PySAR 2.5.0__tar.gz → 2.5.1__tar.gz

{pysar-2.5.0 → pysar-2.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PySAR
-Version: 2.5.0
+Version: 2.5.1
 Summary: Analysing Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning.
 Author-email: AJ McKenna <amckenna41@qub.ac.uk>
 Maintainer-email: AJ McKenna <amckenna41@qub.ac.uk>
@@ -33,7 +33,6 @@ License-File: LICENSE
 Requires-Dist: numpy>=1.21
 Requires-Dist: pandas>=1.3
 Requires-Dist: scipy>=1.7
-Requires-Dist: delayed>=0.11
 Requires-Dist: scikit-learn>=1.0
 Requires-Dist: matplotlib>=3.4
 Requires-Dist: seaborn>=0.11
@@ -50,7 +49,7 @@ Requires-Dist: sphinx; extra == "docs"
 Dynamic: license-file
 
 <p align="center">
-<img src="https://raw.githubusercontent.com/amckenna41/pySAR/master/images/pySAR.png" alt="pySARLogo" height="300" width="400"/>
+<img src="https://raw.githubusercontent.com/amckenna41/pySAR/master/images/pySAR.png" alt="pySARLogo" height="400" width="350"/>
 </p>
 
 # pySAR - Python Sequence Activity Relationship #
@@ -126,7 +125,6 @@ Requirements
 * [pandas][pandas] >= 1.3
 * [scikit-learn][sklearn] >= 1.0
 * [scipy][scipy] >= 1.7
-* [delayed][delayed] >= 0.11
 * [tqdm][tqdm] >= 4.60
 * [matplotlib][matplotlib] >= 3.4
 * [seaborn][seaborn] >= 0.11
@@ -711,6 +709,10 @@ Journal of Chemical Information and Modeling 2020 60 (6), 2773-2790
 DOI: 10.1021/acs.jcim.0c00073 <br><br>
 \[8\]: Medina-Ortiz, D., Contreras, S., Amado-Hinojosa, J., Torres-Almonacid, J., Asenjo, J. A., Navarrete, M., & Olivera-Nappa, Á. (2020). Combination of digital signal processing and assembled predictive models facilitates the rational design of proteins. ArXiv [Cs.CE]. <br>
 
+
+[<img src="https://img.shields.io/github/stars/amckenna41/pySAR?color=green&label=star%20it%20on%20GitHub" width="132" height="20" alt="Star it on GitHub">](https://github.com/amckenna41/pySAR)
+
+
 <a href="https://www.buymeacoffee.com/amckenna41" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a>
 
 [Back to top](#TOP)
@@ -727,7 +729,6 @@ DOI: 10.1021/acs.jcim.0c00073 <br><br>
 [tqdm]: https://tqdm.github.io/
 [seaborn]: https://seaborn.pydata.org/
 [matplotlib]: https://matplotlib.org/
-[delayed]: https://pypi.org/project/delayed/
 [PyPi]: https://pypi.org/project/pysar/
 [article]: https://www.sciencedirect.com/science/article/abs/pii/S1532046422000326
 [pdf]: https://github.com/amckenna41/pySAR/blob/master/pySAR_research.pdf

{pysar-2.5.0 → pysar-2.5.1}/PySAR.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PySAR
-Version: 2.5.0
+Version: 2.5.1
 Summary: Analysing Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning.
 Author-email: AJ McKenna <amckenna41@qub.ac.uk>
 Maintainer-email: AJ McKenna <amckenna41@qub.ac.uk>
@@ -33,7 +33,6 @@ License-File: LICENSE
 Requires-Dist: numpy>=1.21
 Requires-Dist: pandas>=1.3
 Requires-Dist: scipy>=1.7
-Requires-Dist: delayed>=0.11
 Requires-Dist: scikit-learn>=1.0
 Requires-Dist: matplotlib>=3.4
 Requires-Dist: seaborn>=0.11
@@ -50,7 +49,7 @@ Requires-Dist: sphinx; extra == "docs"
 Dynamic: license-file
 
