def test(image_list, model_images):
"""Performs testing by performing K-nearest neighbors classification
Stores the predicted orientation in the object itself
:param image_list: List of test images
:param model_images: List of training images
"""
def calculate_distance(image1, image2):
"""Calculates the Euclidean distance between 2 images
:param image1: First image object
:param image2: Second image object
:return: Euclidean distance between the 2 images
"""
dist = 0
for f_image1, f_image2 in zip(image1.features, image2.features):
dist += (f_image1 - f_image2)**2
return 0.0 + dist
# test() starts from here
for test_image in image_list:
# Traversing all the model images and calculating the distance
least_dist = SortedList(K)
for model_image in model_images:
curr_dist = calculate_distance(test_image, model_image)
least_dist.insert(curr_dist, model_image)
# Get a voting from all the K nearest neighbors
model_dict = defaultdict(lambda: 0)
for index in range(K):
curr_img = least_dist.get(index)
model_dict[curr_img.orientation] += 1
# print 'Printing model_dict:', model_dict
max_orientation = max(model_dict, key=model_dict.get)
test_image.pred_orientation = max_orientation
def perform_top_n_filtering(similarity_df, n):
"""Finds the n most similar user/item, and returns it in the form of a list of tuples
:param similarity_df: Pandas dataframe representing pairwise similarities between m users/items
:param n: The number of neighbors
:return: A dictionary that maps a user/item to at most n nearest users/items
"""
neighbor_dict = dict()
for row_idx, row in similarity_df.iterrows():
nearest = SortedList(n)
for col_idx, cell in row.iteritems():
if not (math.isnan(cell) or row_idx == col_idx):
nearest.insert(cell, col_idx)
neighbor_dict[row_idx] = nearest.get_all()
# print neighbor_list
return neighbor_dict
def perform_threshold_filtering(similarity_df, threshold):
"""Finds the user/item whose similarity >= threshold, and returns it in the form of a list of tuples
:param similarity_df: Pandas dataframe representing pairwise similarities between m users/items
:param threshold: The similarity threshold
:return: A list of tuples that maps a user/item to at most n nearest users/items
"""
neighbor_dict = dict()
cols = len(similarity_df.columns)
for row_idx, row in similarity_df.iterrows():
nearest = SortedList(cols)
for col_idx, cell in row.iteritems():
if not (math.isnan(cell) or row_idx == col_idx
or cell < threshold):
nearest.insert(cell, col_idx)
neighbor_dict[row_idx] = nearest.get_all()
# print neighbor_list
return neighbor_dict
