ipo/gz.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Weather test\n",
      "成功访问\n",
      "成功访问\n"
     ]
    }
   ],
   "source": [
    "# weather.py\n",
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "import csv\n",
    "import json\n",
    "\n",
    "\n",
    "def getHTMLtext(url):\n",
    "    \"\"\"请求获得网页内容\"\"\"\n",
    "    try:\n",
    "        r = requests.get(url, timeout=30)\n",
    "        r.raise_for_status()\n",
    "        r.encoding = r.apparent_encoding\n",
    "        print(\"成功访问\")\n",
    "        return r.text\n",
    "    except:\n",
    "        print(\"访问错误\")\n",
    "        return \" \"\n",
    "\n",
    "\n",
    "def get_content(html):\n",
    "    \"\"\"处理得到有用信息保存数据文件\"\"\"\n",
    "    final = []  # 初始化一个列表保存数据\n",
    "    bs = BeautifulSoup(html, \"html.parser\")  # 创建BeautifulSoup对象\n",
    "    body = bs.body\n",
    "    data = body.find('div', {'id': '7d'})  # 找到div标签且id = 7d\n",
    "    # 下面爬取当天的数据\n",
    "    data2 = body.find_all('div', {'class': 'left-div'})\n",
    "    text = data2[2].find('script').string\n",
    "    text = text[text.index('=') + 1:-2]  # 移除改var data=将其变为json数据\n",
    "    jd = json.loads(text)\n",
    "    dayone = jd['od']['od2']  # 找到当天的数据\n",
    "    final_day = []  # 存放当天的数据\n",
    "    count = 0\n",
    "    for i in dayone:\n",
    "        temp = []\n",
    "        if count <= 23:\n",
    "            temp.append(i['od21'])  # 添加时间\n",
    "            temp.append(i['od22'])  # 添加当前时刻温度\n",
    "            temp.append(i['od24'])  # 添加当前时刻风力方向\n",
    "            temp.append(i['od25'])  # 添加当前时刻风级\n",
    "            temp.append(i['od26'])  # 添加当前时刻降水量\n",
    "            temp.append(i['od27'])  # 添加当前时刻相对湿度\n",
    "            temp.append(i['od28'])  # 添加当前时刻控制质量\n",
    "            # print(temp)\n",
    "            final_day.append(temp)\n",
    "        count = count + 1\n",
    "    # 下面爬取7天的数据\n",
    "    ul = data.find('ul')  # 找到所有的ul标签\n",
    "    li = ul.find_all('li')  # 找到左右的li标签\n",
    "    i = 0  # 控制爬取的天数\n",
    "    for day in li:  # 遍历找到的每一个li\n",
    "        if i < 7 and i > 0:\n",
    "            temp = []  # 临时存放每天的数据\n",
    "            date = day.find('h1').string  # 得到日期\n",
    "            date = date[0:date.index('日')]  # 取出日期号\n",
    "            temp.append(date)\n",
    "            inf = day.find_all('p')  # 找出li下面的p标签,提取第一个p标签的值，即天气\n",
    "            temp.append(inf[0].string)\n",
    "\n",
    "            tem_low = inf[1].find('i').string  # 找到最低气温\n",
    "\n",
    "            if inf[1].find('span') is None:  # 天气预报可能没有最高气温\n",
    "                tem_high = None\n",
    "            else:\n",
    "                tem_high = inf[1].find('span').string  # 找到最高气温\n",
    "            temp.append(tem_low[:-1])\n",
    "            if tem_high[-1] == '℃':\n",
    "                temp.append(tem_high[:-1])\n",
    "            else:\n",
    "                temp.append(tem_high)\n",
    "\n",
    "            wind = inf[2].find_all('span')  # 找到风向\n",
    "            for j in wind:\n",
    "                temp.append(j['title'])\n",
    "\n",
    "            wind_scale = inf[2].find('i').string  # 找到风级\n",
    "            index1 = wind_scale.index('级')\n",
