{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b9b5254c",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-12-02 14:32:52.003694: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2022-12-02 14:32:52.118691: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2022-12-02 14:32:52.118713: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n",
      "2022-12-02 14:32:52.145706: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
      "2022-12-02 14:32:52.742955: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory\n",
      "2022-12-02 14:32:52.743061: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n",
      "2022-12-02 14:32:52.743071: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n"
     ]
    }
   ],
   "source": [
    "from library.analysis import loadDataset, testSets\n",
    "from library.generators.XConvGeN import XConvGeN\n",
    "#from library.timing import timing\n",
    "from fdc.fdc import FDC\n",
    "#from matplotlib import pyplot as plt\n",
    "#import numpy as np\n",
    "#import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6bfec0a2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Load 'folding_abalone_17_vs_7_8_9_10'\n",
      "from pickle file\n",
      "Data loaded.\n"
     ]
    }
   ],
   "source": [
    "data = loadDataset(testSets[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6d686da5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(2338, 2280, 58)\n"
     ]
    }
   ],
   "source": [
    "print((len(data.data), len(data.data0), len(data.data1)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9e3e3806",
   "metadata": {},
   "outputs": [],
   "source": [
    "fdc = FDC()\n",
    "fdc.nom_list = [0]\n",
    "fdc.cont_list = list(range(data.data0.shape[1]))[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "01d71d6a",
   "metadata": {},
   "outputs": [],
   "source": [
    "gen = XConvGeN(data.data0.shape[1], neb=5, fdc=fdc, debug=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ad01be2b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-12-02 14:32:59.248314: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory\n",
      "2022-12-02 14:32:59.248342: W tensorflow/stream_executor/cuda/cuda_driver.cc:263] failed call to cuInit: UNKNOWN ERROR (303)\n",
      "2022-12-02 14:32:59.248361: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (f689f5a8be0b): /proc/driver/nvidia/version does not exist\n",
      "2022-12-02 14:32:59.248536: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "neb=5, gen=5\n",
      "Model: \"model\"\n",
      "__________________________________________________________________________________________________\n",
      " Layer (type)                   Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      " input_1 (InputLayer)           [(None, 5, 8)]       0           []                               \n",
      "                                                                                                  \n",
      " UnsharpenInput (Conv1D)        (None, 3, 8)         200         ['input_1[0][0]']                \n",
      "                                                                                                  \n",
      " InputMatrixToVector (Flatten)  (None, 24)           0           ['UnsharpenInput[0][0]']         \n",
      "                                                                                                  \n",
      " P3_dense (Dense)               (None, 15)           375         ['InputMatrixToVector[0][0]']    \n",
      "                                                                                                  \n",
      " P5_dense (Dense)               (None, 10)           250         ['InputMatrixToVector[0][0]']    \n",
      "                                                                                                  \n",
      " P3_reshape (Reshape)           (None, 5, 3)         0           ['P3_dense[0][0]']               \n",
      "                                                                                                  \n",
      " P5_reshape (Reshape)           (None, 5, 2)         0           ['P5_dense[0][0]']               \n",
      "                                                                                                  \n",
      " tf.math.reduce_sum (TFOpLambda  (None, 3)           0           ['P3_reshape[0][0]']             \n",
      " )                                                                                                \n",
      "                                                                                                  \n",
      " tf.math.reduce_sum_1 (TFOpLamb  (None, 2)           0           ['P5_reshape[0][0]']             \n",
      " da)                                                                                              \n",
      "                                                                                                  \n",
      " P3_make_non_zero (Lambda)      (None, 3)            0           ['tf.math.reduce_sum[0][0]']     \n",
      "                                                                                                  \n",
      " P5_make_non_zero (Lambda)      (None, 2)            0           ['tf.math.reduce_sum_1[0][0]']   \n",
      "                                                                                                  \n",
      " tf.math.reciprocal (TFOpLambda  (None, 3)           0           ['P3_make_non_zero[0][0]']       \n",
      " )                                                                                                \n",
      "                                                                                                  \n",
      " tf.math.reciprocal_1 (TFOpLamb  (None, 2)           0           ['P5_make_non_zero[0][0]']       \n",
      " da)                                                                                              \n",
      "                                                                                                  \n",
      " P3_normalize (Multiply)        (None, 5, 3)         0           ['tf.math.reciprocal[0][0]',     \n",
      "                                                                  'P3_reshape[0][0]']             \n",
