def create_flat_images_db(start=0, end=100, dim=(100, 100)):
"""For each image in path, resizes it to the given dim, transforms it into a flat vector
and stores in a df. Then dumps it into a joblib file.
Start and end define which images to consider."""
if len(os.listdir(IMAGES_PATH)) < start:
return None
elif len(os.listdir(IMAGES_PATH)) < end:
end = len(os.listdir(IMAGES_PATH))
filelist = sorted(os.listdir(IMAGES_PATH),
key=lambda x: int(x.strip('.jpg')))[start:end]
# stores flat images in a dataframe
img_db = pd.DataFrame()
print("Creating joblib database...")
for filename in tqdm(filelist,
bar_format='{l_bar}{bar:30}{r_bar}{bar:-10b}'):
img = preprocess_image(os.path.join(IMAGES_PATH, filename), dim=dim)
img_db = img_db.append(
pd.DataFrame(img, index=[int(filename.strip('.jpg'))]))
# save df to joblib file
path = join(dirname(__file__), '..', 'raw_data', 'test_images_db_2',
'flat_resized_images')
img_db.sort_index(inplace=True)
joblib.dump(img_db, '_'.join([path, str(start), str(end - 1)]) + '.joblib')
print(
f"=> Created file {'_'.join([path,str(start),str(end-1)])+'.joblib'}")
def create_flat_images_db(size=100, path=IMAGES_PATH, dim=(36,42)):
"""For each image in path, resizes it to the given dim, transforms it into a flat vector
and stores in a df. Then dumps it into a joblib file"""
# stores flat images in a dataframe
img_db = pd.DataFrame()
print("\nCreating joblib database...")
for filename in tqdm(os.listdir(IMAGES_PATH)[:size], bar_format='{l_bar}{bar:30}{r_bar}{bar:-10b}'):
img = preprocess_image(os.path.join(IMAGES_PATH, filename),dim=dim)
img_db = img_db.append(pd.DataFrame(img,index=[filename.strip('.jpg')]))
# save df to joblib file
img_db.sort_index(inplace=True)
if size:
joblib.dump(img_db,FLAT_IMAGES_DB_PATH_ROOT+'_'+str(size)+'.joblib')
else:
joblib.dump(img_db,FLAT_IMAGES_DB_PATH_ROOT+'.joblib')
client = storage.Client()
dataset_filename = 'catalog.csv'
path = f"gs://{BUCKET_NAME}/{BUCKET_INITIAL_DATASET_FOLDER}/{dataset_filename}"
df = pd.read_csv(path, encoding='unicode_escape')
df['URL'] = df['URL'].map(get_jpg_link)
urls = [df.iloc[i]['URL'] for i in indexes]
if not all_info:
return urls
# get additional info
titles = [df.iloc[i]['TITLE'] for i in indexes]
authors = [df.iloc[i]['AUTHOR'] for i in indexes]
return urls, titles, authors
if __name__ == '__main__':
from vincentvanbot.preprocessing import preprocess_image
path = os.path.join(os.path.dirname(__file__), '..', '..', 'notebooks',
'example-input.jpg')
# print(path)
user_img = preprocess_image(path, dim=(36, 42))
indexes = get_closest_images_indexes(user_img)
urls = get_info_from_index(indexes)
print(urls)
'''Chnage path to local here'''
max_results=50,
proba_threshold=0.5,
manual=False).keys()]
'''sum eahch row for the resulting dataframe (=KNN Dataframe with only mathcing labels to the input data)'''
KNN_index['SUM'] = KNN_index.sum(axis=1)
KNN_index = KNN_index.sort_values(by=['SUM'], ascending=False)[:3]
return list(KNN_index.index.values)
if __name__ == '__main__':
from vincentvanbot.preprocessing import preprocess_image
path = os.path.join(os.path.dirname(__file__), '..', 'notebooks',
'example-input.jpg')
#get_labels_from_local_path(path, max_results = 10 , proba_threshold=0.5, manual=False).keys()
user_img = preprocess_image(path, dim=(100, 100))
print(get_info_from_index(filter_KNN_results(user_img, path)))
# from vincentvanbot.data import get_data_locally
# df_total = get_data_locally(100)
# import numpy as np
# df_list = []
# for i, df in enumerate(np.array_split(df_total,10)):
# print(f"\nWorking on slice {i+1}")
# labels_df = get_labels_df(df,100_000, source='local', manual=False)
# df_list.append(labels_df)
# import pandas as pd
# labels_df_total = pd.concat(df_list,axis=0)
# labels_df_total.fillna(0, inplace= True)
def process_user_file(file, n_similar=3):
response = []
# Getting a file from a user
contents = file.read()
temp_file_name = str(time.time())
with open(temp_file_name, 'wb') as user_file:
user_file.write(contents)
try:
# Labeling a user pic
labels_dict = get_labels_from_local_path(temp_file_name,
50,
0.5,
manual=False)
labels_list = [
label for label in labels_dict.keys()
if label in labeled_dataframe.columns
]
# Sequence of bytes/file is passed to preprocessor {preproc.transform(X)}. OUTPUT: Vector of size matching the KNN model.
image_processed = preprocess_image(temp_file_name)
# n_similar closest neighbors are returned {knn_model} = their indice
index_neighbors = knn_model.kneighbors(image_processed,
n_neighbors=n_similar * 2)[1][0]
base_indices = [int(train_indices[i]) for i in list(index_neighbors)]
# Getting the knn rank
labeled_knn_filtered = labeled_dataframe.loc[base_indices, :]
labeled_knn_filtered['KNN_RANK'] = labeled_knn_filtered.reset_index(
).index.values + 1
indices_with_knn_rank = labeled_knn_filtered[['KNN_RANK']]
# Getting the labels rank
labeled_knn_filtered = labeled_knn_filtered[labels_list]
labeled_knn_filtered['SUM'] = labeled_knn_filtered.sum(axis=1)
labeled_knn_filtered = labeled_knn_filtered.sort_values(
by=['SUM'], ascending=False)
labeled_knn_filtered['LABELS_RANK'] = labeled_knn_filtered.reset_index(
).index.values + 1
indices_with_labels_rank = labeled_knn_filtered[['LABELS_RANK']]
# Calculating the combined rank
knn_with_labels = indices_with_knn_rank.join(indices_with_labels_rank,
how='inner')
knn_with_labels['RANK_SUM'] = knn_with_labels[
'KNN_RANK'] + knn_with_labels['LABELS_RANK']
knn_with_labels = knn_with_labels.sort_values(by=['RANK_SUM'],
ascending=True)
results = list(knn_with_labels.index.values)[:n_similar]
# Send response back. Response structure: [ n_similar pieces of {img_url, html_url, author, title, created, museum}]
for ind in results:
response_item = dict (img_url = get_jpg_link(database.at[ind, 'URL']), html_url = database.at[ind, 'URL'], \
author = database.at[ind, 'AUTHOR'], title = database.at[ind, 'TITLE'], \
created = database.at[ind, 'DATE'], museum = database.at[ind, 'LOCATION'])
response.append(response_item)
except BaseException as e:
print(e)
finally:
# Deleting user pic
os.remove(temp_file_name)
return response