feat(data-tools): Add dbstats.ipynb and .gitignore files

- Added dbstats.ipynb file to perform database queries and data processing
- Created a .gitignore file to exclude the 'data/' directory from version control

wowskarma_data_tools/.gitignore

@@ -0,0 +1 @@
+data/

wowskarma_data_tools/dbstats.ipynb

@@ -0,0 +1,192 @@
+{
+ "cells": [
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": "region = 'eu'",
+   "id": "bcac0e82dd6465d8",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {
+    "SqlCellData": {
+     "data_source_name": "[email protected]",
+     "variableName$1": "df_players"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "%%sql\n",
+    "/* SQL: Import players from database */\n",
+    "SELECT * FROM \"Players\""
+   ],
+   "id": "dd6907f7abb39669",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {
+    "SqlCellData": {
+     "data_source_name": "[email protected]",
+     "variableName$1": "df_posts"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "%%sql\n",
+    "/* SQL: Import posts from database */\n",
+    "SELECT * FROM \"Posts\""
+   ],
+   "id": "336f355903439be5",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "# Importing the libraries\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd"
+   ],
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "# Posts: The Flairs column is actually a bitfield, so we need to convert it to a list of flairs :\n",
+    "# Neutral=0\n",
+    "# Perfomance: Good=1 Bad=2\n",
+    "# Teamplay: Good=4 Bad=8\n",
+    "# Courtessy: Good=16 Bad=32\n",
+    "\n",
+    "# We will use the following function to convert the flairs bitfield into a series of nullable booleans\n",
+    "class PostFlairs:\n",
+    "    Neutral = 0x00\n",
+    "    PerformanceGood = 0x01\n",
+    "    PerformanceBad = 0x02\n",
+    "    TeamplayGood = 0x04\n",
+    "    TeamplayBad = 0x08\n",
+    "    CourtesyGood = 0x10\n",
+    "    CourtesyBad = 0x20\n",
+    "\n",
+    "def flairs_to_maskvalue(flairs, neg_mask, pos_mask):\n",
+    "    flairs_bit = bin(flairs)\n",
+    "        \n",
+    "    if flairs is None or 0: return 'neutral'\n",
+    "    elif flairs & pos_mask != 0: return 'positive'\n",
+    "    elif flairs & neg_mask != 0: return 'negative'\n",
+    "    else: return 'neutral'\n",
+    "\n",
+    "def flairs_to_list(flairs):\n",
+    "    return [\n",
+    "        flairs_to_maskvalue(flairs, PostFlairs.PerformanceBad, PostFlairs.PerformanceGood), # Performance\n",
+    "        flairs_to_maskvalue(flairs, PostFlairs.TeamplayBad, PostFlairs.TeamplayGood), # Teamplay\n",
+    "        flairs_to_maskvalue(flairs, PostFlairs.CourtesyBad, PostFlairs.CourtesyGood) # Courtesy\n",
+    "    ]"
+   ],
+   "id": "fdbeb06bdfd97c4d",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "# Process flairs and add each property to the dataframe\n",
+    "df_posts_flairs = df_posts.copy()\n",
+    "[df_posts_flairs['Performance'], df_posts_flairs['Teamplay'], df_posts_flairs['Courtesy']] = zip(*df_posts_flairs['Flairs'].apply(flairs_to_list))"
+   ],
+   "id": "28207ecdd331f213",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": "df_posts_flairs",
+   "id": "d7300e72dc20fd37",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "# Define the post type as a median of the flairs : Negative gives -1, Neutral gives 0, Positive gives 1.\n",
+    "# The post type is determined as greater, lesser, or equal to 0, which gives us respectively the following types : Positive, Negative, Neutral\n",
+    "def flairs_to_type(metrics):\n",
+    "    balance = 0\n",
+    "    \n",
+    "    for metric in metrics:\n",
+    "        if metric == 'positive' : balance += 1\n",
+    "        elif metric == 'negative': balance -= 1\n",
+    "    \n",
+    "    return 'positive' if balance > 0 \\\n",
+    "        else 'negative' if balance < 0 \\\n",
+    "        else 'neutral'"
+   ],
+   "id": "efccd08d5b98a45f",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "# Process flairs and add the post type to the dataframe\n",
+    "df_posts_flairs['Type'] = df_posts_flairs[['Performance', 'Teamplay', 'Courtesy']].apply(flairs_to_type, axis=1)"
+   ],
+   "id": "302b5eff474e7d17",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": "df_posts_flairs",
+   "id": "baf9c9bd66f630e2",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "# Export the dataframe to a JSON file\n",
+    "df_posts_flairs.to_json(f'data/{region}_posts.json', indent=1, orient='records')"
+   ],
+   "id": "5c61f8949161b427",
+   "outputs": [],
+   "execution_count": null
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}