Velar/AI/train/training.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(\"transcations.csv\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a074a45e",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "df = df[['Description', 'Category']].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fe26b20f",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "df[['Description', 'Category']].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "44c3995d",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "df['Description'] = df['Description'].str.lower().str.replace('[^a-z\\s]', '', regex=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "82245456",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "df['Category'] = df['Category'].str.lower().str.replace('[^a-z\\s]', '', regex=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "620ef271",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X = df['Description']\n",
    "y = df['Category']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3eebf352",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "\n",
    "vectorizer = TfidfVectorizer()\n",
    "X_train_vec = vectorizer.fit_transform(X_train)\n",
    "X_test_vec = vectorizer.transform(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "75a141a8",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "\n",
    "model = MultinomialNB()\n",
    "model.fit(X_train_vec, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "184354db",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "def predict_category(text):\n",
    "    text = [text.lower()]\n",
    "    text_vec = vectorizer.transform(text)\n",
    "    return model.predict(text_vec)[0]\n",
    "\n",
    "# Example\n",
    "print(predict_category(\"Netflix\"))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c30b9f27",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "y_pred = model.predict(X_test_vec)\n",
    "print(classification_report(y_test, y_pred))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "109a12d5",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# Save model\n",
    "with open('model.pkl', 'wb') as f:\n",
    "    pickle.dump(model, f)\n",
    "\n",
    "# Save vectorizer\n",
    "with open('vectorizer.pkl', 'wb') as f:\n",
    "    pickle.dump(vectorizer, f)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bcb76b6a",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "import joblib\n",
    "\n",
    "joblib.dump(model, 'model.pkl')\n",
    "joblib.dump(vectorizer, 'vectorizer.pkl')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f16d6da5",
   "metadata": {
    "vscode": {
     "languageId": "plaintext"
    }
   },
   "outputs": [],
   "source": [
    "from google.colab import files\n",
    "files.download('model.pkl')\n",
    "files.download('vectorizer.pkl')\n"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}