data().T\n",
" data = np.append(data, eeg_data, axis = 0)\n",
" except:\n",
" fail_count += 1\n",
" continue\n",
"\n",
"print(fail_count)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"scaler = StandardScaler()\n",
"scaled_data = scaler.fit_transform(data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Петр и Девушки. Обе команды использовали StandartScaller"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Девушки"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import keras"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/anaconda3/lib/python3.6/site-packages/keras/models.py:245: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
" warnings.warn('No training configuration found in save file: '\n"
]
}
],
"source": [
"encoder = keras.models.load_model('./catherineglazkova_tasssshhhha/encoder.p')\n",
"decoder = keras.models.load_model('./catherineglazkova_tasssshhhha/decoder.p')"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.24630945127079723"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_encoded = encoder.predict(scaled_data)\n",
"alpha = data_encoded.shape[1] / 61\n",
"data_decoded = decoder.predict(data_encoded)\n",
"data_pred = scaler.inverse_transform(data_decoded)\n",
"mse = mean_squared_error(data, data_pred)\n",
"score = (1 + mse) * alpha\n",
"score"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.0016584351679086453"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mse"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(50462050, 15)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_encoded.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Петр"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pickle"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import tempfile\n",
"def make_keras_picklable():\n",
" def __getstate__(self):\n",
" model_str = \"\"\n",
" with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:\n",
" keras.models.save_model(self, fd.name, overwrite=True)\n",
" model_str = fd.read()\n",
" d = { 'model_str': model_str }\n",
" return d\n",
"\n",
" def __setstate__(self, state):\n",
" with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:\n",
" fd.write(state['model_str'])\n",
" fd.flush()\n",
" model = keras.models.load_model(fd.name)\n",
" self.__dict__ = model.__dict__\n",
"\n",
"\n",
" cls = keras.models.Model\n",
" cls.__getstate__ = __getstate__\n",
" cls.__setstate__ = __setstate__\n",
"make_keras_picklable()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/anaconda3/lib/python3.6/site-packages/keras/models.py:245: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
" warnings.warn('No training configuration found in save file: '\n"
]
}
],
"source": [
"load_encoder = pickle.load(open(\"./Petr/encoder.pkl\", \"rb\"))\n",
"load_decoder = pickle.load(open(\"./Petr/decoder.pkl\", \"rb\"))"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.9195437515270669"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_encoded = load_encoder.predict(scaled_data)\n",
"alpha = data_encoded.shape[1] / 61\n",
"data_decoded = load_decoder.predict(data_encoded)\n",
"data_pred = scaler.inverse_transform(data_decoded)\n",
"mse = mean_squared_error(data, data_pred)\n",
"score = (1 + mse) * alpha\n",
"score"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.0016458721991263316"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mse"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(50462050, 56)"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_encoded.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Комадна Валентин, Валерия, Костя"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from os import walk\n",
"\n",
"mne.set_log_level('WARNING')\n",
"data_path = u\"./data/new_data/\""
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def getBatches(arr, batch_size=50, axis=0):\n",
" n = arr.shape[axis] // batch_size\n",
" return np.array_split(arr, n, axis=axis)\n",
"\n",
"def prepareData(file_path):\n",
" raw = np.array(mne.io.read_raw_brainvision(file_path, preload=True).to_data_frame())\n",
" batches = np.array(getBatches(raw))\n",
" del raw\n",
" \n",
" return batches"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"files = []\n",
"data = []\n",
"for elem in walk(data_path):\n",
" for file in elem[-1]:\n",
" if file[-4:] == \"vhdr\":\n",
" files.append(file)\n",
"\n",
"data = np.ndarray(shape=(0, 50, 61))\n",
"flag = False\n",
"for file in files:\n",
" file_name = data_path + file\n",
" \n",
" try:\n",
" batches = prepareData(file_name)\n",
" data = np.concatenate((data, batches), axis=0)\n",
" except:\n",
" continue"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/conda/anaconda3/lib/python3.6/site-packages/keras/models.py:245: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
" warnings.warn('No training configuration found in save file: '\n"
]
}
],
"source": [
"encoder = keras.models.load_model('./biryuk_v_nyaaak_erreth_akbe/encoder_elu.h5')\n",
"decoder = keras.models.load_model('./biryuk_v_nyaaak_erreth_akbe/decoder_elu.h5')"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(1009241, 50, 61)"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.shape"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(1009241, 1000)"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_encoded = encoder.predict(data)\n",
"data_encoded.shape"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(1009241, 50, 61)"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_pred = decoder.predict(data_encoded)\n",
"data_pred.shape"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.32786885245901637"
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"alpha = 1000 / (50 * 61)\n",
"alpha"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data_original = data.reshape((1009241 * 50, 61))\n",
"data_original_pred = data_pred.reshape((1009241 * 50, 61))\n",
"mse = mean_squared_error(data_original, data_original_pred)"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"14357335228541.21"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mse"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4707323025751.544"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"score = (1 + mse) * alpha\n",
"score"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Последняя команда делала так как сказано в начале статьи(делили еег по времени на группы размера 50). У них самый худший результат, но взоможно из-за того, что они не делала Scaller. У первой команды(девушки), в коде есть перебо размерности закодированных данных и там видно, что mse почти не меняется. Итоговый результат такой\n",
"1) Девушки\n",
"2) Петр и Марк\n",
"3) Валентин, Валерия и Константин"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th>Team </th><th style=\"text-align: right;\"> Alpha</th><th style=\"text-align: right;\"> Mse</th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td>Девушки </td><td style=\"text-align: right;\"> 0.246 </td><td style=\"text-align: right;\">0.0016 </td></tr>\n",
"<tr><td>Петр </td><td style=\"text-align: right;\"> 0.91 </td><td style=\"text-align: right;\">0.00165 </td></tr>\n",
"<tr><td>Валентин, Валерия, Костя</td><td style=\"text-align: right;\"> 0.3279</td><td style=\"text-align: right;\">1.43573e+13</td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from tabulate import tabulate\n",
"from IPython.display import HTML\n",
"HTML(tabulate([[\"Девушки\", 0.246, 0.0016], [\"Петр\", 0.91, 0.00165], [\"Валентин, Валерия, Костя\", 0.3279, 14357335228541.21]],\n",
