mirror of
https://github.com/c-sooyoung/lemon-sandbox.git
synced 2026-11-16 04:07:59 +09:00
moved notebooks from bo-ptycho to here
This commit is contained in:
swim committed
1 parent
b19ce33092
commit
1134926369
2 files changed
+213
-85
No files matched your search
@@ -2,36 +2,34 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "090d6ad2",
|
||||
"execution_count": 7,
|
||||
"id": "65e78297",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import numpy as np\n",
|
||||
"from matplotlib import pyplot as plt"
|
||||
"import matplotlib.pyplot as plt"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "e8c7045b",
|
||||
"execution_count": 8,
|
||||
"id": "033186ec",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 700x300 with 2 Axes>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(3, 564)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"train_x = np.load(\"./train_X_8keV.npy\")[1:].T\n",
|
||||
"train_y = np.load(\"./train_Y_8keV.npy\")[1:].T\n",
|
||||
"result_dir = \"/home/swim/bo-ptycho/results/Si8V2_2/260815\"\n",
|
||||
"train_x = np.load(os.path.join(result_dir, 'train_x.npy')).T\n",
|
||||
"train_y = np.load(os.path.join(result_dir, 'train_y.npy')).T\n",
|
||||
"\n",
|
||||
"xparams = [\n",
|
||||
" 'defocus [A]',\n",
|
||||
@@ -39,66 +37,20 @@
|
||||
" 'thickness [A]'\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"sort_index = np.argsort(train_y)\n",
|
||||
"\n",
|
||||
"x = train_x[:,sort_index]\n",
|
||||
"y = train_y[sort_index]\n",
|
||||
"\n",
|
||||
"EPSILON = 1e-5 # choose best according to plot\n",
|
||||
"\n",
|
||||
"y_scaled = np.log(-y + y[-1] + EPSILON)\n",
|
||||
"\n",
|
||||
"fig, ax = plt.subplots(1, 2, figsize=(7,3))\n",
|
||||
"ax[0].plot(y, 'k')\n",
|
||||
"ax[1].plot(y_scaled, 'k')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "adeb047c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 950x350 with 3 Axes>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Projection plots\n",
|
||||
"\n",
|
||||
"cut = 200 # set to -1 to get all points\n",
|
||||
"\n",
|
||||
"fig, axs = plt.subplots(1, len(x), figsize=(3*len(x)+0.5, 3.5), sharey=True)\n",
|
||||
"\n",
|
||||
"for i, axi in enumerate(axs):\n",
|
||||
" axi.scatter(x[i][cut:], -y[cut:], c=y_scaled[cut:], cmap='coolwarm')\n",
|
||||
