Datasets
Models
Downloads: 1
[a8e9b4]:
/
MultiscaleNetRefactored.ipynb
499 lines (498 with data), 25.0 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook is a refactored version of a Multiscale Convolutional Network solution for NeuroHack at Yandex"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import random\n",
"\n",
"from tqdm import tqdm\n",
"import pandas as pd\n",
"import h5py\n",
"import numpy as np\n",
"from scipy.signal import resample"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"train_path = \"hackaton_data/train.h5\"\n",
"test_path = \"hackaton_data/test.h5\"\n",
"model_dump_path = \"hackaton_data/convnet-multiscale-true-01988\"\n",
"\n",
"slice_len = 1125"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Read train data into a dict of (subject_id, (X, y)) pairs"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"subjects = {}\n",
"with h5py.File(train_path, \"r\") as data_file:\n",
" for subject, subject_data in data_file.items():\n",
" X = subject_data[\"data\"][:]\n",
" y = subject_data[\"labels\"][:][0]\n",
" subjects[subject] = (X, y)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"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."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"\n",
"def train_val_split(X, y):\n",
" start_indices = list(range(0, len(X) - slice_len))\n",
" y = y[:len(start_indices)]\n",
" indices_train, indices_test, _, _ = train_test_split(start_indices, y)\n",
" return {\"train_ind\": indices_train, \"val_ind\": indices_test, \"X\": X, \"y\": y}"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"for subject in subjects:\n",
" X, y = subjects[subject][0], subjects[subject][1]\n",
" X = X.T\n",
" subjects[subject] = train_val_split(X, y)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Define utility function to convert class labels to one-hot encoding"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def to_onehot(y):\n",
" onehot = np.zeros(3)\n",
" onehot[y] = 1\n",
" return onehot"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Define a funtion that will select random subject and find a random subsequence of consistent class"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def generate_slice(slice_len, val=False):\n",
" subject_data = random.choice(list(subjects.values()))\n",
" if val is True:\n",
" indices, y, X = subject_data[\"val_ind\"], subject_data[\"y\"], subject_data[\"X\"]\n",
" else:\n",
" indices, y, X = subject_data[\"train_ind\"], subject_data[\"y\"], subject_data[\"X\"]\n",
" \n",
" while True:\n",
" slice_start = random.choice(indices)\n",
" slice_end = slice_start + slice_len\n",
" slice_x = X[slice_start:slice_end]\n",
" slice_y = y[slice_start:slice_end]\n",
" \n",
" if len(set(slice_y)) == 1:\n",
" return slice_x, to_onehot(slice_y)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Define a generator that will yield batches of resampled input time series and according class labels in infinite loop"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def data_generator(batch_size, slice_len, val=False):\n",
" while True:\n",
" batch_x = []\n",
" batch_y = []\n",
" \n",
" for i in range(0, batch_size):\n",
" x, y = generate_slice(slice_len, val=val)\n",
" batch_x.append(x)\n",
" batch_y.append(y)\n",
" \n",
" y = np.array(batch_y)\n",
" \n",
" x_256 = np.array([resample(i, 256) for i in batch_x])\n",
" x_500 = np.array([resample(i, 500) for i in batch_x])\n",
" x = np.array([i for i in batch_x])\n",
" yield ([x_256, x_500, x], y)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Lets build a neural network. Import all needed layers and keras utilities"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
}
],
"source": [
"from keras.layers import Convolution1D, Dense, Dropout, Input, merge, GlobalMaxPooling1D\n",
"from keras.models import Model, load_model\n",
"from keras.optimizers import RMSprop"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This function builds a base neural net model that performs feature extraction"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def get_base_model(input_len, fsize):\n",
" '''Base network to be shared (eq. to feature extraction).\n",
" '''\n",
" input_seq = Input(shape=(input_len, 24))\n",
" nb_filters = 150\n",
" convolved = Convolution1D(nb_filters, fsize, border_mode=\"same\", activation=\"tanh\")(input_seq)\n",
" processed = GlobalMaxPooling1D()(convolved)\n",
" compressed = Dense(150, activation=\"tanh\")(processed)\n",