" headers= ['Team', 'Alpha', 'Mse'], tablefmt='html'))"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting parameters from ./data/resting_state/pre_egg_petuhova3103.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602749 = 0.000 ... 602.749 secs...\n",
"Extracting parameters from ./data/resting_state/2205_miloslavov_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 623249 = 0.000 ... 623.249 secs...\n",
"Extracting parameters from ./data/resting_state/kozunova_pre_eeg_2103.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602849 = 0.000 ... 602.849 secs...\n",
"Extracting parameters from ./data/resting_state/2505_shirokova_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 606599 = 0.000 ... 606.599 secs...\n",
"Extracting parameters from ./data/resting_state/gorbacheva_03021300_rest_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 625249 = 0.000 ... 625.249 secs...\n",
"Extracting parameters from ./data/resting_state/200317_ivanova_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602099 = 0.000 ... 602.099 secs...\n",
"Extracting parameters from ./data/resting_state/2403_kutuzova_posteeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604199 = 0.000 ... 604.199 secs...\n",
"Extracting parameters from ./data/resting_state/3103_petuhova_posteeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 630049 = 0.000 ... 630.049 secs...\n",
"Extracting parameters from ./data/resting_state/2103_glebko_posteeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 633899 = 0.000 ... 633.899 secs...\n",
"Extracting parameters from ./data/resting_state/glebko_2103_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 643749 = 0.000 ... 643.749 secs...\n",
"Extracting parameters from ./data/resting_state/gorin_310117_rest_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 609999 = 0.000 ... 609.999 secs...\n",
"Extracting parameters from ./data/resting_state/zavrib_post_eeg_eyesopen15021500.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 321599 = 0.000 ... 321.599 secs...\n",
"Extracting parameters from ./data/resting_state/gorbacheva_03_02_2017_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603949 = 0.000 ... 603.949 secs...\n",
"Extracting parameters from ./data/resting_state/post_eeg_tsoy_2504.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604949 = 0.000 ... 604.949 secs...\n",
"Extracting parameters from ./data/resting_state/2403_kutuzova_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602849 = 0.000 ... 602.849 secs...\n",
"Extracting parameters from ./data/resting_state/2505_shirokova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604799 = 0.000 ... 604.799 secs...\n",
"Extracting parameters from ./data/resting_state/dagaev_post_rest_eeg_30011600.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603799 = 0.000 ... 603.799 secs...\n",
"Extracting parameters from ./data/resting_state/zagirova_pre_eeg_2704.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 607549 = 0.000 ... 607.549 secs...\n",
"Extracting parameters from ./data/resting_state/08021400_post_eeg_shuhova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 607199 = 0.000 ... 607.199 secs...\n",
"Extracting parameters from ./data/resting_state/2704_zagirova_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604549 = 0.000 ... 604.549 secs...\n",
"Extracting parameters from ./data/resting_state/shuhova_08022017_rest_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 637949 = 0.000 ... 637.949 secs...\n",
"Extracting parameters from ./data/resting_state/zavrin_open_eyes_eeg_15021500.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 301999 = 0.000 ... 301.999 secs...\n",
"Extracting parameters from ./data/resting_state/zavrin_eyes_closed_eeg_15021500.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 302749 = 0.000 ... 302.749 secs...\n",
"Extracting parameters from ./data/resting_state/tsoy_pre_eeg_2504.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 652699 = 0.000 ... 652.699 secs...\n",
"Extracting parameters from ./data/resting_state/2003_ivanova_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 616599 = 0.000 ... 616.599 secs...\n",
"Extracting parameters from ./data/resting_state/bagaeva_post_eeg_13031500.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603899 = 0.000 ... 603.899 secs...\n",
"Extracting parameters from ./data/resting_state/gorin_rest_eeg_post_31011200.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603699 = 0.000 ... 603.699 secs...\n",
"Extracting parameters from ./data/resting_state/bagaeva_13021500_rest_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603949 = 0.000 ... 603.949 secs...\n",
"Extracting parameters from ./data/resting_state/miloslavov_22_05_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603399 = 0.000 ... 603.399 secs...\n",
"Extracting parameters from ./data/resting_state/300120171600_dagaev_rest_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 615599 = 0.000 ... 615.599 secs...\n",
"Extracting parameters from ./data/resting_state/zavrin_15021500_eyesclosed_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 319299 = 0.000 ... 319.299 secs...\n",
"Extracting parameters from ./data/resting_state/2103_kozunova_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603199 = 0.000 ... 603.199 secs...\n"
]
}
],
"source": [
"batch_size = 256\n",
"epoch_num = 7\n",
"\n",
"channels_num = 61\n",
"encoding_dim_vars = [50,40,35,30,25,20,15]\n",
"\n",
"train_eeg_dir = \"./data/resting_state/\"\n",
"train_eeg_names = [x for x in os.listdir(train_eeg_dir) \n",
" if x[-5:] == \".vhdr\"]\n",
"\n",
"\n",
"train_data = np.zeros((0,channels_num))\n",
"\n",
"for eeg_name in train_eeg_names:\n",
" eeg_data = mne.io.read_raw_brainvision(train_eeg_dir + eeg_name, preload=True).get_data().T\n",
" train_data = np.append(train_data, eeg_data, axis = 0)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"scaler = StandardScaler()\n",
"train_data_scaled = scaler.fit_transform(train_data)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting parameters from ./data/new_data/0311_pre_eeg_popova.vhdr...\n",
"Setting channel info structure...\n",
"Extracting parameters from ./data/new_data/2509_post_eeg_rinata.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 601549 = 0.000 ... 601.549 secs...\n",
"Extracting parameters from ./data/new_data/2510_post_eeg_osipova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602949 = 0.000 ... 602.949 secs...\n",
"Extracting parameters from ./data/new_data/0311_post_eeg_mazurova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 603349 = 0.000 ... 603.349 secs...\n",
"Extracting parameters from ./data/new_data/3111_post_eeg_popova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 612499 = 0.000 ... 612.499 secs...\n",
"Extracting parameters from ./data/new_data/1909_pre_eeg_eliseev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 608399 = 0.000 ... 608.399 secs...\n",
"Extracting parameters from ./data/new_data/14071200_limanskaya_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604549 = 0.000 ... 604.549 secs...\n",
"Extracting parameters from ./data/new_data/3010_pre_eeg_suhareva.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 609899 = 0.000 ... 609.899 secs...\n",
"Extracting parameters from ./data/new_data/2809_pre_eeg_lukyanov.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 615899 = 0.000 ... 615.899 secs...\n",