    "            temp.append(int(wind_scale[index1 - 1:index1]))\n",
    "            final.append(temp)\n",
    "        i = i + 1\n",
    "    return final_day, final\n",
    "\n",
    "\n",
    "# print(final)\n",
    "def get_content2(html):\n",
    "    \"\"\"处理得到有用信息保存数据文件\"\"\"\n",
    "    final = []  # 初始化一个列表保存数据\n",
    "    bs = BeautifulSoup(html, \"html.parser\")  # 创建BeautifulSoup对象\n",
    "    body = bs.body\n",
    "    data = body.find('div', {'id': '15d'})  # 找到div标签且id = 15d\n",
    "    ul = data.find('ul')  # 找到所有的ul标签\n",
    "    li = ul.find_all('li')  # 找到左右的li标签\n",
    "    final = []\n",
    "    i = 0  # 控制爬取的天数\n",
    "    for day in li:  # 遍历找到的每一个li\n",
    "        if i < 8:\n",
    "            temp = []  # 临时存放每天的数据\n",
    "            date = day.find('span', {'class': 'time'}).string  # 得到日期\n",
    "            date = date[date.index('（') + 1:-2]  # 取出日期号\n",
    "            temp.append(date)\n",
    "            weather = day.find('span', {'class': 'wea'}).string  # 找到天气\n",
    "            temp.append(weather)\n",
    "            tem = day.find('span', {'class': 'tem'}).text  # 找到温度\n",
    "            temp.append(tem[tem.index('/') + 1:-1])  # 找到最低气温\n",
    "            temp.append(tem[:tem.index('/') - 1])  # 找到最高气温\n",
    "            wind = day.find('span', {'class': 'wind'}).string  # 找到风向\n",
    "            if '转' in wind:  # 如果有风向变化\n",
    "                temp.append(wind[:wind.index('转')])\n",
    "                temp.append(wind[wind.index('转') + 1:])\n",
    "            else:  # 如果没有风向变化，前后风向一致\n",
    "                temp.append(wind)\n",
    "                temp.append(wind)\n",
    "            wind_scale = day.find('span', {'class': 'wind1'}).string  # 找到风级\n",
    "            index1 = wind_scale.index('级')\n",
    "            temp.append(int(wind_scale[index1 - 1:index1]))\n",
    "\n",
    "            final.append(temp)\n",
    "    return final\n",
    "\n",
    "\n",
    "def write_to_csv(file_name, data, day=14):\n",
    "    \"\"\"保存为csv文件\"\"\"\n",
    "    with open(file_name, 'a', errors='ignore', newline='') as f:\n",
    "        if day == 14:\n",
    "            header = ['日期', '天气', '最低气温', '最高气温', '风向1', '风向2', '风级']\n",
    "        else:\n",
    "            header = ['小时', '温度', '风力方向', '风级', '降水量', '相对湿度', '空气质量']\n",
    "        f_csv = csv.writer(f)\n",
    "        f_csv.writerow(header)\n",
    "        f_csv.writerows(data)\n",
    "\n",
    "\n",
    "def main():\n",
    "    \"\"\"主函数\"\"\"\n",
    "    print(\"Weather test\")\n",
    "    # 珠海\n",
    "    url1 = 'http://www.weather.com.cn/weather/101280701.shtml'  # 7天天气中国天气网\n",
    "    url2 = 'http://www.weather.com.cn/weather15d/101280701.shtml'  # 8-15天天气中国天气网\n",
    "\n",
    "    html1 = getHTMLtext(url1)\n",
    "    data1, data1_7 = get_content(html1)  # 获得1-7天和当天的数据\n",
    "\n",
    "    html2 = getHTMLtext(url2)\n",
    "    data8_14 = get_content2(html2)  # 获得8-14天数据\n",
    "    data14 = data1_7 + data8_14\n",
    "    # print(data)\n",
    "    write_to_csv('weather14.csv', data14, 14)  # 保存为csv文件\n",
    "    write_to_csv('weather1.csv', data1, 1)\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    main()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    小时  温度 风力方向  风级  降水量  相对湿度  空气质量\n",
