File size: 10,269 Bytes
699b928 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\Jose\\Desktop\\Nuanced_Recommendation_System\\.venv\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:1617: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be deprecated in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
" warnings.warn(\n"
]
}
],
"source": [
"import os\n",
"import json\n",
"\n",
"from sentence_transformers import SentenceTransformer\n",
"from sklearn.metrics.pairwise import cosine_similarity\n",
"\n",
"model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')\n",
"\n",
"import gradio as gr"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def get_n_weighted_scores(embeddings, query, n, objective_weight, subjective_weight):\n",
" query = [model.encode(query)]\n",
"\n",
" weighted_scores = []\n",
"\n",
" for key, value in embeddings.items():\n",
" objective_embedding = value['objective_embedding']\n",
" subjective_embeddings = value['subjective_embeddings']\n",
" \n",
" objective_score = cosine_similarity(query, objective_embedding).item()\n",
" subjective_scores = cosine_similarity(query, subjective_embeddings)\n",
"\n",
" max_score = 0\n",
" max_review_index = 0\n",
" for idx, score in enumerate(subjective_scores[0].tolist()):\n",
" weighted_score = ((objective_score * objective_weight)+(score * subjective_weight))\n",
" if weighted_score > max_score:\n",
" max_score = weighted_score\n",
" max_review_index = idx\n",
" \n",
" weighted_scores.append((key, max_score, max_review_index))\n",
" \n",
" return sorted(weighted_scores, key=lambda x: x[1], reverse=True)[:n]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def filter_anime(embeddings, genres, themes, rating):\n",
" genres = set(genres)\n",
" themes = set(themes)\n",
" rating = set(rating)\n",
"\n",
" filtered_anime = embeddings.copy()\n",
" for key, anime in embeddings.items():\n",
"\n",
" anime_genres = set(anime['genres'])\n",
" anime_themes = set(anime['themes'])\n",
" anime_rating = set([anime['rating']])\n",
"\n",
" if genres.intersection(anime_genres) or 'ALL' in genres:\n",
" pass\n",
" else:\n",
" filtered_anime.pop(key)\n",
" continue\n",
" if themes.intersection(anime_themes) or 'ALL' in themes:\n",
" pass\n",
" else:\n",
" filtered_anime.pop(key)\n",
" continue\n",
" if rating.intersection(anime_rating) or 'ALL' in rating:\n",
" pass\n",
" else:\n",
" filtered_anime.pop(key)\n",
" continue\n",
" \n",
" return filtered_anime"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"with open('./embeddings/data.json') as f:\n",
" data = json.load(f)\n",
" embeddings = data['embeddings']\n",
" filters = data['filters']"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"def get_recommendation(query, number_of_recommendations, genres, themes, rating, objective_weight, subjective_weight):\n",
" filtered_anime = filter_anime(embeddings, genres, themes, rating)\n",
" results = []\n",
" weighted_scores = get_n_weighted_scores(filtered_anime, query, number_of_recommendations, float(objective_weight), float(subjective_weight))\n",
" for idx, (key, score, review_index) in enumerate(weighted_scores, start=1):\n",
" data = embeddings[key]\n",
" if not data['english']:\n",
" name = data['japanese']\n",
" else:\n",
" name = data['english']\n",
" description = data['description']\n",
" review = data['reviews'][review_index]['text']\n",
" image = data['image']\n",
"\n",
" results.append(gr.Image(label=f\"Recommendation {idx}: {name}\",value=image, height=435, width=500, visible=True))\n",
" results.append(gr.Textbox(label=f\"Synopsis\", value=description, max_lines=7, visible=True))\n",
" results.append(gr.Textbox(label=f\"Most Relevant User Review\",value=review, max_lines=7, visible=True))\n",
"\n",
" for _ in range(10-number_of_recommendations):\n",
" results.append(gr.Image(visible=False))\n",
" results.append(gr.Textbox(visible=False))\n",
" results.append(gr.Textbox(visible=False))\n",
" \n",
" return results"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7863\n",
"\n",
"To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"http://127.0.0.1:7863/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\Jose\\Desktop\\Nuanced_Recommendation_System\\.venv\\Lib\\site-packages\\gradio\\analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.44.1, however version 5.0.1 is available, please upgrade. \n",
"--------\n",
" warnings.warn(\n"
]
}
],
"source": [
"with gr.Blocks(theme=gr.themes.Soft(primary_hue='red')) as demo:\n",
" with gr.Row():\n",
" with gr.Column():\n",
" gr.Markdown(\n",
" '''\n",
" # Welcome to the Nuanced Recommendation System!\n",
" ### This system **combines** both objective (synopsis, episode count, themes) and subjective (user reviews) data, in order to recommend the most approprate anime. Feel free to refine using the **optional** filters below! \n",
" '''\n",
" )\n",
" with gr.Column():\n",
" pass\n",
" \n",
"\n",
" with gr.Row():\n",
" with gr.Column() as input_col:\n",
" query = gr.Textbox(label=\"What are you looking for?\")\n",
" number_of_recommendations = gr.Slider(label= \"# of Recommendations\", minimum=1, maximum=10, value=3, step=1)\n",
" genres = gr.Dropdown(label='Genres',multiselect=True,choices=filters['genres'], value=['ALL'])\n",
" themes = gr.Dropdown(label='Themes',multiselect=True,choices=filters['themes'], value=['ALL'])\n",
" rating = gr.Dropdown(label='Rating',multiselect=True,choices=filters['rating'], value=['ALL'])\n",
" objective_weight = gr.Slider(label= \"Objective Weight\", minimum=0, maximum=1, value=.5, step=.1)\n",
" subjective_weight = gr.Slider(label= \"Subjective Weight\", minimum=0, maximum=1, value=.5, step=.1)\n",
" submit_btn = gr.Button(\"Submit\")\n",
"\n",
" examples = gr.Examples(\n",
" examples=[\n",
" ['A sci-fi anime set in a future where AI and robots have become self-aware', 3, ['Action', 'Sci-Fi', 'Fantasy'], ['ALL'], ['PG-13 - Teens 13 or older'], .8, .2],\n",
" ['An anime where a group of students form a band, and the story focuses on their personal growth and struggles with adulthood', 5, ['ALL'], ['Music'], ['PG-13 - Teens 13 or older', 'R - 17+ (violence & profanity)'], .3, .7],\n",
" ['An anime where the main character starts as a villain but slowly redeems themselves', 3, ['Suspense', 'Action'], ['ALL'], ['PG-13 - Teens 13 or older', 'R - 17+ (violence & profanity)'], .2, .8],\n",
" ],\n",
" inputs=[query, number_of_recommendations, genres, themes, rating, objective_weight, subjective_weight],\n",
" )\n",
"\n",
" outputs = []\n",
" with gr.Column():\n",
" for i in range(10):\n",
" with gr.Row():\n",
" with gr.Column():\n",
" outputs.append(gr.Image(height=435, width=500, visible=False))\n",
" with gr.Column():\n",
" outputs.append(gr.Textbox(max_lines=7, visible=False))\n",
" outputs.append(gr.Textbox(max_lines=7, visible=False))\n",
" \n",
"\n",
" submit_btn.click(\n",
" get_recommendation,\n",
" [query, number_of_recommendations, genres, themes, rating, objective_weight, subjective_weight],\n",
" outputs\n",
" )\n",
"\n",
" demo.launch()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"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": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|