      "                                                                                                  \n",
      " P5_normalize (Multiply)        (None, 5, 2)         0           ['tf.math.reciprocal_1[0][0]',   \n",
      "                                                                  'P5_reshape[0][0]']             \n",
      "                                                                                                  \n",
      " tf.__operators__.getitem (Slic  (5, 3)              0           ['P3_normalize[0][0]']           \n",
      " ingOpLambda)                                                                                     \n",
      "                                                                                                  \n",
      " tf.__operators__.getitem_1 (Sl  (5, 2)              0           ['P5_normalize[0][0]']           \n",
      " icingOpLambda)                                                                                   \n",
      "                                                                                                  \n",
      " tf.compat.v1.transpose (TFOpLa  (3, 5)              0           ['tf.__operators__.getitem[0][0]'\n",
      " mbda)                                                           ]                                \n",
      "                                                                                                  \n",
      " tf.compat.v1.transpose_1 (TFOp  (2, 5)              0           ['tf.__operators__.getitem_1[0][0\n",
      " Lambda)                                                         ]']                              \n",
      "                                                                                                  \n",
      " tf.linalg.matmul (TFOpLambda)  (None, 3, 8)         0           ['tf.compat.v1.transpose[0][0]', \n",
      "                                                                  'input_1[0][0]']                \n",
      "                                                                                                  \n",
      " tf.linalg.matmul_1 (TFOpLambda  (None, 2, 8)        0           ['tf.compat.v1.transpose_1[0][0]'\n",
      " )                                                               , 'input_1[0][0]']               \n",
      "                                                                                                  \n",
      " tf.concat (TFOpLambda)         (None, 5, 8)         0           ['tf.linalg.matmul[0][0]',       \n",
      "                                                                  'tf.linalg.matmul_1[0][0]']     \n",
      "                                                                                                  \n",
      " RandomNoise (Sequential)       (None, 40)           3280        ['tf.concat[0][0]']              \n",
      "                                                                                                  \n",
      " ReshapeNoise (Reshape)         (None, 5, 8)         0           ['RandomNoise[0][0]']            \n",
      "                                                                                                  \n",
      " AddNoise (Add)                 (None, 5, 8)         0           ['tf.concat[0][0]',              \n",
      "                                                                  'ReshapeNoise[0][0]']           \n",
      "                                                                                                  \n",
      "==================================================================================================\n",
      "Total params: 4,105\n",
      "Trainable params: 4,105\n",
      "Non-trainable params: 0\n",
      "__________________________________________________________________________________________________\n",
      "None\n",
      "\n",
      "\n",
      "Model: \"model_1\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " input_3 (InputLayer)        [(None, 8)]               0         \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 250)               2250      \n",
      "                                                                 \n",
      " dense_2 (Dense)             (None, 125)               31375     \n",
      "                                                                 \n",
      " dense_3 (Dense)             (None, 75)                9450      \n",
      "                                                                 \n",
      " dense_4 (Dense)             (None, 2)                 152       \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 43,227\n",
      "Trainable params: 0\n",
      "Non-trainable params: 43,227\n",
      "_________________________________________________________________\n",
      "None\n",
      "\n",
      "\n",
      "Model: \"model_2\"\n",
      "__________________________________________________________________________________________________\n",
      " Layer (type)                   Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      " input_4 (InputLayer)           [(None, 2, 5, 8)]    0           []                               \n",
      "                                                                                                  \n",
      " SplitForGen (Lambda)           (None, 5, 8)         0           ['input_4[0][0]']                \n",
      "                                                                                                  \n",
      " model (Functional)             (None, 5, 8)         4105        ['SplitForGen[0][0]']            \n",
      "                                                                                                  \n",
      " SplitForDisc (Lambda)          (None, 5, 8)         0           ['input_4[0][0]']                \n",
      "                                                                                                  \n",
      " tf.reshape_1 (TFOpLambda)      (None, 8)            0           ['model[0][0]']                  \n",
      "                                                                                                  \n",
      " tf.reshape (TFOpLambda)        (None, 8)            0           ['SplitForDisc[0][0]']           \n",
      "                                                                                                  \n",
