{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "os.chdir(\"../\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'c:\\\\MLOps\\\\CICD\\\\End-to-End-ML'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dataclasses import dataclass\n",
    "from pathlib import Path\n",
    "\n",
    "@dataclass(frozen=True)\n",
    "class DataTransformationConfig:\n",
    "    root_dir: Path\n",
    "    data_path:Path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "from mlProject.constants import *\n",
    "from mlProject.utils.common import read_yaml, create_directories "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "class ConfigurationManager:\n",
    "    def __init__(\n",
    "       self, \n",
    "       config_filepath=CONFIG_FILE_PATH,\n",
    "       params_filepath=PARAMS_FILE_PATH,\n",
    "       schema_filepath=SCHEMA_FILE_PATH):     \n",
    "       \n",
    "       self.config=read_yaml(config_filepath)\n",
    "    #    self.params=read_yaml(params_filepath)\n",
    "       self.schema=read_yaml(schema_filepath)\n",
    "       create_directories([self.config.artifacts_root])\n",
    "\n",
    "    def get_transformation_config(self)->DataTransformationConfig:\n",
    "        config=self.config.data_transformation\n",
    "        create_directories([config.root_dir])\n",
    "\n",
    "        # create an object by initialization\n",
    "        data_transformation_config=DataTransformationConfig(\n",
    "            root_dir=config.root_dir,\n",
    "            data_path=config.data_path\n",
    "        )\n",
    "\n",
    "        return data_transformation_config          \n",
    "    \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from mlProject import logger\n",
    "from sklearn.model_selection import train_test_split\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "class DataTransformation:\n",
    "    def __init__(self, config: DataTransformationConfig):\n",
    "        self.config=config\n",
    "\n",
    "    def train_test_splitting(self):\n",
    "        data=pd.read_csv(self.config.data_path)\n",
    "        data.drop(['Unnamed: 0','RowNumber'], axis=1, inplace=True)\n",
    "        data.set_index('CustomerId', inplace=True)\n",
    "        train,test=train_test_split(data)\n",
    "\n",
    "        train.to_csv( os.path.join(self.config.root_dir,\"train.csv\"), index=True)\n",
    "        test.to_csv(os.path.join(self.config.root_dir, \"test.csv\"), index=True)\n",
    "\n",
    "        logger.info(\"Splitted data into training and the test sets\")\n",
    "        logger.info(train.shape)\n",
    "        logger.info(test.shape)\n",
    "\n",
    "        print(f\"Train Shape :{train.shape}\")\n",
    "        print(f\"Test Shape :{test.shape}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2024-03-10 17:28:06,122:INFO:common: yaml file: config\\config.yaml loaded successfully]\n",
      "[2024-03-10 17:28:06,129:INFO:common: yaml file: schema.yaml loaded successfully]\n",
      "[2024-03-10 17:28:06,129:INFO:common: created directory at: artifacts]\n",
      "[2024-03-10 17:28:06,137:INFO:common: created directory at: artifacts/data_transformation]\n",
      "[2024-03-10 17:28:06,226:INFO:3354807181: Splitted data into training and the test sets]\n",
      "[2024-03-10 17:28:06,226:INFO:3354807181: (7500, 12)]\n",
      "[2024-03-10 17:28:06,234:INFO:3354807181: (2500, 12)]\n",
      "Train Shape :(7500, 12)\n",
      "Test Shape :(2500, 12)\n"
     ]
    }
   ],
   "source": [
    "config=ConfigurationManager()\n",
    "data_transformation_config=config.get_transformation_config()\n",
    "data_transformation=DataTransformation(config=data_transformation_config)\n",
    "data_transformation.train_test_splitting()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_e2eml",
   "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": "3.8.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}