 <p align="center">
-<img src="https://raw.githubusercontent.com/amckenna41/pySAR/master/images/pySAR.png" alt="pySARLogo" height="300" width="400"/>
+<img src="https://raw.githubusercontent.com/amckenna41/pySAR/master/images/pySAR.png" alt="pySARLogo" height="400" width="350"/>
 </p>
 
 # pySAR - Python Sequence Activity Relationship #
@@ -126,7 +125,6 @@ Requirements
 * [pandas][pandas] >= 1.3
 * [scikit-learn][sklearn] >= 1.0
 * [scipy][scipy] >= 1.7
-* [delayed][delayed] >= 0.11
 * [tqdm][tqdm] >= 4.60
 * [matplotlib][matplotlib] >= 3.4
 * [seaborn][seaborn] >= 0.11
@@ -711,6 +709,10 @@ Journal of Chemical Information and Modeling 2020 60 (6), 2773-2790
 DOI: 10.1021/acs.jcim.0c00073 <br><br>
 \[8\]: Medina-Ortiz, D., Contreras, S., Amado-Hinojosa, J., Torres-Almonacid, J., Asenjo, J. A., Navarrete, M., & Olivera-Nappa, Á. (2020). Combination of digital signal processing and assembled predictive models facilitates the rational design of proteins. ArXiv [Cs.CE]. <br>
 
+
+[<img src="https://img.shields.io/github/stars/amckenna41/pySAR?color=green&label=star%20it%20on%20GitHub" width="132" height="20" alt="Star it on GitHub">](https://github.com/amckenna41/pySAR)
+
+
 <a href="https://www.buymeacoffee.com/amckenna41" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a>
 
 [Back to top](#TOP)
@@ -727,7 +729,6 @@ DOI: 10.1021/acs.jcim.0c00073 <br><br>
 [tqdm]: https://tqdm.github.io/
 [seaborn]: https://seaborn.pydata.org/
 [matplotlib]: https://matplotlib.org/
-[delayed]: https://pypi.org/project/delayed/
 [PyPi]: https://pypi.org/project/pysar/
 [article]: https://www.sciencedirect.com/science/article/abs/pii/S1532046422000326
 [pdf]: https://github.com/amckenna41/pySAR/blob/master/pySAR_research.pdf

{pysar-2.5.0 → pysar-2.5.1}/PySAR.egg-info/requires.txt

@@ -1,7 +1,6 @@
 numpy>=1.21
 pandas>=1.3
 scipy>=1.7
-delayed>=0.11
 scikit-learn>=1.0
 matplotlib>=3.4
 seaborn>=0.11

{pysar-2.5.0 → pysar-2.5.1}/README.md

@@ -1,5 +1,5 @@
 <p align="center">
-<img src="https://raw.githubusercontent.com/amckenna41/pySAR/master/images/pySAR.png" alt="pySARLogo" height="300" width="400"/>
+<img src="https://raw.githubusercontent.com/amckenna41/pySAR/master/images/pySAR.png" alt="pySARLogo" height="400" width="350"/>
 </p>
 
 # pySAR - Python Sequence Activity Relationship #
@@ -75,7 +75,6 @@ Requirements
 * [pandas][pandas] >= 1.3
 * [scikit-learn][sklearn] >= 1.0
 * [scipy][scipy] >= 1.7
-* [delayed][delayed] >= 0.11
 * [tqdm][tqdm] >= 4.60
 * [matplotlib][matplotlib] >= 3.4
 * [seaborn][seaborn] >= 0.11
@@ -660,6 +659,10 @@ Journal of Chemical Information and Modeling 2020 60 (6), 2773-2790
 DOI: 10.1021/acs.jcim.0c00073 <br><br>
 \[8\]: Medina-Ortiz, D., Contreras, S., Amado-Hinojosa, J., Torres-Almonacid, J., Asenjo, J. A., Navarrete, M., & Olivera-Nappa, Á. (2020). Combination of digital signal processing and assembled predictive models facilitates the rational design of proteins. ArXiv [Cs.CE]. <br>
 