      " model_1 (Functional)           (None, 2)            43227       ['tf.reshape_1[0][0]',           \n",
      "                                                                  'tf.reshape[0][0]']             \n",
      "                                                                                                  \n",
      " tf.reshape_2 (TFOpLambda)      (None, 5, 2)         0           ['model_1[0][0]']                \n",
      "                                                                                                  \n",
      " tf.reshape_3 (TFOpLambda)      (None, 5, 2)         0           ['model_1[1][0]']                \n",
      "                                                                                                  \n",
      " tf.concat_1 (TFOpLambda)       (None, 10, 2)        0           ['tf.reshape_2[0][0]',           \n",
      "                                                                  'tf.reshape_3[0][0]']           \n",
      "                                                                                                  \n",
      "==================================================================================================\n",
      "Total params: 47,332\n",
      "Trainable params: 4,105\n",
      "Non-trainable params: 43,227\n",
      "__________________________________________________________________________________________________\n",
      "None\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "gen.reset(data.data1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4698522c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "FDC.normalize (init): 0.00002 / 0.000s\n",
      "|data| = (58, 8)\n",
      "umap with metric 'euclidean'\n",
      "|part| = (58, 7)\n",
      "|emb_A| = (58, 2)\n",
      "|emb_A| = (58, 2)\n",
      "FDC.normalize (clustering CONT): 6.11788 / 6.118s\n",
      "FDC.normalize (clustering ORD): 0.00002 / 6.118s\n",
      "umap with metric 'hamming'\n",
      "|part| = (58, 1)\n",
      "|emb_A| = (58, 1)\n",
      "|emb_A| = (58, 1)\n",
      "FDC.normalize (clustering NOM): 1.17480 / 7.293s\n",
      "FDC.normalize (concat): 0.00003 / 7.293s\n",
      "|fdc| = (58, 3)\n",
      "FDC.normalize (total): 0.00002 / 7.293s\n",
      "|N| = (58, 3)\n",
      "|D| = (58, 8)\n",
      "[==========] [======    ] [======    ]\r"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1600x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "gen.train(data.data1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "cda17654",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2/2 [==============================] - 0s 11ms/step\n"
     ]
    }
   ],
   "source": [
    "syntheticPoints = gen.generateData(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "41853bd3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 0.0000000e+00,  5.0119996e-02,  1.0046461e+00,  5.3926897e-01,\n",
       "         2.2346902e-01, -6.5377390e-01,  2.1368484e-01, -1.4531080e+00],\n",
       "       [ 1.0000000e+00,  2.3565791e+00,  1.1293201e+00, -5.1019591e-01,\n",
       "         1.6728029e+00,  1.9772856e+00, -1.0922477e+00,  1.0376623e+00],\n",
       "       [ 0.0000000e+00,  6.2256587e-01,  1.5022650e+00,  2.4494307e-01,\n",
       "         1.9395508e+00,  2.7475536e-02, -1.4965298e+00, -1.3545752e-03],\n",
       "       [ 0.0000000e+00, -4.9461889e-01,  1.8344898e+00, -1.6180351e+00,\n",
       "         3.6594868e-03,  5.3580952e-01, -1.1517980e+00,  1.4476556e+00],\n",
       "       [ 1.0000000e+00,  1.1227753e+00,  3.8885543e-01, -7.1092069e-01,\n",
       "         5.0170082e-01, -3.1740397e-02, -7.7563524e-01, -1.0346892e+00],\n",
       "       [ 2.0000000e+00, -5.6823897e-01, -6.2967646e-01,  9.2212975e-01,\n",
       "        -9.3808568e-01, -1.3109281e+00, -3.4496129e-02, -8.6400896e-02],\n",
       "       [ 2.0000000e+00,  1.9029684e+00,  1.5553823e+00,  5.4555064e-01,\n",
       "         5.0464439e-01,  2.6258733e+00, -1.1301898e+00, -5.9068507e-01],\n",
       "       [ 2.0000000e+00, -1.7259085e-01,  7.3261225e-01,  9.3265986e-01,\n",
       "        -2.4023092e-01,  9.6727446e-02, -7.6945162e-01,  1.1377940e+00],\n",
       "       [ 2.0000000e+00,  7.2042620e-01, -2.9379535e-01, -1.3445570e+00,\n",
       "        -2.0151107e+00,  3.3371866e-01,  6.7896491e-01,  2.2249806e-01],\n",
       "       [ 2.0000000e+00,  7.2824174e-01, -9.3502915e-01, -1.4286264e+00,\n",
       "        -5.2939773e-01, -7.0454544e-01, -3.5073256e-01, -1.5016291e+00]],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "syntheticPoints"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "da5ebdb9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2.    , 0.565 , 0.425 , 0.16  , 0.9425, 0.3495, 0.2185, 0.275 ],\n",
       "       [0.    , 0.495 , 0.4   , 0.155 , 0.6445, 0.242 , 0.1325, 0.205 ],\n",
       "       [2.    , 0.54  , 0.435 , 0.18  , 0.996 , 0.3835, 0.226 , 0.325 ],\n",
       "       [0.    , 0.69  , 0.56  , 0.215 , 1.719 , 0.68  , 0.299 , 0.47  ],\n",
       "       [0.    , 0.68  , 0.55  , 0.21  , 1.7445, 0.5975, 0.305 , 0.625 ]])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.data1[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4043256c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.046946351737798\n",
      "2.8428130352717704\n",
      "2.1940466061478014\n",
      "3.1070472764345975\n",
      "2.004632053803972\n",
      "2.879989301449882\n",
      "3.242510917632268\n",
      "1.935007376551692\n",
      "3.2762267076268095\n",
      "3.2148741232702065\n"
     ]
    }
   ],
   "source": [
    "import math\n",
    "for p in syntheticPoints:\n",
    "    print(min([math.sqrt(sum(y*y)) for y in (data.data1 - p) ]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3bcc8cb7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2/2 [==============================] - 0s 2ms/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(0.27386373, 0.46166235, 0.3695623777036009)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "v = gen.predictReal(data.data1)\n",
    "(min(v), max(v), sum(v) / len(v))"
   ]
  }
 ],
 "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": "3.8.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}