Spaces:
Sleeping
Sleeping
File size: 9,217 Bytes
06d9388 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.2.1+cu121\n"
]
}
],
"source": [
"import sys\n",
"\n",
"sys.path.insert(0, \"./interactive_tutorials\")\n",
"\n",
"import pandas as pd\n",
"from tqdm import tqdm\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import itertools\n",
"import requests\n",
"import sys\n",
"\n",
"import torch\n",
"import torch.nn.functional as F\n",
"from torch.nn import Linear\n",
"import torch_geometric.transforms as T\n",
"from torch_geometric.nn import SAGEConv, to_hetero\n",
"from torch_geometric.transforms import RandomLinkSplit, ToUndirected\n",
"from sentence_transformers import SentenceTransformer\n",
"from torch_geometric.data import HeteroData\n",
"import yaml\n",
"\n",
"print(torch.__version__)\n",
"\n",
"\n",
"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{('user',\n",
" 'rates',\n",
" 'movie'): tensor([[ 0, 0, 0, ..., 670, 670, 670],\n",
" [ 0, 1, 2, ..., 1327, 1329, 2941]], device='cuda:0'),\n",
" ('movie',\n",
" 'rev_rates',\n",
" 'user'): tensor([[ 0, 1, 2, ..., 1327, 1329, 2941],\n",
" [ 0, 0, 0, ..., 670, 670, 670]], device='cuda:0')}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data = torch.load(\"./PyGdata.pt\")\n",
"data.edge_index_dict\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{('user',\n",
" 'rates',\n",
" 'movie'): tensor([[ 0, 0, 0, ..., 670, 670, 670],\n",
" [ 0, 1, 2, ..., 1327, 1329, 2941]], device='cuda:0'),\n",
" ('movie',\n",
" 'rev_rates',\n",
" 'user'): tensor([[ 0, 1, 2, ..., 1327, 1329, 2941],\n",
" [ 0, 0, 0, ..., 670, 670, 670]], device='cuda:0')}"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"class GNNEncoder(torch.nn.Module):\n",
" def __init__(self, hidden_channels, out_channels):\n",
" super().__init__()\n",
" # these convolutions have been replicated to match the number of edge types\n",
" self.conv1 = SAGEConv((-1, -1), hidden_channels)\n",
" self.conv2 = SAGEConv((-1, -1), out_channels)\n",
"\n",
" def forward(self, x, edge_index):\n",
" x = self.conv1(x, edge_index).relu()\n",
" x = self.conv2(x, edge_index)\n",
" return x\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"class EdgeDecoder(torch.nn.Module):\n",
" def __init__(self, hidden_channels):\n",
" super().__init__()\n",
" self.lin1 = Linear(2 * hidden_channels, hidden_channels)\n",
" self.lin2 = Linear(hidden_channels, 1)\n",
"\n",
" def forward(self, z_dict, edge_label_index):\n",
" row, col = edge_label_index\n",
" # concat user and movie embeddings\n",
" z = torch.cat([z_dict['user'][row], z_dict['movie'][col]], dim=-1)\n",
" # concatenated embeddings passed to linear layer\n",
" z = self.lin1(z).relu()\n",
" z = self.lin2(z)\n",
" return z.view(-1)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"class Model(torch.nn.Module):\n",
" def __init__(self, hidden_channels):\n",
" super().__init__()\n",
" self.encoder = GNNEncoder(hidden_channels, hidden_channels)\n",
" self.encoder = to_hetero(self.encoder, data.metadata(), aggr='sum')\n",
" self.decoder = EdgeDecoder(hidden_channels)\n",
"\n",
" def forward(self, x_dict, edge_index_dict, edge_label_index):\n",
" # z_dict contains dictionary of movie and user embeddings returned from GraphSage\n",
" z_dict = self.encoder(x_dict, edge_index_dict)\n",
" return self.decoder(z_dict, edge_label_index)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"HeteroData(\n",
" user={ x=[671, 671] },\n",
" movie={ x=[9025, 404] },\n",
" (user, rates, movie)={\n",
" edge_index=[2, 99810],\n",
" edge_label=[99810],\n",
" },\n",
" (movie, rev_rates, user)={ edge_index=[2, 99810] }\n",
")\n"
]
}
],
"source": [
"model = Model(hidden_channels=32).to(device)\n",
"model2 = Model(hidden_channels=32).to(device)\n",
"model.load_state_dict(torch.load(\"PyGTrainedModelState.pt\"))\n",
"model.eval()\n",
"\n",
"total_users = data['user'].num_nodes \n",
"total_movies = data['movie'].num_nodes \n",
"print(data)\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 671/671 [00:05<00:00, 121.64it/s]\n"
]
}
],
"source": [
"movie_recs = []\n",
"for user_id in tqdm(range(0, total_users)):\n",
" user_row = torch.tensor([user_id] * total_movies)\n",
" all_movie_ids = torch.arange(total_movies)\n",
" edge_label_index = torch.stack([user_row, all_movie_ids], dim=0)\n",
" pred = model(data.x_dict, data.edge_index_dict,\n",
" edge_label_index)\n",
" pred = pred.clamp(min=0, max=5)\n",
" # we will only select movies for the user where the predicting rating is =5\n",
" rec_movie_ids = (pred == 5).nonzero(as_tuple=True)\n",
" top_ten_recs = [rec_movies for rec_movies in rec_movie_ids[0].tolist()[:10]]\n",
" movie_recs.append({'user': user_id, 'rec_movies': top_ten_recs})"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Movie not found\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\aj\\AppData\\Local\\Temp\\ipykernel_24552\\778055959.py:2: DtypeWarning: Columns (10) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df = pd.read_csv(metadata_path)\n"
]
}
],
"source": [
"metadata_path = './sampled_movie_dataset/movies_metadata.csv'\n",
"df = pd.read_csv(metadata_path)\n",
"df.columns\n",
"\n",
"def get_movie_title(movie_id):\n",
" \"\"\"Looks up a movie title by its ID in the DataFrame.\"\"\"\n",
"\n",
" row = df[df['id'] == movie_id]\n",
"\n",
" if not row.empty:\n",
" return row['title'].iloc[0] # Get the title from the first matching row\n",
" else:\n",
" return \"Movie not found\"\n",
" \n",
"print(get_movie_title(14))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" user rec_movies\n",
"0 0 [14, 85, 101, 106, 111, 131, 132, 150, 210, 216]\n",
"1 1 [13, 45, 95, 108, 109, 126, 130, 132, 213, 220]\n",
"2 2 [562, 571, 894, 1013, 1169, 1289, 1378, 1405, ...\n",
"3 3 [126, 137, 502, 571, 616, 696, 811, 966, 999, ...\n",
"4 4 [364, 436, 493, 502, 509, 706, 781, 811, 1244,...\n",
"Index(['user', 'rec_movies'], dtype='object')\n"
]
}
],
"source": [
"\n",
"movie_recs_df = pd.DataFrame(movie_recs)\n",
"#movie_recs_df = movie_recs_df.set_index('id').join(df[['title']].set_index('id'), how='left')\n",
"print(movie_recs_df.head()) \n",
"print(movie_recs_df.columns) "
]
}
],
"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": "3.12.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|