"Extracting parameters from ./data/new_data/1207_shevchenko_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602849 = 0.000 ... 602.849 secs...\n",
"Extracting parameters from ./data/new_data/0708_pre_eeg_krasovskaya.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604049 = 0.000 ... 604.049 secs...\n",
"Extracting parameters from ./data/new_data/1207_shevchenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2132749 = 0.000 ... 2132.749 secs...\n",
"Extracting parameters from ./data/new_data/0311_eeg_mazurova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2048799 = 0.000 ... 2048.799 secs...\n",
"Extracting parameters from ./data/new_data/3010_post_eeg_suhareva.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 605799 = 0.000 ... 605.799 secs...\n",
"Extracting parameters from ./data/new_data/2809_lukyanov.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2085449 = 0.000 ... 2085.449 secs...\n",
"Extracting parameters from ./data/new_data/1608_post_eeg_polshina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 632899 = 0.000 ... 632.899 secs...\n",
"Extracting parameters from ./data/new_data/17_11_pre_eeg_bachurina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602149 = 0.000 ... 602.149 secs...\n",
"Extracting parameters from ./data/new_data/3110_maistrenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1914399 = 0.000 ... 1914.399 secs...\n",
"Extracting parameters from ./data/new_data/1509_pre_eeg_zvyagincev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 606799 = 0.000 ... 606.799 secs...\n",
"Extracting parameters from ./data/new_data/2306_patrakeeva_post_eeg_rest.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 605199 = 0.000 ... 605.199 secs...\n",
"Extracting parameters from ./data/new_data/3010_eeg_suhareva.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1572349 = 0.000 ... 1572.349 secs...\n",
"Extracting parameters from ./data/new_data/1909_eliseev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2093299 = 0.000 ... 2093.299 secs...\n",
"Extracting parameters from ./data/new_data/1909_post_eeg_eliseev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 842249 = 0.000 ... 842.249 secs...\n",
"Extracting parameters from ./data/new_data/0307_STRELKOVA.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2103349 = 0.000 ... 2103.349 secs...\n",
"Extracting parameters from ./data/new_data/3110_post_eeg_maistrenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 620899 = 0.000 ... 620.899 secs...\n",
"Extracting parameters from ./data/new_data/2606_patrakeeva_main_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2106049 = 0.000 ... 2106.049 secs...\n",
"Extracting parameters from ./data/new_data/1608_rpre_eeg_polshina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 629449 = 0.000 ... 629.449 secs...\n",
"Extracting parameters from ./data/new_data/2510_pre_eeg_osipova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604099 = 0.000 ... 604.099 secs...\n",
"Extracting parameters from ./data/new_data/0311_eeg_popova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1977699 = 0.000 ... 1977.699 secs...\n",
"Extracting parameters from ./data/new_data/0708_post_eeg_krasovskaya.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 614349 = 0.000 ... 614.349 secs...\n",
"Extracting parameters from ./data/new_data/14071200_limaskaya_post_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604849 = 0.000 ... 604.849 secs...\n",
"Extracting parameters from ./data/new_data/2510_osipova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1958699 = 0.000 ... 1958.699 secs...\n",
"Extracting parameters from ./data/new_data/2809_post_eeg_lukyanov.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602149 = 0.000 ... 602.149 secs...\n",
"Extracting parameters from ./data/new_data/1207_shevchenko_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 614199 = 0.000 ... 614.199 secs...\n",
"Extracting parameters from ./data/new_data/0708_eeg_krasovskaya.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2023149 = 0.000 ... 2023.149 secs...\n",
"Extracting parameters from ./data/new_data/2306_patrakeeva_pre_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Extracting parameters from ./data/new_data/0307_POST_EEG_sTRELKOVA.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 602149 = 0.000 ... 602.149 secs...\n",
"Extracting parameters from ./data/new_data/2509_eeg_rinata.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2129299 = 0.000 ... 2129.299 secs...\n",
"Extracting parameters from ./data/new_data/2509-pre_eeg_rinata.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 724899 = 0.000 ... 724.899 secs...\n",
"Extracting parameters from ./data/new_data/17_11_post_eeg_bachurina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 610499 = 0.000 ... 610.499 secs...\n",
"Extracting parameters from ./data/new_data/1608_eeg_polshina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1961799 = 0.000 ... 1961.799 secs...\n",
"Extracting parameters from ./data/new_data/311_pre_eeg_mazurova.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 604349 = 0.000 ... 604.349 secs...\n",
"Extracting parameters from ./data/new_data/1509_zvyagincev.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1910849 = 0.000 ... 1910.849 secs...\n",
"Extracting parameters from ./data/new_data/1407_limanskaya_eeg.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 2406349 = 0.000 ... 2406.349 secs...\n",
"Extracting parameters from ./data/new_data/3110_pre_eeg_maistrenko.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 663199 = 0.000 ... 663.199 secs...\n",
"Extracting parameters from ./data/new_data/17_11_bachurina.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 1979549 = 0.000 ... 1979.549 secs...\n",
"Extracting parameters from ./data/new_data/0307_STRELKOVA_PRE_EEG.vhdr...\n",
"Setting channel info structure...\n",
"Reading 0 ... 601999 = 0.000 ... 601.999 secs...\n"
]
}
],
"source": [
"test_eeg_dir = \"./data/new_data/\"\n",
"test_eeg_names = [x for x in os.listdir(test_eeg_dir) \n",
" if x[-5:] == \".vhdr\"]\n",
"test_data = np.zeros((0,61))\n",
"\n",
"for eeg_name in test_eeg_names:\n",
" try:\n",
" eeg_data = mne.io.read_raw_brainvision(test_eeg_dir + eeg_name, preload=True).get_data().T\n",
" test_data = np.append(test_data, eeg_data, axis = 0)\n",
" except FileNotFoundError:\n",
" continue"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"test_data_scaled = scaler.fit_transform(test_data)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(18411000, 61)"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_data.shape"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(50462050, 61)"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test_data.shape"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"X_train, X_test, _, _ = train_test_split(train_data_scaled, train_data_scaled, test_size=0.1, random_state = 123)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def create_ae(encoding_dim = 30, channels_num = 61):\n",
" input_data = Input(shape=(channels_num,))\n",
" encoded = Dense(encoding_dim, activation='relu')(input_data)\n",
"\n",
" input_encoded = Input(shape=(encoding_dim,))\n",
" decoded = Dense(channels_num, activation='sigmoid')(input_encoded)\n",
"\n",
" encoder = Model(input_data, encoded, name=\"encoder\")\n",
" decoder = Model(input_encoded, decoded, name=\"decoder\")\n",
"\n",
" autoencoder = Model(input_data, decoder(encoder(input_data)), name=\"autoencoder\")\n",
"\n",
