Implemented Stochastic Gradient Descent and Gradient Boost Classifier.

Added plot summarizing all ML methods. Added some functions to avoid repeating code within slopestabilityML module.
Fixed multiple bugs.
All ML methods will train and predict the same datasets thanks to random.seed.

main.py

@@ -61,4 +61,6 @@ else:
 
 for test_name in test_results.keys():
     slopestabilitytools.plot_and_save(test_name, test_results[test_name], 'Test: ' + test_name)
-svm_accuracy_score, svm_accuracy_labels = slopestabilityML.svm_run(test_results)
+
+ml_results = slopestabilityML.run_all_tests(test_results)
+#svm_accuracy_score, svm_accuracy_labels = slopestabilityML.svm_run(test_results)

slopestabilityML/GBC/__init__.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+from .gbc_run import gbc_run
\ No newline at end of file

slopestabilityML/GBC/gbc_run.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+from sklearn import ensemble
+import slopestabilityML.plot_results
+import slopestabilityML.split_dataset
+import slopestabilityML.run_classification
+
+# TODO: as in svm_run
+
+
+def gbc_run(test_results, random_seed):
+
+    test_training, test_prediction = slopestabilityML.split_dataset(test_results.keys(), random_seed)
+
+    # Create classifier
+    clf = ensemble.GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0)
+
+    # Train classifier
+    accuracy_labels, accuracy_score = slopestabilityML.run_classification(test_training, test_prediction, test_results, clf)
+
+    # Plot
+    slopestabilityML.plot_results(accuracy_labels, accuracy_score, 'GBC')
+
+    return accuracy_score, accuracy_labels

slopestabilityML/SGD/__init__.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+from .sgd_run import sgd_run

slopestabilityML/SGD/sgd_run.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+from sklearn.linear_model import SGDClassifier
+
+import slopestabilityML.plot_results
+import slopestabilityML.split_dataset
+import slopestabilityML.run_classification
+
+
+def sgd_run(test_results, random_seed):
+
+    test_training, test_prediction = slopestabilityML.split_dataset(test_results.keys(), random_seed)
+
+    # Create classifier
+    clf = SGDClassifier(loss="hinge", penalty="l2", max_iter=5)
+
+    # Train classifier
+    accuracy_labels, accuracy_score = slopestabilityML.run_classification(test_training, test_prediction, test_results,
+                                                                          clf)
+
+    # Plot
+    slopestabilityML.plot_results(accuracy_labels, accuracy_score, 'GBC')
+
+    return accuracy_score, accuracy_labels

slopestabilityML/SVM/svm_run.py

@@ -7,56 +7,50 @@ Created on 16.01.2021
 """
 
 from sklearn import svm
-import slopestabilitytools
-import random
-import math
 import numpy as np
 import slopestabilityML.plot_results
+import slopestabilityML.split_dataset
+import random
 
 # TODO: for comparability with other ML methods, add option to define which test should be used for training externaly
 
-def svm_run(test_results):
+
+def svm_run(test_results, random_seed):
+
     # https://stackabuse.com/implementing-svm-and-kernel-svm-with-pythons-scikit-learn/
 
+    test_training, test_prediction = slopestabilityML.split_dataset(test_results.keys(), random_seed)
+
     accuracy_score = []
     accuracy_labels = []
 
-    test_number = len(test_results.keys())
-    test_prediction = random.choices(list(test_results.keys()),
-                                     k=math.ceil(test_number * 0.1))
-
-    test_training = slopestabilitytools.set_diff(list(test_results.keys()), set(test_prediction))
-    print(test_prediction)
     # Create classifier
     clf = svm.SVC(gamma=0.001, C=100, kernel='linear')
 
