Datasets
Models
Downloads: 1
Diff of
/MultiscaleNetRefactored.ipynb
[000000]
..
[a8e9b4]
Switch to unified view
| a | b/MultiscaleNetRefactored.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 17, |
||
| 6 | "metadata": { |
||
| 7 | "collapsed": true |
||
| 8 | }, |
||
| 9 | "outputs": [], |
||
| 10 | "source": [ |
||
| 11 | "import os\n", |
||
| 12 | "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\"" |
||
| 13 | ] |
||
| 14 | }, |
||
| 15 | { |
||
| 16 | "cell_type": "markdown", |
||
| 17 | "metadata": {}, |
||
| 18 | "source": [ |
||
| 19 | "This notebook is a refactored version of a Multiscale Convolutional Network solution for NeuroHack at Yandex" |
||
| 20 | ] |
||
| 21 | }, |
||
| 22 | { |
||
| 23 | "cell_type": "code", |
||
| 24 | "execution_count": 4, |
||
| 25 | "metadata": { |
||
| 26 | "collapsed": true |
||
| 27 | }, |
||
| 28 | "outputs": [], |
||
| 29 | "source": [ |
||
| 30 | "import random\n", |
||
| 31 | "\n", |
||
| 32 | "from tqdm import tqdm\n", |
||
| 33 | "import pandas as pd\n", |
||
| 34 | "import h5py\n", |
||
| 35 | "import numpy as np\n", |
||
| 36 | "from scipy.signal import resample" |
||
| 37 | ] |
||
| 38 | }, |
||
| 39 | { |
||
| 40 | "cell_type": "code", |
||
| 41 | "execution_count": 5, |
||
| 42 | "metadata": { |
||
| 43 | "collapsed": true |
||
| 44 | }, |
||
| 45 | "outputs": [], |
||
| 46 | "source": [ |
||
| 47 | "train_path = \"hackaton_data/train.h5\"\n", |
||
| 48 | "test_path = \"hackaton_data/test.h5\"\n", |
||
| 49 | "model_dump_path = \"hackaton_data/convnet-multiscale-true-01988\"\n", |
||
| 50 | "\n", |
||
| 51 | "slice_len = 1125" |
||
| 52 | ] |
||
| 53 | }, |
||
| 54 | { |
||
| 55 | "cell_type": "markdown", |
||
| 56 | "metadata": {}, |
||
| 57 | "source": [ |
||
| 58 | "Read train data into a dict of (subject_id, (X, y)) pairs" |
||
| 59 | ] |
||
| 60 | }, |
||
| 61 | { |
||
| 62 | "cell_type": "code", |
||
| 63 | "execution_count": 6, |
||
| 64 | "metadata": { |
||
| 65 | "collapsed": false |
||
| 66 | }, |
||
| 67 | "outputs": [], |
||
| 68 | "source": [ |
||
| 69 | "subjects = {}\n", |
||
| 70 | "with h5py.File(train_path, \"r\") as data_file:\n", |
||
| 71 | " for subject, subject_data in data_file.items():\n", |
||
| 72 | " X = subject_data[\"data\"][:]\n", |
||
| 73 | " y = subject_data[\"labels\"][:][0]\n", |
||
| 74 | " subjects[subject] = (X, y)" |
||
| 75 | ] |
||
| 76 | }, |
||
| 77 | { |
||
| 78 | "cell_type": "markdown", |
||
| 79 | "metadata": {}, |
||
| 80 | "source": [ |
||
| 81 | "We need to split our data into train and local validation sets. For local validation we select random slices of slice_len. They may overlap with slices in train set, this split is not optimal." |
||
| 82 | ] |
||
| 83 | }, |
||
| 84 | { |
||
| 85 | "cell_type": "code", |
||
| 86 | "execution_count": 7, |
||
| 87 | "metadata": { |
||
| 88 | "collapsed": false |
||
| 89 | }, |
||
| 90 | "outputs": [], |
||
| 91 | "source": [ |
||
| 92 | "from sklearn.model_selection import train_test_split\n", |
||
| 93 | "\n", |
||
| 94 | "def train_val_split(X, y):\n", |
||
| 95 | " start_indices = list(range(0, len(X) - slice_len))\n", |
||
| 96 | " y = y[:len(start_indices)]\n", |
||
| 97 | " indices_train, indices_test, _, _ = train_test_split(start_indices, y)\n", |
||
| 98 | " return {\"train_ind\": indices_train, \"val_ind\": indices_test, \"X\": X, \"y\": y}" |
||
| 99 | ] |
||
| 100 | }, |
||
| 101 | { |
||
| 102 | "cell_type": "code", |
||
| 103 | "execution_count": 8, |
||
| 104 | "metadata": { |
||
| 105 | "collapsed": false |
||
| 106 | }, |
||
| 107 | "outputs": [], |
||
| 108 | "source": [ |
||
| 109 | "for subject in subjects:\n", |
||
| 110 | " X, y = subjects[subject][0], subjects[subject][1]\n", |
||
| 111 | " X = X.T\n", |
||
