Minor refactor + renaming

Author: Hameem1

model/feature_selection_complete.py

@@ -9,7 +9,7 @@
 1)  A ranking of all the features and the predicted model accuracy for using n-features - saved in the data_files_path.
 2)  A plot of "# of features used" vs "Model Performance" - saved in the data_files_path.
 3)  A .csv file containing a list of the features selected for optimal model performance - saved in the data_files_path.
-4)  Two exported trained models, one classifier and one normalizer - saved in the Trained_Models directory.
+4)  Two exported trained models, one classifier and one normalizer - saved in the Trained Models directory.
 5)  Option to import this module and begin testing the pre-trained models (set TESTING = True - in model_config.py)
 
 - The results have proved that the model has the highest accuracy when trained on all 51 features.
@@ -33,9 +33,12 @@
 from sklearn.model_selection import StratifiedKFold
 from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, f1_score, recall_score, \
     roc_auc_score, classification_report
-from config import data_files_path, Path
+from config import data_files_path
 from model_config import *
 
+# list of all feature labels + StepLabel
+cols = pd.read_csv(f'{new_sensor_paths[0]}/{os.listdir(new_sensor_paths[0])[0]}', sep='\t', index_col=0).columns
+
 # Configuration Variables
 # Test on a separate dataset_operations
 DISJOINT_TESTING = False

model/feature_selection_voting.py

@@ -15,6 +15,9 @@
 from model.feature_selection_complete import normalize
 from model_config import *
 
+# list of all feature labels + StepLabel
+cols = pd.read_csv(f'{new_sensor_paths[0]}/{os.listdir(new_sensor_paths[0])[0]}', sep='\t', index_col=0).columns
+
 # Global configurations
 # no. of best features to select
 n_features = 15

model_config.py

@@ -3,8 +3,6 @@
 
 Attributes
 ----------
-cols : list of str
-    List of all feature labels + StepLabel
 row_count : int
     No. of rows of dataset_operations to be used
 RF_ESTIMATORS : int
@@ -34,9 +32,9 @@
 
 DATA_PATH : str
     loading in the actual dataset_operations for one sensor (Data under test)
-NEW_DATASET : str
+PROCESSED_DATASET : str
     Directory name for new data set which contains the training/testing data for the classifier
-NEW_DATASET_PATH : str
+PROCESSED_DATASET_PATH : str
     Directory path for new data set which contains the training/testing data for the classifier
 TRAINED_MODEL_DIR : str
     Trained Model directory name
@@ -60,15 +58,13 @@
 from sklearn.preprocessing import MinMaxScaler
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
-from config import new_sensor_paths, ROOT, Path
+from config import new_sensor_paths, ROOT, Path, DATASETS
 
 # Configuring locale for datetime purposes
-lang = 'de_DE'
-locale.setlocale(locale.LC_ALL, lang)
+lang = 'de_DE.UTF-8'
+locale.setlocale(locale.LC_TIME, lang)
 
 # Model Configuration Variables
-# list of all feature labels + StepLabel
-cols = pd.read_csv(f'{new_sensor_paths[0]}/{os.listdir(new_sensor_paths[0])[0]}', sep='\t', index_col=0).columns
 # Setting numpy print precision
 np.set_printoptions(precision=5)
 # no. of rows of dataset_operations to be used
@@ -99,14 +95,14 @@
 EXPORT_MODEL = False
 
 # Paths
-# loading in the actual dataset_operations for the ML classifier
-DATA_PATH = Path(f"{ROOT}/Features_Dataset/ds_all.csv")
 # Directory name for new data set which contains the training/testing data for the classifier
-NEW_DATASET = "Features_Dataset"
+PROCESSED_DATASET = "Processed_Dataset"
 # Directory path for new data set which contains the training/testing data for the classifier
-NEW_DATASET_PATH = Path(f'{ROOT}/{NEW_DATASET}')
+PROCESSED_DATASET_PATH = Path(f'{DATASETS}/{PROCESSED_DATASET}')
+# loading in the actual dataset for the ML classifier
+DATA_PATH = Path(f"{PROCESSED_DATASET_PATH}/ds_all.csv")
 # Trained Model directory name
-TRAINED_MODEL_DIR = 'Trained_Models'
+TRAINED_MODEL_DIR = 'Trained Models'
 # Trained Model directory path
 TRAINED_MODEL_PATH = Path(f'{ROOT}/{TRAINED_MODEL_DIR}')
 # Trained Model name

visualization/feature_plot.py

@@ -9,7 +9,7 @@
 from dash.dependencies import Input, Output
 import plotly.graph_objs as go
 import numpy as np
-from config import Fs
+from config import Fs, DEBUGGER
 from itertools import compress
 
 # Global variables
@@ -204,7 +204,7 @@ def feature_plot(sub, features_list, features, updated_step_positions, updated_s
     FEATURES = features
     STEP_POSITIONS = updated_step_positions
     STEP_POSITIONS_BOOL = updated_step_positions_bool
-    app.run_server(debug=False, port=5001)
+    app.run_server(debug=DEBUGGER, host="0.0.0.0", port=5001)
 
 
 if __name__ == '__main__':