diff --git a/机器学习竞赛实战_优胜解决方案/游戏销售数据_特征常用构建方法/游戏销售数据-常用特征构造方法.ipynb b/机器学习竞赛实战_优胜解决方案/游戏销售数据_特征常用构建方法/游戏销售数据-常用特征构造方法.ipynb index 2d81053..1dc6681 100644 --- a/机器学习竞赛实战_优胜解决方案/游戏销售数据_特征常用构建方法/游戏销售数据-常用特征构造方法.ipynb +++ b/机器学习竞赛实战_优胜解决方案/游戏销售数据_特征常用构建方法/游戏销售数据-常用特征构造方法.ipynb @@ -9,12 +9,14 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 51, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", - "import numpy as np" + "import numpy as np\n", + "import warnings # 忽略普通警告，不打印太多东西\n", + "warnings.filterwarnings('ignore')" ] }, { @@ -451,19 +453,9 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 52, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "D:\\Anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:415: FutureWarning: The handling of integer data will change in version 0.22. Currently, the categories are determined based on the range [0, max(values)], while in the future they will be determined based on the unique values.\n", - "If you want the future behaviour and silence this warning, you can specify \"categories='auto'\".\n", - "In case you used a LabelEncoder before this OneHotEncoder to convert the categories to integers, then you can now use the OneHotEncoder directly.\n", - " warnings.warn(msg, FutureWarning)\n" - ] - }, { "data": { "text/plain": [ @@ -476,7 +468,7 @@ " [0., 0., 0., ..., 0., 0., 0.]])" ] }, - "execution_count": 26, + "execution_count": 52, "metadata": {}, "output_type": "execute_result" } @@ -1240,6 +1232,930 @@ "dummy_df_true.head()" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 二值特征化" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NameYear
0Wii Sports2006.0
1Super Mario Bros.1985.0
2Mario Kart Wii2008.0
3Wii Sports Resort2009.0
4Pokemon Red/Pokemon Blue1996.0
\n", + "
" + ], + "text/plain": [ + " Name Year\n", + "0 Wii Sports 2006.0\n", + "1 Super Mario Bros. 1985.0\n", + "2 Mario Kart Wii 2008.0\n", + "3 Wii Sports Resort 2009.0\n", + "4 Pokemon Red/Pokemon Blue 1996.0" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "vg_year_df = vg_df[['Name', 'Year']]\n", + "vg_year_df.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "我们把2000年以上的归类为1，其它归类为0" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NameYearYear_tow
0Wii Sports2006.01
1Super Mario Bros.1985.00
2Mario Kart Wii2008.01
3Wii Sports Resort2009.01
4Pokemon Red/Pokemon Blue1996.00
\n", + "
" + ], + "text/plain": [ + " Name Year Year_tow\n", + "0 Wii Sports 2006.0 1\n", + "1 Super Mario Bros. 1985.0 0\n", + "2 Mario Kart Wii 2008.0 1\n", + "3 Wii Sports Resort 2009.0 1\n", + "4 Pokemon Red/Pokemon Blue 1996.0 0" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "vg_year_df['Year_tow'] = np.where(vg_year_df['Year'] >= 2000, 1, 0)\n", + "vg_year_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NameYearYear_towbn_year
