Added normalization, normalized classes, AdaBoost, KNN.

slopestabilityML/KNN/knn_run.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 26.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+from sklearn.neighbors import KNeighborsClassifier
+import slopestabilityML.plot_results
+import slopestabilityML.split_dataset
+import slopestabilityML.run_classi
+
+def knn_run(test_results, random_seed):
+
+    # Split the data set
+    test_training, test_prediction = slopestabilityML.split_dataset(test_results.keys(), random_seed)
+
+    # Create classifier
+    clf = KNeighborsClassifier(n_neighbors=2)
+
+    # Train classifier
+    accuracy_labels, accuracy_score, accuracy_labels_training, accuracy_score_training = \
+        slopestabilityML.run_classification(test_training, test_prediction, test_results, clf, 'KNN')
+
+    # Plot
+    slopestabilityML.plot_results(accuracy_labels, accuracy_score, 'KNN_prediction')
+    slopestabilityML.plot_results(accuracy_labels_training, accuracy_score_training, 'KNN_training')
+
+    return accuracy_score, accuracy_labels, accuracy_score_training, accuracy_labels_training
\ No newline at end of file

slopestabilityML/SGD/sgd_run.py

@@ -10,7 +10,7 @@ from sklearn.linear_model import SGDClassifier
 
 import slopestabilityML.plot_results
 import slopestabilityML.split_dataset
-import slopestabilityML.run_classification
+import slopestabilityML.run_classi
 
 
 def sgd_run(test_results, random_seed):

slopestabilityML/SVM/svm_run.py

@@ -10,6 +10,7 @@ from sklearn import svm
 import numpy as np
 import slopestabilityML.plot_results
 import slopestabilityML.split_dataset
+import slopestabilityML.run_classi
 import random
 
 # TODO: for comparability with other ML methods, add option to define which test should be used for training externaly

slopestabilityML/__init__.py

@@ -8,13 +8,14 @@ Created on 16.01.2021
 
 from .combine_results import combine_results
 from .plot_results import plot_results
-from .run_all_tests import run_all_tests
+from .run_every import run_all_tests
 from .split_dataset import split_dataset
-from .run_classification import run_classification
+from .run_classi import run_classification
 from .preprocess_data import preprocess_data
 
 from .SVM.svm_run import svm_run
 from .GBC.gbc_run import gbc_run
 from .SGD.sgd_run import sgd_run
-
+from .KNN.knn_run import knn_run
+from .ADABOOST.adaboost_run import adaboost_run
 

slopestabilityML/combine_results.py

@@ -27,9 +27,9 @@ def combine_results(ml_results):
     plt.ylabel('Correct points [%]')
     plt.legend(loc='lower right')
 
-    fig.savefig(Path('results/figures/ML_summary_prediction.eps'))
+    # fig.savefig(Path('results/figures/ML_summary_prediction.eps'))
     fig.savefig(Path('results/figures/ML_summary_prediction.png'))
-    fig.savefig(Path('results/figures/ML_summary_prediction.pdf'))
+    # fig.savefig(Path('results/figures/ML_summary_prediction.pdf'))
 
     # Training
     fig = plt.figure()
@@ -46,6 +46,6 @@ def combine_results(ml_results):
     plt.legend(loc='lower right')
 
     fig.tight_layout()
-    fig.savefig(Path('results/figures/ML_summary_training.eps'), bbox_inches="tight")
+    # fig.savefig(Path('results/figures/ML_summary_training.eps'), bbox_inches="tight")
     fig.savefig(Path('results/figures/ML_summary_training.png'), bbox_inches="tight")
-    fig.savefig(Path('results/figures/ML_summary_training.pdf'), bbox_inches="tight")
+    # fig.savefig(Path('results/figures/ML_summary_training.pdf'), bbox_inches="tight")

slopestabilityML/plot_results.py

@@ -23,8 +23,8 @@ def plot_results(accuracy_labels, accuracy_score, clf_name):
     plt.title(clf_name_title+' accuracy score')
     print('plot script is executed')
     fig.tight_layout()
-    fig.savefig(Path('results/figures/ML/'+clf_name+'.eps'), bbox_inches="tight")
-    fig.savefig(Path('results/figures/ML/'+clf_name+'.pdf'), bbox_inches="tight")
+    # fig.savefig(Path('results/figures/ML/'+clf_name+'.eps'), bbox_inches="tight")
+    # fig.savefig(Path('results/figures/ML/'+clf_name+'.pdf'), bbox_inches="tight")
     fig.savefig(Path('results/figures/ML/'+clf_name+'.png'), bbox_inches="tight")
 
     return

slopestabilityML/preprocess_data.py

@@ -6,14 +6,23 @@ Created on 19.01.2021
 @author: Feliks Kiszkurno
 """
 
