基尼系数 java_信息熵和基尼系数.ipynb

{

"cells": [

{

"cell_type": "code",

"execution_count": 2,

"metadata": {},

"outputs": [

{

"data": {

"text/html": [

"

\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",

"\n",

"

" \n",

"

\n",

"

\n",

"

userId\n",

"

movieId\n",

"

rating\n",

"

\n",

"

\n",

"

\n",

"

\n",

"

0\n",

"

1\n",

"

2\n",

"

3.5\n",

"

\n",

"

\n",

"

1\n",

"

1\n",

"

29\n",

"

3.5\n",

"

\n",

"

\n",

"

2\n",

"

1\n",

"

32\n",

"

3.5\n",

"

\n",

"

\n",

"

3\n",

"

1\n",

"

47\n",

"

3.5\n",

"

\n",

"

\n",

"

4\n",

"

1\n",

"

50\n",

"

3.5\n",

"

\n",

"

\n",

"

\n",

"

"

],

"text/plain": [

" userId movieId rating\n",

"0 1 2 3.5\n",

"1 1 29 3.5\n",

"2 1 32 3.5\n",

"3 1 47 3.5\n",

"4 1 50 3.5"

]

},

"execution_count": 2,

"metadata": {},

"output_type": "execute_result"

}

],

"source": [

"import pandas as pd\n",

"import numpy as np\n",

"import matplotlib.pyplot as plt\n",

"# 读取rating.csv\n",

"df_data = pd.read_csv('D:python作业/rating.csv',sep=',',usecols=['userId','movieId','rating'])\n",

"df_data.head()"

]

},

{

"cell_type": "code",

"execution_count": 3,

"metadata": {},

"outputs": [

{

"data": {

"text/plain": [

"296 67310\n",

"356 66172\n",

"318 63366\n",

"593 63299\n",

"480 59715\n",

"Name: movieId, dtype: int64"

]

},

"execution_count": 3,

"metadata": {},

"output_type": "execute_result"

}

],

"source": [

"movie_rating_count = df_data['movieId'].value_counts() # 每个电影ID对应的分数\n",

"movie_rating_count.head()"

]

},

{

"cell_type": "code",

"execution_count": 4,

"metadata": {},

"outputs": [

{

"data": {

"image/png": "iVBORw0KGgoAAAANSUhEUgAAAZIAAAEWCAYAAABMoxE0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nO3deZxcZZ3v8c+3u9OdfW9iSAIJEHAAFSWGuAyzZBDEBcaBIW5Eb+7NiKj4cpwRZrwOOpcZ1OvGCDgoXgIqEHEhLlEZFh0RExoBQ4BIIJCERNKQhZC9u3/3j/NUUtWprq5eqquX7/tlverUc85zzvNUYf/yLOc5igjMzMy6q6baBTAzs4HNgcTMzHrEgcTMzHrEgcTMzHrEgcTMzHrEgcTMzHrEgcQMkPSnktZUuxwAkt4t6RfVLodZuRxIbECQ9LSk/ZImt0t/SFJImtmT80fEf0fECd0s2w2pbC9J2irpDkkvLzPvzFT+uryyfDsi3tSdspR5zXdJakrl3SxpuaQ3Vup6edcNScdV+jrW9xxIbCBZB7wz90HSK4AR1StOgc9FxGhgGvAscH2Vy1OUpI8BXwb+DZgCHAVcA5xTzXLZwOZAYgPJTcCFeZ8XAjfmHyBpnKQbJTVLekbSJyXVSGqQtF3SyXnHNkraI+kISX8uaWPeviMlfS+dZ52kj5RTwIjYAywFTsk711skPSjpRUkbJF2el+VX6X17aiG8TtL7JP06L39I+oCkJyRtk3S1JKV9tZK+IOn5VM4PtW/h5H83wGeAiyPi+xGxKyIORMSPIuIf0jENkr4saVN6fVlSQ9pXUK68sh2Xtm9IZfuJpJ2SVkg6Nu3L1fPhVM8Lyvk+bWBwILGB5LfAWEl/IqkWuAD4Vrtj/gMYBxwD/BlZ4Hl/ROwDvk9eiwb4W+CXEbEl/wSSaoAfAQ+TtTDmAx+VdGZnBZQ0K