0Wii Sports2006.011.0
1Super Mario Bros.1985.000.0
2Mario Kart Wii2008.011.0
3Wii Sports Resort2009.011.0
4Pokemon Red/Pokemon Blue1996.000.0
\n", + "
" + ], + "text/plain": [ + " Name Year Year_tow bn_year\n", + "0 Wii Sports 2006.0 1 1.0\n", + "1 Super Mario Bros. 1985.0 0 0.0\n", + "2 Mario Kart Wii 2008.0 1 1.0\n", + "3 Wii Sports Resort 2009.0 1 1.0\n", + "4 Pokemon Red/Pokemon Blue 1996.0 0 0.0" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.preprocessing import Binarizer\n", + "# sklearn中的方法\n", + "bn = Binarizer(threshold=2000) # 大于2000我1，小于为0\n", + "vg_year_df['Year']=vg_year_df['Year'].fillna(0) # 数据中有Nan值，需要补0，否则无法二分\n", + "bn_year = bn.transform([vg_year_df['Year']])[0] # 获取转换的值，取第0列\n", + "vg_year_df['bn_year'] = bn_year # 插入数据\n", + "vg_year_df.head() # 结果与手动一致" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 多项式特征\n", + "获得特征的更高维度和互相间关系的项。" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NA_SalesEU_Sales
041.4929.02
129.083.58
215.8512.88
315.7511.01
411.278.89
\n", + "
" + ], + "text/plain": [ + " NA_Sales EU_Sales\n", + "0 41.49 29.02\n", + "1 29.08 3.58\n", + "2 15.85 12.88\n", + "3 15.75 11.01\n", + "4 11.27 8.89" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "polynomial_df = vg_df[['NA_Sales', 'EU_Sales']]\n", + "polynomial_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[4.1490000e+01, 2.9020000e+01, 1.7214201e+03, 1.2040398e+03,\n", + " 8.4216040e+02],\n", + " [2.9080000e+01, 3.5800000e+00, 8.4564640e+02, 1.0410640e+02,\n", + " 1.2816400e+01],\n", + " [1.5850000e+01, 1.2880000e+01, 2.5122250e+02, 2.0414800e+02,\n", + " 1.6589440e+02],\n", + " ...,\n", + " [0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n", + " 0.0000000e+00],\n", + " [0.0000000e+00, 1.0000000e-02, 0.0000000e+00, 0.0000000e+00,\n", + " 1.0000000e-04],\n", + " [1.0000000e-02, 0.0000000e+00, 1.0000000e-04, 0.0000000e+00,\n", + " 0.0000000e+00]])" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.preprocessing import PolynomialFeatures\n", + "\n", + "# degree二次幂的复杂度\n", + "pf = PolynomialFeatures(degree=2, interaction_only=False, include_bias=False)\n", + "res = pf.fit_transform(polynomial_df)\n", + "res" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "以第一行为例：\n", + "
第一列和第二列分别表示原先的第一列和第二列\n", + "
第三列和第五列表示第一列和第二列分别的平方，第四列表示两者的乘积" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NA_SalesEU_SalesNA_Sales^2NA_Sales*EU_SalesEU_Sales^2
041.4929.021721.42011204.0398842.1604
129.083.58845.6464104.106412.8164
215.8512.88251.2225204.1480165.8944
315.7511.01248.0625173.4075121.2201
411.278.89127.0129100.190379.0321
\n", + "
