{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "fad722b3-d528-45d0-b3b3-4f829a4f51f6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(50425, 2)\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df= pd.read_csv(\"ecommerce_dataset.csv\", names=[\"category\", \"description\"], header=None)\n",
    "print(df.shape)\n",
    "df.head(3)\n",
    "\n",
    "df.dropna(inplace=True)\n",
    "df.shape\n",
    "df.category.unique()\n",
    "\n",
    "df[\"category\"] = df[\"category\"].replace(\"Clothing & Accessories\", \"Clothing_Accessories\")\n",
    "\n",
    "df.category.unique()\n",
    "\n",
    "df['category'] = '__label__' + df['category'].astype(str)\n",
    "df.head(5)\n",
    "\n",
    "df['category_description'] = df['category'] + ' ' + df['description']\n",
    "df.head(3)\n",
    "\n",
    "import re\n",
    "\n",
    "text = \"  VIKI's | Bookcase/Bookshelf (3-Shelf/Shelve, White) | ? . hi\"\n",
    "text = re.sub(r'[^\\w\\s\\']',' ', text)\n",
    "text = re.sub(' +', ' ', text)\n",
    "text.strip().lower()\n",
    "\n",
    "def preprocess(text):\n",
    "    text = re.sub(r'[^\\w\\s\\']',' ', text)\n",
    "    text = re.sub(' +', ' ', text)\n",
    "    return text.strip().lower() \n",
    "\n",
    "df['category_description'] = df['category_description'].map(preprocess)\n",
    "df.head()\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "train, test = train_test_split(df, test_size=0.2)\n",
    "train.shape, test.shape\n",
    "\n",
    "train.to_csv(\"ecommerce.train\", columns=[\"category_description\"], index=False, header=False)\n",
    "test.to_csv(\"ecommerce.test\", columns=[\"category_description\"], index=False, header=False)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f975e1e4-7857-49f8-8945-897e404ea7d2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import fasttext\n",
    "\n",
    "\n",
    "model = fasttext.train_supervised(\n",
    "    input=\"ecommerce.train\",\n",
    "    epoch=25,        # more training iterations\n",
    "    lr=1.0,          # learning rate\n",
    "    wordNgrams=2,    # include word n-grams\n",
    "    minn=2,          # enable subword info (handles typos/unseen words)\n",
    "    maxn=5,\n",
    "    minCount=1       # keep even rare words\n",
    ")\n",
    "\n",
    "\n",
    "print(model.test(\"ecommerce.test\"))\n",
    "\n",
    "# Predictions\n",
    "print(model.predict(\"wintech assemble desktop pc cpu 500 gb sata hdd 4 gb ram intel c2d processor 3\"))\n",
    "print(model.predict(\"ockey men's cotton t shirt fabric details 80 cotton 20 polyester super combed cotton rich fabric\"))\n",
    "print(model.predict(\"think and grow rich deluxe edition\"))\n",
    "\n",
    "\n",
    "print(model.get_nearest_neighbors(\"painting\"))\n",
    "print(model.get_nearest_neighbors(\"sony\"))\n",
    "print(model.get_nearest_neighbors(\"bangalore\"))   \n",
    "print(model.get_nearest_neighbors(\"banglore\"))   \n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dc0f66d8-0a4a-4d1a-a36f-fb8e0af1c7ea",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}