Skip to content

Instantly share code, notes, and snippets.

@renxida

renxida/test_custom_metric_corr.ipynb

Created November 19, 2018 16:18
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save renxida/9e53e1307abd44b33e0984e1ec49937c to your computer and use it in GitHub Desktop.
Save renxida/9e53e1307abd44b33e0984e1ec49937c to your computer and use it in GitHub Desktop.
Download ZIP
with daily-dev
Display the source blob
Display the rendered blob
Raw
test_custom_metric_corr.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
}
],
"source": [
"from keras.models import Model\n",
"from keras.layers import Input, Dense, Conv1D, Flatten, Concatenate\n",
"from keras import regularizers\n",
"import logging\n",
"logger = logging.getLogger('replicate_talos_float_hyperparameter_error')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import talos as ta\n",
"import keras\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def make_net(input_layer, params):\n",
" net = input_layer\n",
"\n",
" if params.get('conv_count', 0) !=0:\n",
" for _ in range(params['conv_count']):\n",
" newConv = Conv1D(\n",
" activation='relu',\n",
" filters=params['conv_filters'],\n",
" kernel_size=params['conv_kernel_size'],\n",
" kernel_regularizer=regularizers.l2(float(params['l2reg'])))\n",
" net = newConv(net)\n",
" # optional pooling\n",
" if params.get('pool_size', None) is not None:\n",
" newPool = keras.layers.MaxPooling1D(\n",
" pool_size=params['pool_size'],\n",
" strides=params.get(\n",
" 'pool_strides',\n",
" params['pool_size']),\n",
" )\n",
" net = newPool(net)\n",
"\n",
" net = Flatten()(net)\n",
" \n",
" if params.get('dense_count', 0) !=0:\n",
" for dense_num in range(params['dense_count']):\n",
" newDense = Dense(\n",
" units=params['dense_units'],\n",
" activation='relu',\n",
" kernel_regularizer=regularizers.l2(float(params['l2reg'])),\n",
" )\n",
" net = newDense(net)\n",
"\n",
" return net\n",
"\n",
"def make_optimizer(params):\n",
" opzr = keras.optimizers.Adam(**params.get('optimizer', {}))\n",
" return opzr\n",
"\n",
"import keras.backend as K\n",
"def model(params):\n",
" \n",
" \n",
" def metric_correlation(y_true, y_pred):\n",
" logger.warn(f'[metric_correlation] y_true size: {y_true.shape}, y_predy size: {y_pred.shape}')\n",
"\n",
" def m(x, w):\n",
" \"\"\"Weighted Mean\"\"\"\n",
" return K.sum(x*w) / K.sum(w)\n",
" def cov(x, y, w):\n",
" \"\"\"Weighted Covariance\"\"\"\n",
" return K.sum(w* (x - m(x, w))*(y - m(y, w)))/ K.sum(w)\n",
"\n",
" def corr(x, y, w):\n",
" \"\"\"Weighted Correlation\"\"\"\n",
" return cov(x, y, w) / K.sqrt(cov(x, x, w) * cov(y, y, w))\n",
" print(y_true.get_shape())\n",
" return corr(y_true, y_pred, K.ones_like(y_true))\n",
" inputs = []\n",
"\n",
" subnets = []\n",
"\n",
"\n",
" inpt = Input(shape=(30,), dtype='float32', name='returns_input')\n",
" inputs.append(inpt)\n",
"\n",
" net = make_net(inpt, params)\n",
" \n",
" condenser = Dense(units=1, activation=None, use_bias=False)\n",
" net = condenser(net)\n",
" \n",
" model = Model(inputs=inputs, outputs = net)\n",
"\n",
" opzr = make_optimizer(params)\n",
" model.compile(\n",
" loss='mean_squared_error',\n",
" optimizer=opzr,\n",
" metrics=[metric_correlation])\n",
" return model"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def model_ta(x_train, y_train, x_val, y_val, params):\n",
" print(params)\n",
" # replace the hyperparameter inputs with references to params dictionary \n",
" mdl = model(params)\n",
" \n",
" history_callback = mdl.fit(x_train, y_train,\n",
" batch_size=params['batch_size'],\n",
" epochs=params['epochs'],\n",
" verbose=1,\n",
" validation_data=[x_val, y_val])\n",
" history_callback.history['val_acc']=[42]\n",
" # modify the output model\n",
" return history_callback, mdl"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"## Compare this:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/3 [00:00<?, ?it/s][metric_correlation] y_true size: (?, ?), y_predy size: (?, 1)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'dense_count': 3, 'dense_units': 200, 'conv_count': 0, 'l2reg': 1000, 'epochs': 4, 'batch_size': 32}\n",
"(?, ?)\n",
"Train on 3500 samples, validate on 1500 samples\n",
"Epoch 1/4\n",
"3500/3500 [==============================] - 1s 283us/step - loss: 149230.8663 - metric_correlation: 0.0016 - val_loss: 17388.8659 - val_metric_correlation: -0.0277\n",
"Epoch 2/4\n",
"3500/3500 [==============================] - 0s 53us/step - loss: 4440.2120 - metric_correlation: 0.0266 - val_loss: 290.6183 - val_metric_correlation: 0.0013\n",
"Epoch 3/4\n",
"3500/3500 [==============================] - 0s 54us/step - loss: 69.2349 - metric_correlation: nan - val_loss: 4.7466 - val_metric_correlation: nan\n",
"Epoch 4/4\n",
"3500/3500 [==============================] - 0s 53us/step - loss: 1.8202 - metric_correlation: nan - val_loss: 1.0265 - val_metric_correlation: nan\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 33%|███▎ | 1/3 [00:01<00:03, 1.97s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'dense_count': 1, 'dense_units': 200, 'conv_count': 0, 'l2reg': 1000, 'epochs': 4, 'batch_size': 32}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[metric_correlation] y_true size: (?, ?), y_predy size: (?, 1)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(?, ?)\n",
"Train on 3500 samples, validate on 1500 samples\n",
"Epoch 1/4\n",
"3500/3500 [==============================] - 0s 77us/step - loss: 20710.3201 - metric_correlation: 0.0077 - val_loss: 4473.2741 - val_metric_correlation: 0.0119\n",
"Epoch 2/4\n",
"3500/3500 [==============================] - 0s 39us/step - loss: 1468.8747 - metric_correlation: -0.0017 - val_loss: 195.5151 - val_metric_correlation: 0.0023\n",