      "0   20  22  东南风   4    0    77   NaN\n",
      "1   19  22  东南风   4    0    71  35.0\n",
      "2   18  22  东南风   3    0    73  36.0\n",
      "3   17  23  东南风   3    0    73  38.0\n",
      "4   16  24  东南风   4    0    71  38.0\n",
      "5   15  24  东南风   4    0    69  38.0\n",
      "6   14  24  东南风   4    0    69  38.0\n",
      "7   13  25  东南风   3    0    67  36.0\n",
      "8   12  26   东风   3    0    65  34.0\n",
      "9   11  24  东南风   4    0    66  26.0\n",
      "10  10  23   东风   3    0    73  24.0\n",
      "11   9  23   东风   3    0    70  24.0\n",
      "12   8  23   东风   3    0    69  25.0\n",
      "13   7  23   东风   2    0    71  31.0\n",
      "14   6  23  东北风   2    0    76  41.0\n",
      "15   5  23   东风   3    0    83  44.0\n",
      "16   4  23  东南风   2    0    85  49.0\n",
      "17   3  22  东南风   2    0    87  49.0\n",
      "18   2  22   东风   2    0    88  51.0\n",
      "19   1  23  东北风   1    0    82  53.0\n",
      "20   0  23  东南风   1    0    82  56.0\n",
      "21  23  23  东南风   2    0    81  54.0\n",
      "22  22  24   东风   2    0    75  52.0\n",
      "23  21  25   东风   1    0    61  52.0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEUCAYAAAAstV3AAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d52cf748>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEUCAYAAAAstV3AAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nI834fwQNPvKr5BCMAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d53664e0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'numpy.float64'>\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEUCAYAAADDdzb+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d5377f28>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1.5, 0, 0, 0, 0, 0, 3.076923076923077, 2.4444444444444446]\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAREAAAEXCAYAAACKzXCTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nANKCSVvsAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d567ceb8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAegAAAGICAYAAACKpHNWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ndP8AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d5744cf8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "相关系数为：-0.6557721797643076\n"
     ]
    }
   ],
   "source": [
    "# data1_analysis.py\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import math\n",
    "\n",
    "\n",
    "def tem_curve(data):\n",
    "    \"\"\"温度曲线绘制\"\"\"\n",
    "    hour = list(data['小时'])\n",
    "    tem = list(data['温度'])\n",
    "    for i in range(0, 24):\n",
    "        if math.isnan(tem[i]) == True:\n",
    "            tem[i] = tem[i - 1]\n",
    "    tem_ave = sum(tem) / 24  # 求平均温度\n",
    "    tem_max = max(tem)\n",
    "    tem_max_hour = hour[tem.index(tem_max)]  # 求最高温度\n",
    "    tem_min = min(tem)\n",
    "    tem_min_hour = hour[tem.index(tem_min)]  # 求最低温度\n",
    "    x = []\n",
    "    y = []\n",
    "    for i in range(0, 24):\n",
    "        x.append(i)\n",
    "        y.append(tem[hour.index(i)])\n",
    "    plt.figure(1)\n",
    "    plt.plot(x, y, color='red', label='温度')  # 画出温度曲线\n",
    "    plt.scatter(x, y, color='red')  # 点出每个时刻的温度点\n",