" autoencoder.compile(optimizer='adam', loss='mean_squared_error')\n",
" #autoencoder.summary()\n",
" return encoder, decoder, autoencoder"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(16569900, 61)"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"batch_size = 256\n",
"epoch_num = 7\n",
"\n",
"channels_num = 61\n",
"encoding_dim_vars = [55, 50, 45, 40, 35, 30, 25, 20, 15]\n",
"X_train.shape"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 189s - loss: 0.5858 - val_loss: 0.5845\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 185s - loss: 0.5844 - val_loss: 0.5844\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 184s - loss: 0.5843 - val_loss: 0.5844\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 186s - loss: 0.5842 - val_loss: 0.5842\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 184s - loss: 0.5842 - val_loss: 0.5842\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 183s - loss: 0.5842 - val_loss: 0.5842\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 183s - loss: 0.5842 - val_loss: 0.5842\n",
"55 0.0016191434877703033\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 183s - loss: 0.5844 - val_loss: 0.5831\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 182s - loss: 0.5829 - val_loss: 0.5828\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 185s - loss: 0.5828 - val_loss: 0.5828\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 186s - loss: 0.5827 - val_loss: 0.5828\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 185s - loss: 0.5827 - val_loss: 0.5828\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 184s - loss: 0.5827 - val_loss: 0.5828\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 184s - loss: 0.5827 - val_loss: 0.5828\n",
"50 0.0016000174893919046\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 175s - loss: 0.5859 - val_loss: 0.5841\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 173s - loss: 0.5838 - val_loss: 0.5838\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 174s - loss: 0.5837 - val_loss: 0.5837\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 176s - loss: 0.5837 - val_loss: 0.5837\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 176s - loss: 0.5836 - val_loss: 0.5837\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 177s - loss: 0.5836 - val_loss: 0.5837\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 176s - loss: 0.5836 - val_loss: 0.5836\n",
"45 0.0016036925670046172\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 172s - loss: 0.5853 - val_loss: 0.5837\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 174s - loss: 0.5836 - val_loss: 0.5836\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 175s - loss: 0.5836 - val_loss: 0.5836\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 174s - loss: 0.5836 - val_loss: 0.5836\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 171s - loss: 0.5834 - val_loss: 0.5831\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 169s - loss: 0.5830 - val_loss: 0.5831\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 173s - loss: 0.5830 - val_loss: 0.5831\n",
"40 0.0016194642290537295\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 172s - loss: 0.5874 - val_loss: 0.5849\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 172s - loss: 0.5848 - val_loss: 0.5848\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 179s - loss: 0.5847 - val_loss: 0.5848\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 175s - loss: 0.5845 - val_loss: 0.5839\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 177s - loss: 0.5838 - val_loss: 0.5838\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 179s - loss: 0.5838 - val_loss: 0.5838\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 177s - loss: 0.5838 - val_loss: 0.5838\n",
"35 0.0016373105322479613\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 175s - loss: 0.5861 - val_loss: 0.5843\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 175s - loss: 0.5834 - val_loss: 0.5833\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 173s - loss: 0.5832 - val_loss: 0.5833\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 169s - loss: 0.5832 - val_loss: 0.5833\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 169s - loss: 0.5832 - val_loss: 0.5832\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 169s - loss: 0.5832 - val_loss: 0.5832\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 168s - loss: 0.5831 - val_loss: 0.5831\n",
"30 0.0016457742816988015\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 163s - loss: 0.5902 - val_loss: 0.5882\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 164s - loss: 0.5881 - val_loss: 0.5881\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 167s - loss: 0.5881 - val_loss: 0.5881\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 166s - loss: 0.5879 - val_loss: 0.5879\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 164s - loss: 0.5876 - val_loss: 0.5876\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 162s - loss: 0.5876 - val_loss: 0.5876\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 164s - loss: 0.5875 - val_loss: 0.5876\n",
"25 0.0016772023516865354\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 160s - loss: 0.5907 - val_loss: 0.5881\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 160s - loss: 0.5879 - val_loss: 0.5879\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 159s - loss: 0.5879 - val_loss: 0.5879\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 160s - loss: 0.5878 - val_loss: 0.5878\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 162s - loss: 0.5878 - val_loss: 0.5878\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 160s - loss: 0.5875 - val_loss: 0.5874\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 161s - loss: 0.5874 - val_loss: 0.5874\n",
"20 0.0016114161782412179\n",
"Train on 16569900 samples, validate on 1841100 samples\n",
"Epoch 1/7\n",
"16569900/16569900 [==============================] - 158s - loss: 0.5994 - val_loss: 0.5959\n",
"Epoch 2/7\n",
"16569900/16569900 [==============================] - 159s - loss: 0.5958 - val_loss: 0.5952\n",
"Epoch 3/7\n",
"16569900/16569900 [==============================] - 159s - loss: 0.5951 - val_loss: 0.5951\n",
"Epoch 4/7\n",
"16569900/16569900 [==============================] - 160s - loss: 0.5950 - val_loss: 0.5950\n",
"Epoch 5/7\n",
"16569900/16569900 [==============================] - 165s - loss: 0.5949 - val_loss: 0.5949\n",
"Epoch 6/7\n",
"16569900/16569900 [==============================] - 166s - loss: 0.5949 - val_loss: 0.5949\n",
"Epoch 7/7\n",
"16569900/16569900 [==============================] - 165s - loss: 0.5945 - val_loss: 0.5944\n",
"15 0.0016173533817821755\n"
]
}
],
"source": [
"mse_vars = []\n",
"\n",
"for enc_dim in encoding_dim_vars:\n",
" encoder, decoder, autoencoder = create_ae(enc_dim)\n",
" hist = autoencoder.fit(X_train, X_train,\n",
" epochs=epoch_num,\n",
" batch_size = batch_size,\n",
" verbose=1, #Verbosity mode. 0 = silent, 1 = progress bar, 2 = one line per epoch.\n",
" validation_data=(X_test, X_test))\n",
" test_data_decoded = autoencoder.predict(test_data_scaled)\n",
" test_data_predict = scaler.inverse_transform(test_data_decoded)\n",
" mse = mean_squared_error(test_data, test_data_predict)\n",
" mse_vars.append(mse)\n",
" print(enc_dim, mse)"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"x = np.array(encoding_dim_vars)\n",
"y = np.array(mse_vars)\n",
"y *= 100;\n",
"x = x / 61."