" axi.set_xlabel(xparams[i])\n",
|
||||
"\n",
|
||||
"axs[0].set_ylabel('$- \\\\log (\\ \\\\mathtt{fourier\\_error}\\ )$')\n",
|
||||
"\n",
|
||||
"plt.tight_layout()\n",
|
||||
"plt.show()"
|
||||
"print(train_x.shape)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "02c25124",
|
||||
"id": "a5d079f2",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"image/png": "iVBORw0KGgoAAAANSUhEUgAABdEAAAEiCAYAAAAWHJuuAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjYsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvq6yFwwAAAAlwSFlzAAAPYQAAD2EBqD+naQAAwj1JREFUeJzs3XlcVNX7B/DPzICQoLigoo2gKe5LpigupWlJpWaaii2EhkiLaSamflu0tFAw0RZzgdSyTGyxXdMgswRBS82tsEQZzd1ADReY8/vD34zMzJ2VGe4sn/frNa/szp17nzkz98zluec+RyGEECAiIiIiIiIiIiIiIhNKuQMgIiIiIiIiIiIiInJXTKITEREREREREREREZnBJDoRERERERERERERkRlMohMRERERERERERERmcEkOhERERERERERERGRGUyiExERERERERERERGZwSQ6EREREREREREREZEZTKITEREREREREREREZnBJDoRERERERERERERkRlMohMRERERERERERERmcEkOhERERERERERERGRGUyiu5mVK1dCoVCgqKioWvb36quvol27dtBqtSbP/frrr+jTpw9q1aoFhUKBfv36VUtM9pg1axYUCoXcYXilzMxM3Hzzzbh06ZLcoRC5zPbt2zFs2DCEh4cjICAAjRo1Qs+ePTFlyhSX7M8VfTz7QSLvkJeXh5EjR6Jx48aoUaMGwsLCMGLECOTm5lZ5282aNcOYMWOqHqQTVfc5LxE5H8+jiDzbnj17MHbsWDRv3hyBgYEIDg7GbbfdhtTUVJw7d07u8FzOnuP/xx9/hEKh0D927NghuV55eTnmz5+P9u3bIzAwEA0bNsQ999yDCxcumN32008/DYVCgSeeeMKh92FOs2bNoFAosGTJEoPlgwcPRrNmzZy6L0ft2LHDoF1//PFHuUOyiEl0H3b8+HGkpqbi1VdfhVJp+lV4/PHHceHCBXzyySfIzc3F4sWLZYjSsnHjxjnlj0syFR8fj6CgIKSmpsodCpFLfPPNN+jVqxdKS0uRmpqK77//HosWLULv3r2xdu1aucMjIh/y1ltvoXfv3tBoNEhNTcXmzZsxf/58HDt2DH369MHbb78td4hERAZ4HkXk2ZYvX46uXbuioKAAU6dOxYYNG/D5559j5MiRWLJkCRISEuQO0S298847yM3NRdu2bSWfT0hIwP/+9z8MHToU3333HZYvX442bdrg2rVrkutv374d69atc2XIbpnL02nbti1yc3PxzjvvyB2KTfzkDoDks2jRItSpUwfDhw+XfH7fvn2YMWMGYmJiqjky26nVaqjVarnD8Ep+fn5ISkrC7NmzMW3aNNSsWVPukIicKjU1Fc2bN8fGjRvh53fj53D06NG8eERE1eaXX37Bs88+i/vuuw+ff/65SX80bNgwTJo0CV26dEHv3r0lt/Hff/9V2+90RUUFysvLERAQUC37IyL3xPMoIs+Vm5uLJ598EnfffTfWr19v8Jt+9913Y8qUKdiwYYPZ11fneYe7adeuHaKjoyWf27p1K95//3289dZbmDBhgn750KFDJdcvLy/H+PHj8eqrr+LJJ590SbytWrXC3r17sXXrVtx+++0u2UdVBAUFITo6GpcvX5Y7FJtwJLqH+PnnnzFgwADUqlULNWvWRK9evfDNN9+YrPfFF1+gU6dOCAgIwC233IJFixZJ3qJy9epVZGZm4uGHHzYYha67RU6hUKC8vByzZ8/W/79xOZedO3di4MCB+pjuuOMO/PTTTwbrmLvlztxtxQqFArNmzcKKFSvQpk0bBAQEIDw8HF9++aXBei1btjS45cOcI0eOIC4uDg0bNkRAQAC6dOmCr776SnJdW/dtC1fs15b1bPlM7NneI488gtLSUnz88