    "    plt.plot([0, 24], [tem_ave, tem_ave], c='blue', linestyle='--', label='平均温度')  # 画出平均温度虚线\n",
    "    plt.text(tem_max_hour + 0.15, tem_max + 0.15, str(tem_max), ha='center', va='bottom', fontsize=10.5)  # 标出最高温度\n",
    "    plt.text(tem_min_hour + 0.15, tem_min + 0.15, str(tem_min), ha='center', va='bottom', fontsize=10.5)  # 标出最低温度\n",
    "    plt.xticks(x)\n",
    "    plt.legend()\n",
    "    plt.title('一天温度变化曲线图')\n",
    "    plt.xlabel('时间/h')\n",
    "    plt.ylabel('摄氏度/℃')\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def hum_curve(data):\n",
    "    \"\"\"相对湿度曲线绘制\"\"\"\n",
    "    hour = list(data['小时'])\n",
    "    hum = list(data['相对湿度'])\n",
    "    for i in range(0, 24):\n",
    "        if math.isnan(hum[i]) == True:\n",
    "            hum[i] = hum[i - 1]\n",
    "    hum_ave = sum(hum) / 24  # 求平均相对湿度\n",
    "    hum_max = max(hum)\n",
    "    hum_max_hour = hour[hum.index(hum_max)]  # 求最高相对湿度\n",
    "    hum_min = min(hum)\n",
    "    hum_min_hour = hour[hum.index(hum_min)]  # 求最低相对湿度\n",
    "    x = []\n",
    "    y = []\n",
    "    for i in range(0, 24):\n",
    "        x.append(i)\n",
    "        y.append(hum[hour.index(i)])\n",
    "    plt.figure(2)\n",
    "    plt.plot(x, y, color='blue', label='相对湿度')  # 画出相对湿度曲线\n",
    "    plt.scatter(x, y, color='blue')  # 点出每个时刻的相对湿度\n",
    "    plt.plot([0, 24], [hum_ave, hum_ave], c='red', linestyle='--', label='平均相对湿度')  # 画出平均相对湿度虚线\n",
    "    plt.text(hum_max_hour + 0.15, hum_max + 0.15, str(hum_max), ha='center', va='bottom', fontsize=10.5)  # 标出最高相对湿度\n",
    "    plt.text(hum_min_hour + 0.15, hum_min + 0.15, str(hum_min), ha='center', va='bottom', fontsize=10.5)  # 标出最低相对湿度\n",
    "    plt.xticks(x)\n",
    "    plt.legend()\n",
    "    plt.title('一天相对湿度变化曲线图')\n",
    "    plt.xlabel('时间/h')\n",
    "    plt.ylabel('百分比/%')\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def air_curve(data):\n",
    "    \"\"\"空气质量曲线绘制\"\"\"\n",
    "    hour = list(data['小时'])\n",
    "    air = list(data['空气质量'])\n",
    "    print(type(air[0]))\n",
    "    for i in range(0, 24):\n",
    "        if math.isnan(air[i]) == True:\n",
    "            air[i] = air[i - 1]\n",
    "    air_ave = sum(air) / 24  # 求平均空气质量\n",
    "    air_max = max(air)\n",
    "    air_max_hour = hour[air.index(air_max)]  # 求最高空气质量\n",
    "    air_min = min(air)\n",
    "    air_min_hour = hour[air.index(air_min)]  # 求最低空气质量\n",
    "    x = []\n",
    "    y = []\n",
    "    for i in range(0, 24):\n",
    "        x.append(i)\n",
    "        y.append(air[hour.index(i)])\n",
    "    plt.figure(3)\n",
    "\n",
    "    for i in range(0, 24):\n",
    "        if y[i] <= 50:\n",
    "            plt.bar(x[i], y[i], color='lightgreen', width=0.7)  # 1等级\n",
    "        elif y[i] <= 100:\n",
    "            plt.bar(x[i], y[i], color='wheat', width=0.7)  # 2等级\n",
    "        elif y[i] <= 150:\n",
    "            plt.bar(x[i], y[i], color='orange', width=0.7)  # 3等级\n",
    "        elif y[i] <= 200:\n",
    "            plt.bar(x[i], y[i], color='orangered', width=0.7)  # 4等级\n",
    "        elif y[i] <= 300:\n",
    "            plt.bar(x[i], y[i], color='darkviolet', width=0.7)  # 5等级\n",
    "        elif y[i] > 300:\n",