+import settings
 import pandas as pd
 
 
 def preprocess_data(data_set):
 
-    x_train = data_set.drop(['X', 'Y', 'Z', 'INM', 'CLASS'], axis='columns')
-    #print(x_train)
-    #y_train = data_set.drop(['X', 'Y', 'Z', 'INM'], axis='columns')
+    if settings.settings['norm'] is True:
+        x_train = data_set.drop(['X', 'Y', 'Z', 'INM', 'RES', 'CLASS', 'CLASSN'], axis='columns')
+    else:
+        x_train = data_set.drop(['X', 'Y', 'Z', 'INM', 'RESN', 'CLASS', 'CLASSN'], axis='columns')
+
+    if settings.settings['sen'] is False:
+        x_train = x_train.drop(['SEN'], axis='columns')
+
+    if settings.settings['norm_class'] is True:
+        y_train = pd.DataFrame(data_set['CLASSN'])
+    else:
         y_train = pd.DataFrame(data_set['CLASS'])
 
     return x_train, y_train

slopestabilityML/run_classification.py → slopestabilityML/run_classi.py

@@ -6,6 +6,7 @@ Created on 19.01.2021
 @author: Feliks Kiszkurno
 """
 
+import settings
 import slopestabilityML
 import numpy as np
 import pandas as pd
@@ -21,13 +22,25 @@ from pathlib import Path
 
 def run_classification(test_training, test_prediction, test_results, clf, clf_name):
 
+    # global settings
+
+
+
+
     accuracy_score = []
     accuracy_labels = []
 
     accuracy_score_training = []
     accuracy_labels_training = []
 
+    if settings.settings['norm'] is True and settings.settings['sen'] is True:
+        num_feat = ['RESN', 'SEN']
+    elif settings.settings['norm'] is False and settings.settings['sen'] is True:
         num_feat = ['RES', 'SEN']
+    elif settings.settings['norm'] is False and settings.settings['sen'] is False:
+        num_feat = ['RES']
+    elif settings.settings['norm'] is True and settings.settings['sen'] is False:
+        num_feat = ['RESN']
     #cat_feat = ['CLASS']
 
     cat_lab = [0, 1]
@@ -42,8 +55,9 @@ def run_classification(test_training, test_prediction, test_results, clf, clf_na
 
     for test_name in test_training:
         # Prepare data
+        print(test_name)
         x_train, y_train = slopestabilityML.preprocess_data(test_results[test_name])
-
+        # print('stop')
         # Train classifier
         # print(type(x_train))
         # print(type(y_train))
@@ -119,9 +133,9 @@ def run_classification(test_training, test_prediction, test_results, clf, clf_na
         cb[2].update_ticks()
 
         fig.tight_layout()
-        fig.savefig(Path('results/figures/ML/prediction/eps/{}_ML_{}_class_res.eps'.format(test_name_pred, clf_name)), bbox_inches="tight")
+        # fig.savefig(Path('results/figures/ML/prediction/eps/{}_ML_{}_class_res.eps'.format(test_name_pred, clf_name)), bbox_inches="tight")
         fig.savefig(Path('results/figures/ML/prediction/png/{}_ML_{}_class_res.png'.format(test_name_pred, clf_name)), bbox_inches="tight")
-        fig.savefig(Path('results/figures/ML/prediction/pdf/{}_ML_{}_class_res.pdf'.format(test_name_pred, clf_name)), bbox_inches="tight")
+        # fig.savefig(Path('results/figures/ML/prediction/pdf/{}_ML_{}_class_res.pdf'.format(test_name_pred, clf_name)), bbox_inches="tight")
 
