testing

AC-BO-Hackathon · Mar 27, 2024 · 5aed9b0 · 5aed9b0
1 parent eb0306c
commit 5aed9b0
Show file tree

Hide file tree

Showing 2 changed files with 218 additions and 630 deletions.
diff --git a/baybe_hack.ipynb b/baybe_hack.ipynb
@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -22,7 +22,7 @@
     "from baybe.parameters import NumericalDiscreteParameter, NumericalContinuousParameter\n",
     "from baybe.searchspace import SearchSpace\n",
     "\n",
-    "from baybe.recommenders import RandomRecommender, SequentialGreedyRecommender, NaiveHybridRecommender\n",
+    "from baybe.recommenders import RandomRecommender, SequentialGreedyRecommender\n",
     "from baybe.surrogates import GaussianProcessSurrogate\n",
     "\n",
     "from baybe.strategies import TwoPhaseStrategy\n",
@@ -55,9 +55,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\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,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "\"\"\"\n",
     "overpotential = NumericalTarget(\n",
@@ -92,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -129,9 +140,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "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]'\"."
+     ]
+    }
+   ],
    "source": [
     "from baybe.parameters import SubstanceParameter\n",
     "\n",
@@ -177,9 +208,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "CustomDiscreteParameter(name='Polymer', data=           Glass_Transition_TempC  Weight_kDalton\n",
+       "Polymer A                      20             120\n",
+       "Polymer B                     -71              32\n",
+       "Polymer C                     -39             241, decorrelate=True, encoding=<CustomEncoding.CUSTOM: 'CUSTOM'>)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "import pandas as pd\n",
     "from baybe.parameters import CustomDiscreteParameter\n",
@@ -205,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -226,9 +271,7 @@
     "The **SequentialGreedyRecommender** is a powerful recommender that leverages BoTorch optimization functions to perform sequential Greedy optimization. It can be applied for discrete, continuous and hybrid sarch spaces. It is an implementation of the BoTorch optimization functions for discrete, continuous and mixed spaces. **It is important to note that this recommender performs a brute-force search when applied in hybrid search spaces, as it optimizes the continuous part of the space while exhaustively searching choices in the discrete subspace.** You can customize this behavior to only sample a certain percentage of the discrete subspace via the sample_percentage attribute and to choose different sampling strategies via the hybrid_sampler attribute. \n",
     "\n",
     "e.g.\n",
-    "strategy = TwoPhaseStrategy(recommender=SequentialGreedyRecommender(hybrid_sampler=\"Farthest\", sampling_percentage=0.3))\n",
-    "\n",
-    "The **NaiveHybridRecommender** can be applied to all search spaces, but is intended to be used in hybrid spaces. This recommender **combines individual recommenders for the continuous and the discrete subspaces. It independently optimizes each subspace and consolidates the best results to generate a candidate for the original hybrid space.** "
+    "strategy = TwoPhaseStrategy(recommender=SequentialGreedyRecommender(hybrid_sampler=\"Farthest\", sampling_percentage=0.3))"
    ]
   },
   {
@@ -241,18 +284,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\lordm\\Desktop\\Projects\\baybe\\.venv\\lib\\site-packages\\baybe\\recommenders\\bayesian.py:492: UserWarning: The value of 'allow_recommending_already_measured' differs from what is specified in the discrete recommender. The value of the discrete recommender will be ignored.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "available_surr_models = [\n",
     "    \"GaussianProcessSurrogate\", \n",
@@ -281,7 +315,7 @@
     "        allow_recommending_already_measured=False,\n",
     "    )\n",
     "\n",
-    "hybrid_recommender = NaiveHybridRecommender(\n",
+    "hybrid_recommender = SequentialGreedyRecommender(\n",
     "    allow_repeated_recommendations=False,\n",
     "    allow_recommending_already_measured=False\n",
     ")"
@@ -296,9 +330,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/vscode/.local/lib/python3.10/site-packages/baybe/strategies/deprecation.py:26: DeprecationWarning: 'TwoPhaseStrategy' is deprecated and will be removed in a future version. Please use 'recommenders.TwoPhaseMetaRecommender' class instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "ename": "NameError",
+     "evalue": "name 'objective' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[10], line 10\u001b[0m\n\u001b[1;32m      1\u001b[0m strategy \u001b[38;5;241m=\u001b[39m TwoPhaseStrategy(\n\u001b[1;32m      2\u001b[0m     initial_recommender \u001b[38;5;241m=\u001b[39m RandomRecommender(),  \u001b[38;5;66;03m# Initial recommender, if no training data is available\u001b[39;00m\n\u001b[1;32m      3\u001b[0m     \u001b[38;5;66;03m# Other initial recommenders don't seem to work for my hybrid search space/set of parameters\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      7\u001b[0m     switch_after\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m  \u001b[38;5;66;03m# Switch to the model-based recommender after 1 batch or iteration (so the initial training data)\u001b[39;00m\n\u001b[1;32m      8\u001b[0m )\n\u001b[0;32m---> 10\u001b[0m campaign \u001b[38;5;241m=\u001b[39m Campaign(searchspace, \u001b[43mobjective\u001b[49m, strategy)\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'objective' is not defined"
+     ]
+    }
+   ],
    "source": [
     "strategy = TwoPhaseStrategy(\n",
     "    initial_recommender = RandomRecommender(),  # Initial recommender, if no training data is available\n",
@@ -354,7 +408,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,