cd2twGRuzt79ixCQ0MN/vDTMb4756OPPkLPnj0RHByM4OBg3HrrrcjMzNQ/v2nTJgwdOhRqtRqBgYFo2bIlkpKScObMGZti2bx5MwYMGIDatWujZs2a6N27N3744QeT9b755hvceuutCAgIQPPmzTF//nw73zURuZuUlBQoFAq8++67Jv2Rn58fFi9eDIVCgblz5wK4cevxr7/+ihEjRqBu3bpo0aIFAODatWt4/vnnERYWhpo1a6JPnz7Iz8+X3O+JEyeQlJQEtVqNGjVqoHnz5njllVdQXl6uX6eoqAgKhQKpqamYM2cOmjdvjoCAAOTk5AC4fgvu/fffj3r16iEwMBBdunRBVlaWyb7y8vLQu3dvBAYGokmTJpgxY4bZEVlE5Bl4HkXkuV5//XUoFAosW7ZM8qJ4jRo1cP/99wOwfN4B2Jar0m3jt99+w/Dhw1G7dm2EhITg0UcfxenTpx1et7CwEA8//LA+79K2bVuzI5qr4/j/+OOPERQUhMTERJvWf+ONN6BSqTB+/Hi79nPw4EEcPHjQpnWbN2+OmJgYq6PR7cnvbdmyBYMGDUJwcDAiIiKQnp5usj17cmKehCPRPcCWLVtw9913o1OnTsjMzERAQAAWL16MIUOGYM2aNYiNjQUAbNiwAcOHD8cdd9yBtWvX6msxnTx50mSb27dvx9mzZ3HnnXcaLB80aJC+PErPnj2RkJCAcePGAQBq166tX+/QoUPo27cvbrnlFqxYsQL+/v6YN28e7rrrLuTm5qJr164Ov99vvvkGpaWlmDFjBpo2bYrffvsNFy9eNFjnk08+weXLl5GRkWFwAlZZcXExevTogZtuuglpaWkICwvDRx99hAceeADfffcdBg4c6NC+rXHlfi2t58hnYm2/YWFhaNOmDb755hs8/vjjdrUDkbvr2bMnMjIyMHHiRDzyyCO47bbb4O/vb7Leyy+/jNmzZ2P48OGYMmUKQkJCsHfvXhw5ckS/zl9//YWePXti3LhxCAkJQVFRERYsWIA+ffrg999/l9yuzurVq/HYY49h6NChWLVqFfz9/bF06VLExMRg48aNGDBgAADghx9+wNChQ9GzZ098/PHHqKioQGpqqmQfT0SeoaKiAjk5OejWrZvZO+uaNm2Krl27Ijs7GxUVFfrlw4cPx+jRo/HEE0/o5y9JTEzE+++/j+TkZNx9993Yu3cvhg8fblKH88SJE+jevTuUSiVefvlltGjRArm5uZgzZw6KioqwYsUKg/XffPNNtGrVCvPnz0ft2rURGRmJnJwc3HPPPejRoweWLFmCkJAQfPzxx4iNjcV///2nHyyxf/9+DBgwAM2aNcPKlStRs2ZNLF68GB999JETW5KIqhvPo4g8U0VFBbKzs9G1a1c0bdrU5tdJnXfYmqvSGTZsGEaNGoUnnngC+/btw0svvYT9+/dj+/btJse5tXX379+PXr16ITw8HG+88QbCwsKwceNGTJw4EWfOnMHMmTP126qu43/Xrl1o164dPv74Y8ycORMajQYtWrTA//73P8THxxuse/jwYbz66qvYtGmTZHllS3SlZIQQNq3/1FNPYcSIETh58iQaNWpk8ry9uaTExERMnDgRzz77LJYvX47nnnsOPXv21I/QdyQn5jEEuZUVK1YIAOLw4cP6ZdHR0aJhw4biwoUL+mXl5eWiQ4cOQq1WC61WK4QQIioqSjRt2lRcuXJFv96FCxdE/fr1hfFHPW/ePAFAnDhxwmwsAMTMmTMln3v66aeFSqUSR44c0S87d+6cqFmzphg5cqTF9yOEEBERESI+Pl5ynyEhIeLMmTNm46ps5syZJu9NZ+zYsaJGjRqisLDQYPltt90mevbsWeV9m+Oq/Vpbz9bPxN79PvLII6JRo0YW1yHyRGfOnBF9+vQRAAQA4e/vL3r16iVSUlL0/e3ff/8tVCqVeOSRR2zerlarFdeuXRNHjhwRAMQXX3yhf864T7x06ZKoV6+eGDJkiME2KioqROfOnUX37t31y3r06CGaNGkiysrK9MtKS0tFvXr1zPaDROTeTpw4IQCI0aNHW1wvNjZWABAnT57Un/u8/PLLBuscOHBAABCTJ082WP7hhx8KAAbnXUlJSSI4ONjgnEEIIebPny8AiH379gkhhDh8+LAAIFq0aCGuXr1qsG6bNm1Ely5dxLVr1wyWDx48WDRu3FhUVFToY7/pppsMzjnLy8tFmzZtJM8Ricgz8DyKyDPZeu6hY+68Qwjbc1W6bZg7R1m9erXJ/qytGxMTI9RqtSgpKTFYb8KECSIwMFCcO3dOv8wZx39OTo4AIHJycsyu06pVKxEWFiYaNWokVqxYITZt2qQ/h9uwYYPBujExMSIuLk7//wBEUlKSTbHo+l1rIiIiRExMjKioqBARERFizpw5QgghBg0aJCIiIvTr2Zvfe/PNN/XLLly4IPz9/cVLL72kX2ZvTkwI29rXHbCciwsZz95r6bFr1y7JbVy6dAnbt2/HiBEjEBwcrF+uUqkQFxcHjUaDP/74A5cuXcKOHTvwwAMPoEaNGvr1goODMWTIEJPtHj9+HAqFAqGhoQ69t7y8PLRv3x7h4eH6ZXXr1kWvXr2Ql5fn0DZ1hgwZgvr161dpGwDw3XffITo6Gs2aNUN5ebn+obu1+erVqy7Ztyv3a2k9Rz4TW/bbsGFDnDp1yuD2biJvUL9+fWzduhUFBQWYO3cuhg4dij///BMzZsxAx44dcebMGWzatAkVFRV4+umnLW7r1KlTeOKJJ9C0aVP4+fnB398fERERAIADBw6Yfd22bdtw7tw5xMfHG/QXWq0W99xzDwoKCnDp0iVcunQJBQUFGD58OAIDA/Wvr1WrlmQfT0TeRfz/SKPKJewefPBBg3V0JVYeeeQRg+WjRo0yKbfw9ddf484770STJk0M+p57770XwPWRZZXdf//9BiPEDh06hIMHD+r3VXkb9913H/755x/88ccf+rgGDBhgMPJJpVKZjE4jIs/C8ygi32J83mFrrqoyc+counMYW9e9fPkyfvjhBwwbNgw1a9Y0OQ+5fPmyPgdSnce/VqvFiRMnsHjLine truncated
|
||||
"text/plain": [
|
||||
"<Figure size 950x950 with 9 Axes>"
|
||||
"<Figure size 1500x300 with 5 Axes>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
@@ -106,32 +58,87 @@
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Cross-correlation plots\n",
|
||||
"EPSILON = 1e-4\n",
|
||||
"START = 64\n",
|
||||
"END = None\n",
|
||||
"\n",
|
||||
"fig, axs = plt.subplots(len(x), len(x), figsize=(3*len(x)+0.5, 3*len(x)+0.5))\n",
|
||||
"sort_index = np.argsort(train_y)\n",
|
||||
"x = train_x[:,sort_index]\n",
|
||||
"y = train_y[sort_index]\n",
|
||||
"y_scaled = np.log(-y + y[-1] + EPSILON)\n",
|
||||
"train_y_scaled = np.log(-train_y + y[-1] + EPSILON)\n",
|
||||
"\n",
|
||||
"for i, axi in enumerate(axs):\n",
|
||||
" for j, axij in enumerate(axi):\n",
|
||||
" axij.scatter(\n",
|
||||
" x[i], x[j],\n",
|
||||
" c = y_scaled, # color\n",
|
||||
" cmap = 'coolwarm',\n",
|
||||
" s = 20, # size\n",
|
||||
" alpha = 0 if i == j else 1 # make diagonal transparent\n",
|
||||
" )\n",
|
||||
" if i == len(x)-1:\n",
|
||||
" axij.set_xlabel(xparams[j])\n",
|
||||
" else:\n",
|
||||
" axij.set_xticks([])\n",
|
||||
" if j == 0:\n",
|
||||
" axij.set_ylabel(xparams[i])\n",
|
||||
" else:\n",
|
||||
" axij.set_yticks([])\n",
|
||||
"fig, ax = plt.subplots(1, 5, figsize=(15,3))\n",
|
||||
"ax[0].plot(-train_y, 'k.')\n",
|
||||
"ax[0].set_title(\"$-\\\\log(\\\\mathtt{fourier\\\\_error})$\")\n",
|
||||
"ax[1].plot(train_y_scaled, 'k.')\n",
|
||||
"ax[1].set_title(\"Scaled\")\n",