"Epoch 3/4\n",
"3500/3500 [==============================] - 0s 40us/step - loss: 53.3786 - metric_correlation: 0.0280 - val_loss: 4.7616 - val_metric_correlation: -0.0027\n",
"Epoch 4/4\n",
"3500/3500 [==============================] - 0s 39us/step - loss: 1.8406 - metric_correlation: 0.0354 - val_loss: 1.0286 - val_metric_correlation: -0.0225\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 67%|██████▋ | 2/3 [00:02<00:01, 1.65s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'dense_count': 1, 'dense_units': 100, 'conv_count': 0, 'l2reg': 1, 'epochs': 4, 'batch_size': 32}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[metric_correlation] y_true size: (?, ?), y_predy size: (?, 1)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(?, ?)\n",
"Train on 3500 samples, validate on 1500 samples\n",
"Epoch 1/4\n",
"3500/3500 [==============================] - 0s 75us/step - loss: 23.8993 - metric_correlation: -0.0101 - val_loss: 9.1448 - val_metric_correlation: -0.0156\n",
"Epoch 2/4\n",
"3500/3500 [==============================] - 0s 39us/step - loss: 4.5872 - metric_correlation: -0.0084 - val_loss: 2.0304 - val_metric_correlation: -0.0062\n",
"Epoch 3/4\n",
"3500/3500 [==============================] - 0s 40us/step - loss: 1.4057 - metric_correlation: 0.0063 - val_loss: 1.0943 - val_metric_correlation: -0.0180\n",
"Epoch 4/4\n",
"3500/3500 [==============================] - 0s 40us/step - loss: 1.0367 - metric_correlation: 0.0385 - val_loss: 1.0130 - val_metric_correlation: -0.0246\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 3/3 [00:03<00:00, 1.42s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Scan Finished!\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"h = ta.Scan(x=np.random.normal(loc=0.0, scale=1.0, size=(5000, 30)),\n",
" y=np.random.normal(loc=0.0, scale=1.0, size=(5000, 1)), \n",
" params={\n",
" 'dense_count': [1, 2, 3],\n",
" 'dense_units': [50, 100, 150, 200],\n",
" 'conv_count': [0],\n",
" 'l2reg': [1, 100, 1000],\n",
" 'epochs':[4],\n",
" 'batch_size':[32]\n",
" },\n",
" model=model_ta,\n",
" grid_downsample=0.1)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"rpt = ta.Reporting(h)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"ename": "ValueError",
"evalue": "cannot insert metric_correlation, already exists",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-8-21813ace0770>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mrpt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorrelate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'metric_correlation'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/talos/commands/reporting.py\u001b[0m in \u001b[0;36mcorrelate\u001b[0;34m(self, metric)\u001b[0m\n\u001b[1;32m 53\u001b[0m \u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mc\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mc\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mc\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmetric_names\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[1;32m 54\u001b[0m \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 55\u001b[0;31m \u001b[0mout\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmetric\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmetric\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 56\u001b[0m \u001b[0mout\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mout\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mmetric\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 57\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36minsert\u001b[0;34m(self, loc, column, value, allow_duplicates)\u001b[0m\n\u001b[1;32m 3217\u001b[0m \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sanitize_column\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbroadcast\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3218\u001b[0m self._data.insert(loc, column, value,\n\u001b[0;32m-> 3219\u001b[0;31m allow_duplicates=allow_duplicates)\n\u001b[0m\u001b[1;32m 3220\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3221\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0massign\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/pandas/core/internals.py\u001b[0m in \u001b[0;36minsert\u001b[0;34m(self, loc, item, value, allow_duplicates)\u001b[0m\n\u001b[1;32m 4336\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mallow_duplicates\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mitem\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4337\u001b[0m \u001b[0;31m# Should this be a different kind of error??\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4338\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'cannot insert {}, already exists'\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4339\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4340\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: cannot insert metric_correlation, already exists"
]
}
],
"source": [
"rpt.correlate('metric_correlation')"
]
}
],
"metadata": {
"_draft": {
"nbviewer_url": "https://gist.github.com/fba8417e04b1c9094bf924db0a2938ec"
},
"gist": {
"data": {
"description": "test_custom_metric_corr.ipynb",
"public": true
},
"id": "fba8417e04b1c9094bf924db0a2938ec"
},
"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": "3.6.5"
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": false,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": false,
"toc_position": {
"height": "calc(100% - 180px)",
"left": "10px",
"top": "150px",
"width": "381px"
},
"toc_section_display": true,
"toc_window_display": true
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment