Fixed bug with pos_group

pyproject.toml

@@ -3,4 +3,9 @@ requires = [
     "setuptools",
     "wheel"
 ]
-build-backend = "setuptools.build_meta"
+build-backend = "setuptools.build_meta"
+
+[tool.pytest.ini_options]
+pythonpath = [
+  ".", "spare_scores",
+]

spare_scores/classes.py

@@ -2,11 +2,10 @@
 from typing import Any
 
 import pandas as pd
-
-from spare_scores.data_prep import logging_basic_config
-from spare_scores.mlp import MLPModel
-from spare_scores.mlp_torch import MLPTorchModel
-from spare_scores.svm import SVMModel
+from data_prep import logging_basic_config
+from mlp import MLPModel
+from mlp_torch import MLPTorchModel
+from svm import SVMModel
 
 
 class SpareModel:

spare_scores/cli.py

@@ -2,7 +2,7 @@
 
 import pkg_resources  # type: ignore
 
-from spare_scores.spare_scores import spare_test, spare_train
+from spare_scores import spare_test, spare_train
 
 VERSION = pkg_resources.require("spare_scores")[0].version
 

spare_scores/data_prep.py

@@ -6,16 +6,14 @@
 import numpy as np
 import pandas as pd
 from scipy import stats
-
-from spare_scores.util import convert_to_number_if_possible
+from util import convert_to_number_if_possible
 
 
 def check_train(
     df: pd.DataFrame,
     predictors: list,
     to_predict: str,
-    verbose: int = 1,  # this needs to be removed(non used). If i remove
-    # it, then there are bugs to the test cases(check_train() unexpected argument verbose)
+    verbose: int = 1,  # this needs to be removed(non used)
     pos_group: str = "",
 ) -> Union[str, Tuple[pd.DataFrame, list, str]]:
     """Checks training dataframe for errors.

spare_scores/mlp.py

@@ -4,13 +4,14 @@
 
 import numpy as np
 import pandas as pd
+from data_prep import logging_basic_config
 from sklearn import metrics
+from sklearn.exceptions import ConvergenceWarning
 from sklearn.model_selection import GridSearchCV, KFold
 from sklearn.neural_network import MLPClassifier, MLPRegressor
 from sklearn.pipeline import Pipeline
 from sklearn.preprocessing import StandardScaler
-
-from spare_scores.data_prep import logging_basic_config
+from sklearn.utils._testing import ignore_warnings
 
 
 class MLPModel:
@@ -105,7 +106,7 @@ def __init__(
     def set_parameters(self, **parameters: Any) -> None:
         self.__dict__.update(parameters)
 
-    # @ignore_warnings(category=RuntimeWarning)
+    @ignore_warnings(category=RuntimeWarning)  # type: ignore
     def _fit(self, df: pd.DataFrame) -> None:
 
         X = df[self.predictors].astype("float64")
@@ -152,7 +153,7 @@ def _fit(self, df: pd.DataFrame) -> None:
 
         self.get_stats(y, self.y_hat)
 
-    # @ignore_warnings(category=(ConvergenceWarning, UserWarning))
+    @ignore_warnings(category=(ConvergenceWarning, UserWarning))  # type: ignore
     def fit(self, df: pd.DataFrame, verbose: int = 1) -> dict:
         """
         Trains the model using the provided dataframe and default parameters.

spare_scores/mlp_torch.py

@@ -8,6 +8,8 @@
 import torch
 import torch.nn as nn
 import torch.optim as optim
+from data_prep import logging_basic_config
+from sklearn.exceptions import ConvergenceWarning
 from sklearn.metrics import (
     accuracy_score,
     balanced_accuracy_score,
@@ -23,10 +25,9 @@
 )
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
+from sklearn.utils._testing import ignore_warnings
 from torch.utils.data import DataLoader, Dataset
 
-from spare_scores.data_prep import logging_basic_config
-
 device = (
     "cuda"
     if torch.cuda.is_available()
@@ -383,7 +384,7 @@ def set_parameters(self, **parameters: Any) -> None:
         else:
             self.__dict__.update(parameters)
 