    "            plt.bar(x[i], y[i], color='maroon', width=0.7)  # 6等级\n",
    "    plt.plot([0, 24], [air_ave, air_ave], c='black', linestyle='--')  # 画出平均空气质量虚线\n",
    "    plt.text(air_max_hour + 0.15, air_max + 0.15, str(air_max), ha='center', va='bottom', fontsize=10.5)  # 标出最高空气质量\n",
    "    plt.text(air_min_hour + 0.15, air_min + 0.15, str(air_min), ha='center', va='bottom', fontsize=10.5)  # 标出最低空气质量\n",
    "    plt.xticks(x)\n",
    "    plt.title('一天空气质量变化曲线图')\n",
    "    plt.xlabel('时间/h')\n",
    "    plt.ylabel('空气质量指数AQI')\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def wind_radar(data):\n",
    "    \"\"\"风向雷达图\"\"\"\n",
    "    wind = list(data['风力方向'])\n",
    "    wind_speed = list(data['风级'])\n",
    "    for i in range(0, 24):\n",
    "        if wind[i] == \"北风\":\n",
    "            wind[i] = 90\n",
    "        elif wind[i] == \"南风\":\n",
    "            wind[i] = 270\n",
    "        elif wind[i] == \"西风\":\n",
    "            wind[i] = 180\n",
    "        elif wind[i] == \"东风\":\n",
    "            wind[i] = 360\n",
    "        elif wind[i] == \"东北风\":\n",
    "            wind[i] = 45\n",
    "        elif wind[i] == \"西北风\":\n",
    "            wind[i] = 135\n",
    "        elif wind[i] == \"西南风\":\n",
    "            wind[i] = 225\n",
    "        elif wind[i] == \"东南风\":\n",
    "            wind[i] = 315\n",
    "    degs = np.arange(45, 361, 45)\n",
    "    temp = []\n",
    "    for deg in degs:\n",
    "        speed = []\n",
    "        # 获取 wind_deg 在指定范围的风速平均值数据\n",
    "        for i in range(0, 24):\n",
    "            if wind[i] == deg:\n",
    "                speed.append(wind_speed[i])\n",
    "        if len(speed) == 0:\n",
    "            temp.append(0)\n",
    "        else:\n",
    "            temp.append(sum(speed) / len(speed))\n",
    "    print(temp)\n",
    "    N = 8\n",
    "    theta = np.arange(0. + np.pi / 8, 2 * np.pi + np.pi / 8, 2 * np.pi / 8)\n",
    "    # 数据极径\n",
    "    radii = np.array(temp)\n",
    "    # 绘制极区图坐标系\n",
    "    plt.axes(polar=True)\n",
    "    # 定义每个扇区的RGB值（R,G,B），x越大，对应的颜色越接近蓝色\n",
    "    colors = [(1 - x / max(temp), 1 - x / max(temp), 0.6) for x in radii]\n",
    "    plt.bar(theta, radii, width=(2 * np.pi / N), bottom=0.0, color=colors)\n",
    "    plt.title('一天风级图', x=0.2, fontsize=20)\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def calc_corr(a, b):\n",
    "    \"\"\"计算相关系数\"\"\"\n",
    "    a_avg = sum(a) / len(a)\n",
    "    b_avg = sum(b) / len(b)\n",
    "    cov_ab = sum([(x - a_avg) * (y - b_avg) for x, y in zip(a, b)])\n",
    "    sq = math.sqrt(sum([(x - a_avg) ** 2 for x in a]) * sum([(x - b_avg) ** 2 for x in b]))\n",
    "    corr_factor = cov_ab / sq\n",
    "    return corr_factor\n",
    "\n",
    "\n",
    "def corr_tem_hum(data):\n",
    "    \"\"\"温湿度相关性分析\"\"\"\n",
    "    tem = data['温度']\n",
    "    hum = data['相对湿度']\n",
    "    plt.scatter(tem, hum, color='blue')\n",
    "    plt.title(\"温湿度相关性分析图\")\n",
    "    plt.xlabel(\"温度/℃\")\n",
    "    plt.ylabel(\"相对湿度/%\")\n",
    "    plt.text(20, 40, \"相关系数为：\" + str(calc_corr(tem, hum)), fontdict={'size': '10', 'color': 'red'})\n",
    "    plt.show()\n",
    "    print(\"相关系数为：\" + str(calc_corr(tem, hum)))\n",