" + ], + "text/plain": [ + " NA_Sales EU_Sales NA_Sales^2 NA_Sales*EU_Sales EU_Sales^2\n", + "0 41.49 29.02 1721.4201 1204.0398 842.1604\n", + "1 29.08 3.58 845.6464 104.1064 12.8164\n", + "2 15.85 12.88 251.2225 204.1480 165.8944\n", + "3 15.75 11.01 248.0625 173.4075 121.2201\n", + "4 11.27 8.89 127.0129 100.1903 79.0321" + ] + }, + "execution_count": 63, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "intr_features = pd.DataFrame(res, columns=['NA_Sales',\n", + " 'EU_Sales',\n", + " 'NA_Sales^2',\n", + " 'NA_Sales*EU_Sales',\n", + " 'EU_Sales^2'])\n", + "intr_features.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
RankNamePlatformYearGenrePublisherNA_SalesEU_SalesJP_SalesOther_SalesGlobal_SalesGenreLabelGenreMap
01Wii SportsWii2006.0SportsNintendo41.4929.023.778.4682.741010
12Super Mario Bros.NES1985.0PlatformNintendo29.083.586.810.7740.2444
23Mario Kart WiiWii2008.0RacingNintendo15.8512.883.793.3135.8266
34Wii Sports ResortWii2009.0SportsNintendo15.7511.013.282.9633.001010
45Pokemon Red/Pokemon BlueGB1996.0Role-PlayingNintendo11.278.8910.221.0031.3777
\n", + "
" + ], + "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", + "\n", + " NA_Sales EU_Sales JP_Sales Other_Sales Global_Sales GenreLabel \\\n", + "0 41.49 29.02 3.77 8.46 82.74 10 \n", + "1 29.08 3.58 6.81 0.77 40.24 4 \n", + "2 15.85 12.88 3.79 3.31 35.82 6 \n", + "3 15.75 11.01 3.28 2.96 33.00 10 \n", + "4 11.27 8.89 10.22 1.00 31.37 7 \n", + "\n", + " GenreMap \n", + "0 10 \n", + "1 4 \n", + "2 6 \n", + "3 10 \n", + "4 7 " + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "vg_df.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Binning 特征\n", + "一般用来处理年龄" + ] + }, + { + "cell_type": "code", + "execution_count": 116, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NameYear
0Wii Sports2006.0
1Super Mario Bros.1985.0
2Mario Kart Wii2008.0
3Wii Sports Resort2009.0
4Pokemon Red/Pokemon Blue1996.0
\n", + "
" + ], + "text/plain": [ + " Name Year\n", + "0 Wii Sports 2006.0\n", + "1 Super Mario Bros. 1985.0\n", + "2 Mario Kart Wii 2008.0\n", + "3 Wii Sports Resort 2009.0\n", + "4 Pokemon Red/Pokemon Blue 1996.0" + ] + }, + "execution_count": 116, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bin_df = vg_df[['Name','Year']] # 假设GenreLabel是年龄\n", + "bin_df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 117, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Text(0, 0.5, 'Frequency')" + ] + }, + "execution_count": 117, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY4AAAEZCAYAAACAZ8KHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nO3de5xdVX338c+XJNwSIMFASi4SFKogKkK4qmUA5aYQ+lQUSyUgPmihrbaooIKKiqKlgrZVpBDlHlMUiQpiBKY+FoOA3ALhEiCQISkRMglJJEDw9/yx1ml2hpnJrJlzmWS+79frvM7ea99+Z519zu+stffZWxGBmZlZX23S6gDMzGzD4sRhZmZFnDjMzKyIE4eZmRVx4jAzsyJOHGZmVsSJw+pOUrukj7Q6jr6SFJJ27sN8J0r6TT+30Sapoz/LFmxjgaR3NXIbZuDEsdHKXyIvSFohaZmk2yR9TNKQes8lbSXpm7k+Vkl6StK1kvZpdWzdkfSO/F4tl7RU0n9L2ruF8bwqGQ0kgVbW0fBEao0zpL5EhqCjImIrYEfgPOAM4NLWhtQYkoZ3U7YZcAvwZuC9wNbArsAM4MimBtgHkrYGfgb8K7AtMAE4B3ixlXFtiCQNa3UMGzMnjiEgIpZHxCzgA8A0SbtD+mKVdH7+Ff6MpIskbZGnzZP03to6JA2X9KykPfP4fvmX8TJJ90pq627bkjaRdJakJyUtkXS5pG3ytMm5m+gUSYskLZZ0epdlz5T0mKTnJM2UtG2XZU+W9BQpQXT1IWAicExEzI2IVyJiVURcGxFf7CHebXKMf8gxn9WllSZJ/5pbBA9JOqQy4aRcbyskPS7po+t9c9b15wARcU2O9YWI+GVE3JfX/3pJt+S6eFbSVZJG9/A6equ7zSVdmcuXSbpD0rjCWKvb2jV3Ty6T9ICkoyvTjpT0YK6TpyV9UtJI4EZgvKSV+TE+748X5n1hUR7erLKuT+d9ZJGkj6jSxSjpB5K+K+kGSauAgyS9R9Ldkp6XtFDSFyvrqu0/J+VpnUot8r0l3Zdfy7/1t042ehHhx0b4ABYA7+qm/Cngb/PwhcAs0q/brYCfAl/L0z4PXFVZ7j3AQ3l4AvAc6Vf7JsC78/h2eXo78JE8/GFgPvA6YBTwY+CKPG0yEMA1wEhSy+APtbiBTwBzSF/+mwHfA67psuzledktunmtM4Af9KGuAtg5D18OXJ/rYzLwCHBynnYisAb4R2AEKREvB7at1NHrAQEHAn8E9szT2oCO9cSxda7Hy4AjgDFdpu+c63ozYDvg18CF3b3n66m7j+b3ektgGLAXsHVf96NcD7/JwyPy+/tZYFPgYGAF8IY8fTHwzjw8prf6AL6UY94+v77bgC/naYcD/wO8Kcd9RZf37Qf5vXg7aZ/cPG/jzXn8LcAzpB8R1f3nojzvocBq4Cd5+xOAJcCBrf4sD8ZHywPwo0FvbM+JYw7wufzltgp4fWXa/sATeXjn/AWwZR6/Cvh8Hj6D/OVfWfYmYFoebmdt4rgZOLUy3xuAl4HhlQ/vGyvTvwFcmofnAYdUpu3QzbKv66UOfgWcVxnfA1gGPA88XCmP/HqHkbqFdqtM+yjQnodPBBYBqkz/HfChHrb/E+DjebiN9SSOPN+u+Uuwg5SkZgHjepj3GODu7t7z9dTdh0lfym/p4360Mtdb7fFH1iaOd5K+0DepLHMN8MU8/FSuw627rPdV9QE8BhxZGT8MWJCHp5N/1FT2z66J4/L1vJYLgQvycG3/mVCZ/hzwgcr4j4BPtOozPJgf7qoaeiYAS0m/6LYE7srN8mXAL3I5ETGf9OVzlKQtgaOBq/M6dgSOrS2Xl30H6cupq/HAk5XxJ0lfXtWukYVdpo+vbOe6yjbmAa/0smxXz1Vjioh7ImI08H9Iv8K7Gkv61dw13gmV8acjf6t0jVfSEZLmKB3UXkZqkY3tJb5XiYh5EXFiREwEds/rvjCvf3tJM3KXz/PAlb2sv7e6u4KU6Gfkbp9vSBrRS1jHRMTo2gM4tTJtPLAwIv7UpU5qdfZXpHp4UtJ/Sdq/l+10t6+Mr0yrvtfdve/rlEnaV9KtudtxOfAxXl1fz1SGX+hmfFQv8Q5ZThxDiNLZOROA3wDPkj4Yb6p8KWwTEdUPyjXAB4GpwIM5mUD6gF5R/TKJiJERcV43m11E+hKreS3pl3T1Azqpy/RFle0c0WU7m0fE05X5e7u8883AoblPvS+eJf0q7xpvdXsTJKlrvLkv/kfA+aQWwmjgBlLLrl8i4iHSL+ndc9HXSK/3LRGxNfA3vay/x7qLiJcj4pyI2A04gHTiwAn9DHMRMKnLcaD/rbOIuCMippK6f34CzKy9vB7W1bXua/vCYlK3W011n6npus6rSS22SRGxDalbqt/vh63lxDEESNpa6UD3DODKiLg//0L8D+ACSdvn+SZIOqyy6AxS3+/fsra1AemX7lGSDpM0LB9sbZNU/WDXXAP8o6SdJI0Cvgr8MCLWVOY5W9KWkt4EnAT8MJdfBJwraccc33aSpha89MtJXzjXSdq9FiswpbuZI+IV0hfbuUqn8e4I/FN+vTXbA/8gaYSkY0ldSzeQWiqbkY7RrJF0BKnu+kzSGyWdXqtHSZNIiXtOnmUrcreRpAnAp3pZXY91J+kgSW9WOvPoeVKyfKUk1orbSV2en8510gYcRWrNbCrpeEnbRMTLeVu17TwDvEb5RInsGuCsHOtY0nG2Wt3PBE5SOhC/ZZ62PlsBSyNitdLp13/dz9doXThxbNx+KmkF6dfn54Bvkr6Ya84gHdick7s+fkU6BgFARCwGfkv6VfrDSvlCUivks6QvyoWkL7Hu9qfppK6RXwNPkA5A/n2Xef4rx3EzcH5E/DKXf4v0i/GX+XXMAfbt64uPiNXAQcCDwM/JxzaAvYH397DY35O+CB8ntcyuzq+h5nZgF1Lr5FzgfRHxXESsAP6B9AXXSfqSmtXXWLMVpNd3ez4zaA4wF6idaXYOsCfpIPDPSSca9KS3uvsz4FpSfcwj1f+V3a1kfSLiJVI35hGkOvkOcEJuLUE6s21B3r8+Rmol1VpT1wCP5+608cBXgDuB+4D7gd/nMiLiRuDbwK2kfeW3ef29nap8KvCl/Po/z9rWjg2Q1u2uNWseSZNJyWRElxaIWa8k7UpKqpt532k+tzjMbIMg6S9z99cY4OvAT500WsOJw6yJJL1Wa//01vXx2lbHN8h9lNQ1+hjpWMnftjacoctdVWZmVsQtDjMzK/KqC8NtbMaOHRuTJ0/u9/KrVq1i5Mi+/g2geRxXGcdVxnGV2Rjjuuuuu56NiO26ndjqv643+rHXXnvFQNx6660DWr5RHFcZx1XGcZXZGOMC7gxfcsTMzOrBicPMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVceIwM7MiThxmZlZko7/kiJkNLjNvm9vvZUesWt3v5d9/wO7rn8n6xC0OMzMr4sRhZmZFnDjMzKyIE4eZmRVx4jAzsyJOHGZmVqRpiUPSAkn3S7pH0p25bFtJsyU9mp/H5HJJ+rak+ZLuk7RnZT3T8vyPSprWrPjNzCxpdovjoIjYIyKm5PEzgZsjYhfg5jwOcASwS36cAnwXUqIBvgDsC+wDfKGWbMzMrDla3VU1FbgsD18GHFMpvzzfwXAOMFrSDsBhwOyIWBoRncBs4PBmB21mNpQp3Vq2CRuSngA6gQC+FxEXS1oWEaMr83RGxBhJPwPOi4jf5PKbgTOANmDziPhKLj8beCEizu+yrVNILRXGjRu314wZM/od98qVKxk1alS/l28Ux1XGcZVpZFydq1b3e1mteYkYvmm/lh0zcvN+b3d9Nsb38aCDDrqr0ju0jmZecuTtEbFI0vbAbEkP9TKvuimLXsrXLYi4GLgYYMqUKdHW1taPcJP29nYGsnyjOK4yjqtMI+Ma0CVHOjt4eczEfi3b1sBLjgy197FpXVURsSg/LwGuIx2jeCZ3QZGfl+TZO4BJlcUnAot6KTczsyZpSuKQNFLSVrVh4FBgLjALqJ0ZNQ24Pg/PAk7IZ1ftByyPiMXATcChksbkg+KH5jIzM2uSZnVVjQOuk1Tb5tUR8QtJdwAzJZ0MPAUcm+e/ATgSmA/8ETgJICKWSvoycEee70sRsbRJr8HMzGhS4oiIx4G3dlP+HHBIN+UBnNbDuqYD0+sdo5mZ9U2rT8c1M7MNjBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWZGmJg5JwyTdLelneXwnSbdLelTSDyVtmss3y+Pz8/TJlXV8Jpc/LOmwZsZvZmbNb3F8HJhXGf86cEFE7AJ0Aifn8pOBzojYGbggz4ek3YDjgDcBhwPfkTSsSbGbmRlNTBySJgLvAS7J4wIOBq7Ns1wGHJOHp+Zx8vRD8vxTgRkR8WJEPAHMB/ZpziswMzMARURzNiRdC3wN2Ar4JHAiMCe3KpA0CbgxInaXNBc4PCI68rTHgH2BL+Zlrszll+Zlru2yrVOAUwDGjRu314wZM/od98qVKxk1alS/l28Ux1XGcZVpZFydq1b3e1mteYkYvmm/lh0zcvN+b3d9Nsb38aCDDrorIqZ0N234gKLqI0nvBZZExF2S2mrF3cwa65nW2zJrCyIuBi4GmDJlSrS1tXWdpc/a29sZyPKN4rjKOK4yjYxr5m1z+73siM4OXh4zsV/Lth2we7+3uz5D7X1sSuIA3g4cLelIYHNga+BCYLSk4RGxBpgILMrzdwCTgA5Jw4FtgKWV8prqMmZm1gRNOcYREZ+JiIkRMZl0cPuWiDgeuBV4X55tGnB9Hp6Vx8nTb4nUpzYLOC6fdbUTsAvwu2a8BjMzS5rV4ujJGcAMSV8B7gYuzeWXAldImk9qaRwHEBEPSJoJPAisAU6LiFeaH7bZhm193UUjVq0eUJeSbdyanjgioh1oz8OP081ZURGxGji2h+XPBc5tXIRmZtYb/3PczMyKOHGYmVkRJw4zMyvixGFmZkWcOMzMrIgTh5mZFXHiMDOzIk4cZmZWxInDzMyKOHGYmVkRJw4zMyvixGFmZkWcOMzMrIgTh5mZFXHiMDOzIn1OHJL+QdLYRgZjZmaDX0mL413AAkk/k/QBSZs1KigzMxu8+pw4IuJoYEfgRuATwP9IukTSXzQqODMzG3yKjnFExHMR8e8RsT9wILA3cKukBZI+J2lUQ6I0M7NBo/jguKRDJH2fdN/wZ4ATgA8BbyO1RszMbCM2vK8zSjofOA5YDlwOnBURT1emzwE66x6hmZkNKn1OHMDmwF9GxB3dTYyIlyVNqU9YZmY2WJUkjq8Bf6wWSBoDbBERiwAi4qE6xmZmZoNQyTGOnwATu5RNBK6rXzhmZjbYlSSON0TE/dWCPP7G+oZkZmaDWUniWCJp52pBHn+uviGZmdlgVpI4pgM/kvReSbtJOgq4FrikMaGZmdlgVHJw/DzgZeB8YBKwkJQ0vtmAuMzMbJDqc+KIiD8B/5wfZmY2RJW0OJD0BuCtwDqXFomI6fUMyszMBq+Sy6p/FrgXOJ10iZHa42/6sOzmkn4n6V5JD0g6J5fvJOl2SY9K+qGkTXP5Znl8fp4+ubKuz+TyhyUdVvJizcxs4EpaHJ8A9omI+/qxnReBgyNipaQRwG8k3Qj8E3BBRMyQdBFwMvDd/NwZETtLOg74OvABSbuRLnvyJmA88CtJfx4Rr/QjJjMz64eSs6peAPr1z/BIVubREfkRwMGkM7MALgOOycNT8zh5+iGSlMtnRMSLEfEEMB/Ypz8xmZlZ/5QkjrOBf5W0g6RNqo++LCxpmKR7gCXAbOAxYFlErMmzdAAT8vAE0llb5OnLgddUy7tZxszMmqCkq+oH+fkjlTKRWg7D1rdw7k7aQ9Jo0mVKdu1utsp6u5vWU/k6JJ0CnAIwbtw42tvb1xdej1auXDmg5RvFcZVxXOsasWp1r9O15iVGdHY0KZq+G0hc7e3P1