+
+[<img src="https://img.shields.io/github/stars/amckenna41/pySAR?color=green&label=star%20it%20on%20GitHub" width="132" height="20" alt="Star it on GitHub">](https://github.com/amckenna41/pySAR)
+
+
 <a href="https://www.buymeacoffee.com/amckenna41" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a>
 
 [Back to top](#TOP)
@@ -676,7 +679,6 @@ DOI: 10.1021/acs.jcim.0c00073 <br><br>
 [tqdm]: https://tqdm.github.io/
 [seaborn]: https://seaborn.pydata.org/
 [matplotlib]: https://matplotlib.org/
-[delayed]: https://pypi.org/project/delayed/
 [PyPi]: https://pypi.org/project/pysar/
 [article]: https://www.sciencedirect.com/science/article/abs/pii/S1532046422000326
 [pdf]: https://github.com/amckenna41/pySAR/blob/master/pySAR_research.pdf

{pysar-2.5.0 → pysar-2.5.1}/docs/conf.py

@@ -15,7 +15,7 @@ sys.path.insert(0, os.path.abspath('..'))
 project = 'pySAR'
 copyright = '2026, AJ McKenna'
 author = 'AJ McKenna'
-release = '2.5.0'
+release = '2.5.1'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
@@ -36,7 +36,6 @@ autodoc_mock_imports = [
     'matplotlib',
     'seaborn',
     'tqdm',
-    'delayed',
     'aaindex',
     'protpy',
 ]

{pysar-2.5.0 → pysar-2.5.1}/pySAR/__init__.py

@@ -1,6 +1,6 @@
 """ pySAR software metadata. """
 __name__ = 'pySAR'
-__version__ = "2.5.0"
+__version__ = "2.5.1"
 __description__ = 'A Python package used to analysis Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning.'
 __author__ = 'AJ McKenna: https://github.com/amckenna41'
 __authorEmail__ = 'amckenna41@qub.ac.uk'

{pysar-2.5.0 → pysar-2.5.1}/pySAR/descriptors.py

@@ -8,7 +8,6 @@ import pandas as pd
 import numpy as np
 from difflib import get_close_matches
 import json
-from json import JSONDecodeError
 import itertools
 import time
 from tqdm import tqdm

{pysar-2.5.0 → pysar-2.5.1}/pySAR/evaluate.py

@@ -184,8 +184,8 @@ class Evaluate():
         :rpd: float
             the RPD score for the model.
         """
-        mse = self.mse_()
-        return self.Y_true.std() / np.sqrt(mse) if mse > 0 else np.inf
+        # reuse already-computed self.mse to avoid a redundant sklearn call
+        return self.Y_true.std() / np.sqrt(self.mse) if self.mse > 0 else np.inf
 
     def explained_var_(self, multioutput='uniform_average'):
         """

{pysar-2.5.0 → pysar-2.5.1}/pySAR/globals_.py

@@ -8,14 +8,11 @@ from datetime import datetime
 NOW = datetime.now()
 
 #output dir is the default directory used to store all outputs generated
-global OUTPUT_DIR
 OUTPUT_DIR = 'outputs'
 
 #current datetime appended to output assets & directories to uniquely identify them
-global CURRENT_DATETIME
 CURRENT_DATETIME = NOW.strftime('%Y-%m-%d_%H-%M-%S')
 
 #output folder is the default folder within the OUTPUT_DIR used to store all
 #outputs generated from one run of the program.
-global OUTPUT_FOLDER
 OUTPUT_FOLDER = os.path.join(OUTPUT_DIR, f'model_output_{CURRENT_DATETIME}')

{pysar-2.5.0 → pysar-2.5.1}/pySAR/model.py

@@ -92,7 +92,6 @@ class Model():
         'sgd': SGDRegressor,
         'stochasticgradientdescent': SGDRegressor,
         'gbr': GradientBoostingRegressor,
-        'gradientboost': GradientBoostingRegressor,
         'gradientboostingregressor': GradientBoostingRegressor,
         'svr': SVR,
         'supportvectorregression': SVR,
@@ -123,15 +122,8 @@ class Model():
         else:
             self.parameters = parameters
 
-        #list of valid models available to use for this class
-        self.valid_models = ['plsregression', 'randomforestregressor', 'adaboostregressor',\
-                            'baggingregressor', 'decisiontreeregressor', 'gbr',
-                            'gradientboostingregressor', 'linearregression', 'lasso', 'ridge',
-                            'svr', 'supportvectorregression', 'sgd', 'stochasticgradientdescent',
-                            'kneighborsregressor', 'knearestneighbors', 'knn', 'elasticnet',
-                            'extratreesregressor', 'extratrees', 'histgradientboostingregressor',
-                            'histgradientboosting', 'hgbr', 'gaussianprocessregressor',
-                            'gaussianprocess', 'gpr']
+        #derive valid model names directly from MODEL_CONSTRUCTORS to avoid duplication and sync issues
+        self.valid_models = list(self.MODEL_CONSTRUCTORS.keys())
 
         #raise error if algorithm parameter isnt string type
         if not(isinstance(self.algorithm, str)):
@@ -311,8 +303,8 @@ class Model():
         try:
             with open(save_path, 'wb') as file:
                 pickle.dump(self.model, file)
-        except (pickle.PickleError):
-            print(f"Error pickling model with path: {save_path}.")
+        except pickle.PickleError as e:
+            raise RuntimeError(f"Error pickling model with path: {save_path}.") from e
 
     def hyperparameter_tuning(self, param_grid=None, metric='r2', cv=5, n_jobs=None, verbose=2):
         """
@@ -365,6 +357,8 @@ class Model():
 
         #cv must be of type int and be between 5 and 10, if not then default of 5 is used
         if not isinstance(cv, int) or cv < 5 or cv > 10:
+            import warnings
+            warnings.warn(f'Invalid cv value {cv!r}; must be an int between 5 and 10. Defaulting to 5.', UserWarning, stacklevel=2)
             cv = 5
 
         #copy to avoid mutating caller's dict; filter out parameter names invalid for this model

{pysar-2.5.0 → pysar-2.5.1}/pySAR/pySAR.py

@@ -221,7 +221,7 @@ class PySAR():
 
         #verify no invalid amino acids found in sequences, if so then raise error
         invalid_seqs = valid_sequence(self.sequences)
-        if (invalid_seqs != None):
+        if invalid_seqs is not None:
             raise ValueError(f'Invalid amino acids found in protein sequence dataset: {invalid_seqs}.')
 
         #get closest match for activity column name in dataset
@@ -270,7 +270,7 @@ class PySAR():
             array of the encoded protein sequences in dataset via user input index/indices.
         """
         #validate AAI indices are present in the input parameter, if not raise error
-        if (aai_indices == None or aai_indices == ""):
+        if aai_indices is None or aai_indices == "":
             raise ValueError(f'AAI indices input parameter cannot be None or empty: {aai_indices}.')
 
         #check input indices is of correct type (str/list), if not raise type error
@@ -352,7 +352,7 @@ class PySAR():
             pandas Dataframe storing metrics and results of encoding.
         """
         #validate AAI indices are present in the input parameter
-        if (aai_indices == None or aai_indices == "" or aai_indices == []):
+        if aai_indices is None or aai_indices == "" or aai_indices == []:
             raise ValueError(f'AAI indices input parameter cannot be None or empty: {aai_indices}.')
 