|
||||
"ax[2].sharey(ax[0])\n",
|
||||
"ax[2].plot(-y, 'k')\n",
|
||||
"ax[2].set_title(\"Ordered\")\n",
|
||||
"ax[3].plot(y_scaled, 'k')\n",
|
||||
"ax[3].set_title(\"Scaled\")\n",
|
||||
"ax[4].plot(y_scaled[START:END], 'k')\n",
|
||||
"ax[4].set_title(f\"Cropped $\\\\mathtt{{[{START}:{END}]}}$\")\n",
|
||||
"plt.tight_layout()\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "71fb1484",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA3gAAAJOCAYAAADlOqVKAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjYsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvq6yFwwAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzsnXd0FNUXx78zs32T3fQeEnrvvUlvgmIBERAVFLFSRBB+ihRBwAaKXamKvaCigkhRlN57DZDeyybZPvN+f0yyyZJN291kN8n7nMM5zNuZ9+5uZu68+94tDCGEgEKhUCgUCoVCoVAodR7W0wJQKBQKhUKhUCgUCsU9UAOPQqFQKBQKhUKhUOoJ1MCjUCgUCoVCoVAolHoCNfAoFAqFQqFQKBQKpZ5ADTwKhUKhUCgUCoVCqSdQA49CoVAoFAqFQqFQ6gnUwKNQKBQKhUKhUCiUegI18CgUCoVCoVAoFAqlnkANPAqFQqFQKBQKhUKpJ1ADj1JlNm3aBIZh7P4FBwdj4MCB2L59e42Nq9frsWTJEuzbt6/GxqgMhmGwZMkSj41fVfbs2YNp06ahVatWUKvViIyMxNixY3H8+HGH5584cQJDhw6Fj48P/Pz8cN999yEuLs7huevWrUOrVq0gl8vRuHFjLF26FBaLpUpyvfzyyxgzZgwiIyPBMAweffRRZ78ipR5CdcsSj41/Oz/++CMmTpyIZs2aQalUIjY2FpMnT8bVq1fLnPvSSy+hc+fOCAgIgEKhQJMmTfDEE0/g1q1bVR7v66+/RqdOnaBQKBAREYHZs2ejoKDAnV+JUg+gOmKJx8a/nb/++gvDhg1DREQE5HI5QkJCMHjwYPz+++9lzq2qjliyZEmZv2/pf19//XWFMu3bt6/caw8dOuTW719XoAYepdps3LgRBw8exIEDB/DJJ5+A4zjcdddd+PXXX2tkPL1ej6VLl3pUwdYVPvzwQ9y8eROzZs3C77//jnfeeQfp6eno1asX9uzZY3fupUuXMHDgQJjNZnz77bfYsGEDrly5gv79+yMjI8Pu3BUrVmDWrFm47777sHPnTjz99NN47bXX8Mwzz1RJrjVr1iArKwt33303ZDKZ274vpX5BdYvnWb16NfR6PV566SXs2LEDy5cvx8mTJ9GlSxecP3/e7tzc3FxMnDgRmzdvxo4dO/DCCy9g+/bt6NmzJ7Kysioda+vWrZg4cSK6d++OP/74A4sXL8amTZtw33331dTXo9RxqI7wPFlZWWjbti3WrFmDP//8Ex9//DGkUilGjx6NL774wu7cquqIxx9/HAcPHizzr127dlAqlRg5cmSVZHvttdcc9tEgIRRKFdm4cSMBQI4ePWrXrtfriVwuJxMnTqyRcTMyMggAsnjx4hrpvyp4evyqkpaWVqYtPz+fhIaGkiFDhti1jx8/ngQFBZG8vDxb282bN4lUKiXz58+3tWVmZhKFQkGeeOIJu+tXrFhBGIYh58+fr1Qunudt/1er1eSRRx6p6leiNACobvHc+LfjSIckJSURqVRKHnvssUqv//333wkAsn79+grPs1qtJDw8nAwfPtyufevWrQQA+f3336snOKVeQ3WE58avCmazmURGRpL+/ftXem5VdcSNGzcIwzDkoYceqrTPvXv3EgDku+++q7LM9R26g0dxGYVCAZlMBqlUatduNpuxfPlym1tfcHAwpk6dWmZ3aM+ePRg4cCACAwOhVCrRqFEj3H///dDr9bh58yaCg4MBAEuXLrVtuZfn4peRkQGZTIZFixaV+ezSpUtgGAbvvvuu7dynn34abdq0gY+Pj83NYP/+/ZV+52J