jmatYba/lWSOHaqxwYjYpmkdmA/YLSk4blVMRFYlGfrIP1XpEPScGAbYGmlvKa6THUbFwMXA0yZMiXa2tr6HW97ezsDWb5RHFcZx7WumbfN7XX6iM4OXh7T9dJ0rTeQuNoO2L3O0aw11PavklvHPhkRT5K6il6qjeeyXknaLrc0kLQF6f7l84Bbgffl2aYB1+fhWXmcPP2WiIhcflw+62onYBfgd319DWZmNnAlN3IaDXyH9EX+MjBS0tGkM63OWs/iOwCXSRpGSlYzI+Jnkh4EZkj6CnA3cGme/1LgCknzSS2N4wAi4gFJM4EHgTXAaT6jysysuUq6qi4i3eFvR9IXN8BvgX8Bek0c+RTet3VT/jjdnBUVEauBY3tY17nAuQVxm5lZHZUkjkOA8flOfwEQEX+QtH1jQjMzs8Go5HTc5cDYaoGk1wKL6xqRmZkNaiWJ4xLSZdUPAjaRtD/pT3oXNSQyMzMblEq6qr4OrAb+nfTP7+nA94BvNSAuMzMbpEouqx7AhflhZmZDVMnpuAf3NC0ibqlPOGZmNtiVdFVd2mV8O2BT0r+5X1e3iMzMbFAr6apa55Ij+c98ZwEr6h2UmZkNXiVnVa0j/2P7XODT9QvHzMwGu34njuzdwJ/qEYiZmW0YSg6OL2TdS5hvCWwOnFrvoMzMbPAqOTje9d7iq4BHIuL5OsZjZmaDXMnB8f9qZCBmZrZhKOmquoJu7rbXVUScMKCIzMxsUCs5OL4MOIZ0m9iOvOzUXP5Y5WFmZhuxkmMcfw68JyL+X61A0juAsyPisLpHZmZmg1JJi2M/YE6XstuB/esXjpmZDXYlLY67ga9K+nxEvJDvHX4OcE9jQjPb+HWuWs3M2+a2OgyzIiWJ40TgamC5pE5gDHAncHwD4jIzq6tGJugRvfwAeP8Buzdsu61ScjruAuAASZOA8cDiiHiqUYGZmdngVHTJEUmvAdqAAyPiKUnjJU1sSGRmZjYo9TlxSDoQeJjUNXV2Lt4F+G4D4jIzs0GqpMVxIfCBiDgcWJPLbgf2qXtUZmY2aJUkjskRcXMerv2D/CXKDrCbmdkGriRxPCip6x/93gXcX8d4zMxskCtpLZwO/EzSz4EtJH0POIp02REzMxsi+tziiIg5wFuAB4DpwBPAPhFxR4NiMzOzQahPLY58f/GbgcMi4huNDcnMzAazPrU48v3Fd+rr/GZmtvEqSQTnAN+VtKOkYZI2qT0aFZyZmQ0+JQfHL8nPJ7D2dFzl4WH1DMrMzAav9bYWJP1ZHtyp8nhdftSG17eOSZJulTRP0gOSPp7Lt5U0W9Kj+XlMLpekb0uaL+k+SXtW1jUtz/+opGnFr9jMzAakL91MjwBExJMR8SRwQW24UrY+a4DTI2JX0n09TpO0G3AmcHNE7EI6+H5mnv8I0uVMdgFOIV/WRNK2wBeAfUn/WP9CLdmYmVlz9CVxqMt4W+lGImJxRPw+D68A5gETSP8BuSzPdhnp1rTk8ssjmQOMlrQDcBgwOyKWRkQnMBs4vDQeMzPrv74c44j1z9J3kiYDbyNd52pcRCyGlFwkbZ9nmwAsrCzWkct6Ku+6jVNILRXGjRtHe3t7v+NduXLlgJZvFMdVZrDGpTUvMaKzo9VhvIrjKtNbXO3tzzY5mrUatd/3JXEMl3QQa1seXceJiFv6sjFJo4AfAZ+IiOelro2ZtbN2Uxa9lK9bEHExcDHAlClToq2trS/hdau9vZ2BLN8ojqvMYI3rup//gpfHDL47E4zo7HBcBXqLq62FN3Jq1H7fl8SxhPRP8ZrnuowHfTtAPoKUNK6KiB/n4mck7ZBbGzvkbUFqSUyqLD4RWJTL27qUt/fhNZiZWZ2s9xhHREyOiJ16efQlaQi4FJgXEd+sTJoF1M6MmgZcXyk/IZ9dtR+wPHdp3QQcKmlMPih+aC4zM7MmadYl0d8OfAi4X9I9ueyzwHnATEknA08Bx+ZpNwBHAvOBPwInAUTEUklfBmrXx/pSRCxtzkswMzNoUuKIiN/Q/fEJgEO6mT+A03pY13TW7SozM7Mm8uVCzMysiBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVceIwM7MiThxmZlbEicPMzIo4cZiZWREnDjMzKzK81QGYtdrM2+a2bNsjWrZls/5zi8PMzIo4cZiZWREnDjMzK+LEYWZmRZw4zMysiBOHmZkVaUrikDRd0hJJcytl20qaLenR/Dwml0vStyXNl3SfpD0ry0zL8z8qaVozYjczs3U1q8XxA+DwLmVnAjdHxC7AzXkc4Ahgl/w4BfgupEQDfAHYF9gH+EIt2ZiZWfM0JXFExK+BpV2KpwKX5eHLgGMq5ZdHMgcYLWkH4DBgdkQsjYhOYDavTkZmZtZgrfzn+LiIWAwQEYslbZ/LJwALK/N15LKeyl9F0imk1grjxo2jvb2930GuXLlyQMs3iuMq01tcI1atbm4wFVrzEiM6O1q2/Z44rjK9xdXe/myTo1mrUZ/HwXjJEXVTFr2Uv7ow4mLgYoApU6ZEW1tbv4Npb29nIMs3iuMq01tcLb3kSGcHL4+Z2LLt98RxlektrrYDdm9yNGs16vPYyrOqnsldUOTnJbm8A5hUmW8isKiXcjMza6JWJo5ZQO3MqGnA9ZXyE/LZVfsBy3OX1k3AoZLG5IPih+YyMzNroqZ0VUm6BmgDxkrqIJ0ddR4wU9LJwFPAsXn2G4AjgfnAH4GTACJiqaQvA3fk+b4UEV0PuJuZWYM1JXFExAd7mHRIN/MGcFoP65kOTK9jaGZmVsj/HDczsyJOHGZmVsSJw8zMijhxmJlZEScOMzMr4sRhZmZFnDjMzKyIE4eZmRVx4jAzsyJOHGZmVsSJw8zMijhxmJlZEScOMzMr4sRhZmZFnDjMzKyIE4eZmRVpyo2czPpi5m1zG7buEatWN3T9ZkOJWxxmZlbEicPMzIo4cZiZWREf4zAza6BWHlvbvkHrdYvDzMyKOHGYmVkRJw4zMyvixGFmZkWcOMzMrIgTh5mZFXHiMDOzIk4cZmZWxInDzMyK+J/j69HZoquqvv+A3Zu+TRj4v1x9FVqzjd8GmTgkHQ58CxgGXBIR57U4pLpb35evv6DNrFU2uK4qScOAfweOAHYDPihpt9ZGZWY2dGxwiQPYB5gfEY9HxEvADGBqi2MyMxsyNsSuqgnAwsp4B7BvdQZJpwCn5NGVkh4ewPbGAs8OYPlGcVxlHFcZx1VmY4xrx54mbIiJQ92UxTojERcDF9dlY9KdETGlHuuqJ8dVxnGVcVxlhlpcG2JXVQcwqTI+EVjUoljMzIacDTFx3AHsImknSZsCxwGzWhyTmdmQscF1VUXEGkl/B9xEOh13ekQ80MBN1qXLqwEcVxnHVcZxlRlScSki1j+XmZlZtiF2VZmZWQs5cZiZWZEhlzgkTZe0RNLcStlbJf1W0v2Sfipp61w+QtJluXyepM9Uljlc0sOS5ks6cxDFtSCX3yPpzibHtamk7+fyeyW1VZbZK5fPl/RtSd2dVt2KuNrz+3hPfmw/wLgmSbo1vy8PSPp4Lt9W0mxJj+bnMblcuT7mS7pP0p6VdU3L8z8qadogiuuVSn0N6MSUfsT1xvwevyjpk13WVbfPZJ3jqttnsh9xHZ/fv/sk3SbprZV19b++ImJIPYC/APYE5lbK7gAOzMMfBr6ch/8amJGHtwQWAJNJB+UfA14HbArcC+zW6rjy+AJgbIvq6zTg+3l4e+AuYJM8/jtgf9L/cG4EjhgkcbUDU+pYXzsAe+bhrYBHSJfG+QZwZi4/E/h6Hj4y14eA/YDbc/m2wOP5eUweHtPquPK0lS2sr+2BvYFzgU9W1lPXz2S94srTFlCnz2Q/4jqgtt+QLtNU278GVF9DrsUREb8GlnYpfgPw6zw8G/ir2uzASEnDgS2Al4DnacBlT+oUV90VxrUbcHNebgmwDJgiaQdg64j4baS99nLgmFbHNZDt9xLX4oj4fR5eAcwjXe1gKnBZnu0y1r7+qcDlkcwBRuf6OgyYHRFLI6Izv57DB0FcdVUaV0QsiYg7gJe7rKqun8k6xlVX/Yjrtrz/AMwh/e8NBlhfQy5x9GAucHQePpa1fzC8FlgFLAaeAs6PiKV0f9mTCYMgLkhJ5ZeS7lK69Eoj9BTXvcBUScMl7QTsladNINVRTbPrq6e4ar6fuxHOlgbWhVYlaTLwNuB2YFxELIb04Sf9QoWe96WG7WMDjAtgc0l3SpojaUA/APoRV09aXV+9achnsh9xnUxqRcIA68uJI/kwcJqku0jNv5dy+T7AK8B4YCfgdEmvow+XPWlRXABvj4g9Sc3S0yT9RRPjmk7aAe8ELgRuA9bQ+vrqKS6A4yPizcA78+ND9QhE0ijgR8AnIqK31mBPddOQOqtDXACvjXQZi78GLpT0+ibG1eMquilrZn31pu6fydK4JB1EShxn1Iq6ma3P9eXEAUTEQxFxaETsBVxD6vuD9MH4RUS8nLs4/pvUxdGUy570Iy4iYlF+XgJcR0oyTYkrItZExD9GxB4RMRUYDTxKqq+JlVU0tb56iYuIeDo/rwCupg71JWkE6UN9VUT8OBc/U+vqyc9LcnlP+1Ld97E6xVXdxx4nHSN6WxPj6kmr66tH9f5MlsYl6S3AJcDUiHguFw+ovpw4AOUzaSRtApwFXJQnPQUcnM8wGUk6SPgQTbrsSWlckkZK2iovMxI4lNR905S4JG2Zt4ukdwNrIuLB3HReIWm/3BV0AnB9q+PKXVdjc/kI4L0MsL7y67sUmBcR36xMmgXUzoyaxtrXPws4Ib+X+wHLc33dBBwqaUw+Q+bQXNbSuHI8m+V1jgXeDs2iZSQAAATsSURBVDzYxLh6UtfPZL3iqvdnsjQuSa8Ffgx8KCIeqcw/sPrq61H0jeVB+iW6mHQQq4PUfPs46eyER4DzWPuP+lHAfwIPkD4cn6qs58g8/2PA5wZDXKQzJO7NjwdaENdk4GHSAbtfATtW1jOF9IF5DPi32jKtjAsYSTrD6r5cX98Chg0wrneQmvz3Affkx5HAa0gH6B/Nz9vm+UW6MdljwP1UzvAidb3Nz4+TBkNcpLN07s/72P3AyU2O68/y+/086SSHDtKJF1DHz2S94qLOn8l+xHUJ0FmZ987KuvpdX77kiJmZFXFXlZmZFXHiMDOzIk4cZmZWxInDzMyKOHGYmVkRJw4zMyvixGGWSfqBpK/0cd6QtHM/t7NA0rv6s2wf1/9FSVc2av1mThw2pEg6TtLtklYp3c/jdkmn1vPihvUgabTSPUf+R9IKSY9IOmP9S5o1nhOHDRmSTif9O/yfSf/0HQd8jHTZjE1bGFp3LiBdIWBXYBvSVX8f63UJsyZx4rAhQdI2wJeAUyPi2ohYEcndEXF8RLzYzTL/V+nuaEslzZI0vsssR0p6XNKzkv45XyMLSa+XdIuk5/K0qySNLgx5b+DqiOiMiD9FuoDjtZXYviVpoaTnlS7X/c5eXvt+Snd/W6ZX