v0.4.1

Author: bdiptesh

bin/run_tests.sh

@@ -31,7 +31,7 @@ printf "=%.0s" {1..70}
 # Run unit tests
 if [[ $module == "-a" || $module == "-u" ]]
 then
-	printf "\nRunning unit & integration tests...\n\n"
+	printf "\nRunning unit & integration tests ...\n\n"
 	coverage run -m unittest discover -v -s $test_dir -p "test_*.py"
 	coverage report -m --omit="*/tests/test_*,*/opt/spark-*" > "$proj_dir/logs/cov.out"
 	COV_SCORE=`grep "TOTAL" $proj_dir/logs/cov.out | tail -1 | awk '{ printf("%d", $4) }'`
@@ -48,7 +48,7 @@ fi
 # Rate coding styles for all python scripts
 if [[ $module == "-a" || $module == "-r" ]]
 then
-    printf "\nRating code style...\n\n"
+    printf "\nRating code style ...\n\n"
     score=0
     cnt=0
 		rm $proj_dir/logs/pylint/*.out

logs/cov.out

@@ -7,6 +7,6 @@ Name                                                            Stmts   Miss  Co
 /media/ph33r/Data/Project/CodeLib/Git/mllib/lib/model.py           44      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           156      0   100%
+/media/ph33r/Data/Project/CodeLib/Git/mllib/lib/tree.py           159      0   100%
 ---------------------------------------------------------------------------------------------
-TOTAL                                                             604      0   100%
+TOTAL                                                             607      0   100%

logs/pylint/lib-tree-py.out

@@ -1,8 +1,8 @@
 ************* Module mllib.lib.tree
-tree.py:93:45: 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:94:45: 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:95:46: 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:96:46: 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)
+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)
 
 --------------------------------------------------------------------
 Your code has been rated at 10.00/10 (previous run: 10.00/10, +0.00)

mllib/lib/tree.py

@@ -14,7 +14,7 @@
         - Diptesh
         - Madhu
 
-    Date: Jan 10, 2022
+    Date: Jan 15, 2022
 """
 
 # pylint: disable=invalid-name
@@ -110,7 +110,7 @@ def _compute_metrics(self):
         self.model_summary = model_summary
 
     def _ts_data_transform(self):
-        """Transform input data with significant lag variables. """
+        """Transform input data with significant lag variables."""
         # Determine seasonality and return seaonal lag
         decomposition = seasonal_decompose(self.df[self.y_var],
                                            model="additive")
@@ -172,7 +172,7 @@ def _ts_predict(self,
             df_pred_x = pd.DataFrame(df_op.iloc[i]).T
             for j, _ in enumerate(self.ts_param["ts_lag_var"]):
                 df_pred_x["lag_" + str(self.ts_param["ts_lag_var"][j])] \
-                    = lst_lag_val[len(lst_lag_val) \
+                    = lst_lag_val[len(lst_lag_val)
                                   - self.ts_param["ts_lag_var"][j]]
             df_pred_x = pd.DataFrame(df_pred_x)
             y_hat = self.model.predict(df_pred_x[self.ts_param["ts_x_var"]])
@@ -224,10 +224,6 @@ class RandomForest(Tree):
 
         Number of cross validations folds (the default is 5)
 
-    max_lag : int, optional
-
-        Maximum lag value for auto regression in timeseries (the default is 20)
-
     threshold : float, optional
 
          Threshold to identify significant lag values (the default is 0.05)
@@ -357,10 +353,6 @@ class XGBoost(Tree):
 
         Number of cross validations folds (the default is 5)
 
-    max_lag : int, optional
-
-        Maximum lag value for auto regression in timeseries (the default is 20)
-
     threshold : float, optional
 
          Threshold to identify significant lag values (the default is 0.05)

requirements.txt

@@ -1,10 +1,10 @@
-pmdarima==1.8.0
 xlrd==1.2.0
-statsmodels==0.11.0
-xgboost==1.5.0
-Cython==0.29.15
-pandas==1.0.1
 PuLP==1.6.8
+xgboost==1.5.0
 numpy==1.18.1
+statsmodels==0.11.0
+Cython==0.29.15
 scipy==1.4.1
+pandas==1.0.1
+pmdarima==1.8.0
 scikit_learn==1.0.2