add fugue and duckdb

productive_tools/Fugue_and_Duckdb/preprocessing.ipynb

@@ -0,0 +1,73 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5262523c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import glob"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "46a4838c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def process_files():\n",
+    "    filenames = glob.glob(\"crypto-binance/*/*/\" + \"*.csv\")\n",
+    "    dfs = []\n",
+    "    for filename in filenames:\n",
+    "        df = pd.read_csv(filename)\n",
+    "        df['symbol'] = filename.split('/')[-1].split('.')[0]\n",
+    "        df['time'] = pd.to_datetime(df['Open_time'], unit='ms')\n",
+    "        df = df.drop(['Open_time'], axis=1)\n",
+    "        dfs.append(df)\n",
+    "\n",
+    "    # Concatenate all data into one DataFrame\n",
+    "    big_frame = pd.concat(dfs, ignore_index=True)\n",
+    "    big_frame.to_parquet(\"raw.parquet\")\n",
+    "    \n",
+    "process_files()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.8.10"
+  },
+  "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": 5
+}