     # Train classifier
-
-    for test_name in test_training:
-        # Prepare data
-        data_set = test_results[test_name]
-        x_train = data_set.drop(['Z', 'INM', 'CLASS'], axis='columns')
-        y_train = data_set['CLASS']
-
-        # Train classifier
-        clf.fit(x_train, y_train)
-
-    # Predict with classfier
-    for test_name_pred in test_prediction:
-        # Prepare data
-
-        data_set_pred = test_results[test_name_pred]
-        print(data_set_pred)
-        x_question = data_set_pred.drop(['Z', 'INM', 'CLASS'], axis='columns')
-        y_answer = data_set_pred['CLASS']
-
-        y_pred = clf.predict(x_question)
-
-        # Evaluate result
-        accuracy_score.append(len(np.where(y_pred == y_answer)) / len(y_answer) * 100)
-        accuracy_labels.append(test_name_pred)
+    accuracy_labels, accuracy_score = slopestabilityML.run_classification(test_training, test_prediction, test_results, clf)
+
+    # for test_name in test_training:
+    #
+    #     # Prepare data
+    #     x_train, y_train = slopestabilityML.preprocess_data(test_results[test_name])
+    #
+    #     # Train classifier
+    #     clf.fit(x_train, y_train)
+    #
+    # # Predict with classfier
+    # for test_name_pred in test_prediction:
+    #
+    #     # Prepare data
+    #     x_question, y_answer = slopestabilityML.preprocess_data(test_results[test_name_pred])
+    #
+    #     y_pred = clf.predict(x_question)
+    #
+    #     # Evaluate result
+    #     accuracy_score.append(len(np.where(y_pred == y_answer)) / len(y_answer) * 100)
+    #     accuracy_labels.append(test_name_pred)
 
     # Plot
-    slopestabilityML.plot_results(accuracy_labels, accuracy_score)
+    slopestabilityML.plot_results(accuracy_labels, accuracy_score, 'SVM')
 
     return accuracy_score, accuracy_labels

slopestabilityML/__init__.py

@@ -9,6 +9,12 @@ 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 .split_dataset import split_dataset
+from .run_classification 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
+
 

slopestabilityML/combine_results.py

 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
-Created on 
+Created on 19.01.2021
 
 @author: Feliks Kiszkurno
 """
 
+import matplotlib.pyplot as plt
 
-def combine_results():
 
-    return
+def combine_results(ml_results):
+
+    fig = plt.figure()
+    #ax = fig.subplots(1)
+    fig.suptitle('Accuracy of different ML methods')
+
+    for method_name in ml_results.keys():
+        plt.scatter(ml_results[method_name]['labels'], ml_results[method_name]['score'], label=method_name)
+
+    plt.legend(loc='best')
+
+    fig.savefig('results/figures/ML_summary.eps')
+    fig.savefig('results/figures/ML_summary.png')
+    fig.savefig('results/figures/ML_summary.pdf')
\ No newline at end of file

slopestabilityML/plot_results.py

@@ -9,17 +9,17 @@ Created on 17.01.2021
 import matplotlib.pyplot as plt
 
 
-def plot_results(accuracy_labels, accuracy_score):
+def plot_results(accuracy_labels, accuracy_score, clf_name):
 
     fig = plt.figure()
     ax = plt.subplot(111)
     ax.scatter(accuracy_labels, accuracy_score)
     plt.xlabel('Test name')
     plt.ylabel('Correct points [%]')
-    plt.title('SVM classification accuracy')
+    plt.title(clf_name+' classification accuracy')
     print('plot script is executed')
-    fig.savefig('results/figures/SVM.eps')
-    fig.savefig('results/figures/SVM.pdf')
-    fig.savefig('results/figures/SVM.png')
+    fig.savefig('results/figures/'+clf_name+'.eps')
+    fig.savefig('results/figures/'+clf_name+'.pdf')
+    fig.savefig('results/figures/'+clf_name+'.png')
 
     return

slopestabilityML/preprocess_data.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+
+def preprocess_data(data_set):
+
+    x_train = data_set.drop(['Z', 'INM', 'CLASS'], axis='columns')
+    y_train = data_set['CLASS']
+
+    return x_train, y_train

slopestabilityML/run_all_tests.py

 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 """
-Created on 
+Created on 19.01.2021
 
 @author: Feliks Kiszkurno
 """
 
-def run_all_tests():
+import slopestabilityML
+#import slopestabilityML.SVM.svm_run
+#import slopestabilityML.GBC.gbc_run
 
