nupdated feature vectors | added functionality to specify number of training vectors

src/all_data_splitter.py

@@ -27,14 +27,14 @@ def split_all_data(all_data_path: str, future_training_path: str, future_testing
     random.shuffle(training_data)
     random.shuffle(testing_data)
     with open(future_training_path, 'w') as csv_file: 
-        writer = csv.writer(csv_file, delimiter=";")
+        writer = csv.writer(csv_file, delimiter=";", lineterminator="\n")
-        writer.writerow(['filename','concept', 'vector'])
+        writer.writerow(['brightness','filename','concept', 'vector'])
         for sing in training_data:
             writer.writerow(sing)
 
     with open(future_testing_path, 'w') as csv_file: 
-        writer = csv.writer(csv_file, delimiter=";")
+        writer = csv.writer(csv_file, delimiter=";", lineterminator="\n")
-        writer.writerow(['filename','concept', 'vector'])
+        writer.writerow(['brightness','filename','concept', 'vector'])
         for sing in testing_data:
             writer.writerow(sing)
 

src/classes/neural/network.py

@@ -37,7 +37,7 @@ class NeuralNetwork:
     
         correct_amount = 0
         false_amount = 0
-        for i in range(len(training_set)*30):
+        for i in range(len(training_set)):
             fv_to_train = random.choice(training_set)
             classified_concept, correct = self.classify(fv_to_train)
             

src/main.py

@@ -58,7 +58,7 @@ def decision_tree(training = os.path.abspath(os.path.join(__file__, "..", "train
     # print(f"classified {cnt_correct}/{cnt_data} correctly  ({round(cnt_correct/cnt_data*100, 3)}%)")
     return [cnt_correct, cnt_data - cnt_correct, cnt_data]  # richtig, falsch, amount of testing data
 
-def neural_network(training = os.path.abspath(os.path.join(__file__, "..", "training.csv")), testing = os.path.abspath(os.path.join(__file__, "..", "testing.csv")), cycles = 3):
+def neural_network(training = os.path.abspath(os.path.join(__file__, "..", "training.csv")), testing = os.path.abspath(os.path.join(__file__, "..", "testing.csv")), num_training_vectors = 100):
     from classes.neural.network import NeuralNetwork
     from classes.neural.neuron import Neuron
 
@@ -66,12 +66,21 @@ def neural_network(training = os.path.abspath(os.path.join(__file__, "..", "trai
     with open(training, 'r') as csv_file:
         reader = csv.reader(csv_file, delimiter=";")
         next(reader)
+        i = 0
         for row in reader:
-            float_list = ast.literal_eval(row[2])
+            i += 1
+            if i > num_training_vectors:
+                break
 
-            fv = FeatureVector(concept = Concept.identify_by_str(row[1].split(".")[1]), features_list = [element * 0.01 for element in float_list], loaded = True)
+            float_list = ast.literal_eval(row[3])
+
+            fv = FeatureVector(concept = Concept.identify_by_str(row[2].split(".")[1]), features_list = [element * 0.01 for element in float_list], loaded = True)
             training_data.append(fv)
     
+    while len(training_data) < num_training_vectors:
+        training_data += training_data
+    training_data = training_data[:num_training_vectors+1]
+
     nn = NeuralNetwork()
     nn.learn(training_data)
 
@@ -82,7 +91,7 @@ def neural_network(training = os.path.abspath(os.path.join(__file__, "..", "trai
         next(reader)
         for row in reader:
             cnt_data += 1
-            fv = FeatureVector(concept = Concept.identify_by_str(row[1].split(".")[1]), features_list = ast.literal_eval(row[2]), loaded = True)
+            fv = FeatureVector(concept = Concept.identify_by_str(row[2].split(".")[1]), features_list = ast.literal_eval(row[3]), loaded = True)
             classified_concept, _ = nn.classify(fv)
             cnt_correct += 1 if fv.concept == classified_concept else 0
             # print(f"{fv.concept} was classified as {classified_concept}")