| 112 | " subjects[subject] = train_val_split(X, y)" |
||
| 113 | ] |
||
| 114 | }, |
||
| 115 | { |
||
| 116 | "cell_type": "markdown", |
||
| 117 | "metadata": {}, |
||
| 118 | "source": [ |
||
| 119 | "Define utility function to convert class labels to one-hot encoding" |
||
| 120 | ] |
||
| 121 | }, |
||
| 122 | { |
||
| 123 | "cell_type": "code", |
||
| 124 | "execution_count": 9, |
||
| 125 | "metadata": { |
||
| 126 | "collapsed": false |
||
| 127 | }, |
||
| 128 | "outputs": [], |
||
| 129 | "source": [ |
||
| 130 | "def to_onehot(y):\n", |
||
| 131 | " onehot = np.zeros(3)\n", |
||
| 132 | " onehot[y] = 1\n", |
||
| 133 | " return onehot" |
||
| 134 | ] |
||
| 135 | }, |
||
| 136 | { |
||
| 137 | "cell_type": "markdown", |
||
| 138 | "metadata": {}, |
||
| 139 | "source": [ |
||
| 140 | "Define a funtion that will select random subject and find a random subsequence of consistent class" |
||
| 141 | ] |
||
| 142 | }, |
||
| 143 | { |
||
| 144 | "cell_type": "code", |
||
| 145 | "execution_count": 10, |
||
| 146 | "metadata": { |
||
| 147 | "collapsed": true |
||
| 148 | }, |
||
| 149 | "outputs": [], |
||
| 150 | "source": [ |
||
| 151 | "def generate_slice(slice_len, val=False):\n", |
||
| 152 | " subject_data = random.choice(list(subjects.values()))\n", |
||
| 153 | " if val is True:\n", |
||
| 154 | " indices, y, X = subject_data[\"val_ind\"], subject_data[\"y\"], subject_data[\"X\"]\n", |
||
| 155 | " else:\n", |
||
| 156 | " indices, y, X = subject_data[\"train_ind\"], subject_data[\"y\"], subject_data[\"X\"]\n", |
||
| 157 | " \n", |
||
| 158 | " while True:\n", |
||
| 159 | " slice_start = random.choice(indices)\n", |
||
| 160 | " slice_end = slice_start + slice_len\n", |
||
| 161 | " slice_x = X[slice_start:slice_end]\n", |
||
| 162 | " slice_y = y[slice_start:slice_end]\n", |
||
| 163 | " \n", |
||
| 164 | " if len(set(slice_y)) == 1:\n", |
||
| 165 | " return slice_x, to_onehot(slice_y)" |
||
| 166 | ] |
||
| 167 | }, |
||
| 168 | { |
||
| 169 | "cell_type": "markdown", |
||
| 170 | "metadata": {}, |
||
| 171 | "source": [ |
||
| 172 | "Define a generator that will yield batches of resampled input time series and according class labels in infinite loop" |
||
| 173 | ] |
||
| 174 | }, |
||
| 175 | { |
||
| 176 | "cell_type": "code", |
||
| 177 | "execution_count": 11, |
||
| 178 | "metadata": { |
||
| 179 | "collapsed": true |
||
| 180 | }, |
||
| 181 | "outputs": [], |
||
| 182 | "source": [ |
||
| 183 | "def data_generator(batch_size, slice_len, val=False):\n", |
||
| 184 | " while True:\n", |
||
| 185 | " batch_x = []\n", |
||
| 186 | " batch_y = []\n", |
||
| 187 | " \n", |
||
| 188 | " for i in range(0, batch_size):\n", |
||
| 189 | " x, y = generate_slice(slice_len, val=val)\n", |
||
| 190 | " batch_x.append(x)\n", |
||
| 191 | " batch_y.append(y)\n", |
||
| 192 | " \n", |
||
| 193 | " y = np.array(batch_y)\n", |
||
| 194 | " \n", |
||
| 195 | " x_256 = np.array([resample(i, 256) for i in batch_x])\n", |
||
| 196 | " x_500 = np.array([resample(i, 500) for i in batch_x])\n", |
||
| 197 | " x = np.array([i for i in batch_x])\n", |
||
| 198 | " yield ([x_256, x_500, x], y)" |
||
| 199 | ] |
||
| 200 | }, |
||
| 201 | { |
||
| 202 | "cell_type": "markdown", |
||
| 203 | "metadata": {}, |
||
| 204 | "source": [ |
||
| 205 | "Lets build a neural network. Import all needed layers and keras utilities" |
||
| 206 | ] |
||
| 207 | }, |
||
| 208 | { |
||
| 209 | "cell_type": "code", |
||
| 210 | "execution_count": 12, |
||
| 211 | "metadata": { |
||
| 212 | "collapsed": false |
||
| 213 | }, |
||
| 214 | "outputs": [ |
||
| 215 | { |
||
| 216 | "name": "stderr", |
||
| 217 | "output_type": "stream", |
||
| 218 | "text": [ |
||
| 219 | "Using TensorFlow backend.\n" |
||
| 220 | ] |
