added stuff

AC-BO-Hackathon · Mar 27, 2024 · 0ca557b · 0ca557b
1 parent 1c1dca1
commit 0ca557b
Showing 1 changed file with 129 additions and 26 deletions.
diff --git a/baybe_hack.ipynb b/baybe_hack.ipynb
@@ -9,9 +9,121 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "df_AA2024 = pd.read_excel('data/filtered_AA2024.xlsx')\n",
+    "print(df_AA2024.describe())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(df_AA2024.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from baybe.parameters import (\n",
+    "    NumericalContinuousParameter,\n",
+    ")\n",
+    "\n",
+    "parameters = [\n",
+    "    NumericalContinuousParameter(\n",
+    "        name=\"Time[h]\",\n",
+    "        bounds=(0.500000, 672),\n",
+    "    ),\n",
+    "    NumericalContinuousParameter(\n",
+    "        name=\"pH\",\n",
+    "        bounds=(1, 14),\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from baybe.searchspace import SearchSpace\n",
+    "\n",
+    "searchspace = SearchSpace.from_product(parameters)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from baybe import Campaign\n",
+    "\n",
+    "campaign = Campaign(searchspace, objective)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = campaign.recommend(batch_size=3)\n",
+    "print(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
+   "source": [
+    "############################\n",
+    "############################\n",
+    "############################"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/vscode/.local/lib/python3.10/site-packages/baybe/telemetry.py:222: UserWarning: WARNING: BayBE Telemetry endpoint https://public.telemetry.baybe.p.uptimize.merckgroup.com:4317 cannot be reached. Disabling telemetry. The exception encountered was: ConnectionError, HTTPConnectionPool(host='verkehrsnachrichten.merck.de', port=80): Max retries exceeded with url: / (Caused by NameResolutionError(\"<urllib3.connection.HTTPConnection object at 0x7fa0c7791690>: Failed to resolve 'verkehrsnachrichten.merck.de' ([Errno -2] Name or service not known)\"))\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "import pandas as pd\n",
@@ -55,7 +167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -64,7 +176,7 @@
        "'\\noverpotential = NumericalTarget(\\n    name=\"overpotential\", \\n    mode=\"MAX\", \\n    bounds=(-400, 0),\\n    transformation=\"LINEAR\"  # optional, will be applied if bounds are not None, LINEAR only one available for MAX/MIN\\n    ) \\n\\noverpotential_slope = NumericalTarget(\\n    name=\"overpotential_slope\", \\n    mode=\"MAX\", \\n    bounds=(-0.05, 0.05),\\n    transformation=\"LINEAR\"  # optional, will be applied if bounds are not None, LINEAR only one available for MAX/MIN\\n    )\\n\\nobjective = Objective(\\n    mode=\"DESIRABILITY\",\\n    targets=[overpotential, overpotential_slope],\\n    weights=[1.0, 1.0],  # optional, by default all weights are equal\\n    combine_func=\"GEOM_MEAN\",  # optional, geometric mean is the default\\n)\\n'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -103,7 +215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -140,27 +252,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "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[5], line 3\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 SubstanceParameter\n\u001b[0;32m----> 3\u001b[0m \u001b[43mSubstanceParameter\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      4\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      5\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      6\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mWater\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      7\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m1-Octanol\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;43mCCCCCCCCO\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      8\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mToluene\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;43mCC1=CC=CC=C1\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      9\u001b[0m \u001b[43m    \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     10\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# optional\u001b[39;49;00m\n\u001b[1;32m     11\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdecorrelate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.7\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# optional\u001b[39;49;00m\n\u001b[1;32m     12\u001b[0m \u001b[43m)\u001b[49m\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]'\"."
-     ]
+     "data": {
+      "text/plain": [
+       "SubstanceParameter(name='Solvent', data={'Water': 'O', '1-Octanol': 'CCCCCCCCO', 'Toluene': 'CC1=CC=CC=C1'}, decorrelate=0.7, encoding=<SubstanceEncoding.MORDRED: 'MORDRED'>)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -208,7 +311,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -220,7 +323,7 @@
        "Polymer C                     -39             241, decorrelate=True, encoding=<CustomEncoding.CUSTOM: 'CUSTOM'>)"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -250,7 +353,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -284,7 +387,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [