diff --git a/Retrieve_combined_features.ipynb b/Retrieve_combined_features.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..6c4931f4d54b72a6d0919c955f17a2456051d63d
--- /dev/null
+++ b/Retrieve_combined_features.ipynb
@@ -0,0 +1,309 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "f8b76e74",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "from PIL import Image\n",
+ "from annoy import AnnoyIndex\n",
+ "import random\n",
+ "\n",
+ "base_dir = 'path_to_the_dataset'\n",
+ "top_count = 100\n",
+ "top_K = 11"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "43c9c917",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#the 1st column is index, the second is path to the paintings, rest columns are pre-calculated embeddings\n",
+ "df_artist = pd.read_csv('dino_features_wikiart_artist.csv')\n",
+ "df_genre = pd.read_csv('dino_features_wikiart_genre.csv')\n",
+ "df_style = pd.read_csv('dino_features_wikiart_style.csv')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "be5120fe",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def build_index(df, filename):\n",
+ " NUMBER_OF_TREES = 25\n",
+ " feature_dim = len(df.columns) - 2\n",
+ "\n",
+ " t = AnnoyIndex(feature_dim, metric='euclidean')\n",
+ "\n",
+ " for i in range(len(df)):\n",
+ " vector = df.loc[i][2:]\n",
+ " t.add_item(i, vector)\n",
+ " \n",
+ " _ = t.build(NUMBER_OF_TREES)\n",
+ "\n",
+ " #save indexes\n",
+ " t.save(base_dir + filename)\n",
+ " return t"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "afa13d41",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "t_genre = build_index(df_genre, 'dino_genre.ann')\n",
+ "t_style = build_index(df_style, 'dino_style.ann')\n",
+ "t_artist = build_index(df_artist, 'dino_artist.ann')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "feff4c2f",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#download saved indexes\n",
+ "feature_dim = len(df_genre.columns) - 2\n",
+ "\n",
+ "t_genre = AnnoyIndex(feature_dim, metric='euclidean')\n",
+ "t_genre.load('dino_genre.ann')\n",
+ "\n",
+ "t_style = AnnoyIndex(feature_dim, metric='euclidean')\n",
+ "t_style.load('dino_style.ann')\n",
+ "\n",
+ "t_artist = AnnoyIndex(feature_dim, metric='euclidean')\n",
+ "t_artist.load('dino_artist.ann')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "ee4c29ab",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#receive similar images using ANNOY\n",
+ "def get_similar_images_annoy(vector, t):\n",
+ " indices, dists = t.get_nns_by_vector(vector, top_count+1, include_distances=True)\n",
+ " return indices, dists"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "1b10c4d0",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def show_similar(img_str, img_list, k, distances):\n",
+ " img = Image.open(base_dir + img_str)\n",
+ " plt.title('Request painting')\n",
+ " plt.axis(\"off\")\n",
+ " plt.imshow(img)\n",
+ "\n",
+ " plt.figure(figsize=(30, 30))\n",
+ " ax = plt.subplot(1, k, 1)\n",
+ " \n",
+ " i = 0\n",
+ " for key in img_list:\n",
+ " ax = plt.subplot(1, k, i+1)\n",
+ " img = Image.open(base_dir + key)\n",
+ " plt.title(\"{}\".format(round(distances[i], 4)))\n",
+ " plt.imshow(img)\n",
+ " i+=1\n",
+ "\n",
+ " plt.axis(\"off\")\n",
+ " plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "29ccae77",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#request image\n",
+ "img_str = 'Impressionism/pierre-auguste-renoir_children-on-the-seashore-1883.jpg'\n",
+ "\n",
+ "#pre-calculated embeddings of the request painting\n",
+ "img_req_g = np.array(df_genre[df_genre['file_path']==img_str])[0][2:]\n",
+ "img_req_s = np.array(df_style[df_style['file_path']==img_str])[0][2:]\n",
+ "img_req_a = np.array(df_artist[df_artist['file_path']==img_str])[0][2:]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9c2c37c1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "similar_images_g = []\n",
+ "similar_images_s = []\n",
+ "similar_images_a = []\n",
+ "\n",
+ "similar_img_ids_g, distances_g = get_similar_images_annoy(img_req_g, t_genre)\n",
+ "similar_images_g = list(df_genre.iloc[similar_img_ids_g]['file_path'])\n",
+ "\n",
+ "similar_img_ids_s, distances_s = get_similar_images_annoy(img_req_s, t_style)\n",
+ "similar_images_s = list(df_style.iloc[similar_img_ids_s]['file_path'])\n",
+ "\n",
+ "similar_img_ids_a, distances_a = get_similar_images_annoy(img_req_a, t_artist)\n",
+ "similar_images_a = list(df_artist.iloc[similar_img_ids_a]['file_path'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "eac7636a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#pre-calculated values of mean and std of eucledian distances on WikiArt dataset\n",
+ "mean_genre = 19.6129883775738\n",
+ "std_genre = 2.9717604654152274\n",
+ "mean_style = 18.328733753985198\n",
+ "std_style = 2.5707980486965547\n",
+ "mean_artist = 20.973407871326454\n",
+ "std_artist = 2.9063593849149183"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "08e0941d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Calculating cosine distance\n",
+ "#request painting belongs to the dataset, so we ignore the first similar painting\n",
+ "df_genre_sim = df_genre[df_genre['file_path'].isin(similar_images_g)]\n",
+ "cosines_genre = distances_g[1:]\n",
+ "\n",
+ "df_style_sim = df_style[df_style['file_path'].isin(similar_images_s)]\n",
+ "cosines_style = distances_s[1:]\n",
+ "\n",
+ "df_artist_sim = df_artist[df_artist['file_path'].isin(similar_images_a)]\n",
+ "cosines_artist = distances_a[1:]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b48542d3",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "d = {'file_path': list(df_genre_sim['file_path'].iloc[1:]), 'd_g': cosines_genre}\n",
+ "df_g = pd.DataFrame(data=d)\n",
+ "\n",
+ "d = {'file_path': list(df_style_sim['file_path'].iloc[1:]), 'd_s': cosines_style}\n",
+ "df_s = pd.DataFrame(data=d)\n",
+ "\n",
+ "d = {'file_path': list(df_artist_sim['file_path'].iloc[1:]), 'd_a': cosines_artist}\n",
+ "df_a = pd.DataFrame(data=d)\n",
+ "\n",
+ "df_u = pd.merge(df_g, df_s, on='file_path', how='outer')\n",
+ "df_u = pd.merge(df_u, df_a, on='file_path', how='outer')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "92bb15c8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def func(x):\n",
+ " missing_indices = x.index[x.isnull()]\n",
+ " for index in missing_indices:\n",
+ " if x.name == 'd_g':\n",
+ " img_sim = df_u.loc[index, 'file_path']\n",
+ " eucl_distance = np.linalg.norm(img_req_g - df_genre[df_genre['file_path'] == img_sim].iloc[0, 2:])\n",
+ " x.loc[index] = eucl_distance\n",
+ " elif x.name == 'd_s': \n",
+ " img_sim = df_u.loc[index, 'file_path']\n",
+ " eucl_distance = np.linalg.norm(img_req_s - df_style[df_style['file_path'] == img_sim].iloc[0, 2:])\n",
+ " x.loc[index] = eucl_distance\n",
+ " elif x.name == 'd_a': \n",
+ " img_sim = df_u.loc[index, 'file_path']\n",
+ " eucl_distance = np.linalg.norm(img_req_a - df_artist[df_artist['file_path'] == img_sim].iloc[0, 2:])\n",
+ " x.loc[index] = eucl_distance\n",
+ "\n",
+ " return x\n",
+ "\n",
+ "df_u = df_u.apply(func, axis=0)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "7e464ba0",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df_u['d_g'] = (df_u['d_g'] - mean_genre)/std_genre\n",
+ "df_u['d_s'] = (df_u['d_s'] - mean_style)/std_style\n",
+ "df_u['d_a'] = (df_u['d_a'] - mean_style)/std_style"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "5ea5a057",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#combined recommendations with the same weights\n",
+ "df_u['combined'] = df_u['d_g'] + df_u['d_s'] + df_u['d_a']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b9e0d83f",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "paintings = list(df_u.sort_values(by=['combined'])['file_path'])[:top_K]\n",
+ "dist = list(df_u.sort_values(by=['combined'])['combined'])[:top_K]\n",
+ "show_similar(img_str, paintings, top_K, dist)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.14"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}