maintenance_34_testing

README.md

@@ -13,6 +13,15 @@
     1. [Contribution guidelines](./.github/CONTRIBUTING.md)
 1. [Project documents](./docs)
     1. [Approach](./docs/Approach.pdf)
+1. [Available modules](./mllib/lib)
+    1. [Clustering](./mllib/lib/cluster.py) - determines optimal _k_
+    1. [GLMNet](./mllib/lib/model.py) - classification/regression
+    1. [k-nearest neighbours](./mllib/lib/knn.py) - classification/regression
+    1. [Random forest](./mllib/lib/tree.py) - classification/timeseries/regression
+    1. [XGBoost](./mllib/lib/tree.py) - classification/timeseries/regression
+    1. [Traveling salesman problem](./mllib/lib/opt.py) - integer programming/heuristic
+    1. [Transportation problem](./mllib/lib/opt.py) - integer programming
+    1. [Time series](./mllib/lib/timeseries.py)
 1. [Pull request guidelines](./.github/PULL_REQUEST_TEMPLATE.md)
 1. [Initial setup](./README.md#initial-setup)
 1. [Unit tests](./README.md#run-unit-tests-and-pylint-ratings)

logs/cov.out

@@ -1,12 +1,10 @@
 Name                                                            Stmts   Miss  Cover   Missing
 ---------------------------------------------------------------------------------------------
-/media/ph33r/Data/Project/CodeLib/Git/mllib/__init__.py             7      0   100%
-/media/ph33r/Data/Project/CodeLib/Git/mllib/lib/__init__.py         7      0   100%
 /media/ph33r/Data/Project/CodeLib/Git/mllib/lib/cluster.py        103      0   100%
 /media/ph33r/Data/Project/CodeLib/Git/mllib/lib/knn.py             70      0   100%
-/media/ph33r/Data/Project/CodeLib/Git/mllib/lib/model.py           44      0   100%
+/media/ph33r/Data/Project/CodeLib/Git/mllib/lib/model.py           52      0   100%
 /media/ph33r/Data/Project/CodeLib/Git/mllib/lib/opt.py            157      0   100%
 /media/ph33r/Data/Project/CodeLib/Git/mllib/lib/timeseries.py      60      0   100%
 /media/ph33r/Data/Project/CodeLib/Git/mllib/lib/tree.py           158      0   100%
 ---------------------------------------------------------------------------------------------
-TOTAL                                                             606      0   100%
+TOTAL                                                             600      0   100%

logs/pylint/lib-knn-py.out

@@ -1,8 +1,8 @@
-************* Module mllib.lib.knn
-knn.py:176:45: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-knn.py:177:45: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-knn.py:178:46: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-knn.py:179:46: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+************* Module knn
+knn.py:175:45: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+knn.py:176:45: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+knn.py:177:46: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+knn.py:178:46: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
 
 --------------------------------------------------------------------
 Your code has been rated at 10.00/10 (previous run: 10.00/10, +0.00)

logs/pylint/lib-model-py.out

@@ -1,8 +1,8 @@
-************* Module mllib.lib.model
-model.py:166:41: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-model.py:167:41: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-model.py:168:42: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-model.py:169:42: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+************* Module model
+model.py:180:41: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+model.py:181:41: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+model.py:182:42: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+model.py:183:42: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
 
 --------------------------------------------------------------------
 Your code has been rated at 10.00/10 (previous run: 10.00/10, +0.00)

logs/pylint/lib-timeseries-py.out

@@ -1,8 +1,8 @@
-************* Module mllib.lib.timeseries
-timeseries.py:201:41: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-timeseries.py:202:41: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-timeseries.py:203:42: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-timeseries.py:204:42: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+************* Module timeseries
+timeseries.py:201:41: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+timeseries.py:202:41: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+timeseries.py:203:42: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+timeseries.py:204:42: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
 