    "\n",
    "\n",
    "def main():\n",
    "    plt.rcParams['font.sans-serif'] = ['SimHei']  # 解决中文显示问题\n",
    "    plt.rcParams['axes.unicode_minus'] = False  # 解决负号显示问题\n",
    "    data1 = pd.read_csv('weather1.csv', encoding='gb2312')\n",
    "    print(data1)\n",
    "    tem_curve(data1)\n",
    "    hum_curve(data1)\n",
    "    air_curve(data1)\n",
    "    wind_radar(data1)\n",
    "    corr_tem_hum(data1)\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    main()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    日期     天气  最低气温  最高气温    风向1    风向2  风级\n",
      "0   16     多云    19    22     东风     东风   4\n",
      "1   17      阴    19    22  无持续风向  无持续风向   3\n",
      "2   18     多云    18    23  无持续风向    东北风   3\n",
      "3   19  多云转阵雨    19    25  无持续风向  无持续风向   3\n",
      "4   20  阵雨转多云    20    25  无持续风向  无持续风向   3\n",
      "5   21     多云    22    28  无持续风向  无持续风向   3\n",
      "6   22     多云    23    30  无持续风向    东南风   3\n",
      "7   23      雨    24    27     南风     南风   3\n",
      "8   24      雨    25    28     南风     南风   3\n",
      "9   25    雨转阴    24    27     南风     南风   4\n",
      "10  26      阴    25    28     南风     南风   3\n",
      "11  27    阴转晴    24    28     南风     南风   3\n",
      "12  28      晴    24    28    东南风    东南风   3\n",
      "13  29   多云转晴    25    28    东南风    东南风   3\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAETCAYAAAAxsG14AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xd4VNXWwOHfogQIvQsGgh3x+omABUUFyxV7AUEEFFBR\nsaF4bWBDBJFqA42oIEEEG4qIV0EREUQRc62AqICoVCnSIVnfH/sEJsmknzMzyaz3eeZJ5pwz+6yZ\nZNbs2XufvUVVMcYYEz/KRDsAY4wxkWWJ3xhj4owlfmOMiTOW+I0xJs5Y4jfGmDhjid+YOCJO5WjH\nYaLLEr/JQkReFZFOBTx2pIjc4+O5RUQS8thXIZ/H3yIiLfLYX70IMR0qIm0LeGyhy8/2+I4iUrMA\nx5UvQtnpIlIFOAxYnsdx7UWkWbaYzhARyxWlSLloB2Bizj5gb7gdXlJOV9V0b9NWYHfI/rJAGVXd\nG7KtK3C2qvYMU15P4AxV7eFtOhyYJyKZj68GZADbAAEqiEiyqm4XkWSgixdvpq7ABSIyO2RbeSBF\nVTcCY0VkDXA3MA9o7JWfqYaqVskWZhegsoj8AhwE1AEOBY4FzgO6qOp879gCl+8l0rLAPj1wMc0l\n3mNGeseIF/8+VQ0t53MRuUtV54rIJOAtVX2TvO1U1W0ispuQv1koL6YRQPeQzacCK4CzRWSrqg4L\nOX4xLofsyeO8jVS1fj6xmQizxB/nROQqoC8H3rxHAK1EpB/uG2E1oLWq/gPcAVwdkpgPAtJFpId3\nvxzwLDDWK/tC7/60MOetCwwD3svcpqo/A/VDjnkY2Kyqo8OEvgNYStYPqQfCHFc+5LldDaQAR3nb\nWqjqmpDzLQnz+C7A5cBAoCLwHXAFLjkPVNU/Q44tTPnNgfHAPhHJAJrhauItvee9DPfBUB7oDPzg\nldEeQFXneuXsBdK9fXWAy1U1JczzyPyAzOuKzW7AW8AuETlLVWcD24FdwONABxE5UVW/DDn35aq6\nQkROwb3+52d+kIlIOdyHhokxlvjjnKq+CryaeV9ExgPTVDVHslbVoSIyFbgf6A08BGwGngbeBK5X\n1fUhD+kJPIqrHWc3CvioGHGvB94WkRuA/sCqbIc0A9qo6o/e86oGHKKqvbz7GcAsEQn9xtAwtAAR\nOQM4RlWXeTXlCao6R0SOAX4MTfqFLV9VF4vIcbiEOhqYCVyK+0bxOO5Dtp6XfDPPkQAMB17O/np4\nSTYVWBKybRPuw2Q3UEVE5gEJwEHe7xWBxqpaT0SOAG4CzgfGAd+KSG3gFOBgoBPwN5AIhCb+zCau\nF4CdwFci0hT3N3mWrN/ITIywxB/HvKYZQppuwh1TBkhQ1V3esb95be1nhBzWGViWLekDdASuCVPm\nOUAS8EjofhFZifufzKyVVgMyROSuzENwiStJVTObK9KB74F3s52mj7cvUyXgQRH5WlUHe+cZC2wJ\nOWZItjIeInwzxnZc84/gXpvdRSz/FqCtd57sqgCTReQaVZ3pbXsC9+GR/e+ViHv+P6nqHSHb9wJX\neDXyzaraRkSSgHne74cDn3rHtgcaAJ8Ba4GpuL/Nz8BnqvqQ97/QUkRqe01n4L6VTMd9KHwGfAFc\nh6sMWL9AjLLEH99OA4aISGYiSQKSge4issDbVgbXtt4deIcDiexJXE0wHfgT1+SzCKgKXKmq36iq\nutx4gIhUwtX2L/MeH+oIYG9IU8FiXJ9Bc+++ABVCkj7AB4RvTrgT+CPzjqquxTVV1PE2/QfI3hnb\nKyTODsAGIPTD7GkR2eK9Tm29feWAk4pQ/kHADcA5qrrLq7GXxX2wlVfVBSLSERghIrOAFrja98gw\nz/Up4AlVfSLb9owwx2