File size: 6,438 Bytes
830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a 0e43e41 830ee7a |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'c:\\\\Users\\\\nikhil\\\\OneDrive\\\\Desktop\\\\ML Projects\\\\ipp\\\\research'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%pwd"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"os.chdir(\"../\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'c:\\\\Users\\\\nikhil\\\\OneDrive\\\\Desktop\\\\ML Projects\\\\ipp'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%pwd"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"from dataclasses import dataclass\n",
"from pathlib import Path\n",
"\n",
"@dataclass(frozen=True)\n",
"class DataIngestionConfig:\n",
" root_dir: Path\n",
" source_URL: str\n",
" local_data_file: Path\n",
" train_data_file: Path\n",
" test_data_file: Path"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"\n",
"from insurancePP.constants import *\n",
"from insurancePP.utils.common import read_yaml, create_directories"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"class ConfigurationManager:\n",
" def __init__(self, config_filepath= CONFIG_FILE_PATH, params_filepath= PARAMS_FILE_PATH):\n",
" self.config = read_yaml(config_filepath)\n",
" self.params = read_yaml(params_filepath)\n",
" \n",
" create_directories([self.config.artifacts_root])\n",
" # logger.info(f\"Root directory {self.config.artifacts_root} created successfully\") \n",
" \n",
" \n",
" def get_data_ingestion_config(self) -> DataIngestionConfig:\n",
" config = self.config.data_ingestion\n",
" create_directories([config.root_dir])\n",
"\n",
" data_ingestion_config = DataIngestionConfig(\n",
" root_dir = config.root_dir,\n",
" source_URL = config.source_URL,\n",
" local_data_file = config.local_data_file,\n",
" train_data_file = config.train_data_file,\n",
" test_data_file = config.test_data_file\n",
" )\n",
"\n",
" return data_ingestion_config"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import urllib.request as request\n",
"import zipfile\n",
"import pandas as pd\n",
"from insurancePP.logging import logger\n",
"from insurancePP.utils.common import get_size\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"class DataIngestion:\n",
" def __init__(self, config: DataIngestionConfig):\n",
" self.config = config\n",
"\n",
" def download_file(self):\n",
" if not os.path.exists(self.config.local_data_file):\n",
" filename, headers = request.urlretrieve(\n",
" url = self.config.source_URL,\n",
" filename = self.config.local_data_file\n",
" )\n",
" logger.info(f'Downloaded {filename} to {self.config.local_data_file}')\n",
" else:\n",
" logger.info(f'File {self.config.local_data_file} already exists')\n",
"\n",
"\n",
" def initiate_data_ingestion(self):\n",
" logger.info(\"Entered inside the data ingestion component\")\n",
"\n",
" try:\n",
" data = pd.read_csv(self.config.local_data_file)\n",
" logger.info(\"train test split initiated\")\n",
"\n",
" train, test = train_test_split(data, test_size=0.2, random_state=50)\n",
" train.to_csv(self.config.train_data_file)\n",
" test.to_csv(self.config.test_data_file)\n",
" except Exception as e:\n",
" raise e\n"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-02-25 12:08:14,157 : INFO : common : yaml file: config\\config.yaml loaded successfully]\n",
"[2024-02-25 12:08:14,161 : INFO : common : yaml file: params.yaml loaded successfully]\n",
"[2024-02-25 12:08:14,164 : INFO : common : directory artifacts created]\n",
"[2024-02-25 12:08:14,166 : INFO : common : directory artifacts/data_ingestion created]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-02-25 12:08:15,563 : INFO : 489743891 : Downloaded artifacts/data_ingestion/data.csv to artifacts/data_ingestion/data.csv]\n",
"[2024-02-25 12:08:15,563 : INFO : 489743891 : Entered inside the data ingestion component]\n",
"[2024-02-25 12:08:15,592 : INFO : 489743891 : train test split initiated]\n"
]
}
],
"source": [
"try:\n",
" config = ConfigurationManager()\n",
" data_ingestion_config = config.get_data_ingestion_config()\n",
" data_ingestion = DataIngestion(data_ingestion_config)\n",
" data_ingestion.download_file()\n",
" data_ingestion.initiate_data_ingestion()\n",
"\n",
"except Exception as e:\n",
" raise e"
]
}
],
"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": "0.0.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|