Integrating the data in the note book YIPPEEEE

This commit is contained in:
LinlyBoi
2023-03-28 11:23:05 +02:00
parent cd04ac218d
commit 91571fb520

View File

@@ -36,9 +36,9 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"import pandas as pd\n", "import pandas as pd\n",
"from tkinter.filedialog import askopenfilename\n",
"filename = askopenfilename()\n", "filename = askopenfilename()\n",
"df1= pd.read_csv(filename)\n", "df1= pd.read_csv(filename)"
"from tkinter.filedialog import askopenfilename"
] ]
}, },
{ {
@@ -64,27 +64,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 23, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
" Name\n",
"0 Baldur's Gate 3 Early Access \n",
"1 Control: Ultimate Edition Cloud Version \n",
"2 Doom Eternal: The Ancient Gods Part 1 \n",
"3 Watch Dogs: Legion \n",
"4 Ring Of Pain \n",
"5 Pikmin 3 Deluxe \n",
"6 Ghostrunner \n",
"7 Disc Room \n",
"8 NHL 21 \n",
"9 Noita \n"
]
}
],
"source": [ "source": [
"# CLeaning\n", "# CLeaning\n",
"nuke=df1['GameName'].to_list()\n", "nuke=df1['GameName'].to_list()\n",
@@ -121,7 +103,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Integrating Game Sales with the previous cleaned data set" "# Integrating Game Datasets together"
] ]
}, },
{ {
@@ -129,7 +111,42 @@
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "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": { "metadata": {