update docs

nkululeko/demo.py

@@ -28,7 +28,7 @@
 
 def main(src_dir):
     parser = argparse.ArgumentParser(
-        description="Call the nkululeko framework.")
+        description="Call the nkululeko DEMO framework.")
     parser.add_argument("--config", default="exp.ini",
                         help="The base configuration")
     parser.add_argument(

nkululeko/explore.py

@@ -1,17 +1,20 @@
 # explore.py
 # explore the feature sets
 
-from nkululeko.experiment import Experiment
-import configparser
-from nkululeko.utils.util import Util
-from nkululeko.constants import VERSION
 import argparse
+import configparser
 import os
 
+from nkululeko.constants import VERSION
+from nkululeko.experiment import Experiment
+from nkululeko.utils.util import Util
+
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    parser = argparse.ArgumentParser(
+        description="Call the nkululeko EXPLORE framework.")
+    parser.add_argument("--config", default="exp.ini",
+                        help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -46,9 +49,11 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
+    util.debug(
+        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
-    plot_feats = eval(util.config_val("EXPL", "feature_distributions", "False"))
+    plot_feats = eval(util.config_val(
+        "EXPL", "feature_distributions", "False"))
     tsne = eval(util.config_val("EXPL", "tsne", "False"))
     scatter = eval(util.config_val("EXPL", "scatter", "False"))
     spotlight = eval(util.config_val("EXPL", "spotlight", "False"))

nkululeko/multidb.py

@@ -3,23 +3,27 @@
 
 import argparse
 import ast
-import seaborn as sn
-import pandas as pd
-import matplotlib.pyplot as plt
+import configparser
+import os
+
 import matplotlib.cm as cm
+import matplotlib.pyplot as plt
 import numpy as np
-import os
+import pandas as pd
+import seaborn as sn
+
+import nkululeko.glob_conf as glob_conf
+from nkululeko.aug_train import doit as aug_train
 from nkululeko.experiment import Experiment
-import configparser
-from nkululeko.utils.util import Util
 from nkululeko.nkululeko import doit as nkulu
-from nkululeko.aug_train import doit as aug_train
-import nkululeko.glob_conf as glob_conf
+from nkululeko.utils.util import Util
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    parser = argparse.ArgumentParser(
+        description="Call the nkululeko MULTIDB framework.")
+    parser.add_argument("--config", default="exp.ini",
+                        help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -54,7 +58,8 @@ def main(src_dir):
                 dataset = datasets[i]
                 print(f"running {dataset}")
                 if extra_trains:
-                    extra_trains_1 = extra_trains.removeprefix("[").removesuffix("]")
+                    extra_trains_1 = extra_trains.removeprefix(
+                        "[").removesuffix("]")
                     config["DATA"]["databases"] = f"['{dataset}', {extra_trains_1}]"
                     extra_trains_2 = ast.literal_eval(extra_trains)
                     for extra_train in extra_trains_2:
@@ -67,7 +72,8 @@ def main(src_dir):
                 test = datasets[j]
                 print(f"running train: {train}, test: {test}")
                 if extra_trains:
-                    extra_trains_1 = extra_trains.removeprefix("[").removesuffix("]")
+                    extra_trains_1 = extra_trains.removeprefix(
+                        "[").removesuffix("]")
                     config["DATA"][
                         "databases"
                     ] = f"['{train}', '{test}', {extra_trains_1}]"

nkululeko/predict.py

@@ -1,17 +1,21 @@
 # predict.py
-# use some model and add automatically predicted labels to train and test splits, than save as a new dataset
+# use some model and add automatically predicted labels to train and test splits
+# then save as a new dataset
 
-from nkululeko.experiment import Experiment
-import configparser
-from nkululeko.utils.util import Util
-from nkululeko.constants import VERSION
 import argparse
+import configparser
 import os
 
+from nkululeko.constants import VERSION
+from nkululeko.experiment import Experiment
+from nkululeko.utils.util import Util
+
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    parser = argparse.ArgumentParser(
+        description="Call the nkululeko PREDICT framework.")
+    parser.add_argument("--config", default="exp.ini",
+                        help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -41,7 +45,8 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
+    util.debug(
+        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
     # process the data
     df = expr.autopredict()

nkululeko/reporter.py

@@ -1,5 +1,4 @@
-"""
-Reporter module.
+"""Reporter module.
 
 This module contains the Reporter class which is responsible for generating reports.
 """

nkululeko/resample.py

@@ -1,19 +1,23 @@
 # resample.py
 # change the sampling rate for train and test splits
 
-from nkululeko.experiment import Experiment
-import configparser
-from nkululeko.utils.util import Util
-from nkululeko.constants import VERSION
 import argparse
+import configparser
 import os
+
 import pandas as pd
+
 from nkululeko.augmenting.resampler import Resampler
+from nkululeko.constants import VERSION
+from nkululeko.experiment import Experiment
+from nkululeko.utils.util import Util
 
 
 def main(src_dir):
-    parser = argparse.ArgumentParser(description="Call the nkululeko framework.")
-    parser.add_argument("--config", default="exp.ini", help="The base configuration")
+    parser = argparse.ArgumentParser(
+        description="Call the nkululeko RESAMPLE  framework.")
+    parser.add_argument("--config", default="exp.ini",
+                        help="The base configuration")
     args = parser.parse_args()
     if args.config is not None:
         config_file = args.config
@@ -48,7 +52,8 @@ def main(src_dir):
 
     # split into train and test
     expr.fill_train_and_tests()
-    util.debug(f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
+    util.debug(
+        f"train shape : {expr.df_train.shape}, test shape:{expr.df_test.shape}")
 
     sample_selection = util.config_val("RESAMPLE", "sample_selection", "all")
     if sample_selection == "all":