         #check input indices is of correct type (str/list), if not raise type error
@@ -385,7 +385,7 @@ class PySAR():
             #else use the AAI indices encoding's themselves as the feature/training data (X)
             if (self.use_dsp):
                 #if input spectrum is none or empty, raise error.
-                if (self.spectrum == None or self.spectrum == ""):
+                if self.spectrum is None or self.spectrum == "":
                     raise ValueError(f'Spectrum cannot be None or empty: {self.spectrum}.')
                 pyDSP = PyDSP(self.config_file, protein_seqs=encoded_seqs)
                 X = pd.DataFrame(pyDSP.spectrum_encoding) #set training data to FFT spectrum encoding
@@ -471,7 +471,7 @@ class PySAR():
             inputted descriptor(s).
         """
         #raise error if no descriptors specified in input
-        if (descriptors == None or descriptors == "" or descriptors == []): 
+        if descriptors is None or descriptors == "" or descriptors == []:
             raise ValueError(f'Descriptors input parameter cannot be None or empty: {descriptors}.')
         
         #check input descriptor is of correct type str or list, if not raise type error
@@ -551,7 +551,7 @@ class PySAR():
             pandas dataframe storing metrics and results of encoding.
         """
         #raise error if no descriptor specified in input
-        if (descriptors == None or descriptors == ""):
+        if descriptors is None or descriptors == "" or descriptors == []:
             raise ValueError(f'Descriptors input parameter cannot be None or empty: {descriptors}.')
 
         #check input descriptor is of correct type (str or list), if not raise type error
@@ -633,7 +633,7 @@ class PySAR():
         desc_df['Group'] = desc_df['Group'].astype(pd.StringDtype())
 
         #ensure aai indices attribute doesn't show up in output results
-        if (self.aai_indices != None):
+        if self.aai_indices is not None:
             self.aai_indices = None
 
         #print out results from encoding
@@ -684,8 +684,8 @@ class PySAR():
             pandas dataframe storing metrics and results of encoding.
         """
         #validate AAI indices and Descriptors are present in the input parameters, return error if either is None
-        if (descriptors == None or descriptors == "") or (aai_indices == None or aai_indices == ""):
-                raise ValueError('AAI Indices and Descriptor input parameters must not be empty or None.')
+        if (descriptors is None or descriptors in ("", [])) or (aai_indices is None or aai_indices in ("", [])):
+            raise ValueError('AAI Indices and Descriptor input parameters must not be empty or None.')
 
         #check input descriptor & indices are of correct type (str/list), if not raise type error
         if (not isinstance(aai_indices, str) and (not isinstance(aai_indices, list)) or \
@@ -810,8 +810,7 @@ class PySAR():
             evaluation.rmse, evaluation.mse, evaluation.mae, evaluation.rpd, evaluation.explained_var]
 
         #convert Index, Category, Descriptor and Group from default Object type -> String datatypes
-        # aai_desc_df['Index'] = aai_desc_df['Index'].astype(pd.StringDtype())
-        aai_desc_df['Index'] = aai_desc_df['Index'].astype("string")
+        aai_desc_df['Index'] = aai_desc_df['Index'].astype(pd.StringDtype())
         aai_desc_df['Category'] = aai_desc_df['Category'].astype(pd.StringDtype())
         aai_desc_df['Descriptor'] = aai_desc_df['Descriptor'].astype(pd.StringDtype())
         aai_desc_df['Group'] = aai_desc_df['Group'].astype(pd.StringDtype())

{pysar-2.5.0 → pysar-2.5.1}/pySAR/utils.py

@@ -149,43 +149,6 @@ def remove_gaps(sequences):
     cleaned = ''.join(str(c) for c in sequences if str(c) != '-')
     return [cleaned]
 
