486 lines
15 KiB
Plaintext
486 lines
15 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>Rank</th>\n",
|
|
" <th>Name</th>\n",
|
|
" <th>Platform</th>\n",
|
|
" <th>Year</th>\n",
|
|
" <th>Genre</th>\n",
|
|
" <th>Publisher</th>\n",
|
|
" <th>NA_Sales</th>\n",
|
|
" <th>EU_Sales</th>\n",
|
|
" <th>JP_Sales</th>\n",
|
|
" <th>Other_Sales</th>\n",
|
|
" <th>Global_Sales</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>1</td>\n",
|
|
" <td>Wii Sports</td>\n",
|
|
" <td>Wii</td>\n",
|
|
" <td>2006.0</td>\n",
|
|
" <td>Sports</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>41.49</td>\n",
|
|
" <td>29.02</td>\n",
|
|
" <td>3.77</td>\n",
|
|
" <td>8.46</td>\n",
|
|
" <td>82.74</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>2</td>\n",
|
|
" <td>Super Mario Bros.</td>\n",
|
|
" <td>NES</td>\n",
|
|
" <td>1985.0</td>\n",
|
|
" <td>Platform</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>29.08</td>\n",
|
|
" <td>3.58</td>\n",
|
|
" <td>6.81</td>\n",
|
|
" <td>0.77</td>\n",
|
|
" <td>40.24</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>3</td>\n",
|
|
" <td>Mario Kart Wii</td>\n",
|
|
" <td>Wii</td>\n",
|
|
" <td>2008.0</td>\n",
|
|
" <td>Racing</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>15.85</td>\n",
|
|
" <td>12.88</td>\n",
|
|
" <td>3.79</td>\n",
|
|
" <td>3.31</td>\n",
|
|
" <td>35.82</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>4</td>\n",
|
|
" <td>Wii Sports Resort</td>\n",
|
|
" <td>Wii</td>\n",
|
|
" <td>2009.0</td>\n",
|
|
" <td>Sports</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>15.75</td>\n",
|
|
" <td>11.01</td>\n",
|
|
" <td>3.28</td>\n",
|
|
" <td>2.96</td>\n",
|
|
" <td>33.00</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>5</td>\n",
|
|
" <td>Pokemon Red/Pokemon Blue</td>\n",
|
|
" <td>GB</td>\n",
|
|
" <td>1996.0</td>\n",
|
|
" <td>Role-Playing</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>11.27</td>\n",
|
|
" <td>8.89</td>\n",
|
|
" <td>10.22</td>\n",
|
|
" <td>1.00</td>\n",
|
|
" <td>31.37</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>5</th>\n",
|
|
" <td>6</td>\n",
|
|
" <td>Tetris</td>\n",
|
|
" <td>GB</td>\n",
|
|
" <td>1989.0</td>\n",
|
|
" <td>Puzzle</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>23.20</td>\n",
|
|
" <td>2.26</td>\n",
|
|
" <td>4.22</td>\n",
|
|
" <td>0.58</td>\n",
|
|
" <td>30.26</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>6</th>\n",
|
|
" <td>7</td>\n",
|
|
" <td>New Super Mario Bros.</td>\n",
|
|
" <td>DS</td>\n",
|
|
" <td>2006.0</td>\n",
|
|
" <td>Platform</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>11.38</td>\n",
|
|
" <td>9.23</td>\n",
|
|
" <td>6.50</td>\n",
|
|
" <td>2.90</td>\n",
|
|
" <td>30.01</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>7</th>\n",
|
|
" <td>8</td>\n",
|
|
" <td>Wii Play</td>\n",
|
|
" <td>Wii</td>\n",
|
|
" <td>2006.0</td>\n",
|
|
" <td>Misc</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>14.03</td>\n",
|
|
" <td>9.20</td>\n",
|
|
" <td>2.93</td>\n",
|
|
" <td>2.85</td>\n",
|
|
" <td>29.02</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>8</th>\n",
|
|
" <td>9</td>\n",
|
|
" <td>New Super Mario Bros. Wii</td>\n",
|
|
" <td>Wii</td>\n",
|
|
" <td>2009.0</td>\n",
|
|
" <td>Platform</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>14.59</td>\n",
|
|
" <td>7.06</td>\n",
|
|
" <td>4.70</td>\n",
