Implemented first notebook

AC-BO-Hackathon · Mar 27, 2024 · 0571abd · 0571abd
1 parent 32c1699
commit 0571abd
Showing 1 changed file with 146 additions and 0 deletions.
diff --git a/BayBE_basic.ipynb b/BayBE_basic.ipynb
@@ -0,0 +1,146 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Import filtered data set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "df_AA2024 = pd.read_excel('data/filtered_AA2024.xlsx')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                    SMILES  Time_h    pH  Inhib_Concentrat_M  \\\n",
+      "0             COCCOC(=O)OCSc1nc2c(s1)cccc2    24.0   4.0               0.001   \n",
+      "1             COCCOC(=O)OCSc1nc2c(s1)cccc2    24.0  10.0               0.001   \n",
+      "2            Cc1ccc(c(c1)n1nc2c(n1)cccc2)O    24.0   4.0               0.001   \n",
+      "3            Cc1ccc(c(c1)n1nc2c(n1)cccc2)O    24.0  10.0               0.001   \n",
+      "4  Clc1ccc(cc1)CC[C@](C(C)(C)C)(Cn1cncn1)O    24.0   4.0               0.001   \n",
+      "\n",
+      "   Efficiency  \n",
+      "0         0.0  \n",
+      "1         0.0  \n",
+      "2        30.0  \n",
+      "3        30.0  \n",
+      "4        30.0  \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_AA2024.head())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set objectives and parameters in BayBE"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from baybe.targets import NumericalTarget\n",
+    "from baybe.objective import Objective\n",
+    "\n",
+    "target = NumericalTarget(\n",
+    "    name=\"Efficiency\",\n",
+    "    mode=\"MAX\",\n",
+    ")\n",
+    "objective = Objective(mode=\"SINGLE\", targets=[target])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "OptionalImportError",
+     "evalue": "The requested functionality requires the installation of optional chemistry dependencies. Please run \"pip install 'baybe[chem]'\".",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/baybe/utils/chemistry.py:17\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 17\u001b[0m     \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mmordred\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Calculator, descriptors\n\u001b[1;32m     18\u001b[0m     \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mrdkit\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Chem, RDLogger\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'mordred'",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mOptionalImportError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[18], line 18\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mbaybe\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mparameters\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m      2\u001b[0m     CategoricalParameter,\n\u001b[1;32m      3\u001b[0m     NumericalDiscreteParameter,\n\u001b[1;32m      4\u001b[0m     SubstanceParameter,\n\u001b[1;32m      5\u001b[0m )\n\u001b[1;32m      7\u001b[0m parameters \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m      8\u001b[0m     CategoricalParameter(\n\u001b[1;32m      9\u001b[0m         name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mGranularity\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m     10\u001b[0m         values\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcoarse\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmedium\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfine\u001b[39m\u001b[38;5;124m\"\u001b[39m],\n\u001b[1;32m     11\u001b[0m         encoding\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOHE\u001b[39m\u001b[38;5;124m\"\u001b[39m,  \u001b[38;5;66;03m# one-hot encoding of categories\u001b[39;00m\n\u001b[1;32m     12\u001b[0m     ),\n\u001b[1;32m     13\u001b[0m     NumericalDiscreteParameter(\n\u001b[1;32m     14\u001b[0m         name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPressure[bar]\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m     15\u001b[0m         values\u001b[38;5;241m=\u001b[39m[\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m5\u001b[39m, \u001b[38;5;241m10\u001b[39m],\n\u001b[1;32m     16\u001b[0m         tolerance\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.2\u001b[39m,  \u001b[38;5;66;03m# allows experimental inaccuracies up to 0.2 when reading values\u001b[39;00m\n\u001b[1;32m     17\u001b[0m     ),\n\u001b[0;32m---> 18\u001b[0m     \u001b[43mSubstanceParameter\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     19\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mSolvent\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     20\u001b[0m \u001b[43m        \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\n\u001b[1;32m     21\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mSolvent A\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mCOC\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     22\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mSolvent B\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mCCC\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# label-SMILES pairs\u001b[39;49;00m\n\u001b[1;32m     23\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mSolvent C\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mO\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     24\u001b[0m \u001b[43m            \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mSolvent D\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mCS(=O)C\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m     25\u001b[0m \u001b[43m        \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     26\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mMORDRED\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# chemical encoding via mordred package\u001b[39;49;00m\n\u001b[1;32m     27\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m     28\u001b[0m ]\n",