 --------------------------------------------------------------------
 Your code has been rated at 10.00/10 (previous run: 10.00/10, +0.00)

logs/pylint/lib-tree-py.out

@@ -1,8 +1,8 @@
-************* Module mllib.lib.tree
-tree.py:96:45: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-tree.py:97:45: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-tree.py:98:46: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-tree.py:99:46: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+************* Module tree
+tree.py:96:45: I1101: Module 'metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+tree.py:97:45: I1101: Module 'metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+tree.py:98:46: I1101: Module 'metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
+tree.py:99:46: I1101: Module 'metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-allow-list if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
 
 --------------------------------------------------------------------
 Your code has been rated at 10.00/10 (previous run: 10.00/10, +0.00)

logs/pylint/tests-test_metrics-py.out

@@ -1,10 +1,3 @@
-************* Module tests.test_metrics
-test_metrics.py:61:22: I1101: Module 'mllib.lib.metrics' has no 'rsq' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-test_metrics.py:69:22: I1101: Module 'mllib.lib.metrics' has no 'mse' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-test_metrics.py:77:22: I1101: Module 'mllib.lib.metrics' has no 'rmse' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-test_metrics.py:85:22: I1101: Module 'mllib.lib.metrics' has no 'mae' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-test_metrics.py:93:22: I1101: Module 'mllib.lib.metrics' has no 'mape' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
-test_metrics.py:101:22: I1101: Module 'mllib.lib.metrics' has no 'aic' member, but source is unavailable. Consider adding this module to extension-pkg-whitelist if you want to perform analysis based on run-time introspection of living objects. (c-extension-no-member)
 
 --------------------------------------------------------------------
 Your code has been rated at 10.00/10 (previous run: 10.00/10, +0.00)

mllib/lib/knn.py

@@ -3,7 +3,7 @@
 
 **Available routines:**
 
-- class ``KNN``: Builds K-Nearest Neighnour model using cross validation.
+- class ``KNN``: Builds K-Nearest Neighbours model using cross validation.
 
 Credits
 -------
@@ -123,7 +123,7 @@ def __init__(self,
         self.model = None
         self.k_fold = k_fold
         if param is None:
-            max_k = max(int(len(self.df)/(self.k_fold * 2)), 1)
+            max_k = max(int(len(self.df) / (self.k_fold * 2)), 1)
             param = {"n_neighbors": list(range(1, max_k, 2)),
                      "weights": ["uniform", "distance"],
                      "metric": ["euclidean", "manhattan"]}
@@ -163,8 +163,7 @@ def _fit(self) -> Dict[str, Any]:
                               return_train_score=True,
                               cv=self.k_fold,
                               n_jobs=-1)
-        gs_op = gs.fit(self.df[self.x_var],
-                       self.df[self.y_var])
+        gs_op = gs.fit(self.df[self.x_var], self.df[self.y_var])
         self.model = gs_op
         return gs_op.best_params_
 

mllib/lib/model.py

@@ -16,10 +16,11 @@
 """
 
 # pylint: disable=invalid-name
-# pylint: disable=R0902,R0903,R0913,C0413
+# pylint: disable=R0902,R0903,R0913,C0413,W0511
 
 from typing import List, Dict
 
+import warnings
 import re
 import sys
 from inspect import getsourcefile
@@ -42,6 +43,17 @@
 # =============================================================================
 
 
+def ignore_warnings(test_func):
+    """Suppress warnings."""
+
+    def do_test(self, *args, **kwargs):
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore")
+            test_func(self, *args, **kwargs)
+
+    return do_test
+
+
 class GLMNet():
     """GLMNet module.
 
@@ -133,6 +145,8 @@ def __init__(self,
         self._fit()
         self._compute_metrics()
 
+    # TODO: Remove this once GLMNet is updated
+    @ignore_warnings
     def _fit(self) -> None:
         """Fit the best GLMNet model."""
         train_x, test_x,\

mllib/lib/opt.py

@@ -46,9 +46,9 @@
 
 class TSP:
     """
-    Travelling salesman problem.
+    Traveling salesman problem.
 