||
| 221 | } |
||
| 222 | ], |
||
| 223 | "source": [ |
||
| 224 | "from keras.layers import Convolution1D, Dense, Dropout, Input, merge, GlobalMaxPooling1D\n", |
||
| 225 | "from keras.models import Model, load_model\n", |
||
| 226 | "from keras.optimizers import RMSprop" |
||
| 227 | ] |
||
| 228 | }, |
||
| 229 | { |
||
| 230 | "cell_type": "markdown", |
||
| 231 | "metadata": {}, |
||
| 232 | "source": [ |
||
| 233 | "This function builds a base neural net model that performs feature extraction" |
||
| 234 | ] |
||
| 235 | }, |
||
| 236 | { |
||
| 237 | "cell_type": "code", |
||
| 238 | "execution_count": 13, |
||
| 239 | "metadata": { |
||
| 240 | "collapsed": false |
||
| 241 | }, |
||
| 242 | "outputs": [], |
||
| 243 | "source": [ |
||
| 244 | "def get_base_model(input_len, fsize):\n", |
||
| 245 | " '''Base network to be shared (eq. to feature extraction).\n", |
||
| 246 | " '''\n", |
||
| 247 | " input_seq = Input(shape=(input_len, 24))\n", |
||
| 248 | " nb_filters = 150\n", |
||
| 249 | " convolved = Convolution1D(nb_filters, fsize, border_mode=\"same\", activation=\"tanh\")(input_seq)\n", |
||
| 250 | " processed = GlobalMaxPooling1D()(convolved)\n", |
||
| 251 | " compressed = Dense(150, activation=\"tanh\")(processed)\n", |
||
| 252 | " compressed = Dropout(0.3)(compressed)\n", |
||
| 253 | " compressed = Dense(150, activation=\"tanh\")(compressed)\n", |
||
| 254 | " model = Model(input=input_seq, output=compressed) \n", |
||
| 255 | " return model" |
||
| 256 | ] |
||
| 257 | }, |
||
| 258 | { |
||
| 259 | "cell_type": "markdown", |
||
| 260 | "metadata": {}, |
||
| 261 | "source": [ |
||
| 262 | "Build and compile a graph with 3 inputs and one output" |
||
| 263 | ] |
||
| 264 | }, |
||
| 265 | { |
||
| 266 | "cell_type": "code", |
||
| 267 | "execution_count": 14, |
||
| 268 | "metadata": { |
||
| 269 | "collapsed": false |
||
| 270 | }, |
||
| 271 | "outputs": [], |
||
| 272 | "source": [ |
||
| 273 | "input256_seq = Input(shape=(256, 24))\n", |
||
| 274 | "input500_seq = Input(shape=(500, 24))\n", |
||
| 275 | "input1125_seq = Input(shape=(1125, 24))\n", |
||
| 276 | " \n", |
||
| 277 | "base_network256 = get_base_model(256, 4)\n", |
||
| 278 | "base_network500 = get_base_model(500, 7)\n", |
||
| 279 | "base_network1125 = get_base_model(1125, 10)\n", |
||
| 280 | "\n", |
||
| 281 | "embedding_256 = base_network256(input256_seq)\n", |
||
| 282 | "embedding_500 = base_network500(input500_seq)\n", |
||
| 283 | "embedding_1125 = base_network1125(input1125_seq)\n", |
||
| 284 | " \n", |
||
| 285 | "merged = merge([embedding_256, embedding_500, embedding_1125], mode=\"concat\")\n", |
||
| 286 | "out = Dense(3, activation='softmax')(merged)\n", |
||
| 287 | " \n", |
||
| 288 | "model = Model(input=[input256_seq, input500_seq, input1125_seq], output=out)\n", |
||
| 289 | " \n", |
||
| 290 | "opt = RMSprop(lr=0.005, clipvalue=10**6)\n", |
||
| 291 | "model.compile(loss=\"categorical_crossentropy\", optimizer=opt)" |
||
| 292 | ] |
||
| 293 | }, |
||
| 294 | { |
||
| 295 | "cell_type": "markdown", |
||
| 296 | "metadata": {}, |
||
| 297 | "source": [ |
||
| 298 | "This cell will train the model from scratch, lets load it from the model dump instead (take a look at next code cell)!" |
||
| 299 | ] |
||
| 300 | }, |
||
| 301 | { |
||
| 302 | "cell_type": "code", |
||
| 303 | "execution_count": 15, |
||
| 304 | "metadata": { |
||
| 305 | "collapsed": false |
||
| 306 | }, |
||
| 307 | "outputs": [ |
||
| 308 | { |
||
| 309 | "name": "stdout", |
||
| 310 | "output_type": "stream", |
||
| 311 | "text": [ |
||
| 312 | "Epoch 1/100000\n", |
||
| 313 | "1100/4000 [=======>......................] - ETA: 83s - loss: 9.9279 \b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b" |