3gtspdiO5efOmXfs333yD3r17Q61Ww8fHByNGjMDJkycrHae6hISElGnz8fFBmzZtkJCQYGuzWq3Yvn077r//fmg0Glt7TEwMBg0ahJ9++snWtmPHDhiNRkydOtWu36lTp4IQgm3btlUqF8tSVUOpPlS3lFBbusWRDomIiEBUVJSdDimP4t9UIpFUeN6hQ4eQkpJSRq+MHz8ePj4+djqIQikPqiNK8OT8QyqVws/Pr9LnHqi6jtiwYQMIIXj88cfdImNDg866KNWG53lYrVZYLBYkJiZi9uzZKCwsxKRJk2znCIKAsWPHYtWqVZg0aRJ+++03rFq1Crt27cLAgQNhMBgAADdv3sTo0aMhk8mwYcMG7NixA6tWrYJarYbZbEZ4eDh27NgBAHjsscdsW+6OFCggKo4xY8Zg8+bNEATB7rONGzdCJpNh8uTJAIDs7GwAwOLFi/Hbb79h48aNaNKkCQYOHOhWd4zXXnsNEydORJs2bfDtt9/i888/R35+Pvr3748LFy7Yzrt582aNxKfl5eXhxIkTaNu2ra3t+vXrMBgM6NChQ5nzO3TogGvXrsFoNAIAzp07BwBo37693Xnh4eEICgqyfU6huArVLdWjtnRLXFwcbt26ZadDSmO1WmEwGHDy5EnMnj0bLVq0qNTNslhv3K6DpFIpWrVqRfUKxSFUR1SPmtQRgiDAarUiOTkZixcvxpUrVzB37lyH51ZXRwiCgE2bNqFZs2YYMGBAlWV65plnIJFIoNFoMGLECPz7779Vvrbe4ektRErdodhF4vZ/crmcfPDBB3bnfvXVVwQA+eGHH+zajx49SgDYzv/+++8JAHLq1Klyx62ui8Qvv/xCAJA///zT1ma1WklERAS5//77y73OarUSi8VChgwZQu699167z24ff/HixcTR41P8G924cYMQQkh8fDyRSCTkueeeszsvPz+fhIWFkQceeMDWdvPmTcJxHJk2bVqVvmdVmTx5MpFIJOTYsWO2tv/++48AIF999VWZ81977TUCgCQnJxNCCJk+fTqRy+UO+27RokUZF6vKoC6alNuhuqVkfG/TLRaLhQwcOJBoNBoSHx9f5vOUlBS7v1nPnj1JUlJSpf2uWLGCACApKSllPhs+fDhp0aJFtWWl1F+ojigZ31t0xIgRI2x/B41GQ3788UeH5zmjI/744w8CgKxcubJKspw4cYLMmjWL/PTTT+Sff/4hGzZsIK1btyYcx5EdO3ZU+TvVJ+gOHqXabNmyBUePHsXRo0fxxx9/4JFHHsEzzzyD9957z3bO9u3b4efnh7vuugtWq9X2r1OnTggLC7OtUHXq1AkymQxPPPEENm/eXG4Gx+owatQohIWFYePGjba2nTt3Ijk5GdOmTbM796OPPkKXLl2gUCggkUgglUqxe/duXLx40WU5ise1Wq14+OGH7X4HhUKBAQMG2K3UxcTEwGq1Yv369RX2SQix68tqtZZ77qJFi7B161asWbMGXbt2LfO5IzcPR59V9TwKxRWobqk6NaFbbocQgsceewz79+/Hli1bEB0dXeacoKAgHD16FP/++y8+/fRTZGdnY9CgQUhJSanSGOXpD6pXKI6gOqLq1LSOWLduHY4cOYKff/4ZI0aMwIQJE/DVV1+VOc8ZHbF+/XpIJJIq7yh27twZa9euxT333IP+/ftj6tSpOHDgAMLDwzF//vwqf6d6hactTErdobwgZ0LElRylUklycnIIIYQMHTrU4Wpb8b/Bgwfbrv3nn3/ImDFjiFqtJgBIkyZNyNq1a22fOxPkPG/ePKJQKGzyjB8/noSHhxOr1Wo756233iIAyJNPPkm2b99ODh06RI4ePUpGjhxJYmJi7Pq7ffyqrqAtX768wt+BZdkqf6diioOJS/8rHq80S5YsIQDIihUrynx26dIlAoC8//77ZT574YUXCMMwxGAwEEIIWbBgAQFACgsLy5wbFBRU7eB2uoNHuR2qW0rG96RuKY0gCGTatGmEZVny+eefV/m6hIQEIpFIyMyZMys876OPPiIAHCZp6tatG+ndu3e1ZabUX6iOKBnfW3TE7YwcOZL4+/vbJVVzRGU6IiMjg8hkMjJ27FiXZXryyScJAKLX613uq65ReTQkhVIFOnTogJ07d+LKlSvo0aMHgoKCEBgYaPNfvx1fX1/b//v374/+/fuD53kcO3YM69atw+zZsxEaGooHH3zQKXmmTp2KN954A19//TUmTJiAX375BbNnzwbHcbZzvvjiCwwcOBAffvih3bX5+fmV9q9QKAAAJpMJcrnc1p6ZmWl3XlBQEADg+++/R0xMjFPf5Xa6du2Ko0eP2rVFRETYHS9duhRLlizBkiVL8L///a9MH02bNoVSqcTZs2fLfHb27Fk0a9bM9h2LY+/Onj2Lnj172s5LTU1FZmZmw01BTKkVqG4RqQ3dUgwpSmywceNGrF+/Hg899FCVr42KikJERASuXLlS4Xml9UqbNm1s7VarFZcuXcLEiROdE57S4KA6QqQ2dYQjevTogR07diAjIwOhoaHlnleZjvj8889hNpvdklyFEAKgYXoEUAOP4hZOnToFoCQ70pgxY/D111+D53k7o6AiOI5Dz5490apVK2zduhUnTpzAgw8+aFNgxYHRVaF169bo2bMnNm7cCJ7nYTKZymRrYxjGTjkCwJkzZ3Dw4EGHrkiliY2NtZ3fvXt3W/vttXhGjBgBiUSC69ev4/7776+y/BXh6+uLbt26lfv5q6++iiVLluDll1/G4sWLHZ4jkUhw11134ccff8Trr79ue+HFx8dj7969mDNnju3ckSNHQqFQYNOmTXZ/y+KMXffcc49bvheF4giqW0RqQ7cA4oRo+vTp2LhxIz7++OMy360yrl27hsTERNx9990VntezZ0+Eh4dj06ZNmDBhgq39+++/R0FBAa2FR6kyVEeI1JaOcAQhBH///Tf8/PwQGBhY4bmV6Yj169cjIiICo0aNckmmnJwcbN++HZ06dbIZxQ0JauBRqs25c+dscV9ZWVn48ccfsWvXLtx7771o3LgxAODBBx/E1q1bceedd2LWrFno0aMHpFIpEhMTsXfvXowdOxb33nsvPvroI+zZswejR49Go0aNYDQasWHDBgDA0KFDAYgGTUxMDH7++WcMGTILine truncated
|
||||
"text/plain": [
|
||||
"<Figure size 900x600 with 6 Axes>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" Best BO trial : index 391\n",
|
||||
" defocus [A] : -200.06\n",
|
||||
" layers : 23.00\n",
|
||||
" thickness [A] : 337.54\n",
|
||||
" log fourier : -0.47124\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"fig, axs = plt.subplots(2, len(x), figsize=(3*len(x), 6), sharey='row', sharex='col')\n",
|
||||
"for i, axi in enumerate(axs[0]):\n",
|
||||
" axi.scatter(x[i][START:END], -y[START:END], c=y_scaled[START:END], cmap='coolwarm', s=10)\n",
|
||||
" axi.set_title(f\"Best value: {x[i,-1]:.1f}\")\n",
|
||||
"\n",
|
||||
"axs[0][0].set_ylabel('$- \\\\log (\\\\mathtt{fourier\\\\_error})$')\n",
|
||||
"\n",
|
||||
"for i, axi in enumerate(axs[1]):\n",
|
||||
" axi.scatter(x[i][START:END], y_scaled[START:END], c=y_scaled[START:END], cmap='coolwarm', s=10)\n",
|
||||
" axi.set_xlabel(xparams[i])\n",
|
||||
"axs[1][0].set_ylabel('Scaled')\n",
|
||||
"plt.tight_layout()\n",
|
||||
"plt.show()\n",
|
||||
"\n"
|
||||
"\n",
|
||||
"print(f\" Best BO trial : index {train_y.argmax()}\")\n",
|
||||
"print(\"\\n\".join([f'{xparams[i]:>15} : {x[i, -1]:> 9.2f}' for i in range(len(xparams))]))\n",
|
||||
"print(f\" log fourier : {-y[-1]:9.5f}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "63358241",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
Reference in new issue
Block a user