workbench 0.8.162__py3-none-any.whl → 0.8.202__py3-none-any.whl

workbench/model_scripts/scikit_learn/generated_model_script.py

@@ -4,11 +4,11 @@ None
 # Template Placeholders
 TEMPLATE_PARAMS = {
     "model_type": "regressor",
-    "target_column": "solubility",
-    "feature_list": ['molwt', 'mollogp', 'molmr', 'heavyatomcount', 'numhacceptors', 'numhdonors', 'numheteroatoms', 'numrotatablebonds', 'numvalenceelectrons', 'numaromaticrings', 'numsaturatedrings', 'numaliphaticrings', 'ringcount', 'tpsa', 'labuteasa', 'balabanj', 'bertzct'],
+    "target_column": "udm_asy_res_efflux_ratio",
+    "feature_list": ['chi2v', 'fr_sulfone', 'chi1v', 'bcut2d_logplow', 'fr_piperzine', 'kappa3', 'smr_vsa1', 'slogp_vsa5', 'fr_ketone_topliss', 'fr_sulfonamd', 'fr_imine', 'fr_benzene', 'fr_ester', 'chi2n', 'labuteasa', 'peoe_vsa2', 'smr_vsa6', 'bcut2d_chglo', 'fr_sh', 'peoe_vsa1', 'fr_allylic_oxid', 'chi4n', 'fr_ar_oh', 'fr_nh0', 'fr_term_acetylene', 'slogp_vsa7', 'slogp_vsa4', 'estate_vsa1', 'vsa_estate4', 'numbridgeheadatoms', 'numheterocycles', 'fr_ketone', 'fr_morpholine', 'fr_guanido', 'estate_vsa2', 'numheteroatoms', 'fr_nitro_arom_nonortho', 'fr_piperdine', 'nocount', 'numspiroatoms', 'fr_aniline', 'fr_thiophene', 'slogp_vsa10', 'fr_amide', 'slogp_vsa2', 'fr_epoxide', 'vsa_estate7', 'fr_ar_coo', 'fr_imidazole', 'fr_nitrile', 'fr_oxazole', 'numsaturatedrings', 'fr_pyridine', 'fr_hoccn', 'fr_ndealkylation1', 'numaliphaticheterocycles', 'fr_phenol', 'maxpartialcharge', 'vsa_estate5', 'peoe_vsa13', 'minpartialcharge', 'qed', 'fr_al_oh', 'slogp_vsa11', 'chi0n', 'fr_bicyclic', 'peoe_vsa12', 'fpdensitymorgan1', 'fr_oxime', 'molwt', 'fr_dihydropyridine', 'smr_vsa5', 'peoe_vsa5', 'fr_nitro', 'hallkieralpha', 'heavyatommolwt', 'fr_alkyl_halide', 'peoe_vsa8', 'fr_nhpyrrole', 'fr_isocyan', 'bcut2d_chghi', 'fr_lactam', 'peoe_vsa11', 'smr_vsa9', 'tpsa', 'chi4v', 'slogp_vsa1', 'phi', 'bcut2d_logphi', 'avgipc', 'estate_vsa11', 'fr_coo', 'bcut2d_mwhi', 'numunspecifiedatomstereocenters', 'vsa_estate10', 'estate_vsa8', 'numvalenceelectrons', 'fr_nh2', 'fr_lactone', 'vsa_estate1', 'estate_vsa4', 'numatomstereocenters', 'vsa_estate8', 'fr_para_hydroxylation', 'peoe_vsa3', 'fr_thiazole', 'peoe_vsa10', 'fr_ndealkylation2', 'slogp_vsa12', 'peoe_vsa9', 'maxestateindex', 'fr_quatn', 'smr_vsa7', 'minestateindex', 'numaromaticheterocycles', 'numrotatablebonds', 'fr_ar_nh', 'fr_ether', 'exactmolwt', 'fr_phenol_noorthohbond', 'slogp_vsa3', 'fr_ar_n', 'sps', 'fr_c_o_nocoo', 'bertzct', 'peoe_vsa7', 'slogp_vsa8', 'numradicalelectrons', 'molmr', 'fr_tetrazole', 'numsaturatedcarbocycles', 'bcut2d_mrhi', 'kappa1', 'numamidebonds', 'fpdensitymorgan2', 'smr_vsa8', 'chi1n', 'estate_vsa6', 'fr_barbitur', 'fr_diazo', 'kappa2', 'chi0', 'bcut2d_mrlow', 