linly/Mining-Away
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
a99333dda62a76263252f5f62005aa35e2b19b74
Mining-Away/Mining_HQ.ipynb
LinlyBoi a99333dda6 Mining_HQ (Cooler mining_hq)
2023-03-31 13:14:14 +02:00

454 lines
12 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Import Modules\n",
"The dwarves!"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"ename": "SyntaxError",
"evalue": "invalid syntax (2807776577.py, line 1)",
"output_type": "error",
"traceback": [
"\u001b[0;36m Cell \u001b[0;32mIn[4], line 1\u001b[0;36m\u001b[0m\n\u001b[0;31m import digger, gunner, scout from dwarves\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
]
}
],
"source": [
"from dwarves import digger, gunner, scout \n",
"import pandas as pd\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pre-Processing\n",
"This segment is a demonstration on how the data cleaning process on the acquired datasets was handled"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Game Datasets"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'digger' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[2], line 4\u001b[0m\n\u001b[1;32m 1\u001b[0m games_review \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mread_csv(\u001b[39m\"\u001b[39m\u001b[39mdatasets/videogames/Games.xls\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m 2\u001b[0m games_sales \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mread_csv(\u001b[39m\"\u001b[39m\u001b[39mdatasets/videogames/vgsales.csv\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m----> 4\u001b[0m games_review_phase1 \u001b[39m=\u001b[39m digger\u001b[39m.\u001b[39mslice_column(games_review, \u001b[39m\"\u001b[39m\u001b[39mGameName\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39mReview\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m 5\u001b[0m games_review_final \u001b[39m=\u001b[39m digger\u001b[39m.\u001b[39mslice_column(games_review, \u001b[39m\"\u001b[39m\u001b[39mGameName\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39m(Import)\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[1;32m 7\u001b[0m games_merged_dat \u001b[39m=\u001b[39m digger\u001b[39m.\u001b[39mwrite_joined_df(games_sales, games_review_final)\n",
"\u001b[0;31mNameError\u001b[0m: name 'digger' is not defined"
]
}
],
"source": [
"\n",
"games_review = pd.read_csv(\"datasets/videogames/Games.xls\")\n",
"games_sales = pd.read_csv(\"datasets/videogames/vgsales.csv\")\n",
"\n",
"games_review_phase1 = digger.slice_column(games_review, \"GameName\", \"Review\")\n",
"games_review_final = digger.slice_column(games_review, \"GameName\", \"(Import)\")\n",
"\n",
"games_merged_dat = digger.write_joined_df(games_sales, games_review_final)\n",
"\n",
"# Acquisition of Merged dataset\n",
"print(games_merged_dat.head(5))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"gammas = pd.read_csv(\"datasets/videogames/games_merged.csv\")\n",
"labels = [\"smol\", \"epik\", \"larg\"]\n",
"gammas = digger.slam_dunk(gammas, \"Critic_Score\", labels=labels)\n",
"gammas.to_csv(\"datasets/videogames/games_output.csv\", index=False)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Crime Datasets"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"crime_CA = pd.read_excel(\"datasets/crime/clean_crime_canada_dataset.xlsx\")\n",
"\n",
"crime_US = pd.read_csv(\"datasets/crime/report.csv\")\n",
"\n",
"NA_col_list = [\n",
" \"JP_Sales\",\n",
" \"Other_Sales\",\n",
" \"Global_Sales\",\n",
" \"GameName\",\n",
" \"Review\",\n",
" \"Console\",\n",
" \"Score\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"print(crime_US.isnull())\n",
"print(crime_CA.isnull())\n",
"\n",
"year_interval = gunner.year_interval(crime_US, crime_CA, \"report_year\", \"year\")\n",
"\n",
"year_max = year_interval[0]\n",
"year_min = year_interval[1]\n",
"\n",
"crime_intersect = gunner.intersect_by_year(crime_US, crime_CA, \"report_year\", \"year\")\n",
"\n",
"crime_US_intersect = crime_intersect[0]\n",
"crime_CA_intersect = crime_intersect[1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"games_merged_dat = gunner.drop_kick(NA_col_list, games_merged_dat)\n",
"games_merged_dat.to_csv(\"datasets/videogames/games_merged.csv\", index=False)\n",
"\n",