||
| 314 | ] |
||
| 315 | }, |
||
| 316 | { |
||
| 317 | "ename": "KeyboardInterrupt", |
||
| 318 | "evalue": "", |
||
| 319 | "output_type": "error", |
||
| 320 | "traceback": [ |
||
| 321 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 322 | "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", |
||
| 323 | "\u001b[0;32m<ipython-input-15-7db8dac50f16>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 7\u001b[0m model.fit_generator(data_generator(batch_size=50, slice_len=slice_len), samples_per_epoch, nb_epoch, \n\u001b[1;32m 8\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mearlyStopping\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnb_val_samples\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2000\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m validation_data=data_generator(batch_size=50, slice_len=slice_len, val=True))\n\u001b[0m", |
||
| 324 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mfit_generator\u001b[0;34m(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, nb_worker, pickle_safe, initial_epoch)\u001b[0m\n\u001b[1;32m 1551\u001b[0m outs = self.train_on_batch(x, y,\n\u001b[1;32m 1552\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1553\u001b[0;31m class_weight=class_weight)\n\u001b[0m\u001b[1;32m 1554\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1555\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mouts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 325 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/keras/engine/training.py\u001b[0m in \u001b[0;36mtrain_on_batch\u001b[0;34m(self, x, y, sample_weight, class_weight)\u001b[0m\n\u001b[1;32m 1314\u001b[0m \u001b[0mins\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0msample_weights\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1315\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_train_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1316\u001b[0;31m \u001b[0moutputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mins\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1317\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1318\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0moutputs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 326 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m 1898\u001b[0m \u001b[0msession\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_session\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1899\u001b[0m updated = session.run(self.outputs + [self.updates_op],\n\u001b[0;32m-> 1900\u001b[0;31m feed_dict=feed_dict)\n\u001b[0m\u001b[1;32m 1901\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mupdated\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1902\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 327 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 764\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 765\u001b[0m result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[0;32m--> 766\u001b[0;31m run_metadata_ptr)\n\u001b[0m\u001b[1;32m 767\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 768\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 328 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_run\u001b[0;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 962\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mfinal_fetches\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mfinal_targets\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 963\u001b[0m results = self._do_run(handle, final_targets, final_fetches,\n\u001b[0;32m--> 964\u001b[0;31m feed_dict_string, options, run_metadata)\n\u001b[0m\u001b[1;32m 965\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 966\u001b[0m \u001b[0mresults\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 