'balabanj', 'peoe_vsa4', 'numhacceptors', 'fr_sulfide', 'chi3n', 'smr_vsa2', 'fr_al_oh_notert', 'fr_benzodiazepine', 'fr_phos_ester', 'fr_aldehyde', 'fr_coo2', 'estate_vsa5', 'fr_prisulfonamd', 'numaromaticcarbocycles', 'fr_unbrch_alkane', 'fr_urea', 'fr_nitroso', 'smr_vsa10', 'fr_c_s', 'smr_vsa3', 'fr_methoxy', 'maxabspartialcharge', 'slogp_vsa9', 'heavyatomcount', 'fr_azide', 'chi3v', 'smr_vsa4', 'mollogp', 'chi0v', 'fr_aryl_methyl', 'fr_nh1', 'fpdensitymorgan3', 'fr_furan', 'fr_hdrzine', 'fr_arn', 'numaromaticrings', 'vsa_estate3', 'fr_azo', 'fr_halogen', 'estate_vsa9', 'fr_hdrzone', 'numhdonors', 'fr_alkyl_carbamate', 'fr_isothiocyan', 'minabspartialcharge', 'fr_al_coo', 'ringcount', 'chi1', 'estate_vsa7', 'fr_nitro_arom', 'vsa_estate9', 'minabsestateindex', 'maxabsestateindex', 'vsa_estate6', 'estate_vsa10', 'estate_vsa3', 'fr_n_o', 'fr_amidine', 'fr_thiocyan', 'fr_phos_acid', 'fr_c_o', 'fr_imide', 'numaliphaticrings', 'peoe_vsa6', 'vsa_estate2', 'nhohcount', 'numsaturatedheterocycles', 'slogp_vsa6', 'peoe_vsa14', 'fractioncsp3', 'bcut2d_mwlow', 'numaliphaticcarbocycles', 'fr_priamide', 'nacid', 'nbase', 'naromatom', 'narombond', 'sz', 'sm', 'sv', 'sse', 'spe', 'sare', 'sp', 'si', 'mz', 'mm', 'mv', 'mse', 'mpe', 'mare', 'mp', 'mi', 'xch_3d', 'xch_4d', 'xch_5d', 'xch_6d', 'xch_7d', 'xch_3dv', 'xch_4dv', 'xch_5dv', 'xch_6dv', 'xch_7dv', 'xc_3d', 'xc_4d', 'xc_5d', 'xc_6d', 'xc_3dv', 'xc_4dv', 'xc_5dv', 'xc_6dv', 'xpc_4d', 'xpc_5d', 'xpc_6d', 'xpc_4dv', 'xpc_5dv', 'xpc_6dv', 'xp_0d', 'xp_1d', 'xp_2d', 'xp_3d', 'xp_4d', 'xp_5d', 'xp_6d', 'xp_7d', 'axp_0d', 'axp_1d', 'axp_2d', 'axp_3d', 'axp_4d', 'axp_5d', 'axp_6d', 'axp_7d', 'xp_0dv', 'xp_1dv', 'xp_2dv', 'xp_3dv', 'xp_4dv', 'xp_5dv', 'xp_6dv', 'xp_7dv', 'axp_0dv', 'axp_1dv', 'axp_2dv', 'axp_3dv', 'axp_4dv', 'axp_5dv', 'axp_6dv', 'axp_7dv', 'c1sp1', 'c2sp1', 'c1sp2', 'c2sp2', 'c3sp2', 'c1sp3', 'c2sp3', 'c3sp3', 'c4sp3', 'hybratio', 'fcsp3', 'num_stereocenters', 'num_unspecified_stereocenters', 'num_defined_stereocenters', 'num_r_centers', 'num_s_centers', 'num_stereobonds', 'num_e_bonds', 'num_z_bonds', 'stereo_complexity', 'frac_defined_stereo', 'tertiary_amine_count', 'type_i_pattern_count', 'type_ii_pattern_count', 'aromatic_interaction_score', 'molecular_axis_length', 'molecular_asymmetry', 'molecular_volume_3d', 'radius_of_gyration', 'asphericity', 'charge_centroid_distance', 'nitrogen_span', 'amide_count', 'hba_hbd_ratio', 'intramolecular_hbond_potential', 'amphiphilic_moment'],
     "model_class": PyTorch,
-    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/aqsol-pytorch-reg/training",
-    "train_all_data": False
+    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/caco2-er-reg-pytorch-test/training",
+    "train_all_data": False,
 }
 