aX+SH7rKo+LSJTgAeB33HNcN2Ay0XkVNyH0SpgAJCZ+NOBW3Gv1Txcs+EF\nqpphHcKxyxJ/HFPVOUBrAG80yee4r/FVcM09wzOP9ZLuUd4bugKupvglUBeXDDqGdFLm5SHgFVX9\nWUSyJH5V3V+7FpGTcG3La0XkMlV92yt/V8gxfwK/5nUyETlMVRt4v9cAnhWRZ3HJMtzxL6jqs7ga\n9BzgfyG7b/Waeq4GklX10WyPLXD5qrpGRC4BPvD6TI7BfYhVABp5H6JPASd6z3uhiLQBbvPKEdwH\nyeXA/ar6TC4vweteM1VuTT2hsd2L+7Dc48VzJa5v4UTgYuBa4GtVXRbysEbAw97vr+L+h24QkRTc\nNxoTgyzxm8w22um4mvipuAR0n4hsUtUXAbzko17NdAIwG9eUsAVoA7wqIj0zm4TycBFQR0TuxCWh\nSiJSTVUvD4knAXgG1/n7Ha6t/CtVXZ2trL24mnczXGIK9S7wI1mHLp6J+3aSCKThOlfb4r4xHASs\nxg13xBuZtDHMN5ZEYBGugze7Apfv+RU4AegHzFHVu7xz3Oq9Tq+Gfpiq6h4vngq4BPsn7sMp++sS\nKr+mnjnecfWB23Ed5o8Cz6jqLV48fXDt/72ADtnK/x3Xqf0nbjTQYFwHd29yGT1kos++isU5EfkX\nLonMUNUXvM27cEMV7xaRyV5nZmbzxAxck0TmCBrFveFrAN+LSBevOScsVT1GVeur6kG42uqUbEm/\nLu5D6CdVnaqqP+G+JXzidYZmKc77eRiujT3Vu9UB/hXm9B1xzRe59mnks+9Y4GPciJsjRKSuiDSU\nA9cXFKp8dfao6hCgnIiME5GBuGGdl6lqbh2ju4GuqtoR17a+n4j8K6/XPzeq+pf3zegCXN/EkV55\nZYCVuM7mdrgPhv2n8x77B24I6y24Tv5PVXWr91yzfnKamGCJP455zSkf44YlZnY8lgHEG7HSEteO\nPc9r4/0RV8Pr4o0rzzx2B66GOhXXPJG97b4gsVQWkd64jtrluA5CAFR1HK5j9BMRmZj5QcSBpLIN\n901lvHdrjmuD3v//7TVlnY3rgCyMMl7ya4gbpfQV7vk9hfuGdD3Qq6jli3M0rtZ+Dq6m/BWuE7Vh\nmHbyzNf8N+9+Bq7PIbOz/jkOjMMXXFPPPA409bzFgaae10LiOEtE/gDm4r7NbBKRY3Hf7FYCm4CT\ncR3YmX0V+y8kU9WhwIW4v8VRIfFaq0IsUlW7xfENqJ7t/jRc52zotorez6OzbR8F3JNtW2IR42iB\na3Y4M49jkoGhmTHjmhfK5XJsRVwSm+zdPxPXBt0RV2tdhWuOWY77QFuGa89eCdwYUs5Gr6zTgcrA\nSbjhjoL7kPkL10xSqPKBWsAC3AfpdFz7eRXvdj3wPm6o7HKgckg8/UNfc1wn+fe4YZxLgFlATW/f\nZqBJHq/n4cA67/dyQMOQfZd4sV7m3W/ilb8VOMzbtth7bml53NZG+3/cbjlv4v0BjSl1RCRBs3YY\nl9Pcm0/8OF+hyheRRsAfmvWq3OzHVFHVbb4EWEhhXr8EoJqqbvDu18ZdYJdX05aJQZb4jTEmzlgb\nvzHGxBlL/MYYE2disse9Tp062qRJk2iHYYwxJcrXX3+9QVXr5ndcTCb+Jk2asGjRomiHYYwxJYo3\n31W+rKnHxIx//vmHmTNnsmRJuNmRjTF+scRvYsK2bds499xzSUtL49prr2X69OlMmDCB448/nosv\nvpgtW7bkX4gxpkBisqnHxJ+lS5fSv39/LrjgAv71r3/x1ltvsXjxYhYuXMjChQsZMWIEAwcOjHaY\nxpQKlvhNTGjZsiUA3333Hc8++yynnXYadevWpWLFipx++ukMHTo0yhGakmbv3r2sXr2aXbvymzew\n5KlYsSJJSUmUL1/o5ZcBS/wmxnz00UesW7eOjIwMDj7YTfkjIqXyzWuCtXr1aqpWrUqTJk3IPstq\nSaaqbNy4kdWrV3PIIYcUqQxr4zcx5c477+SJJ55g5MiRbN++ff/2rVu3RjEqUxLt2rWL2rVrl6qk\nD64iVLt27WJVhizxm5gwceJEHnzwQQA2bdpEx44dmTdvHgDLly+nZs2a0QzPlFClLelnKu7zCizx\ni0gtETknZCk6Y3LVuXNnlixZwmmnncaECRMYPHgw1atXp3fv3nTp0oXrr7++8IVOmgRNmkCZMu7n\npEl+h21MoWzatIkdO3bk2L5z586IxhFIG7+INMDN+/0eMFJEzgQeB44G3lfVQUGc15RcCQkJTJ06\nNcu21NRUpk+fTs+ePWndunXhCpw0CXr3hsw32cqV7j5A164+RGxM/tauXcuvv/66v4Y+dOhQjjvu\nONq3bw9ARkYGTZs25dJLL2XgwIF89dVXvPjii1SpUgWAjRs3MmzYMDp27OhrXEF17h4D3KGqX3gL\nVJwJlFXVU0RkjIgcoao/B3RuU0qULVuWSy+9tGgP7t//QNLPtGOH226J30TIxo0bWbx4MWXLlgXg\n3HPPBSAtLQ2A9PR0GjRowKuvvsqTTz5Jw4YNGTduHG3atAFg/PjxgcQVSOJX1VkAInI6bqHmWrjV\nmcCt+NQGyJL4vdWXegM0btw4iLBMPFm1qnDbjQlAs2bNaNasGccffzzVq1ffv33v3r0ceuihTJw4\nkRUrVrB7926GDRvG6NGjufXWW/cfu2bNGgYN8r+BJLDhnOK+23TGLYgtwB/erq24lX+yUNUU3CLN\ntGrVyhYJMMVTvz6sWZNzu1Uq4lPfvuDVsn3TvDmMHl2gQ1u0aMERRxyx//7evXv3/16hQgVuvPFG\nhgwZwr59+zj55JNJTk4G4Ouvv/Y3Zk9giV/dCi83i8ijuOXoMheAroKNJjJB2rXLdeiKQOhCQ4mJ\n8Nhj0YvLxJ0tW7ZwySWXAPDLL7/k2D979mzeeustUlNTqVq1Kg0bNmTDhg3793fs2JEGDRr4HldQ\nnbv3AH+p6itADVzHbhvgC+A43JqkxgTjwQfhzz/hnnvgtddcxy7AsGHWvh+vClgz91tGRgY1atRg\n2rRpTJ8+nfR0t0qliHDJJZfQsWNHRISJEyfSuHFj7rjjDipXrsyuXbvYvHkzhx12GGXLlmXu3Lm+\nxhVUzTsF6C4ic4GyuAW8u4vISKATMCOg85p4N38+DB/uRvA8/jisWAGZs32uWxfV0Ez8CR1v/+yz\nz1KjRg1