" compressed = Dropout(0.3)(compressed)\n",
" compressed = Dense(150, activation=\"tanh\")(compressed)\n",
" model = Model(input=input_seq, output=compressed) \n",
" return model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Build and compile a graph with 3 inputs and one output"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"input256_seq = Input(shape=(256, 24))\n",
"input500_seq = Input(shape=(500, 24))\n",
"input1125_seq = Input(shape=(1125, 24))\n",
" \n",
"base_network256 = get_base_model(256, 4)\n",
"base_network500 = get_base_model(500, 7)\n",
"base_network1125 = get_base_model(1125, 10)\n",
"\n",
"embedding_256 = base_network256(input256_seq)\n",
"embedding_500 = base_network500(input500_seq)\n",
"embedding_1125 = base_network1125(input1125_seq)\n",
" \n",
"merged = merge([embedding_256, embedding_500, embedding_1125], mode=\"concat\")\n",
"out = Dense(3, activation='softmax')(merged)\n",
" \n",
"model = Model(input=[input256_seq, input500_seq, input1125_seq], output=out)\n",
" \n",
"opt = RMSprop(lr=0.005, clipvalue=10**6)\n",
"model.compile(loss=\"categorical_crossentropy\", optimizer=opt)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This cell will train the model from scratch, lets load it from the model dump instead (take a look at next code cell)!"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/100000\n",
"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"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\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",
"\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",
"\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",
"\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",
"\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",
"\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",
"\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",
"\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",
"\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",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"from keras.callbacks import EarlyStopping\n",
"\n",
"nb_epoch = 100000\n",
"earlyStopping = EarlyStopping(monitor='val_loss', patience=10, verbose=0, mode='auto')\n",
"samples_per_epoch = 4000\n",
"\n",
"model.fit_generator(data_generator(batch_size=50, slice_len=slice_len), samples_per_epoch, nb_epoch, \n",
" callbacks=[earlyStopping], verbose=1, nb_val_samples=2000,\n",
" validation_data=data_generator(batch_size=50, slice_len=slice_len, val=True))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"model = load_model(\"hackaton_data/convnet-multiscale-true-01988\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"model.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Read test data into a nested structure with multiple chunks for each subject"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"with h5py.File(\"hackaton_data/test.h5\", \"r\") as data_file:\n",
" test = {}\n",
" for subject, subject_data in data_file.items():\n",
" test[subject] = {}\n",
" for chunk_id, chunk in data_file[subject].items():\n",
" test[subject][chunk_id] = chunk[:]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"test['subject_0']['chunk_0'].shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# utility function that performs resampling of input timeseries \n",
"def multiscale(chunk):\n",
" resampled_256 = resample(chunk, 256)\n",
" resampled_500 = resample(chunk, 500)\n",
" return [resampled_256, resampled_500, chunk]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Make prediction for test data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"df = []\n",
"for subj in test:\n",
" for chunk in tqdm(test[subj]):\n",
" data = {}\n",
" data[\"subject_id\"] = int(subj.split(\"_\")[-1])\n",
" data[\"chunk_id\"] = int(chunk.split(\"_\")[-1])\n",
" arr = test[subj][chunk].T\n",
" preds = model.predict([np.array([i]) for i in multiscale(arr)])[0]\n",
" data[\"class_0_score\"] = preds[0]\n",
" data[\"class_1_score\"] = preds[1]\n",
" data[\"class_2_score\"] = preds[2]\n",
" for i in range(0, 1125):\n",
" data[\"tick\"] = i\n",
" df.append(data.copy())\n",
"df = pd.DataFrame(df)\n",
"df = df[[\"subject_id\", \"chunk_id\", \"tick\", \"class_0_score\",\n",
" \"class_1_score\",\"class_2_score\"]]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# save submission to .csv\n",
"df.to_csv(\"submission.csv\")"
]
}
],
"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": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}