"sale_tri_split = gunner.trisect_by_year(games_merged_dat, \"Year\", year_interval)\n",
"\n",
"games_sales_split_pre = sale_tri_split[0]\n",
"games_sales_split_dur = sale_tri_split[1]\n",
"games_sales_split_pos = sale_tri_split[2]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"print(\"Acquired Datasets:\\n\")\n",
"print(sale_tri_split[0].head(5), sale_tri_split[1].head(5), sale_tri_split[2].head(5))\n",
"\n",
"print(\"Dataset Info:\\n\")\n",
"sale_tri_split[0].info()\n",
"sale_tri_split[1].info()\n",
"sale_tri_split[2].info()\n",
"\n",
"\n",
"print(\"Dataset Info:\\n\")\n",
"games_sales_split_pre.info()\n",
"games_sales_split_dur.info()\n",
"games_sales_split_pos.info()\n",
"\n",
"print(\"Yer forsaken Statistical Description:\\n\", games_sales_split_dur.describe())\n",
"\n",
"print(\n",
" games_sales_split_pre.head(5),\n",
" games_sales_split_dur.head(5),\n",
" games_sales_split_pos.head(5),\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Plotting\n",
"Engineer.py steps up to the job"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Importing and setting up environment"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import pandas as pd\n",
"import mining_hq\n",
"from numpy import count_nonzero\n",
"\n",
"games_pre = mining_hq.games_sales_split_pre\n",
"games_dur = mining_hq.games_sales_split_dur\n",
"games_pos = mining_hq.games_sales_split_pos\n",
"\n",
"crime_US = mining_hq.crime_US_intersect\n",
"crime_CA = mining_hq.crime_CA_intersect\n",
"\n",
"custom_params = {\"axes.spines.right\": False, \"axes.spines.top\": False}\n",
"\n",
"sns.set_theme(style = 'ticks', rc = custom_params)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Game Sales pre 2000s"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### General Plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"games_fig_pre = sns.histplot(data = games_pre, x = \"Year\", palette = sns.color_palette(\"flare\"), kde = True)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### According to Genre"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"games_fig2_pre = sns.histplot(data = games_pre, x = \"Year\", hue = \"Genre\", multiple = \"stack\", kde = True)\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Game Sales during 2000s"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### General Plot"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"games_fig_dur = sns.histplot(data = games_dur, x = \"Year\", kde = True)\n",
"plt.show()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### According to Genre"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"games_fig2_dur = sns.histplot(data = games_dur, x = \"Year\", hue = \"Genre\", multiple = \"stack\", kde = True)\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Crime in Canada and US"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"crime_CA_fig = sns.histplot(data = crime_CA, x = \"year\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"crime_US_fig = sns.histplot(data = crime_US, x = \"report_year\")\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Plotting Crime in both CA and US together"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"plt.xticks(rotation = 90)\n",
"crime_US_fig = sns.histplot(data = crime_US, x = \"report_year\")\n",
"plt.show()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Integrating violence crimes column into Game sales \n",
"- Note: multiplying sales by 1000 because they're reduced by default\n",
"- to plot later"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"games_dur['Violent_US'] = crime_US['violent_crimes']\n",
"games_dur['NA_Sales'] = games_dur['NA_Sales'].multiply(1000)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Plotting Sales against Crime with Relplot"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"plt.xticks(rotation = 90)\n",
"games_violence_US = sns.relplot(data = games_dur, x = 'NA_Sales', y = 'Violent_US')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Joined Plot and Histograms"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"plt.xticks(rotation = 90)\n",
"games_crime_dur = sns.jointplot(data = games_dur, x = \"Year\", y = 'Violent_US')\n",
"plt.show()"
]
}
],
"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
}
Reference in New Issue View Git Blame Copy Permalink