kNN implemented with analyse

src/classes/feature_vector.py

@@ -3,15 +3,21 @@ import numpy as np
 import os
 import pickle
 
-from concept import Concept
+from classes.concept import Concept
-from feature import Feature
+from classes.feature import Feature
 
 
 class FeatureVector:
 
-	def __init__(self, concept: Concept, features: dict = {}) -> None:
+	def __init__(self, concept: Concept, features: dict = {}, features_list: list = None, loaded: bool = False) -> None:
-		self.features: dict = features
+		if loaded == False:
-		self.concept: Concept = concept
+			self.loaded: bool = False
+			self.features: dict = features
+			self.concept: Concept = concept
+		else:
+			self.loaded: bool = True
+			self.concept: Concept = concept
+			self.features_list: list = features_list
 
 
 	def _get_values_of_feature(self, feature: Feature) -> list[int]:
@@ -53,6 +59,9 @@ class FeatureVector:
 
 
 	def get_vector(self) -> list:
+		if self.loaded:
+			return self.features_list
+		
 		ret = []
 		for feature in Feature:
 			ret = ret + self._get_values_of_feature(feature)

src/classes/learner.py

@@ -0,0 +1,83 @@
+import csv
+import ast
+import math
+
+from classes.concept import Concept
+from classes.feature_vector import FeatureVector
+
+class Learner:
+	# The training method, that changes the internal state of the learner such that 
+	# it will classify examples of a similar set (i.e. the testSet better.
+	# 
+	# @param trainingSet contains feature vectors and corresponding concepts 
+	# to provide experience to learn from  
+
+	def learn(self, path_to_training_set: str):
+		training_set = []
+		with open(path_to_training_set, mode='r' ,newline='') as csv_file:
+			reader = csv.reader(csv_file, delimiter=';')
+			next(reader) # read from 2. row without header
+			for row in reader:
+				fv = FeatureVector(concept = row[1], features_list = ast.literal_eval(row[2]), loaded = True)
+				training_set.append(fv)
+
+		self.training_set = training_set
+
+		return training_set
+	
+	# find the concept of the example from the internal knowledge of the lerner
+	# this method must not consider example.getConcept() at all!!
+	# 
+	# @param example: is a feature vector
+	# @return the concept of the examplke as learned by this before
+	def classify(self, input_feature_vector):
+		distances = []
+		result: dict = {
+			Concept.LINKS_ABBIEGEN: 0,
+			Concept.RECHTS_ABBIEGEN: 0,
+			Concept.RECHTS_VOR_LINKS: 0,
+			Concept.STOP: 0,
+			Concept.VORFAHRT_GEWAEHREN: 0,
+			Concept.VORFAHRT_STRASSE: 0
+		}
+		for single_fv in self.training_set: 
+			single_dist = self.euclid_distance(single_fv.get_vector(), input_feature_vector)
+			distances.append((single_fv.get_concept(), single_dist))
+
+		sorted_distances = sorted(distances, key=lambda tuple: tuple[1])
+		k_nearest = 3
+		interested_distances = sorted_distances[:k_nearest]
+
+		for interested_fv in interested_distances:
+			concept = self.string_to_enum(Concept, interested_fv[0])
+			result[concept] += 1
+
+		return result
+
+
+
+	def euclid_distance(self, list_a, list_b):
+		if len(list_a) != len(list_b):
+			raise Exception("Both lists must equal in size!")
+		
+		sum = 0
+		for i in range(0, len(list_a)):
+			sum += (list_b[i] - list_a[i]) ** 2
+
+		return math.sqrt(sum)
+	
+	def string_to_enum(self, enum_class, enum_string):
+		try:
+			# Split the string to get the enum member name
+			_, member_name = enum_string.split('.')
+			# Use getattr to get the enum member
+			return getattr(enum_class, member_name)
+		except (AttributeError, ValueError) as e:
+			print(f"Error: {e}")
+			return None
+		
+	def analyse(self, result, k):
+		sorted_dict_result = {key: value for key, value in sorted(result.items(), key=lambda item: item[1])}
+		for key, amount in sorted_dict_result.items():
+			probability = (amount/k) * 100
+			print(f" Probability of {key} is {probability}%")

src/create_feature_vectors.py

@@ -2,10 +2,10 @@ import os
 import csv
 import cv2 as cv
 
-from featue_extraction import get_color_percentage, get_raster_color_percentage, get_edges, get_corners, get_contours
+from util.featue_extraction import get_color_percentage, get_raster_color_percentage, get_edges, get_corners, get_contours
-from feature_vector import FeatureVector
+from classes.feature_vector import FeatureVector
-from concept import Concept
+from classes.concept import Concept
-from feature import Feature
+from classes.feature import Feature
 
 img_path = os.path.abspath(os.path.join(__file__, "..", "..", "data", "processed"))
 vector_path = os.path.abspath(os.path.join(__file__, "..", "..", "data", "vectors"))

src/learner.py

@@ -1,17 +0,0 @@
-class Learner:
-	# The training method, that changes the internal state of the learner such that 
-	# it will classify examples of a similar set (i.e. the testSet better.
-	# 
-	# @param trainingSet contains feature vectors and corresponding concepts 
-	# to provide experience to learn from  
-
-	def learn(trainingSet):
-		pass
-	
-	# find the concept of the example from the internal knowledge of the lerner
-	# this method must not consider example.getConcept() at all!!
-	# 
-	# @param example: is a feature vector
-	# @return the concept of the examplke as learned by this before
-	def classify(example):
-		pass

src/main.py

@@ -0,0 +1,11 @@
+from classes.learner import Learner
+
+path_to_training_set = '/Users/denysseredenko/StreetsignRecognition/src/feature_vectors.csv'
+
+learner = Learner()
+learner.learn(path_to_training_set)
+
+#TODO: add feature vector
+distances = learner.classify([0, 27, 0, 9, 0, 64, 0, 0, 0, 0, 0, 100, 0, 0, 0, 0, 0, 100, 0, 26, 0, 8, 0, 66, 0, 54, 0, 24, 0, 22, 0, 0, 0, 0, 0, 100, 0, 34, 0, 12, 0, 54, 0, 59, 0, 40, 0, 1, 0, 23, 0, 10, 0, 67, 0, 25, 0, 9, 0, 66, 0, 89, 0, 9, 0, 2, 0, 36, 0, 9, 0, 55, 0, 0, 0, 0, 0, 100, 0, 59, 0, 19, 0, 22, 0, 25, 0, 8, 0, 67, 0, 0, 0, 0, 0, 100, 0, 0, 0, 0, 0, 100, 6, 18, 104])
+
+learner.analyse(distances, 3)

src/util/featue_extraction.py

@@ -1,7 +1,7 @@
 import cv2 as cv
 import numpy as np
 
-from image_processing import raster_image
+from util.image_processing import raster_image
 
 blue_lower_hsv = np.array([90, 75, 75])
 blue_upper_hsv = np.array([130, 255, 255])