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZIAAAEWCAYAAABMoxE0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAHfpJREFUeJzt3X2UXXV97/H35ybkGpAYMFMeQjRxNRIiatSBq9XlVRF5\n8NYEpRp8AnUVaAXELrhGe31s75UqLrU1hQs0ilhFRR6iVZDCwva6qOZEgjwZjZGYjIEMIqJIISGf\n+8feQw6HmTNnsmfPOZP5vNY6a/b+7d/e53tmJvPJfvpt2SYiImJ3/ZduFxAREZNbgiQiIipJkERE\nRCUJkoiIqCRBEhERlSRIIiKikgRJxCQlab4kS5o+nn0jxipBEns8SXdLelTSnJb2W8o/rvPL+UMk\nfUPSfZJ+K+l2SaeUy4b+EP++5fWmCaj/FeV7v6/u94rYHQmSmCp+AZw0NCPpucDeLX0uAzYDzwSe\nDrwNuLelz2zbT216fbXGmoecDNwPvH0C3itizBIkMVVcxhP/EJ8MfLGlzxHAF2w/ZHuH7Vtsf2es\nbyTpTZIaLW3vlbS6nD5e0p2SfidpQNI5bba1D3Ai8G5goaT+Nn1vkvRxST+U9KCkayTt39LtLZJ+\nWe51/XXTukdKulnSA5K2SvqcpBlj/ewxNSVIYqr4D2CWpMMkTQOWA18aps9KScslPaPCe30TOFTS\nwqa2NwNfLqf/CTjN9r7A4cCNbbb1euD3wNeB6ygCsJ23A+8EDgJ2AH/fsvxlwKHAUcCHJB1Wtj8G\nvBeYA7ykXP6Xo7xXBJAgiallaK/kaOAuYKBl+Z8B/w58EPiFpHWSjmjpc1/5v/ah12Ety7H9B+Aa\nykNpZaAsAlaXXbYDiyXNsv0b2z9qU/PJwFdtP0YRRMsl7dXuM9q+3fZD5ed4YxmcQz5q+2HbtwK3\nAs8va15r+z/KPbG7gf8L/Pc27xPxuARJTCWXUewZnMKTD2tR/lFfYfs5wAHAOuBqSWrqNsf27KbX\nXSO815fZdU7mzcDVZcAAvAE4Htgk6XuSXjLcBiTNA14J/HPZdA3wFOC1bT7j5qbpTcBeFHsZQ+5p\nmv4D8NTyvZ4t6VuS7pH0IPB/WtaLGFGCJKYM25soTrofD1w5St/7gPOBg4HW8wyduB7ok7SEIlCG\nDmthe43tpcAfAVcDXxthG2+j+Df6TUn3ABspgqTd4a15TdPPoNj7ua+Dei8AfgIstD0L+ACg9qtE\nFBIkMdW8C3hVeejnCST9naTDJU2XtC/wF8AG278e65vY3k5xXuOTFEF0ffkeMyS9RdLTyj4PAjtH\n2MzJwEeBJU2vNwDHS3r6COu8VdJiSXsDHwOuKA+LjWbfspbfS1pE8dkjOpIgiSnF9s9tN0ZYvDdw\nFfAAxf/+nwm8rqXPAy33kfxVm7f7MvBq4Ou2dzS1vw24uzyEdDrwltYVJb24fP+Vtu9peq0GNtB0\nKXOLy4AvUBzCegpwVpv6mp1DcQjud8DFwERc1hx7COXBVhF7Bkk3AV+yfUm3a4mpJXskERFRSYIk\nIiIqyaGtiIioJHskERFRyZQYUnrOnDmeP39+t8uIiJhU1q5de5/tvtH6TYkgmT9/Po3GSFd8RkTE\ncCRt6qRfDm1FREQlCZKIiKgkQRIREZUkSCIiopIESUREVJIgiYiIShIkERFRSYIkIiIqSZBEREQl\nCZKIiKgkQRIREZUkSCIiopIESUREVJIgiYiISmoNEknHSlovaYOkFcMsXyTpZkmPSDqnZdl7Jd0h\n6XZJX5H0lLJ9f0nXS/pZ+XW/Oj9DRES0V1uQSJoGrASOAxYDJ0la3NLtfuAs4PyWdeeW7f22Dwem\nAcvLxSuAG2wvBG4o5yMiokvq3CM5Ethge6PtR4HLgaXNHWxvs70G2D7M+tOBmZKmA3sDvyrblwKX\nltOXAsvqKD4iIjpTZ5DMBTY3zW8p20Zle4BiL+WXwFbgt7a/Wy4+wPbWcvoe4IDhtiHpVEkNSY3B\nwcHdqT8iIjrQkyfby/MeS4EFwMHAPpLe2trPtgEPtw3bF9nut93f1zfqI4cjImI31RkkA8C8pvlD\nyrZOvBr4he1B29uBK4E/KZfdK+kggPLrtnGqNyIidkOdQbIGWChpgaQZFCfLV3e47i+BF0vaW5KA\no4C7ymWrgZPL6ZOBa8ax5oiIGKPpdW3Y9g5JZwDXUVx1tcr2HZJOL5dfKOlAoAHMAnZKOhtYbPsH\nkq4AfgTsAG4BLio3fR7wNUnvAjYBb6zrM0RExOhUnGbYs/X397vRaHS7jIiISUXSWtv9o/XryZPt\nERExeSRIIiKikgRJRERUkiCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERlSRIIiKikgRJ\nRERUkiCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERlSRIIiKikgRJRERUUmuQSDpW0npJ\nGyStGGb5Ikk3S3pE0jlN7YdKWtf0elDS2eWyj0gaaFp2fJ2fISIi2pte14YlTQNWAkcDW4A1klbb\nvrOp2/3AWcCy5nVtrweWNG1nALiqqcunbZ9fV+0REdG5OvdIjgQ22N5o+1HgcmBpcwfb22yvAba3\n2c5RwM9tb6qv1IiI2F11BslcYHPT/JaybayWA19paTtT0o8lrZK033ArSTpVUkNSY3BwcDfeNiIi\nOtHTJ9slzQBeB3y9qfkC4FkUh762Ap8abl3bF9nut93f19dXe60REVNVnUEyAMxrmj+kbBuL44Af\n2b53qMH2vbYfs70TuJjiEFpERHRJnUGyBlgoaUG5Z7EcWD3GbZxEy2EtSQc1zZ4A3F6pyoiIqKS2\nq7Zs75B0BnAdMA1YZfsOSaeXyy+UdCDQAGYBO8tLfBfbflDSPhRXfJ3WsulPSFoCGLh7mOURETGB\nZLvbNdSuv7/fjUaj22VEREwqktba7h+tX0+fbI+IiN6XIImIiEoSJBERUUmCJCIiKkmQREREJQmS\niIioJEESERGVJEgiIqKSBElERFSSIImIiEoSJBERUUmCJCIiKkmQREREJQmSiIioJEESERGVJEgi\nIqKSBElERFSSIImIiEoSJBERUUmtQSLpWEnrJW2QtGKY5Ysk3SzpEUnnNLUfKmld0+tBSWeXy/aX\ndL2kn5Vf96vzM0RERHu1BYmkacBK4DhgMXCSpMUt3e4HzgLOb260vd72EttLgBcBfwCuKhevAG6w\nvRC4oZyPiIguqXOP5Ehgg+2Nth8FLgeWNnewvc32GmB7m+0cBfzc9qZyfilwaTl9KbBsfMuOiIix\nqDNI5gKbm+a3lG1jtRz4StP8Aba3ltP3AAcMt5KkUyU1JDUGBwd3420jIqITPX2yXdIM4HXA14db\nbtuAR1h2ke1+2/19fX01VhkRMbXVGSQDwLym+UPKtrE4DviR7Xub2u6VdBBA+XVbpSojIqKSOoNk\nDbBQ0oJyz2I5sHqM2ziJJx7WotzGyeX0ycA1laqMiIhKpte1Yds7JJ0BXAdMA1bZvkPS6eXyCyUd\nCDSAWcDO8hLfxbYflLQPcDRwWsumzwO+JuldwCbgjXV9hoiIGJ2K0wx7tv7+fjcajW6XERExqUha\na7t/tH49fbI9IiJ6X4IkIiIqSZBEREQltZ1sj6np6lsG+OR16/nVAw9z8OyZnHvMoSx7we7chxoR\nk0WCJMbN1bcM8P4rb+Ph7Y8BMPDAw7z/ytsAEiYRe7C2QSLpGIqxrIb+CgwA19i+tu7CYvL55HXr\nHw+RIQ9vf4xPXrc+QRKxBxsxSCR9Bng28EWKcbKguDv9LEnH2X7PBNQXk8ivHnh4TO0RsWdot0dy\nvO1ntzZK+irwUyBBEk9w8OyZDAwTGgfPntmFaiJiorS7aus/JR0xTPsRwH/WVE9MYucecygz95r2\nhLaZe03j3GMO7VJFETER2u2RnAJcIGlfdh3amgf8tlwW8QRD50Fy1VbE1DJikNj+EfDfyvGwHj/Z\nbvueCaksJqVlL5ib4IiYYka7akvAM9kVJNMl3eupMEBXRER0pN1VW68B/hH4GbueI3II8MeS/tL2\ndyegvoiI6HHt9kg+C7za9t3NjZIWAN8GDquxroiImCTaXbU1nV0n2ZsNAHvVU05EREw27fZIVgFr\nJF0ObC7b5lE86fCf6i4sIiImh3ZXbX1c0tXAUuAlZfMA8Bbbd05EcRER0fvaXrVl+y7grgmqJSIi\nJqHdeh6JpO+MdyERETE5jRgkkl44wutFwJJONi7pWEnrJW2QtGKY5Ysk3SzpEUnntCybLekKST+R\ndJekl5TtH5E0IGld+Tp+jJ85IiLGUbtDW2uA7wEaZtns0TYsaRqwEjia4uqvNZJWt5xfuR84i2Ko\n+lafBa61faKkGcDeTcs+bfv80WqIiIj6tQuSu4DTbP+sdYGkzcP0b3UksMH2xnKdyylO3D8eJLa3\nAdskvbZl+08DXk45ppftR4FHO3jPiCfJUxsj6tXuHMlH2iw/s4Ntz2XXZcNQ7JV0+q93ATAIfF7S\nLZIukbRP8/tL+rGkVZL2G24Dkk6V1JDUGBwc7PBtY08z9NTGgQcexux6auPVtwyMum5EdGbEILF9\nhe31Iyy7ur6SgGJP6YXABbZfADwEDJ1juQB4FsV5mq3Ap0ao8SLb/bb7+/r6ai43elW7pzZGxPjY\nrau2OjRAcQPjkEPYNWbXaLYAW2z/oJy/giJYsH2v7cds7wQupjiEFjGsPLUxon51BskaYKGkBeXJ\n8uXA6k5WLIeq3yxp6IlIR1GeW5F0UFPXE4Dbx6/k2NOM9HTGPLUxYvy0vSGxCts7JJ0BXAdMA1bZ\nvkPS6eXyC8tnnTSAWcBOSWcDi20/SHEe5p/LENoIvKPc9CckLQEM3A2cVtdniMnv3GMO5f1X3vaE\nw1u98NTGXAAQexK1e7SIpL+1/b8kfcz2hyawrnHV39/vRqPR7TKiS3rtj/bQBQCt4fbx1z83YRI9\nRdJa2/2j9Rttj2SNpJUUexURk1KvPbWx3QUAvVRnRKfaPdjqw8D+wEnAdklLbH9swiqL2EPlAoDY\n07S7/Pej5eRLyvmESMQ4yAUAsacZ7aqtz5f3knx+IoqJmArOPeZQZu417QltvXABQMTuGm0Y+XXl\n11snppyIPd/QeZBeugAgooraLv+NiJH12gUAEVXUeUNiRERMAe2eR/LWpumXtiw7o86iIiJi8mh3\naOuvgC+V0/9AOdZV6Z3A5+oqKiImXq/duBmd6/bPrl2QaITp4eb3eN3+QUXUqfVu+6Hh9oH8nve4\nXvjZtTtH4hGmh5vfo+WZFrGny3D7k1cv/OzaBcmi8uFRtzVND81PqQvee+EHFVGn3G0/efXCz67