Files
Mining-Away/jupyter-notes/Panda Bamboo.ipynb
2023-03-28 11:23:05 +02:00

175 lines
3.5 KiB
Plaintext

{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pandas Crash Course\n",
"As usual, documenting what is being used from pandas here ig\n",
"\n",
"Docs:\n",
"- https://pandas.pydata.org/docs/getting_started/index.html#getting-started"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Cleaning Game/Score/Rating Dataset\n",
"Error found: Game Names had Reviews attached to them"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Game Datasets"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from tkinter.filedialog import askopenfilename\n",
"filename = askopenfilename()\n",
"df1= pd.read_csv(filename)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"### Cleaning: Removing the word review and anything after it"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Unclean showcase\n",
"unclean = df1\n",
"#limit this output 3 rows pls\n",
"print(unclean[['GameName']].head(5))\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# CLeaning\n",
"nuke=df1['GameName'].to_list()\n",
"nuke2 = list()\n",
"\n",
"for orphan in nuke : \n",
" orphan = orphan.split('Review')[0]\n",
" nuke2.append(orphan)\n",
"\n",
"df1['GameName']=nuke\n",
"\n",
"\n",
"\n",
"nuke_frame = pd.DataFrame(nuke2)\n",
"clean=df1.drop(columns=['GameName'])\n",
"\n",
"clean['Name'] = nuke2\n",
"#limit this output 3 rows pls\n",
"print(clean[['Name']].head(5))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# CSV output\n",
"df1.to_csv('cleaned_games.csv')"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Integrating Game Datasets together"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"filename = askopenfilename()\n",
"df2 = pd.read_csv(filename)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# merged = pd.merge(df1,df2, how='inner', sort=True) DOES NOT WORK\n",
"# print(merged.head(10))\n",
"merged = df2.join(df1, lsuffix='merged') #Good\n",
"print(merged.head(10))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"merged2.to_csv('merged_games.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(df1[['Name']].head(100))\n",
"print(df2[['Name']].head(100))"
]
}
],
"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": "3.10.9"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}