329 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_do_run\u001b[0;34m(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 1012\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mhandle\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1013\u001b[0m return self._do_call(_run_fn, self._session, feed_dict, fetch_list,\n\u001b[0;32m-> 1014\u001b[0;31m target_list, options, run_metadata)\n\u001b[0m\u001b[1;32m 1015\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1016\u001b[0m return self._do_call(_prun_fn, self._session, handle, feed_dict,\n", |
||
| 330 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_do_call\u001b[0;34m(self, fn, *args)\u001b[0m\n\u001b[1;32m 1019\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_do_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1020\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1021\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1022\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mOpError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1023\u001b[0m \u001b[0mmessage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompat\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mas_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 331 | "\u001b[0;32m/home/akis/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_run_fn\u001b[0;34m(session, feed_dict, fetch_list, target_list, options, run_metadata)\u001b[0m\n\u001b[1;32m 1001\u001b[0m return tf_session.TF_Run(session, options,\n\u001b[1;32m 1002\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget_list\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1003\u001b[0;31m status, run_metadata)\n\u001b[0m\u001b[1;32m 1004\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1005\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_prun_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msession\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 332 | "\u001b[0;31mKeyboardInterrupt\u001b[0m: " |
||
| 333 | ] |
||
| 334 | } |
||
| 335 | ], |
||
| 336 | "source": [ |
||
| 337 | "from keras.callbacks import EarlyStopping\n", |
||
| 338 | "\n", |
||
| 339 | "nb_epoch = 100000\n", |
||
| 340 | "earlyStopping = EarlyStopping(monitor='val_loss', patience=10, verbose=0, mode='auto')\n", |
||
| 341 | "samples_per_epoch = 4000\n", |
||
| 342 | "\n", |
||
| 343 | "model.fit_generator(data_generator(batch_size=50, slice_len=slice_len), samples_per_epoch, nb_epoch, \n", |
||
| 344 | " callbacks=[earlyStopping], verbose=1, nb_val_samples=2000,\n", |
||
| 345 | " validation_data=data_generator(batch_size=50, slice_len=slice_len, val=True))" |
||
| 346 | ] |
||
| 347 | }, |
||
| 348 | { |
||
| 349 | "cell_type": "code", |
||
| 350 | "execution_count": null, |
||
| 351 | "metadata": { |
||
| 352 | "collapsed": true |
||
| 353 | }, |
||
| 354 | "outputs": [], |
||
| 355 | "source": [ |
||
| 356 | "model = load_model(\"hackaton_data/convnet-multiscale-true-01988\")" |
||
| 357 | ] |
||
| 358 | }, |
||
| 359 | { |
||
| 360 | "cell_type": "code", |
||
| 361 | "execution_count": null, |
||
| 362 | "metadata": { |
||
| 363 | "collapsed": false |
||
| 364 | }, |
||
| 365 | "outputs": [], |
||
| 366 | "source": [ |
||
| 367 | "model.summary()" |
||
| 368 | ] |
||
| 369 | }, |
||
| 370 | { |
||
| 371 | "cell_type": "markdown", |
||
| 372 | "metadata": {}, |
||
| 373 | "source": [ |
||
| 374 | "Read test data into a nested structure with multiple chunks for each subject" |
||
| 375 | ] |
||
| 376 | }, |
||
| 377 | { |
||
| 378 | "cell_type": "code", |
||
| 379 | "execution_count": null, |
||
| 380 | "metadata": { |
||
| 381 | "collapsed": false |
||
| 382 | }, |
||
| 383 | "outputs": [], |
||
| 384 | "source": [ |
||
