Spaces:
Runtime error
Runtime error
File size: 5,974 Bytes
a0f1e38 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.chdir('../')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'c:\\\\mlops project\\\\image-colorization-mlops'"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%pwd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"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_dir : Path\n",
" local_data_file: Path\n",
" unzip_dir : Path"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from src.imagecolorization.constants import *\n",
"from src.imagecolorization.utils.common import read_yaml, create_directories\n",
"\n",
"class ConfigurationManager:\n",
" def __init__(\n",
" self,\n",
" config_filepath = CONFIG_FILE_PATH,\n",
" params_filepath = PARAMS_FILE_PATH):\n",
"\n",
" self.config = read_yaml(config_filepath)\n",
" self.params = read_yaml(params_filepath)\n",
"\n",
" create_directories([self.config.artifacts_root])\n",
"\n",
" \n",
"\n",
" def get_data_ingestion_config(self) -> DataIngestionConfig:\n",
" config = self.config.data_ingestion\n",
"\n",
" create_directories([config.root_dir])\n",
"\n",
" data_ingestion_config = DataIngestionConfig(\n",
" root_dir=config.root_dir,\n",
" source_dir=config.source_dir,\n",
" local_data_file=config.local_data_file,\n",
" unzip_dir=config.unzip_dir \n",
" )\n",
"\n",
" return data_ingestion_config\n",
" \n",
" \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import zipfile\n",
"from src.imagecolorization.logging import logger\n",
"from tqdm.notebook import tqdm\n",
"from dataclasses import replace\n",
"\n",
"class DataIngestion:\n",
" def __init__(self, config: DataIngestionConfig):\n",
" self.config = config\n",
" \n",
" def load_file(self):\n",
" if os.path.exists(self.config.source_dir):\n",
" self.config = replace(self.config, local_data_file=self.config.source_dir)\n",
" logger.info(f'File Found at: {self.config.local_data_file}')\n",
" else:\n",
" logger.info(f\"File not found at {self.config.source_dir}\")\n",
" raise FileNotFoundError(f'No file found at {self.config.source_dir}')\n",
" \n",
" \n",
" \n",
" def extract_zip_file(self):\n",
" unzip_path = self.config.unzip_dir\n",
" os.makedirs(unzip_path, exist_ok=True)\n",
" \n",
" # open the zip file\n",
" with zipfile.ZipFile(self.config.local_data_file, 'r') as zip_ref:\n",
" total_files = len(zip_ref.infolist())\n",
" \n",
" for file in tqdm(iterable=zip_ref.infolist(), total=total_files, desc='Extracting files'):\n",
" zip_ref.extract(member=file, path=unzip_path)\n",
" \n",
" logger.info(f'Extacted {self.config.local_data_file} to {unzip_path}')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-08-18 02:08:07,443: INFO: common: yaml file: config\\config.yaml loaded successfully]\n",
"[2024-08-18 02:08:07,444: INFO: common: yaml file: params.yaml loaded successfully]\n",
"[2024-08-18 02:08:07,445: INFO: common: created directory at: artifacts]\n",
"[2024-08-18 02:08:07,446: INFO: common: created directory at: artifacts/data_ingestion]\n",
"[2024-08-18 02:08:07,446: INFO: 2749353352: File Found at: C:\\\\mlops project\\\\archive.zip]\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b91326c533ac4f588a5224910549cd65",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Extracting files: 0%| | 0/5 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2024-08-18 02:08:34,311: INFO: 2749353352: Extacted C:\\\\mlops project\\\\archive.zip to artifacts/data_ingestion]\n"
]
}
],
"source": [
"try:\n",
" config = ConfigurationManager()\n",
" data_ingestion_config = config.get_data_ingestion_config()\n",
" data_ingestion = DataIngestion(config=data_ingestion_config)\n",
" data_ingestion.load_file()\n",
" data_ingestion.extract_zip_file()\n",
"except Exception as e:\n",
" raise e"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.11.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|