d\noa3DJqyKHtcLP6jh5HBbjJeDZ89kYJjf59xt3/t64WfXboiUTc0v4PcUJ9znlPNTRi8OaZHDbTGe\ncrf95NULP7t2l/9+S9Lh5fRBFA+QeidwWfnckCmjF35QrXK4LcbTshfM5eOvfy5zZ89EwNzZMzOs\n/STRCz+7doe2FtgeevrgO4Drbb9d0r7A94HP1F5dj+jFIS169XBbTF65237y6vbPrl2QbG+aPori\n+ejY/p2knbVW1YO6/YNq1QvHRSMioP1VW5slnSnpBIpzI9cCSJoJ7DURxcXIevFwW8R4u/qWAV56\n3o0sWPEvvPS8G3MOsEe12yN5F/Ax4NXAm2w/ULa/mAwr33W9eLgtYjz1wo120Zm2z2yvvHHpWOCz\nwDTgEtvntSxfRBFKLwT+2vb5TctmA5cAh1PcAPlO2zdL2h/4KjAfuBt4o+3ftKsjz2yPmHxeet6N\nwx6+nTt7Jt9f8aouVFSYSpfdV35mu6TV7Va0/bpRCpgGrASOBrZQPP99te07m7rdD5wFLBtmE58F\nrrV9oqQZwN5l+wrgBtvnSVpRzr+vXS0RMfn04gUl2UsaXrtDWy8BNgNfAX7A2MfXOhLYYHsjgKTL\ngaXA40FiexuwTdJrm1eU9DTg5cApZb9HgUfLxUuBV5TTlwI3kSCJ2OP04gUl7S67n8pB0u5k+4HA\nBygOLX2WYs/iPtvfs/29DrY9lyKIhmwp2zqxABgEPi/pFkmXSNqnXHaA7a3l9D3AAcNtQNKpkhqS\nGoODgx2+bUT0il68oKQX95J6Qbs72x+zfa3tkylOsG8AbpqgZ5FMpzhvcoHtFwAPURzCaq3RjDCA\npO2LbPfb7u/r66u12IgYf71wo12rXhzlohe0fdSupP8KvBY4ieLk9t8DV3W47QFgXtP8IWVbJ7YA\nW2z/oJy/gl1Bcq+kg2xvLe+439bhNiNikum1+7fOPebQJ5wjge7vJfWCdifbv0hxWOvbwEeb7nLv\n1BpgoaQFFAGyHHhzJyvavkfSZkmH2l5PcUPk0LmV1cDJwHnl12vGWFdExG7JZffDG/Hy3/Lu9YfK\n2eZOojiqNGvUjUvHUwylMg1YZft/SzqdYgMXSjoQaACzgJ0UA0Mutv2gpCUUl//OADYC77D9G0lP\nB74GPAPYRHH57/3t6sjlvxERY9fp5b+13kfSKxIkERFj12mQtLtqKyIiYlQJkoiIqCRBEhERlSRI\nIiKikgRJRERUkiCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERlSRIIiKikgRJRERUkiCJ\niIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERldQaJJKOlbRe0gZJK4ZZvkjSzZIekXROy7K7\nJd0maZ2kRlP7RyQNlO3rJB1f52eIiIj2pte1YUnTgJXA0cAWYI2k1bbvbOp2P3AWsGyEzbzS9n3D\ntH/a9vnjWnBEROyWOvdIjgQ22N5o+1HgcmBpcwfb22yvAbbXWEdERNSoziCZC2xumt9StnXKwL9K\nWivp1JZlZ0r6saRVkvYbbmVJp0pqSGoMDg6OrfKIiOhYL59sf5ntJcBxwLslvbxsvwB4FrAE2Ap8\nariVbV9ku992f19f34QUHBExFdUZJAPAvKb5Q8q2jtgeKL9uA66iOFSG7XttP2Z7J3DxUHtERHRH\nnUGyBlgoaYGkGcByYHUnK0raR9K+Q9PAa4Dby/mDmrqeMNQeERHdUdtVW7Z3SDoDuA6YBqyyfYek\n08vlF0o6EGgAs4Cdks4GFgNzgKskDdX4ZdvXlpv+hKQlFOdQ7gZOq+szRETE6GS72zXUrr+/341G\nY/SOERHxOElrbfeP1q+XT7ZHRMQkkCCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERlSRI\nIiKikgRJRERUkiCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERlSRIIiKikgRJRERUkiCJ\niIhKEiQREVFJrUEi6VhJ6yVtkLRimOWLJN0s6RFJ57Qsu1vSbZLWSWo0te8v6XpJPyu/7lfnZ4iI\niPZqCxJJ04CVwHHAYuAkSYtbut0PnAWcP8JmXml7ScvD51cAN9heCNxQzkdERJfUuUdyJLDB9kbb\njwKXA0ubO9jeZnsNsH0M210KXFpOXwosG49iIyJi99QZJHOBzU3zW8q2Thn4V0lrJZ3a1H6A7a3l\n9D3AAcOtLOlUSQ1JjcHBwbHUHRERY9DLJ9tfZnsJxaGxd0t6eWsH26YInCexfZHtftv9fX19NZca\nETF11RkkA8C8pvlDyraO2B4ov24DrqI4VAZwr6SDAMqv28al2oiI2C11BskaYKGkBZJmAMuB1Z2s\nKGkfSfsOTQOvAW4vF68GTi6nTwauGdeqIyJiTKbXtWHbOySdAVwHTANW2b5D0unl8gslHQg0gFnA\nTklnU1zhNQe4StJQjV+2fW256fOAr0l6F7AJeGNdnyEiIkan4jTDnq2/v9+NRmP0jhER8ThJa1tu\nvxhWL59sj4iISSBBEhERlSRIIiKikgRJRERUkiCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRB\nEhERlSRIIiKikgRJRERUkiCJiIhKEiQREVFJgiQiIipJkERERCUJkoiIqCRBEhERlSRIIiKiklqD\nRNKxktZL2iBpxTDLF0m6WdIjks4ZZvk0SbdI+lZT20ckDUhaV76Or/MzREREe9Pr2rCkacBK4Ghg\nC7BG0mrbdzZ1ux84C1g2wmbeA9wFzGpp/7Tt88e55IiI2A117pEcCWywvdH2o8DlwNLmDra32V4D\nbG9dWdIhwGuBS2qsMSIiKqozSOYCm5vmt5RtnfoM8D+BncMsO1PSjyWtkrTfcCtLOlVSQ1JjcHBw\nDG8bERFj0ZMn2yX9D2Cb7bXDLL4AeBawBNgKfGq4bdi+yHa/7f6+vr76io2ImOLqDJIBYF7T/CFl\nWydeCrxO0t0Uh8ReJelLALbvtf2Y7Z3AxRSH0CIioktqO9kOrAEWSlpAESDLgTd3sqLt9wPvB5D0\nCuAc228t5w+yvbXsegJw+2jbW7t27X2SNo35E3TPHOC+bhcxRql5YqTmiTMZ6x7vmp/ZSafagsT2\nDklnANcB04BVtu+QdHq5/EJJBwINiquydko6G1hs+8E2m/6EpCWAgbuB0zqoZVId25LUsN3f7TrG\nIjVPjNQ8cSZj3d2quc49Emx/G/h2S9uFTdP3UBzyareNm4CbmubfNq5FRkREJT15sj0iIiaPBElv\nuqjbBeyG1DwxUvPEmYx1d6Vm2e7G+0ZExB4ieyQREVFJgiQiIipJkHRJByMjLy2HgVlXDvXysm7U\n2VJT25qb+h0haYekEyeyvpF08L1+haTfNo0o/aFu1NlS06jf67LudZLukPS9ia5xmHpG+z6f2/Q9\nvl3SY5L270atTTWNVvPTJH1T0q3l9/kd3aizpabRat5P0lXl348fSjq89qJs5zXBL4r7an5OMdTL\nDOBWivtnmvs8lV3nsJ4H/KTXa27qdyPFZd8nTpLv9SuAb3W71jHWPBu4E3hGOf9HvV5zS/8/BW7s\n9ZqBDwB/V073UYxYPqPHa/4k8OFyehFwQ911ZY+kOzoZGfn3Ln8TgH0obsDsplFrLp0JfAPYNpHF\ntdFp3b2kk5rfDFxp+5dQjKQ9wTW2Guv3+STgKxNS2cg6qdnAvpJE8Z+7+4EdE1vmE3RS82KK/8xh\n+yfAfEkH1FlUgqQ7OhoZWdIJkn4C/AvwzgmqbSSj1ixpLsWwNRdMYF2j6XQU6j8pDwV8R9JzJqa0\nEXVS87OB/STdJGmtpLdPWHXD63i0b0l7A8dS/Iejmzqp+XPAYcCvgNuA97gY569bOqn5VuD1AJKO\npBjmpO2N31UlSHqY7atsL6J48NffdLueDnwGeF+X/6Htjh9RHCJ6HvAPwNVdrqcT04EXUTyz5xjg\ng5Ke3d2SOvanwPdt39/tQjpwDLAOOJhixPHPSWp90F6vOQ+YLWkdxRGCW4DH6nzDWodIiRGNaWRk\n2/8m6VmS5tju1iByndTcD1xeHAVgDnC8pB22u/mHedS63TS2m+1vS/rHSfC93gL82vZDwEOS/g14\nPvDTiSnxScbyO72c7h/Wgs5qfgdwXnmYeYOkX1Ccd/jhxJT4JJ3+Pr8DoDwk9wtgY61Vdeuk0VR+\nUQT4RmABu06YPaelzx+z62T7C8tfFvVyzS39v0BvnGzv5Ht9YNP3+kjgl73+vaY43HJD2XdvilGw\nD+/lmst+T6M4z7DPJPnduAD4SDl9QPnvcE6P1zyb8oIA4M+BL9ZdV/ZIusAdjIwMvAF4u6TtwMPA\nm1z+ZvRwzT2nw7pPBP5C0g6K7/XyXv9e275L0rXAjymeInqJ7VEfqdDNmsuuJwDfdbEn1VUd1vw3\nwBck3QaI4tBt14aW77Dmw4BLJRm4A3hX3XVliJSIiKgkJ9sjIqKSBElERFSSIImIiEoSJBERUUmC\nJCIiKkmQRIwjScskWdKicn6+pLaX5XbSJ6KXJUgixtdJwP8rv0ZMCQmSiHEi6anAyyhuAFs+zPJT\nJF1TDrT4M0kfblo8TdLF5TMvvitpZrnOn0taUz4P4xvlgIcRPSVBEjF+lgLX2v4p8GtJLxqmz5EU\noxY8D/gzSf1l+0Jgpe3nAA+UfaAYKv4I288H7mIC7lKOGKsEScT4OYni+RCUX4c7vHW97V/bfhi4\nkmIPBuAXtteV02uB+eX04ZL+vRyi4y1At4e4j3iSjLUVMQ7KR8a+CnhuOcbRNIqHIq1s6do6JtHQ\n/CNNbY8BM8vpLwDLbN8q6RSKpzlG9JTskUSMjxOBy2w/0/Z82/Mohu+e19LvaEn7l+dAlgHfH2W7\n+wJbJe1FsUcS0XMSJBHj4yTgqpa2bwDvb2n7Ydn+Y+AbthujbPeDwA8oAucn41BnxLjL6L8RE6Q8\nNNVv+4xu1xIxnrJHEhERlWSPJCIiKskeSUREVJIgiYiIShIkERFRSYIkIiIqSZBEREQl/x/a0aeI\nQAJw9gAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fa7deebd278>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.scatter(x, y)\n",
"plt.title(\"MSE vs Alpha\")\n",
"plt.xlabel(\"Alpha\")\n",
"plt.ylabel(\"MSE * 100\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment