Delete notebooks directory

notebooks/planar_execute.ipynb

-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "94169c2a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os \n",
-    "os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' \n",
-    "import numpy as np\n",
-    "from sklearn.preprocessing import StandardScaler\n",
-    "import tensorflow as tf\n",
-    "tf.compat.v1.disable_eager_execution() \n",
-    "import tensorflow_probability as tfp\n",
-    "import matplotlib.pyplot as plt\n",
-    "from data_loader import load_data\n",
-    "from data_preprocesser import preprocess_data\n",
-    "from planar import Planar"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "087e74b6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def train(session, loss, optimizer, steps=int(1e5)):\n",
-    "    \n",
-    "    \"\"\" optimize for all dimensions \"\"\"\n",
-    "    \n",
-    "    recorded_steps = []\n",
-    "    recorded_losses = []\n",
-    "    for i in range(steps):\n",
-    "        _, loss_per_iteration = session.run([optimizer, loss])\n",
-    "        if i % 100 == 0:\n",
-    "            recorded_steps.append(i)\n",
-    "            recorded_losses.append(loss_per_iteration)\n",
-    "        if i % int(1e4) == 0:\n",
-    "            print('Iteration {iteration}: {loss}'.format(iteration=i,loss=loss_per_iteration))\n",
-    "    return recorded_losses\n",
-    "\n",
-    "def plot_results(recorded_losses):\n",
-    "    \n",
-    "    \"\"\" plot loss \"\"\"\n",
-    "    print('Displaying results...')\n",
-    "    fig = plt.figure(figsize=(10,5))\n",
-    "    x = np.arange(len(recorded_losses))\n",
-    "    y = recorded_losses\n",
-    "    m, b = np.polyfit(x, y, 1) \n",
-    "    plt.scatter(x, y, s=10, alpha=0.3)\n",
-    "    plt.plot(x, m*x+b, c=\"r\")\n",
-    "    plt.title('Loss per 100 iteration')\n",
-    "    plt.xlabel('Iteration')\n",
-    "    plt.ylabel('Loss')\n",
-    "    plt.tight_layout()\n",
-    "    plt.show()\n",
-    "    \n",
-    "def create_tensor(data, batch_size):\n",
-    "    dataset = tf.data.Dataset.from_tensor_slices(data.astype(np.float32))\n",
-    "    dataset = dataset.repeat()\n",
-    "    dataset = dataset.shuffle(buffer_size=data.shape[0])\n",
-    "    dataset = dataset.prefetch(2*batch_size)\n",
-    "    dataset = dataset.batch(batch_size)\n",
-    "    data_iterator = tf.compat.v1.data.make_one_shot_iterator(dataset)\n",
-    "    samples = data_iterator.get_next()\n",
-    "    return samples\n",
-    "\n",
-    "\"\"\" \n",
-    "if any error on tensorflow is displayed claiming tf.float32 is not displayed,\n",
-    "do the following (one of them is probably enough)\n",
-    "    ** downgrade keras to 2.3.1\n",
-    "    ** replace tf.float32 with np.float32\n",
-    "\"\"\"\n",
-    "def check_version():    \n",
-    "    print(f'Tensorflow version: {tf.__version__}')\n",
-    "    print(f'Tensorflow-probability version: {tfp.__version__}')\n",
-    "    print(f'Keras version: {tf.keras.__version__}\\n')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "23f55548",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Data successfully loaded...\n",
-      "\n",
-      "Data successfully preprocessed...\n",
-      "\n",
-      "Optimizer and loss successfully defined...\n",
-      "\n",
-      "Iteration 0: 95.97050476074219\n",
-      "Iteration 10000: 57.572265625\n",
-      "Iteration 20000: 49.272705078125\n",
-      "Iteration 30000: 46.765769958496094\n",
-      "Iteration 40000: 46.634979248046875\n",
-      "Iteration 50000: 44.979713439941406\n"
-     ]
-    }
-   ],
-   "source": [
-    "def main():\n",
-    "    \n",
-    "    \"\"\" load data \"\"\"\n",
-    "\n",
-    "    filename = 'prostate.xls'\n",
-    "    directory = '/Users/kaanguney.keklikci/Data/'\n",
-    "\n",
-    "    loader = load_data(filename, directory)\n",
-    "    loader.create_directory(directory)\n",
-    "    data = loader.read_data(directory, filename)\n",
-    "    print('Data successfully loaded...\\n')\n",
-    "    \n",
-    "    \"\"\" preprocess data \"\"\"\n",
-    "\n",
-    "    fillna_vals = ['sz', 'sg', 'wt']\n",
-    "    dropna_vals = ['ekg', 'age']\n",
-    "    drop_vals = ['patno', 'sdate']\n",
-    "\n",
-    "    preprocesser = preprocess_data(StandardScaler(), fillna_vals, dropna_vals, drop_vals)\n",
-    "    data = preprocesser.dropna_features(data)\n",
-    "    data = preprocesser.impute(data)\n",
-    "    data = preprocesser.drop_features(data)\n",
-    "    data = preprocesser.encode_categorical(data)\n",
-    "    data = preprocesser.scale(data)\n",
-    "    print('Data successfully preprocessed...\\n')\n",
-    "    \n",
-    "    \"\"\" set Planar parameters \"\"\"\n",
-    "    \n",
-    "    tfd = tfp.distributions\n",
-    "    tfb = tfp.bijectors\n",
-    "\n",
-    "    batch_size = 32\n",
-    "    dtype = np.float32\n",
-    "    layers = 8\n",
-    "    dims = data.shape[1]\n",
-    "    # multivariate normal for base distribution\n",
-    "    base_dist = tfd.MultivariateNormalDiag(loc=tf.zeros(shape=dims, dtype=dtype))\n",
-    "    learning_rate = 1e-4\n",
-    "    \n",
-    "    \"\"\" initialize samples \"\"\"\n",
-    "    samples = create_tensor(data, batch_size)\n",
-    "    \n",
-    "    \"\"\" make Planar \"\"\"\n",
-    "\n",
-    "    bijectors = []\n",
-    "    for i in range(0, layers):\n",
-    "        bijectors.append(Planar(input_dimensions=dims, case='density_estimation'))\n",
-    "    bijector = tfb.Chain(bijectors=list(reversed(bijectors)), name='chain_of_planar')\n",
-    "    planar_flow = tfd.TransformedDistribution(\n",
-    "        distribution=base_dist,\n",
-    "        bijector=bijector\n",
-    "    )\n",
-    "\n",
-    "    loss = -tf.reduce_mean(planar_flow.log_prob(samples))\n",
-    "    optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate).minimize(loss)\n",
-    "\n",
-    "    session = tf.compat.v1.Session()\n",
-    "    tf.compat.v1.set_random_seed(42)\n",
-    "    session.run(tf.compat.v1.global_variables_initializer())\n",
-    "    print('Optimizer and loss successfully defined...\\n')\n",
-    "    \n",
-    "    \"\"\" start training \"\"\"\n",
-    "    recorded_losses = train(session, loss, optimizer)\n",
-    "    print('Training finished...\\n')\n",
-    "    \n",
-    "    \"\"\" display results \"\"\"\n",
-    "    plot_results(recorded_losses)\n",
-    "    \n",
-    "    \n",
-    "if __name__ == \"__main__\":\n",
-    "    main()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0d33af87",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "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": "3.7.10"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}