parser notebook

notebooks/parse_all.ipynb

@@ -0,0 +1,211 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-02-14T15:33:38.550994Z",
+     "start_time": "2020-02-14T15:33:36.901949Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "import glob\n",
+    "from tqdm import tqdm_notebook as tqdm\n",
+    "from itertools import chain\n",
+    "import sys\n",
+    "sys.path.append(r'C:\\Users\\shossein\\Documents\\personal\\research\\VisualFeatureFull')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-02-14T15:33:38.567949Z",
+     "start_time": "2020-02-14T15:33:38.552978Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<module 'src.parser.base' from 'C:\\\\Users\\\\shossein\\\\Documents\\\\personal\\\\research\\\\VisualFeatureFull\\\\src\\\\parser\\\\base.py'>"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from src.parser import base \n",
+    "import importlib\n",
+    "importlib.reload(base)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-02-14T15:33:38.573950Z",
+     "start_time": "2020-02-14T15:33:38.568947Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "hdf_store_path = 'hdf.hf'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-02-14T15:33:38.581945Z",
+     "start_time": "2020-02-14T15:33:38.577950Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "str_data_folder = r'C:\\Users\\shossein\\Documents\\personal\\research\\data\\ew'\n",
+    "str_faces = 'rek-exp-cluster6\\p1\\output\\cluster6\\p1\\000112473\\faces'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2020-02-14T15:33:36.913Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "l_faces_json = glob.glob(os.path.join(str_data_folder, '*', '*', '*', '*', '*', '*', 'faces', '*.json'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2020-02-14T15:33:36.918Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "42b93c427f78417bb133db94d832523f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=142651), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "hdf = pd.HDFStore(hdf_store_path, 'a')\n",
+    "\n",
+    "base.parse_jsons(l_faces_json, hdf, 50, 'faces')\n",
+    "\n",
+    "hdf.flush()\n",
+    "hdf.close()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2020-02-14T15:33:36.920Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "l_labels_json = glob.glob(os.path.join(str_data_folder, '*', '*', '*', '*', '*', '*', 'labels', '*.json'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2020-02-14T15:33:36.925Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "hdf = pd.HDFStore(hdf_store_path, 'a')\n",
+    "\n",
+    "base.parse_jsons(l_labels_json, hdf, 50, 'labels')\n",
+    "\n",
+    "hdf.flush()\n",
+    "hdf.close()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "ExecuteTime": {
+     "start_time": "2020-02-14T15:33:36.930Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "hdf = pd.HDFStore(hdf_store_path, 'a')\n",
+    "\n",
+    "base.parse_jsons(l_celeb_json, hdf, 50, 'celebrity')\n",
+    "\n",
+    "hdf.flush()\n",
+    "hdf.close()\n"
+   ]
+  }
+ ],
+ "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": "3.7.1"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}