move kaggle dataset into new folder structure (ourownstory#9)

SimonWittner · Dec 4, 2022 · c8676d1 · c8676d1
1 parent e1f5aab
commit c8676d1
Show file tree

Hide file tree

Showing 6 changed files with 87 additions and 391 deletions.
diff --git a/datasets/kaggle-energy/tutorial01.csv → kaggle-energy/datasets/tutorial01.csv b/datasets/kaggle-energy/tutorial01.csv → kaggle-energy/datasets/tutorial01.csv
diff --git a/datasets_raw/kaggle-energy/description.txt → kaggle-energy/description.txt b/datasets_raw/kaggle-energy/description.txt → kaggle-energy/description.txt
diff --git a/kaggle-energy/preprocessing/kaggle-energy-preprocessing.ipynb b/kaggle-energy/preprocessing/kaggle-energy-preprocessing.ipynb
@@ -0,0 +1,87 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"../datasets_raw/energy/kaggle-energy-consumption-generation/energy_dataset.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Select only the columns we need\n",
+    "df = df[[\"time\", \"price actual\"]]\n",
+    "\n",
+    "# Drop NaN values\n",
+    "df = df[[\"time\", \"price actual\"]].dropna()\n",
+    "\n",
+    "# Rename columns ds and y\n",
+    "df = df.rename(columns={\"time\": \"ds\", \"price actual\": \"y\"})\n",
+    "\n",
+    "# Convert to datetime\n",
+    "df[\"ds\"] = pd.to_datetime(df[\"ds\"], utc=True).dt.tz_localize(None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"../datasets/kaggle-energy/tutorial01.csv\", index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.10.8 64-bit",
+   "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": "3.10.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "949777d72b0d2535278d3dc13498b2535136f6dfe0678499012e853ee9abcab1"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/...sets_raw/kaggle-energy/energy_dataset.csv → ...le-energy/raw-datasets/energy_dataset.csv b/...sets_raw/kaggle-energy/energy_dataset.csv → ...le-energy/raw-datasets/energy_dataset.csv
diff --git a/...ts_raw/kaggle-energy/weather_features.csv → ...-energy/raw-datasets/weather_features.csv b/...ts_raw/kaggle-energy/weather_features.csv → ...-energy/raw-datasets/weather_features.csv