diff --git a/content_based.ipynb b/content_based.ipynb
index e2c880307e714ff3b9290d78752c3d12b709a239..0b8b6361aa101788dabd8ed147de7315de551f2f 100644
--- a/content_based.ipynb
+++ b/content_based.ipynb
@@ -10,19 +10,10 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 1,
"id": "277473a3",
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The autoreload extension is already loaded. To reload it, use:\n",
- " %reload_ext autoreload\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
@@ -40,7 +31,13 @@
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.ensemble import GradientBoostingRegressor, RandomForestRegressor\n",
"from sklearn.svm import SVR\n",
- "from sklearn.feature_extraction.text import TfidfVectorizer"
+ "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+ "from sklearn.linear_model import Lasso, Ridge, ElasticNet\n",
+ "from sklearn.neighbors import KNeighborsRegressor\n",
+ "from sklearn.tree import DecisionTreeRegressor\n",
+ "from sklearn.ensemble import AdaBoostRegressor\n",
+ "from xgboost import XGBRegressor\n",
+ "from lightgbm import LGBMRegressor"
]
},
{
@@ -53,26 +50,89 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 2,
"id": "e8378976",
"metadata": {},
"outputs": [
{
- "ename": "FileNotFoundError",
- "evalue": "[Errno 2] No such file or directory: 'data/test/content/movies.csv'",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[16], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# All the dataframes\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m df_items \u001b[38;5;241m=\u001b[39m \u001b[43mload_items\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m df_ratings \u001b[38;5;241m=\u001b[39m load_ratings()\n\u001b[1;32m 4\u001b[0m df_tag \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(C\u001b[38;5;241m.\u001b[39mCONTENT_PATH\u001b[38;5;241m/\u001b[39mC\u001b[38;5;241m.\u001b[39mTAGS_FILENAME)\n",
- "File \u001b[0;32m~/Desktop/UniversiteÌ/Recommender Systems/recomsys/loaders.py:34\u001b[0m, in \u001b[0;36mload_items\u001b[0;34m()\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mload_items\u001b[39m():\n\u001b[1;32m 29\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Loads items data.\u001b[39;00m\n\u001b[1;32m 30\u001b[0m \n\u001b[1;32m 31\u001b[0m \u001b[38;5;124;03m Returns:\u001b[39;00m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;124;03m DataFrame: Items data.\u001b[39;00m\n\u001b[1;32m 33\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m---> 34\u001b[0m df_items \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mC\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCONTENT_PATH\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m/\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mC\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mITEMS_FILENAME\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# ce qui se trouve dans le movie csv\u001b[39;00m\n\u001b[1;32m 35\u001b[0m df_items \u001b[38;5;241m=\u001b[39m df_items\u001b[38;5;241m.\u001b[39mset_index(C\u001b[38;5;241m.\u001b[39mITEM_ID_COL) \u001b[38;5;66;03m# movie id\u001b[39;00m\n\u001b[1;32m 36\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m df_items\n",
- "File \u001b[0;32m~/.pyenv/versions/3.12.0/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m 1014\u001b[0m dialect,\n\u001b[1;32m 1015\u001b[0m delimiter,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1022\u001b[0m dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m 1023\u001b[0m )\n\u001b[1;32m 1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.pyenv/versions/3.12.0/lib/python3.12/site-packages/pandas/io/parsers/readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m 619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m 623\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
- "File \u001b[0;32m~/.pyenv/versions/3.12.0/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m 1617\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.pyenv/versions/3.12.0/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1880\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m 1878\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m mode:\n\u001b[1;32m 1879\u001b[0m mode \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m-> 1880\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;241m=\u001b[39m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1881\u001b[0m \u001b[43m \u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1882\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1883\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1884\u001b[0m \u001b[43m \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcompression\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1885\u001b[0m \u001b[43m \u001b[49m\u001b[43mmemory_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmemory_map\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1886\u001b[0m \u001b[43m \u001b[49m\u001b[43mis_text\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_text\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1887\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoding_errors\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstrict\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1888\u001b[0m \u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstorage_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1889\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1890\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1891\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles\u001b[38;5;241m.\u001b[39mhandle\n",
- "File \u001b[0;32m~/.pyenv/versions/3.12.0/lib/python3.12/site-packages/pandas/io/common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m 868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 869\u001b[0m \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[1;32m 870\u001b[0m \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[1;32m 871\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[1;32m 872\u001b[0m \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[0;32m--> 873\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 874\u001b[0m \u001b[43m \u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 875\u001b[0m \u001b[43m \u001b[49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 876\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mioargs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 877\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 878\u001b[0m \u001b[43m \u001b[49m\u001b[43mnewline\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 879\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 880\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 881\u001b[0m \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[1;32m 882\u001b[0m handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
- "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'data/test/content/movies.csv'"
- ]
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>n_character_title</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>movieId</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>4993</th>\n",
+ " <td>57</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5952</th>\n",
+ " <td>45</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>527</th>\n",
+ " <td>23</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2028</th>\n",
+ " <td>26</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4308</th>\n",
+ " <td>19</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " n_character_title\n",
+ "movieId \n",
+ "4993 57\n",
+ "5952 45\n",
+ "527 23\n",
+ "2028 26\n",
+ "4308 19"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/plain": [
+ "0 long\n",
+ "1 boring\n",
+ "2 long\n",
+ "3 romance\n",
+ "4 stupidity\n",
+ "Name: tag, dtype: object"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
}
],
"source": [
@@ -106,26 +166,20 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"id": "16b0a602",
"metadata": {},
"outputs": [
{
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "0\n",
- "1\n",
- "2\n",
- "3\n",
- "4\n",
- "5\n",
- "None\n",
- "{'n_character_title': array([0.03019692])}\n",
- "{'n_character_title': array([0.04098154])}\n",
- "{'n_character_title': array([0.02942264])}\n",
- "{'n_character_title': array([0.08196307])}\n",
- "{'n_character_title': array([0.02798739])}\n"
+ "ename": "NameError",
+ "evalue": "name 'Lasso' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[3], line 147\u001b[0m\n\u001b[1;32m 145\u001b[0m trainset \u001b[38;5;241m=\u001b[39m surprise_data\u001b[38;5;241m.\u001b[39mbuild_full_trainset()\n\u001b[1;32m 146\u001b[0m testset \u001b[38;5;241m=\u001b[39m trainset\u001b[38;5;241m.\u001b[39mbuild_anti_testset()\n\u001b[0;32m--> 147\u001b[0m \u001b[43mcb\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtrainset\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 150\u001b[0m \u001b[38;5;66;03m#print(\"RMSE: \", cb.rmse(testset))\u001b[39;00m\n\u001b[1;32m 151\u001b[0m \n\u001b[1;32m 152\u001b[0m \n\u001b[1;32m 153\u001b[0m \u001b[38;5;66;03m#Example explanations for users:\u001b[39;00m\n\u001b[1;32m 154\u001b[0m \u001b[38;5;28mprint\u001b[39m(cb\u001b[38;5;241m.\u001b[39mexplain(\u001b[38;5;241m11\u001b[39m))\n",
+ "Cell \u001b[0;32mIn[3], line 88\u001b[0m, in \u001b[0;36mContentBased.fit\u001b[0;34m(self, trainset)\u001b[0m\n\u001b[1;32m 80\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39muser_profile[u] \u001b[38;5;241m=\u001b[39m [rating \u001b[38;5;28;01mfor\u001b[39;00m (_, rating) \u001b[38;5;129;01min\u001b[39;00m trainset\u001b[38;5;241m.\u001b[39mur[u]]\n\u001b[1;32m 82\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 83\u001b[0m regressor_models \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m 84\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlinear_regression\u001b[39m\u001b[38;5;124m'\u001b[39m: LinearRegression(fit_intercept\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m),\n\u001b[1;32m 85\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msvr_regression\u001b[39m\u001b[38;5;124m'\u001b[39m: SVR(kernel\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrbf\u001b[39m\u001b[38;5;124m'\u001b[39m, C\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m10\u001b[39m, epsilon\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.2\u001b[39m),\n\u001b[1;32m 86\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgradient_boosting\u001b[39m\u001b[38;5;124m'\u001b[39m: GradientBoostingRegressor(n_estimators\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m100\u001b[39m, learning_rate\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.1\u001b[39m, max_depth\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m3\u001b[39m),\n\u001b[1;32m 87\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrandom_forest\u001b[39m\u001b[38;5;124m'\u001b[39m: RandomForestRegressor(n_estimators\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m100\u001b[39m),\n\u001b[0;32m---> 88\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlasso_regression\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[43mLasso\u001b[49m(alpha\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.1\u001b[39m),\n\u001b[1;32m 89\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mridge_regression\u001b[39m\u001b[38;5;124m'\u001b[39m: Ridge(alpha\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.0\u001b[39m),\n\u001b[1;32m 90\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124melastic_net\u001b[39m\u001b[38;5;124m'\u001b[39m: ElasticNet(alpha\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.0\u001b[39m, l1_ratio\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.5\u001b[39m),\n\u001b[1;32m 91\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mknn_regression\u001b[39m\u001b[38;5;124m'\u001b[39m: KNeighborsRegressor(n_neighbors\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m),\n\u001b[1;32m 92\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdecision_tree\u001b[39m\u001b[38;5;124m'\u001b[39m: DecisionTreeRegressor(max_depth\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m),\n\u001b[1;32m 93\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124madaboost\u001b[39m\u001b[38;5;124m'\u001b[39m: AdaBoostRegressor(n_estimators\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m50\u001b[39m),\n\u001b[1;32m 94\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mxgboost\u001b[39m\u001b[38;5;124m'\u001b[39m: XGBRegressor(n_estimators\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m100\u001b[39m, learning_rate\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.1\u001b[39m, max_depth\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m3\u001b[39m),\n\u001b[1;32m 95\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlightgbm\u001b[39m\u001b[38;5;124m'\u001b[39m: LGBMRegressor(n_estimators\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m100\u001b[39m, learning_rate\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.1\u001b[39m, max_depth\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m3\u001b[39m)\n\u001b[1;32m 96\u001b[0m }\n\u001b[1;32m 98\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mregressor_method \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m regressor_models:\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mRegressor method \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mregressor_method\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m not yet implemented\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'Lasso' is not defined"
]
}
],
@@ -344,7 +398,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.12.0"
+ "version": "3.12.2"
}
},
"nbformat": 4,