         # Evaluate result
         #accuracy_score.append(len(np.where(y_pred == y_answer.to_numpy())) / len(y_answer.to_numpy()) * 100)

slopestabilityML/run_all_tests.py → slopestabilityML/run_every.py

@@ -6,13 +6,15 @@ Created on 19.01.2021
 @author: Feliks Kiszkurno
 """
 
+# import slopestabilityML.combine_results
+import slopestabilityML.SVM.svm_run
+import slopestabilityML.GBC.gbc_run
+import slopestabilityML.SGD.sgd_run
+import slopestabilityML.KNN.knn_run
+import slopestabilityML.ADABOOST.adaboost_run
 import slopestabilityML
 
 
-# import slopestabilityML.SVM.svm_run
-# import slopestabilityML.GBC.gbc_run
-
-
 def run_all_tests(test_results):
     random_seed = 999
 
@@ -36,7 +38,19 @@ def run_all_tests(test_results):
     ml_results['sgd'] = {'score': sgd_accuracy_score, 'labels': sgd_accuracy_labels,
                          'score_training': sgd_accuracy_score_training, 'labels_training': sgd_accuracy_labels_training}
 
+    print('Running KNN...')
+    knn_accuracy_score, knn_accuracy_labels, knn_accuracy_score_training, knn_accuracy_labels_training = \
+        slopestabilityML.KNN.knn_run(test_results, random_seed)
+    ml_results['KNN'] = {'score': knn_accuracy_score, 'labels': knn_accuracy_labels,
+                         'score_training': knn_accuracy_score_training, 'labels_training': knn_accuracy_labels_training}
+
+    print('Running ADABOOST...')
+    ada_accuracy_score, ada_accuracy_labels, ada_accuracy_score_training, ada_accuracy_labels_training = \
+        slopestabilityML.ADABOOST.adaboost_run(test_results, random_seed)
+    ml_results['ADA'] = {'score': ada_accuracy_score, 'labels': ada_accuracy_labels,
+                         'score_training': ada_accuracy_score_training, 'labels_training': ada_accuracy_labels_training}
+
     slopestabilityML.combine_results(ml_results)
-    print('end')
+    print('ML classification finished')
 
     return ml_results

slopestabilitytools/__init__.py

@@ -16,6 +16,9 @@ from .model_params import model_params
 from .plot_and_save import plot_and_save
 from .set_labels import set_labels
 from .set_diff import set_diff
+from .normalize import normalize
+from .assign_classes import assign_classes
+from .def_classes import def_classes
 
 from .folder_structure.create_folder_structure import create_folder_structure
 from .folder_structure.create_folder_for_test import create_folder_for_test

slopestabilitytools/assign_classes.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 21.03.2021
+
+@author: Feliks Kiszkurno
+"""
+
+import numpy as np
+import settings
+import slopestabilitytools.def_classes
+
+
+# It assumes, that input array is normalized
+
+def assign_classes(data_array):
+
+    classes_def = slopestabilitytools.def_classes(settings.settings['norm_class_num'])
+    # classes_def = np.array([[0, 0, 0.1],
+    #                         [1, 0.1, 0.2],
+    #                         [2, 0.2, 0.3],
+    #                         [3, 0.3, 0.4],
+    #                         [4, 0.4, 0.5],
+    #                         [5, 0.5, 0.6],
+    #                         [6, 0.6, 0.7],
+    #                         [7, 0.7, 0.8],
+    #                         [8, 0.8, 0.9],
+    #                         [9, 0.9, 1.0]])
+    #
+    # classes_def = np.array([[0, 0, 0.2],
+    #                         [1, 0.2, 0.4],
+    #                         [2, 0.4, 0.6],
+    #                         [3, 0.6, 0.8],
+    #                         [4, 0.8, 1.0]])
+
+    # TODO: maybe reshaping is not necessary, as long as I supply the input as a vector. Think about and change it.
+    classes = np.zeros_like(data_array)
+    classes_shape = classes.shape
+    classes = classes.reshape([classes.size])
+
+    for class_pair in classes_def:
+        # print(class_pair)
+        ind = np.argwhere(np.logical_and(data_array > class_pair[1], data_array <= class_pair[2]))
+        # print(ind)
+        classes[ind] = class_pair[0]
+
+    classes_array = classes.reshape(classes_shape)
+
+    return classes_array