 import awswrangler as wr
@@ -99,10 +99,7 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     # Load training data from the specified directory
-    training_files = [
-        os.path.join(args.train, file)
-        for file in os.listdir(args.train) if file.endswith(".csv")
-    ]
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
     all_df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
 
     # Check if the DataFrame is empty
@@ -116,10 +113,7 @@ if __name__ == "__main__":
 
     if needs_standardization:
         # Create a pipeline with standardization and the model
-        model = Pipeline([
-            ("scaler", StandardScaler()),
-            ("model", model)
-        ])
+        model = Pipeline([("scaler", StandardScaler()), ("model", model)])
 
     # Handle logic based on the model_type
     if model_type in ["classifier", "regressor"]:
@@ -206,6 +200,7 @@ if __name__ == "__main__":
     with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
         json.dump(feature_list, fp)
 
+
 #
 # Inference Section
 #

workbench/model_scripts/scikit_learn/scikit_learn.template

@@ -8,7 +8,7 @@ TEMPLATE_PARAMS = {
     "feature_list": "{{feature_list}}",
     "model_class": "{{model_class}}",
     "model_metrics_s3_path": "{{model_metrics_s3_path}}",
-    "train_all_data": "{{train_all_data}}"
+    "train_all_data": "{{train_all_data}}",
 }
 
 import awswrangler as wr
@@ -99,10 +99,7 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     # Load training data from the specified directory
-    training_files = [
-        os.path.join(args.train, file)
-        for file in os.listdir(args.train) if file.endswith(".csv")
-    ]
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
     all_df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
 
     # Check if the DataFrame is empty
@@ -116,10 +113,7 @@ if __name__ == "__main__":
 
     if needs_standardization:
         # Create a pipeline with standardization and the model
-        model = Pipeline([
-            ("scaler", StandardScaler()),
-            ("model", model)
-        ])
+        model = Pipeline([("scaler", StandardScaler()), ("model", model)])
 
     # Handle logic based on the model_type
     if model_type in ["classifier", "regressor"]:
@@ -206,6 +200,7 @@ if __name__ == "__main__":
     with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
         json.dump(feature_list, fp)
 
+
 #
 # Inference Section
 #

workbench/model_scripts/script_generation.py

@@ -70,6 +70,11 @@ def fill_template(template_path: str, params: dict, output_script: str) -> str:
     # Sanity check to ensure all placeholders were replaced
     if "{{" in template and "}}" in template:
         msg = "Not all template placeholders were replaced. Please check your params."
+
+        # Show which placeholders are still present
+        start = template.index("{{")
+        end = template.index("}}", start) + 2
+        msg += f" Unreplaced placeholder: {template[start:end]}"
         log.critical(msg)
         raise ValueError(msg)
 
@@ -88,6 +93,7 @@ def generate_model_script(template_params: dict) -> str:
         template_params (dict): Dictionary containing the parameters:
             - model_imports (str): Import string for the model class
             - model_type (ModelType): The enumerated type of model to generate
+            - model_framework (str): The enumerated model framework to use
             - model_class (str): The model class to use (e.g., "RandomForestRegressor")
             - target_column (str): Column name of the target variable
             - feature_list (list[str]): A list of columns for the features
@@ -98,22 +104,24 @@ def generate_model_script(template_params: dict) -> str:
     Returns:
         str: The name of the generated model script
     """
-    from workbench.api import ModelType  # Avoid circular import
+    from workbench.api import ModelType, ModelFramework  # Avoid circular import
 
     # Determine which template to use based on model type
     if template_params.get("model_class"):
-        if template_params["model_class"].lower() == "pytorch":
-            template_name = "pytorch.template"
-            model_script_dir = "pytorch_model"
-        else:
-            template_name = "scikit_learn.template"
-            model_script_dir = "scikit_learn"
+        template_name = "scikit_learn.template"
+        model_script_dir = "scikit_learn"
+    elif template_params["model_framework"] == ModelFramework.PYTORCH_TABULAR:
+        template_name = "pytorch.template"
+        model_script_dir = "pytorch_model"
+    elif template_params["model_framework"] == ModelFramework.CHEMPROP:
+        template_name = "chemprop.template"
+        model_script_dir = "chemprop"
     elif template_params["model_type"] in [ModelType.REGRESSOR, ModelType.CLASSIFIER]:
         template_name = "xgb_model.template"
         model_script_dir = "xgb_model"
     elif template_params["model_type"] == ModelType.UQ_REGRESSOR:
-        template_name = "quant_regression.template"
-        model_script_dir = "quant_regression"
+        template_name = "mapie.template"
+        model_script_dir = "uq_models"
     elif template_params["model_type"] == ModelType.ENSEMBLE_REGRESSOR:
         template_name = "ensemble_xgb.template"
         model_script_dir = "ensemble_xgb"