-    # @ignore_warnings(category=(ConvergenceWarning, UserWarning))
+    @ignore_warnings(category=(ConvergenceWarning, UserWarning))  # type: ignore
     def fit(self, df: pd.DataFrame, verbose: int = 1, **kwargs: Any) -> dict:
         logger = logging_basic_config(verbose, content_only=True)
 

spare_scores/spare_scores.py

@@ -3,28 +3,21 @@
 
 import numpy as np
 import pandas as pd
-
-from spare_scores.classes import MetaData, SpareModel
-from spare_scores.data_prep import (
+from classes import MetaData, SpareModel
+from data_prep import (
     check_test,
     check_train,
     convert_cat_variables,
     logging_basic_config,
 )
-from spare_scores.util import (
-    check_file_exists,
-    is_unique_identifier,
-    load_df,
-    load_model,
-    save_file,
-)
+from util import check_file_exists, is_unique_identifier, load_df, load_model, save_file
 
 
 def spare_train(
     df: Union[pd.DataFrame, str],
     to_predict: str,
     model_type: str = "SVM",
-    pos_group: Any = "",
+    pos_group: str = "",
     key_var: str = "",
     data_vars: list = [],
     ignore_vars: list = [],
@@ -33,7 +26,7 @@ def spare_train(
     verbose: int = 1,
     logs: str = "",
     **kwargs: Any,
-) -> Any:
+) -> dict:
     """
     Trains a SPARE model, either classification or regression
 
@@ -114,7 +107,7 @@ def spare_train(
     try:
         df, predictors, mdl_task = check_train(
             df, predictors, to_predict, verbose, pos_group
-        )  # type: ignore
+        )
     except Exception as e:
         err = "Dataset check failed before training was initiated."
         logger.error(err)
@@ -207,6 +200,9 @@ def spare_train(
     if output != "" and output is not None:
         save_file(result, output, "train", logger)
 
+    print("###### PRINTING ########")
+    print(result)
+    print("####### END ###########")
     res["status"] = "OK"
     res["data"] = result
     res["status_code"] = 0

spare_scores/svm.py

@@ -4,13 +4,12 @@
 
 import numpy as np
 import pandas as pd
+from data_prep import logging_basic_config
 from sklearn import metrics
 from sklearn.model_selection import GridSearchCV, RepeatedKFold
 from sklearn.preprocessing import StandardScaler
 from sklearn.svm import SVC, LinearSVC, LinearSVR
-
-from spare_scores.data_prep import logging_basic_config
-from spare_scores.util import expspace
+from util import expspace
 
 
 class SVMModel:
@@ -150,7 +149,7 @@ def fit(self, df: pd.DataFrame, verbose: int = 1, **kwargs: Any) -> dict:
             sampled_df = df.sample(n=500, random_state=2023)
             sampled_df = sampled_df.reset_index(drop=True)
             self.train_initialize(sampled_df, self.to_predict)
-            self.run_CV(sampled_df, **kwargs)
+            self.run_CV(sampled_df)
             # Use the optimal parameters to train the model on the full data
             param_grid = {
                 par: expspace(
@@ -166,7 +165,7 @@ def fit(self, df: pd.DataFrame, verbose: int = 1, **kwargs: Any) -> dict:
         # Train the model on the full data, with the optimal parameters
         logger.info("Training SVM model...")
         self.train_initialize(df, self.to_predict)
-        self.run_CV(df, **kwargs)
+        self.run_CV(df)
         training_time = time.time() - start_time
         self.stats["training_time"] = round(training_time, 4)
 

tests/unit/test_data_prep.py

@@ -16,7 +16,7 @@
     smart_unique,
 )
 
-from spare_scores.util import load_df
+from util import load_df
 
 
 class CheckDataPrep(unittest.TestCase):

tests/unit/test_spare_scores.py

@@ -1,10 +1,11 @@
 import unittest
 from pathlib import Path
-
+import sys
 import pandas as pd
 
-from spare_scores.spare_scores import spare_test, spare_train
-from spare_scores.util import load_df, load_model
+sys.path.append("../spare_scores")
+from spare_scores import spare_test, spare_train
+from util import load_df, load_model
 
 
 class CheckSpareScores(unittest.TestCase):
@@ -74,9 +75,9 @@ def test_spare_train(self):
             ],
         )
 
-        status, result = result["status"], result["data"]
-
-        metadata = result[1]  
+        status, result_data = result["status"], result["data"]
+        
+        metadata = result_data[1]
         self.assertTrue(status == "OK")
         self.assertTrue(metadata["mdl_type"] == self.model_fixture[1]["mdl_type"])
         self.assertTrue(metadata["kernel"] == self.model_fixture[1]["kernel"])

tests/unit/test_util.py

@@ -1,13 +1,14 @@
 import logging
 import os
-import re
+import sys
 import unittest
 from pathlib import Path
 
 import numpy as np
 import pandas as pd
 
-from spare_scores.util import (
+sys.path.append("../spare_scores")
+from util import (
     add_file_extension,
     check_file_exists,
     convert_to_number_if_possible,