|
|
" <td>2.26</td>\n",
|
|
" <td>28.62</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>9</th>\n",
|
|
" <td>10</td>\n",
|
|
" <td>Duck Hunt</td>\n",
|
|
" <td>NES</td>\n",
|
|
" <td>1984.0</td>\n",
|
|
" <td>Shooter</td>\n",
|
|
" <td>Nintendo</td>\n",
|
|
" <td>26.93</td>\n",
|
|
" <td>0.63</td>\n",
|
|
" <td>0.28</td>\n",
|
|
" <td>0.47</td>\n",
|
|
" <td>28.31</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Rank Name Platform Year Genre Publisher \\\n",
|
|
"0 1 Wii Sports Wii 2006.0 Sports Nintendo \n",
|
|
"1 2 Super Mario Bros. NES 1985.0 Platform Nintendo \n",
|
|
"2 3 Mario Kart Wii Wii 2008.0 Racing Nintendo \n",
|
|
"3 4 Wii Sports Resort Wii 2009.0 Sports Nintendo \n",
|
|
"4 5 Pokemon Red/Pokemon Blue GB 1996.0 Role-Playing Nintendo \n",
|
|
"5 6 Tetris GB 1989.0 Puzzle Nintendo \n",
|
|
"6 7 New Super Mario Bros. DS 2006.0 Platform Nintendo \n",
|
|
"7 8 Wii Play Wii 2006.0 Misc Nintendo \n",
|
|
"8 9 New Super Mario Bros. Wii Wii 2009.0 Platform Nintendo \n",
|
|
"9 10 Duck Hunt NES 1984.0 Shooter Nintendo \n",
|
|
"\n",
|
|
" NA_Sales EU_Sales JP_Sales Other_Sales Global_Sales \n",
|
|
"0 41.49 29.02 3.77 8.46 82.74 \n",
|
|
"1 29.08 3.58 6.81 0.77 40.24 \n",
|
|
"2 15.85 12.88 3.79 3.31 35.82 \n",
|
|
"3 15.75 11.01 3.28 2.96 33.00 \n",
|
|
"4 11.27 8.89 10.22 1.00 31.37 \n",
|
|
"5 23.20 2.26 4.22 0.58 30.26 \n",
|
|
"6 11.38 9.23 6.50 2.90 30.01 \n",
|
|
"7 14.03 9.20 2.93 2.85 29.02 \n",
|
|
"8 14.59 7.06 4.70 2.26 28.62 \n",
|
|
"9 26.93 0.63 0.28 0.47 28.31 "
|
|
]
|
|
},
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"df = pd.read_csv('vgsales.csv')\n",
|
|
"df.head(10)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"(16598, 11)"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.shape"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>Rank</th>\n",
|
|
" <th>Year</th>\n",
|
|
" <th>NA_Sales</th>\n",
|
|
" <th>EU_Sales</th>\n",
|
|
" <th>JP_Sales</th>\n",
|
|
" <th>Other_Sales</th>\n",
|
|
" <th>Global_Sales</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>count</th>\n",
|
|
" <td>16598.000000</td>\n",
|
|
" <td>16327.000000</td>\n",
|
|
" <td>16598.000000</td>\n",
|
|
" <td>16598.000000</td>\n",
|
|
" <td>16598.000000</td>\n",
|
|
" <td>16598.000000</td>\n",
|
|
" <td>16598.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>mean</th>\n",
|
|
" <td>8300.605254</td>\n",
|
|
" <td>2006.406443</td>\n",
|
|
" <td>0.264667</td>\n",
|
|
" <td>0.146652</td>\n",
|
|
" <td>0.077782</td>\n",
|
|
" <td>0.048063</td>\n",
|
|
" <td>0.537441</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>std</th>\n",
|
|
" <td>4791.853933</td>\n",
|
|
" <td>5.828981</td>\n",
|
|
" <td>0.816683</td>\n",
|
|
" <td>0.505351</td>\n",
|
|
" <td>0.309291</td>\n",
|
|
" <td>0.188588</td>\n",
|
|
" <td>1.555028</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>min</th>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1980.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.010000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>25%</th>\n",
|
|
" <td>4151.250000</td>\n",
|
|
" <td>2003.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.060000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>50%</th>\n",
|
|
" <td>8300.500000</td>\n",
|
|
" <td>2007.000000</td>\n",
|
|
" <td>0.080000</td>\n",
|
|
" <td>0.020000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.010000</td>\n",
|
|
" <td>0.170000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>75%</th>\n",
|
|
" <td>12449.750000</td>\n",
|
|
" <td>2010.000000</td>\n",
|
|
" <td>0.240000</td>\n",
|
|
" <td>0.110000</td>\n",
|
|
" <td>0.040000</td>\n",
|
|
" <td>0.040000</td>\n",
|
|
" <td>0.470000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>max</th>\n",
|
|
" <td>16600.000000</td>\n",
|
|
" <td>2020.000000</td>\n",
|
|
" <td>41.490000</td>\n",
|
|
" <td>29.020000</td>\n",
|
|
" <td>10.220000</td>\n",
|
|
" <td>10.570000</td>\n",
|
|
" <td>82.740000</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Rank Year NA_Sales EU_Sales JP_Sales \\\n",
|
|
"count 16598.000000 16327.000000 16598.000000 16598.000000 16598.000000 \n",
|
|
"mean 8300.605254 2006.406443 0.264667 0.146652 0.077782 \n",
|
|
"std 4791.853933 5.828981 0.816683 0.505351 0.309291 \n",
|
|
"min 1.000000 1980.000000 0.000000 0.000000 0.000000 \n",
|
|
"25% 4151.250000 2003.000000 0.000000 0.000000 0.000000 \n",
|
|
"50% 8300.500000 2007.000000 0.080000 0.020000 0.000000 \n",
|
|
"75% 12449.750000 2010.000000 0.240000 0.110000 0.040000 \n",
|
|
"max 16600.000000 2020.000000 41.490000 29.020000 10.220000 \n",
|
|
"\n",
|
|
" Other_Sales Global_Sales \n",
|
|
"count 16598.000000 16598.000000 \n",
|
|
"mean 0.048063 0.537441 \n",
|
|
"std 0.188588 1.555028 \n",
|
|
"min 0.000000 0.010000 \n",
|
|
"25% 0.000000 0.060000 \n",
|
|
"50% 0.010000 0.170000 \n",
|
|
"75% 0.040000 0.470000 \n",
|
|
"max 10.570000 82.740000 "
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.describe()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([[1, 'Wii Sports', 'Wii', ..., 3.77, 8.46, 82.74],\n",
|
|
" [2, 'Super Mario Bros.', 'NES', ..., 6.81, 0.77, 40.24],\n",
|
|
" [3, 'Mario Kart Wii', 'Wii', ..., 3.79, 3.31, 35.82],\n",
|
|
" ...,\n",
|
|
" [16598, 'SCORE International Baja 1000: The Official Game', 'PS2',\n",
|
|
" ..., 0.0, 0.0, 0.01],\n",
|
|
" [16599, 'Know How 2', 'DS', ..., 0.0, 0.0, 0.01],\n",
|
|
" [16600, 'Spirits & Spells', 'GBA', ..., 0.0, 0.0, 0.01]],\n",
|
|
" dtype=object)"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.values"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|
"RangeIndex: 16598 entries, 0 to 16597\n",
|
|
"Data columns (total 11 columns):\n",
|
|
" # Column Non-Null Count Dtype \n",
|
|
"--- ------ -------------- ----- \n",
|
|
" 0 Rank 16598 non-null int64 \n",
|
|
" 1 Name 16598 non-null object \n",
|
|
" 2 Platform 16598 non-null object \n",
|
|
" 3 Year 16327 non-null float64\n",
|
|
" 4 Genre 16598 non-null object \n",
|
|
" 5 Publisher 16540 non-null object \n",
|
|
" 6 NA_Sales 16598 non-null float64\n",
|
|
" 7 EU_Sales 16598 non-null float64\n",
|
|
" 8 JP_Sales 16598 non-null float64\n",
|
|
" 9 Other_Sales 16598 non-null float64\n",
|
|
" 10 Global_Sales 16598 non-null float64\n",
|
|
"dtypes: float64(6), int64(1), object(4)\n",
|
|
"memory usage: 1.4+ MB\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"df.info()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3.8.11 ('base')",
|
|
"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": "3.8.13"
|
|
},
|
|
"orig_nbformat": 4,
|
|
"vscode": {
|
|
"interpreter": {
|
|
"hash": "5819c1eaf6d552792a1bbc5e8998e6c2149ab26a1973a0d78107c0d9954e5ba0"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|