-    return
+
+def run_all_tests(test_results):
+
+    random_seed = 999
+
+    ml_results = {}
+
+    print('Running SVM...')
+    svm_accuracy_score, svm_accuracy_labels = slopestabilityML.SVM.svm_run(test_results, random_seed)
+    ml_results['svm'] = {'score': svm_accuracy_score, 'labels': svm_accuracy_labels}
+
+    print('Running GBC...')
+    gbc_accuracy_score, gbc_accuracy_labels = slopestabilityML.GBC.gbc_run(test_results, random_seed)
+    ml_results['gbc'] = {'score': gbc_accuracy_score, 'labels': gbc_accuracy_labels}
+
+    print('Running SGD...')
+    sgd_accuracy_score, sgd_accuracy_labels = slopestabilityML.SGD.sgd_run(test_results, random_seed)
+    ml_results['sgd'] = {'score': sgd_accuracy_score, 'labels': sgd_accuracy_labels}
+
+    slopestabilityML.combine_results(ml_results)
+    print('end')
+
+    return ml_results

slopestabilityML/run_classification.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+import slopestabilityML
+import numpy as np
+
+
+def run_classification(test_training, test_prediction, test_results, clf):
+
+    accuracy_score = []
+    accuracy_labels = []
+
+    for test_name in test_training:
+        # Prepare data
+        x_train, y_train = slopestabilityML.preprocess_data(test_results[test_name])
+
+        # Train classifier
+        clf.fit(x_train, y_train)
+
+    # Predict with classifier
+    for test_name_pred in test_prediction:
+        # Prepare data
+        x_question, y_answer = slopestabilityML.preprocess_data(test_results[test_name_pred])
+
+        y_pred = clf.predict(x_question)
+
+        # Evaluate result
+        accuracy_score.append(len(np.where(y_pred == y_answer)) / len(y_answer) * 100)
+        accuracy_labels.append(test_name_pred)
+
+    return accuracy_labels, accuracy_score
+

slopestabilityML/split_dataset.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on 19.01.2021
+
+@author: Feliks Kiszkurno
+"""
+
+import slopestabilitytools
+import random
+import math
+
+
+def split_dataset(test_names, random_seed):
+
+    random.seed(random_seed)
+
+    test_number = len(test_names)
+    test_prediction = random.choices(list(test_names),
+                                     k=math.ceil(test_number * 0.1))
+
+    test_training = slopestabilitytools.set_diff(list(test_names), set(test_prediction))
+
+    return test_training, test_prediction

slopestabilitytools/datamanagement/test_list.py

@@ -21,12 +21,7 @@ def test_list(extension):
     for file in file_list:
 
         test_names.append(file[:file.find(extension)])
-        print(file[:file.find(extension)])
 
-    print('start')
-    print(test_names)
-    print('end')
     test_names = sorted(test_names)
-    print(test_names)
 
     return test_names

slopestabilitytools/folder_structure/check_create_folder.py

@@ -14,7 +14,6 @@ def check_create_folder(folder_path):
     if os.path.isdir(folder_path):
         print("Folder for figures exists!")
     else:
-        print(folder_path)
         os.mkdir(folder_path)
         print("Created folder for figures!")
 

slopestabilitytools/model_params.py

@@ -103,7 +103,6 @@ def model_params(n_of_tests, rho_spread, rho_max, layers_n_min, layers_n_max, de
         layer_id = 1
 
         for rho in rho_temp:
-            print(rho)
             rho_final.append([layer_id, rho])
             layer_id += 1
 

slopestabilitytools/plot_and_save.py

@@ -15,20 +15,17 @@ import slopestabilitytools
 def plot_and_save(test_name, test_result, plot_title):
 
     x = test_result['X']
-    print(x)
     y = test_result['Y']
     inm = test_result['INM']
     res = test_result['RES']
 
     x_vec = np.unique(np.array(x))
     y_vec = np.unique(np.array(y))
-    print(y_vec)
     X, Y = np.meshgrid(x_vec, y_vec)
     [m, n] = X.shape
     inm_plot = np.array(inm).reshape((m, n))
     res_plot = np.array(res).reshape((m, n))
     print('plot_and_save')
-    print(X)
 
     fig, ax = plt.subplots(3)