-def flatten(array):
-    """
-    Lambda function for flattening list of lists or array of lists into one
-    1-dimensional array/list. Input must contain an array of arrays of the same
-    length. Input will be flattened into a 1-dimensional array of size (M * N, 1)
-    where M = len(array) and N = len(array[0]). The flattened output can then be
-    reshaped into the required shape and format.
-
-    Parameters
-    ==========
-    :array: np.ndarray/list
-        array of arrays or list of lists to be flattened.
-
-    Returns
-    =======
-    :flatten(array/list): np.ndarray/list
-        flattened 1-dimensional list or array.
-    """
-    #if input is a string then return input as cannot be flattened
-    if (isinstance(array, str)):
-        return array
-
-    #create flatten lambda function
-    _flatten = lambda array: [item for sublist in array for item in sublist]
-
-    #flatten array/list
-    try:
-        flattened_array = _flatten(array)
-    except (TypeError, ValueError):
-        raise TypeError(f'Error flattening array of type: {type(array)} and size {len(array)}.')
-
-    #if input is a numpy array then reshape to 1D numpy array else return list
-    if (isinstance(array,np.ndarray)):
-        return (np.array(flattened_array).reshape([-1, 1]))
-    else:
-        return flattened_array
-
 def zero_padding(sequences): 
     """ 
     Pad sequences in input array with 0's such that every sequence is of the same length

{pysar-2.5.0 → pysar-2.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "PySAR"
-version = "2.5.0"
+version = "2.5.1"
 description = "Analysing Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning."
 readme = "README.md"
 license = { text = "MIT" }
@@ -54,7 +54,6 @@ dependencies = [
     "numpy>=1.21",
     "pandas>=1.3",
     "scipy>=1.7",
-    "delayed>=0.11",
     "scikit-learn>=1.0",
     "matplotlib>=3.4",
     "seaborn>=0.11",

{pysar-2.5.0 → pysar-2.5.1}/tests/test_model.py

@@ -96,7 +96,7 @@ class ModelTests(unittest.TestCase):
         aliases = [
             ('plsreg', 'plsregression', 'PLSRegression'),
             ('randomfor', 'randomforestregressor', 'RandomForestRegressor'),
-            ('adaboo', 'adaboostregressor', 'AdaBoostRegressor'),
+            ('adaboost', 'adaboostregressor', 'AdaBoostRegressor'),
             ('bagging', 'baggingregressor', 'BaggingRegressor'),
             ('decisiontree', 'decisiontreeregressor', 'DecisionTreeRegressor'),
             ('linear', 'linearregression', 'LinearRegression'),
@@ -299,7 +299,7 @@ class ModelTests(unittest.TestCase):
     def test_hyperparameter_tuning(self):
         """ Testing hyperparamter tuning functionality. """
 #1.)
-        model = Model(self.dummy_X, self.dummy_Y, algorithm="adaboost")
+        model = Model(self.dummy_X, self.dummy_Y, algorithm="adaboostregressor")
         X_train, X_test, Y_train, Y_test = model.train_test_split(test_split=0.2)
         model.fit()
         param_grid = {'n_estimators': [50,100,150], 'learning_rate': [0.5,0.75,1], 'loss': ['linear','exponential']}

{pysar-2.5.0 → pysar-2.5.1}/tests/test_pySAR.py

@@ -69,8 +69,8 @@ class PySARTests(unittest.TestCase):
     # @unittest.skip("Skipping metadata tests.")
     def test_pySAR_metadata(self):
         """ Testing correct pySAR version and metadata. """
-        self.assertEqual(pysar_.__version__, "2.5.0", 
-            f"pySAR version is not correct, expected 2.5.0, got {pysar_.__version__}.")
+        self.assertEqual(pysar_.__version__, "2.5.1", 
+            f"pySAR version is not correct, expected 2.5.1, got {pysar_.__version__}.")
         self.assertEqual(pysar_.__name__, "pySAR", 
             f"pySAR software name is not correct, expected pySAR, got {pysar_.__name__}.")
         self.assertEqual(pysar_.__author__, "AJ McKenna: https://github.com/amckenna41", 