-    Module for `Travelling salesman problem
+    Module for `Traveling salesman problem
     <https://en.wikipedia.org/wiki/Travelling_salesman_problem>`_ using
     integer programming or nearest neighbour algorithm.
 

requirements.txt

@@ -1,10 +1,11 @@
-pmdarima==1.8.0
-xgboost==1.5.0
-scipy==1.4.1
-xlrd==1.2.0
 PuLP==1.6.8
-numpy==1.18.1
-pandas==1.0.1
-Cython==0.29.15
-statsmodels==0.11.0
+xgboost==1.5.0
+statsmodels==0.13.0
+openpyxl==3.0.9
+pandas==1.3.5
+numpy==1.21.2
+Cython==0.29.25
+pmdarima==1.8.1
+xlrd==2.0.1
+scipy==1.7.3
 scikit_learn==1.0.2

tests/test_model.py

@@ -51,6 +51,7 @@ def do_test(self, *args, **kwargs):
         with warnings.catch_warnings():
             warnings.simplefilter("ignore")
             test_func(self, *args, **kwargs)
+
     return do_test
 
 
@@ -63,21 +64,17 @@ def setUp(self):
     def test_known_equation(self):
         """GLMNet: Test a known equation"""
         df_ip = pd.read_csv(path + "test_glmnet.csv")
-        mod = GLMNet(df=df_ip,
-                     y_var="y",
-                     x_var=["x1", "x2", "x3"])
+        mod = GLMNet(df=df_ip, y_var="y", x_var=["x1", "x2", "x3"])
         op = mod.opt
-        self.assertEqual(np.round(op.get('intercept'), 0), 100.0)
-        self.assertEqual(np.round(op.get('coef')[0], 0), 2.0)
-        self.assertEqual(np.round(op.get('coef')[1], 0), 3.0)
-        self.assertEqual(np.round(op.get('coef')[2], 0), 0.0)
+        self.assertEqual(np.round(op.get("intercept"), 0), 100.0)
+        self.assertEqual(np.round(op.get("coef")[0], 0), 2.0)
+        self.assertEqual(np.round(op.get("coef")[1], 0), 3.0)
+        self.assertEqual(np.round(op.get("coef")[2], 0), 0.0)
 
     def test_predict_target_variable(self):
         """GLMNet: Test to predict a target variable"""
         df_ip = pd.read_csv(path + "test_glmnet.csv")
-        mod = GLMNet(df=df_ip,
-                     y_var="y",
-                     x_var=["x1", "x2", "x3"])
+        mod = GLMNet(df=df_ip, y_var="y", x_var=["x1", "x2", "x3"])
         df_predict = pd.DataFrame({"x1": [10, 20],
                                    "x2": [5, 10],
                                    "x3": [100, 0]})
@@ -91,5 +88,5 @@ def test_predict_target_variable(self):
 # --- Main
 # =============================================================================
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     unittest.main()

tests/test_timeseries.py

@@ -25,6 +25,7 @@
 
 import pandas as pd
 import xlrd
+import openpyxl
 
 # Set base path
 path = abspath(getsourcefile(lambda: 0))
@@ -34,7 +35,7 @@
 
 from mllib.lib.timeseries import AutoArima  # noqa: F841
 
-__all__ = ["xlrd", ]
+__all__ = ["xlrd", "openpyxl", ]
 
 # =============================================================================
 # --- DO NOT CHANGE ANYTHING FROM HERE

tests/test_tree.py

@@ -24,6 +24,8 @@
 from os.path import abspath
 
 import pandas as pd
+import xlrd
+import openpyxl
 
 from sklearn.model_selection import train_test_split as split
 from sklearn import metrics as sk_metrics
@@ -37,6 +39,8 @@
 from mllib.lib.tree import RandomForest  # noqa: F841
 from mllib.lib.tree import XGBoost  # noqa: F841
 
+__all__ = ["xlrd", "openpyxl", ]
+
 # =============================================================================
 # --- DO NOT CHANGE ANYTHING FROM HERE
 # =============================================================================