3wHxxPwaVkh6QtLxhXHaEOTEYUPF/sBm9PHiipIOBr4GvJ9017UnSTe7qfpL0jW49iTdBOfDtcXzsuNJLYZJwBcL450DnCvpJEm7dDP9DmAP0h0Crwb+U9Lm3byOCcDPga/keT8J/EjSdvmie98m3Y1xK9J1qO4pjNOGICcOGyrGAs9GRO0+HFR+hb+gV98j4XhgekT8PrdGPgPsr3TznJqvR7pD31Ok+3x8ECAi5kfE7Ih4MSL+AHwTOLAw3r8HrgL+Dngwt3yOqE2MiCsj4rlIl4z/F1JSfEM36/kb4IaIuCG3XGaT7ktyZJ7+J2B3SVtEurvcA4Vx2hDkxGFDxXPAWKXb7QIQEQdExOg8retnYTyplVGbd2Wer3qXtOod1J7MyyBpe0kzJD0t6XngSlLi6rOIeCEivhrp3iKvAWaSWhXb5m2cLmmepOWSlpGOg3S3jR2BY3OCXJbnfQewQ0SsAj5AOs6zWNLPJb2xJE4bmpw4bKj4LfAifb+v8iLSly7wv/dSeA3wdGWe6o1wXsvaG+F8jXTp67dExNakX/39Pmsr0h3evkq6DPxO+XjGGaRutDE5+S3vYRsLgSsiYnTlMTIizsvrviki3k3qjnsI+I/+xmlDhxOHDQkRsQw4B/iOpPdJGiVpE0l7kL6Qu7oaOEnSHvnGRV8Fbo+IBZV5PpVvbDSJdC+QH+byrYCVwLJ8jOFTpfEq3f98b0mb5mMXHyfd5+HhvP41wB+A4ZI+T7r3Q3euBI6SdJikYZI2l9QmaaKkcZKOzknxxRzzK6Wx2tDjxGFDRkR8A/gn4NOkW2s+A3yP9Ov9ti7z3gycTbpF52Lg9aS7pFVdT7oR1D2kA9CX5vJzSAfMl+fyH1MugO8Dz5JaMu8G3pO7zG4CbiTdhOdJYDXrdptVX8dCUivrs6REs5CUyDbJj9Pz+peSjsOc2o9YbYjxjZzMzKyIWxxmZlbEicOsRSTdKGllN4/Ptjo2s964q8rMzIq4xWFmZkWcOMzMrIgTh5mZFXHiMDOzIv8fEgSYdA1YC3gAAAAASUVORK5CYII=\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "import matplotlib as mpl\n", + "import scipy.stats as spstats\n", + "\n", + "fig, ax = plt.subplots()\n", + "bin_df['Year'].hist(color='#A9C5D3')\n", + "ax.set_title('Developer Global_Sales Hostogram', fontsize=12)\n", + "ax.set_xlabel('Global_Sales', fontsize=12)\n", + "ax.set_ylabel('Frequency', fontsize=12)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "这样区间就出来了，我们可以分成多个区间，如1980-1985是一个区间，1986-1990是一个区间" + ] + }, + { + "cell_type": "code", + "execution_count": 129, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
NameYearYear_bin
0Wii Sports2006.05
1Super Mario Bros.1985.01
2Mario Kart Wii2008.06
3Wii Sports Resort2009.06
4Pokemon Red/Pokemon Blue1996.03
5Tetris1989.02
6New Super Mario Bros.2006.05
7Wii Play2006.05
8New Super Mario Bros. Wii2009.06
9Duck Hunt1984.00
\n", + "
" + ], + "text/plain": [ + " Name Year Year_bin\n", + "0 Wii Sports 2006.0 5\n", + "1 Super Mario Bros. 1985.0 1\n", + "2 Mario Kart Wii 2008.0 6\n", + "3 Wii Sports Resort 2009.0 6\n", + "4 Pokemon Red/Pokemon Blue 1996.0 3\n", + "5 Tetris 1989.0 2\n", + "6 New Super Mario Bros. 2006.0 5\n", + "7 Wii Play 2006.0 5\n", + "8 New Super Mario Bros. Wii 2009.0 6\n", + "9 Duck Hunt 1984.0 0" + ] + }, + "execution_count": 129, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gle = LabelEncoder() # 实例化\n", + "bin_df['Year_bin'] = pd.cut(bin_df['Year'], 9) # 切分成9组\n", + "bin_df['Year_bin'] = bin_df['Year_bin'].astype(str) # 转换类型为字符串\n", + "bin_year = gle.fit_transform(bin_df['Year_bin']) # 利用LabelEncoder方法变成1-9的数值\n", + "bin_df['Year_bin'] = bin_year # 赋值到新的列\n", + "bin_df.head(10)" + ] + }, { "cell_type": "code", "execution_count": null,