+      "File \u001b[0;32m<attrs generated init baybe.parameters.substance.SubstanceParameter>:10\u001b[0m, in \u001b[0;36m__init__\u001b[0;34m(self, name, data, decorrelate, encoding)\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _config\u001b[38;5;241m.\u001b[39m_run_validators \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m      9\u001b[0m     __attr_validator_name(\u001b[38;5;28mself\u001b[39m, __attr_name, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname)\n\u001b[0;32m---> 10\u001b[0m     \u001b[43m__attr_validator_data\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m__attr_data\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     11\u001b[0m     __attr_validator_decorrelate(\u001b[38;5;28mself\u001b[39m, __attr_decorrelate, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdecorrelate)\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/attr/_make.py:3059\u001b[0m, in \u001b[0;36m_AndValidator.__call__\u001b[0;34m(self, inst, attr, value)\u001b[0m\n\u001b[1;32m   3057\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, inst, attr, value):\n\u001b[1;32m   3058\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m v \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validators:\n\u001b[0;32m-> 3059\u001b[0m         \u001b[43mv\u001b[49m\u001b[43m(\u001b[49m\u001b[43minst\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/baybe/parameters/substance.py:77\u001b[0m, in \u001b[0;36mSubstanceParameter._validate_substance_data\u001b[0;34m(self, _, data)\u001b[0m\n\u001b[1;32m     67\u001b[0m \u001b[38;5;129m@data\u001b[39m\u001b[38;5;241m.\u001b[39mvalidator\n\u001b[1;32m     68\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_validate_substance_data\u001b[39m(  \u001b[38;5;66;03m# noqa: DOC101, DOC103\u001b[39;00m\n\u001b[1;32m     69\u001b[0m     \u001b[38;5;28mself\u001b[39m, _: Any, data: \u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Smiles]\n\u001b[1;32m     70\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m     71\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Validate that the substance data, provided as SMILES, is valid.\u001b[39;00m\n\u001b[1;32m     72\u001b[0m \n\u001b[1;32m     73\u001b[0m \u001b[38;5;124;03m    Raises:\u001b[39;00m\n\u001b[1;32m     74\u001b[0m \u001b[38;5;124;03m        ValueError: If one or more of the SMILES are invalid.\u001b[39;00m\n\u001b[1;32m     75\u001b[0m \u001b[38;5;124;03m        ValueError: If the several entries represent the same substance.\u001b[39;00m\n\u001b[1;32m     76\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m---> 77\u001b[0m     \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mbaybe\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m chemistry\n\u001b[1;32m     79\u001b[0m     \u001b[38;5;66;03m# Check for invalid SMILES\u001b[39;00m\n\u001b[1;32m     80\u001b[0m     canonical_smiles \u001b[38;5;241m=\u001b[39m {}\n",
+      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/baybe/utils/chemistry.py:21\u001b[0m\n\u001b[1;32m     19\u001b[0m     \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mrdkit\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mChem\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mrdMolDescriptors\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m GetMorganFingerprintAsBitVect\n\u001b[1;32m     20\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n\u001b[0;32m---> 21\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m OptionalImportError(\n\u001b[1;32m     22\u001b[0m \u001b[38;5;250m        \u001b[39m\u001b[38;5;124;03m\"\"\"The requested functionality requires the installation of optional \"\"\"\u001b[39;00m\n\u001b[1;32m     23\u001b[0m \u001b[38;5;250m        \u001b[39m\u001b[38;5;124;03m\"\"\"chemistry dependencies. Please run \"pip install 'baybe[chem]'\".\"\"\"\u001b[39;00m\n\u001b[1;32m     24\u001b[0m     )\n\u001b[1;32m     26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mbaybe\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mnumerical\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m DTypeFloatNumpy\n\u001b[1;32m     28\u001b[0m _mordred_calculator \u001b[38;5;241m=\u001b[39m Calculator(descriptors)\n",
+      "\u001b[0;31mOptionalImportError\u001b[0m: The requested functionality requires the installation of optional chemistry dependencies. Please run \"pip install 'baybe[chem]'\"."
+     ]
+    }
+   ],
+   "source": [
+    "from baybe.parameters import (\n",
+    "    CategoricalParameter,\n",
+    "    NumericalDiscreteParameter,\n",
+    "    SubstanceParameter,\n",
+    ")\n",
+    "\n",
+    "parameters = [\n",
+    "    NumericalDiscreteParameter(\n",
+    "        name=\"Time[h]\",\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from baybe.searchspace import SearchSpace\n",
+    "\n",
+    "searchspace = SearchSpace.from_product(parameters)"
+   ]
+  }
+ ],
+ "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}