{pysar-2.5.0 → pysar-2.5.1}/tests/test_utils.py

@@ -24,8 +24,6 @@ class UtilsTest(unittest.TestCase):
         testing correct utils.valid_sequence functionality.
     test_remove_gaps:
         testing correct utils.remove_gaps functionality.
-    test_flatten:
-        testing correct utils.flatten functionality.
     test_zero_padding:
         testing correct utils.zero_padding functionality.
     test_save_results:
@@ -129,42 +127,6 @@ class UtilsTest(unittest.TestCase):
         self.assertIsInstance(seq4_test, str, f"Expected output to be of type str, got {type(seq4_test)}.")
         self.assertNotIn('-', seq4_test, "Expected there to be no gaps (-) in the sequence.")
 
-    def test_flatten(self):
-        """ Test flatten utility function that flattens an array or list. """
-        seq1 = np.array([[1, 2, 3], [4, 5, 6]], np.int32)
-        seq2 = np.array([[1, 2, 3], [4, 5, 6],[7, 8, 9]], np.int32)
-        seq3 = np.random.randint(10,90,(4,5,2))
-        seq4 = ["A", "B", "C", "D", "E", "F"]
-        seq5 = "TUVWXYZ"
-#1.) 
-        flattened_array = utils.flatten(seq1)
-        self.assertEqual(flattened_array.shape, (6,1), f"Expected output shape to be (6,1), got {flattened_array.shape}.")
-        self.assertIsInstance(flattened_array, np.ndarray, f"Expected output to be of type np.ndarray, got {type(flattened_array)}.")
-        self.assertEqual(flattened_array.ndim, 2, f"Expected 2 output dimensions, got {flattened_array.ndim}.")
-        self.assertTrue((np.array([[1],[2],[3],[4],[5],[6]]) == flattened_array).all(),
-                        f"Output array doesn't match expected:\n{flattened_array}.")
-#2.)
-        flattened_array_2 = utils.flatten(seq2)
-        self.assertEqual(flattened_array_2.shape, (9,1), f"Expected output shape to be (9,1), got {flattened_array_2.shape}.")
-        self.assertIsInstance(flattened_array_2, np.ndarray, f"Expected output to be of type np.ndarray, got {type(flattened_array_2)}.")
-        self.assertEqual(flattened_array_2.ndim, 2, f"Expected 2 output dimensions, got {flattened_array_2.ndim}.")
-        self.assertTrue((np.array([[1],[2],[3],[4],[5],[6],[7],[8],[9]]) == flattened_array_2).all(),
-                f"Output array doesn't match expected:\n{flattened_array_2}.")
-#3.)
-        flattened_array_3 = utils.flatten(seq3)
-        self.assertEqual(flattened_array_3.shape, (40,1), f"Expected output shape to be (40,1), got {flattened_array_3.shape}.")
-        self.assertIsInstance(flattened_array_3, np.ndarray, f"Expected output to be of type np.ndarray, got {type(flattened_array_3)}.")
-        self.assertEqual(flattened_array_3.ndim, 2, f"Expected 2 output dimensions, got {flattened_array_3.ndim}.")
-#4.)
-        flattened_array_4 = utils.flatten(seq4)
-        self.assertEqual(len(flattened_array_4), 6, f"Expected length of output to be 6, got {len(flattened_array_4)}.")
-        self.assertIsInstance(flattened_array_4, list, f"Expected output to be of type list, got {type(flattened_array_4)}.")
-        self.assertEqual(flattened_array_4, seq4, f"Output doesn't match expected sequence {seq4}.")
-#5.)
-        flattened_array_5 = utils.flatten(seq5)
-        self.assertEqual(flattened_array_5, seq5, f"Output doesn't match expected sequence {seq5}.")
-        self.assertIsInstance(flattened_array_5, str, f"Expected output to be of type string, got {type(flattened_array_5)}.")
-
     def test_zero_padding(self):
         """ Test zero padding utility function that pads an array or list with 0's. """
         seq1 = np.array([[1, 2, 3, 4, 5], [6, 7, 8]], dtype=object)