| 385 | "with h5py.File(\"hackaton_data/test.h5\", \"r\") as data_file:\n", |
||
| 386 | " test = {}\n", |
||
| 387 | " for subject, subject_data in data_file.items():\n", |
||
| 388 | " test[subject] = {}\n", |
||
| 389 | " for chunk_id, chunk in data_file[subject].items():\n", |
||
| 390 | " test[subject][chunk_id] = chunk[:]" |
||
| 391 | ] |
||
| 392 | }, |
||
| 393 | { |
||
| 394 | "cell_type": "code", |
||
| 395 | "execution_count": null, |
||
| 396 | "metadata": { |
||
| 397 | "collapsed": false |
||
| 398 | }, |
||
| 399 | "outputs": [], |
||
| 400 | "source": [ |
||
| 401 | "test['subject_0']['chunk_0'].shape" |
||
| 402 | ] |
||
| 403 | }, |
||
| 404 | { |
||
| 405 | "cell_type": "code", |
||
| 406 | "execution_count": null, |
||
| 407 | "metadata": { |
||
| 408 | "collapsed": true |
||
| 409 | }, |
||
| 410 | "outputs": [], |
||
| 411 | "source": [ |
||
| 412 | "# utility function that performs resampling of input timeseries \n", |
||
| 413 | "def multiscale(chunk):\n", |
||
| 414 | " resampled_256 = resample(chunk, 256)\n", |
||
| 415 | " resampled_500 = resample(chunk, 500)\n", |
||
| 416 | " return [resampled_256, resampled_500, chunk]" |
||
| 417 | ] |
||
| 418 | }, |
||
| 419 | { |
||
| 420 | "cell_type": "markdown", |
||
| 421 | "metadata": {}, |
||
| 422 | "source": [ |
||
| 423 | "Make prediction for test data" |
||
| 424 | ] |
||
| 425 | }, |
||
| 426 | { |
||
| 427 | "cell_type": "code", |
||
| 428 | "execution_count": null, |
||
| 429 | "metadata": { |
||
| 430 | "collapsed": false |
||
| 431 | }, |
||
| 432 | "outputs": [], |
||
| 433 | "source": [ |
||
| 434 | "df = []\n", |
||
| 435 | "for subj in test:\n", |
||
| 436 | " for chunk in tqdm(test[subj]):\n", |
||
| 437 | " data = {}\n", |
||
| 438 | " data[\"subject_id\"] = int(subj.split(\"_\")[-1])\n", |
||
| 439 | " data[\"chunk_id\"] = int(chunk.split(\"_\")[-1])\n", |
||
| 440 | " arr = test[subj][chunk].T\n", |
||
| 441 | " preds = model.predict([np.array([i]) for i in multiscale(arr)])[0]\n", |
||
| 442 | " data[\"class_0_score\"] = preds[0]\n", |
||
| 443 | " data[\"class_1_score\"] = preds[1]\n", |
||
| 444 | " data[\"class_2_score\"] = preds[2]\n", |
||
| 445 | " for i in range(0, 1125):\n", |
||
| 446 | " data[\"tick\"] = i\n", |
||
| 447 | " df.append(data.copy())\n", |
||
| 448 | "df = pd.DataFrame(df)\n", |
||
| 449 | "df = df[[\"subject_id\", \"chunk_id\", \"tick\", \"class_0_score\",\n", |
||
| 450 | " \"class_1_score\",\"class_2_score\"]]" |
||
| 451 | ] |
||
| 452 | }, |
||
| 453 | { |
||
| 454 | "cell_type": "code", |
||
| 455 | "execution_count": null, |
||
| 456 | "metadata": { |
||
| 457 | "collapsed": false |
||
| 458 | }, |
||
| 459 | "outputs": [], |
||
| 460 | "source": [ |
||
| 461 | "df.head()" |
||
| 462 | ] |
||
| 463 | }, |
||
| 464 | { |
||
| 465 | "cell_type": "code", |
||
| 466 | "execution_count": null, |
||
| 467 | "metadata": { |
||
| 468 | "collapsed": true |
||
| 469 | }, |
||
| 470 | "outputs": [], |
||
| 471 | "source": [ |
||
| 472 | "# save submission to .csv\n", |
||
| 473 | "df.to_csv(\"submission.csv\")" |
||
| 474 | ] |
||
| 475 | } |
||
| 476 | ], |
||
| 477 | "metadata": { |
||
| 478 | "kernelspec": { |
||
| 479 | "display_name": "Python 3", |
||
| 480 | "language": "python", |
||
| 481 | "name": "python3" |
||
| 482 | }, |
||
| 483 | "language_info": { |
||
| 484 | "codemirror_mode": { |
||
| 485 | "name": "ipython", |
||
| 486 | "version": 3 |
||
| 487 | }, |
||
| 488 | "file_extension": ".py", |
||
| 489 | "mimetype": "text/x-python", |
||
| 490 | "name": "python", |
||
| 491 | "nbconvert_exporter": "python", |
||
| 492 | "pygments_lexer": "ipython3", |
||
| 493 | "version": "3.5.2" |
||
| 494 | } |
||
| 495 | }, |
||
| 496 | "nbformat": 4, |
||
| 497 | "nbformat_minor": 2 |
||
| 498 | } |