q1KjB448/nuWYDz74gDZt2tCoUSNGjx7NvffeS/v27XnnnXcCuYYlqM7dTcA5odtEpK23\n7QlVtakWjf927oSePV07/vDhB7YfdRRcdBE8+6z7FlCpUu5lGOOj0DXNd+/ezcMPPwxAmTJl9u/f\nuXMn27Zto0aNGmEvzAriIrSIzdXjfRhMzfdAY4pqwABYtgxmzYKqVbPuu/NOaNcOUlOhKBeDGVME\nmU07AJ988kmWfZMmTWLlypV8/PHHnHfeeVx//fUsXbqUAQMG7G/q6dq1Kz/99BOjRo3ijjvu8C0u\nCf1EihWtWrVSW4HLFMq8eXD66XDjjTBmTM79qtCypftW8MMPrvPXlGo//fQTRx99dLTDyFV6evr+\n8f0ZGRn7vwUUVLjnJyJfq2qr/B5r//2m5NuxwzXxJCfDE0+EP0YE+vVz7f0ffBDZ+IwJIzPpA4VO\n+sVlid+UfPffD8uXw8svg3epe1idOsHBB8OIEZGLzZgYZInflGyffgpPPgm33AJt2+Z9bPnycNtt\n8PHH/l/MY0wJYonflFzbt0OvXnDooW7oZkFcfz1UrgyjRgUbmzExzBK/KbnuvRd+/dU18VSuXLDH\n1KwJ114Lkye7i7yMiYB333037HTMmVM3RHpaZkv8pmT65BN45hm4/XY3mqcwbr8d0tPd440JWHp6\nOoMGDWLVqlU89dRTPPDAA3Tr1o0zzjiDcePGkZGRwbnnnsucOXMYNmwYTZs2pVWrVrRq1YpDDjmE\nN954w/eYLPGbkmfbNtfEc/jhMHhw4R9/6KFw2WXw3HOuuciYAM2YMYPTTz+dtLQ0Nm3aRM+ePfn7\n77/59NNPuemmmyhTpgyvvvoqM2bMoFy5cowbN45FixaxaNEiHnrooUBissRvSp6773bz74wf7yZe\nK4o774RNm1wZxgRo5MiRVKlShXLlypGcnMyhhx6aZfhm6LTMIsKtt95K27Ztadu2bZapHfwUsSt3\njfHF7NkwdqxL3KeeWvRyWreGk05yk3fdeCOEjKk2pU+0ZmWeNm1aliQ/YsQIXnvtNRYvXkz79u3Z\nsWMHkyZN4vbbby8d0zIb47utW10Tz5FHQnEXp8i8oKtTJ5g+HYq60pcxeWjatCn9+vXjq6++AqBf\nv3706NGDK664ggkTJpDofWMtFdMyGxOI//wHVq920zP4MdHaZZe5q31HjrTEX8pFaVZmmjZtmiWR\ng5uYrWnTpnz//feceOKJAKVmWmZj/PXhh5CS4mrphV14PTflyrk2gM8+A69GZkyQVq9ezfXXX0+7\ndu1466232LFjB7t37474tMyW+E3s27IFrrsOmjaFgQP9LbtXL6hWzdX6jQlARkYGqsr69etJTU2l\nXr16nHrqqcyfP58XXniB4cOHR3xaZkv8Jvb16wd//OFG4FSs6G/Z1aq5RVtef90WYjeB2L17N7t3\n76Zdu3bMnj2bY489lrfffpuXXnqJuXPnkpSUlGNa5meeeYZ58+bRtWtXFi9ezCifrzS3aZlNbJs5\nE84/312lO2RIMOdYtcqN7e/bN+sCLqZEi/VpmUPZtMzGZNq82c2t06wZeCsXBaJxY7jiCnjhBTdy\nyJQasVixDaewSb+4z8sSv4ldd9wBa9a4Jp4KFYI9V79+Lum/+GKw5zERU7FiRTZu3Fhikn9BqSob\nN26kYjGaPW04p4lNM2a4hN+/P5xwQvDna9UKTjvNTfF8661uxI8p0ZKSkli9ejXr16+Pdii+q1ix\nIklJSUV+vLXxm9izaRMccwzUrg2LFgVf28/0zjtuPP+UKe7CLmNKGGvjNyXX7bfDunUwYULkkj7A\nhRe6id9GjHBr9BpTSlniN7Hl3Xdh4kS3nGKLFpE9d9myrl/hyy9hwYLIntuYCAok8YtIdRGZKSIf\nicjbIlJfRN4Xkc9E5LkgzmlKsEmToEkTN3/O5Ze7UTYDBkQnlmuucYu1RHpd3szXoEwZ93PSpMie\nvzCCiDWo51+SYo0kVfX9BvQBzvF+HwvcBlzl3Z8EtMrr8S1btlQTJ1JTVRMTVV3jirtVrOi2R8t9\n96mKqC5fHpnzhXsNEhOj+xrkJohYg3r+JSlWnwCLtAA5OvDOXRF5A/gGSABGAe8CHVV1XW6Psc7d\nONKkiZtbP7vkZFixItLROH/+6eK68UZ46qngzxeLr0Fucou1ShXo3r1oZU6c6BbX8bPMoMrNrcwY\n+VsVtHM30MQvIq2BQUAvYAiwBEgCblbVvdmO7Q30BmjcuHHLleH+uUzpU6ZM+I5UEcjIiHw8ma65\nBt58E37/3TX9BCm3uVii/RqEk9e8MXXrFq3MvIZbFrXMoMrNrcwY+VsVNPEH0tTjfZjUAhYBybjm\nnWre9juB3nk91pp64khyctavzZm35OToxpWW5uIYOjTY80ye7JqVwr0GSUnBnruwZsxQLVPG/79X\nUP8DQZQbq/+vHgrY1BNU524CMBW4T1VXAonAsSJSFjgJsLFyxnnsMVfrD5WY6LZH03HHwVlnuaae\nPXv8L3/nTteU1KWLG0Ia7irMf/5xi8pH2969brnLCy6ApKScsRb37/XYYzmX0PTjfyCIcoOKNdIK\n8ulQ2BtwE7AJmOPd7gF+ALYBHwFV8nq81fjjyHffuRpTjRqu5pucHDMdZfr++y42v+NZskT1//7P\nlX333ap79rhzJCcfeA0GD1Y96ihXw374YdV9+/yNoaBWrlRt3drFesMNqjt25IzVj9cniDKDKjeo\nWH1AAWv8gTX1FOdmiT+O9OypWqmS6oYN0Y4kp/R01aOPVj3+eNWMDH/KnDhRtXJl1dq1XdNJXv75\nR7V7d/c2bddO9c8//YmhoN55R7VmTdWqVVVfey2y5zZFUtDEbxdwmehZs8aNge7Z003PEGvKlHEX\ndH3zDXz6afHK2rEDrr3WjSY5/ni38vf55+f9mCpV3NXLL70EX3zhVvf+6KPixVEQe/a4xewvucSN\n4lm8GDp3Dv68JmIs8ZvoGTPGtR/37RvtSHLXrZsbAVKcC7p+/BFOPBFeftldkfzJJ66tvCBE3Afj\nV19BnTpw7rnu4rZ9+4oeT15++81NVjdqFNx8M8yf7/ogTKliid9Ex44dLvFffDEccUS0o8ldpUrQ\npw+89x4sXVr4x48f72b+XLcOPvjAdQIWZebPY45xU0n06OHKOOsstyqZn95+230bWbLErUj2zDP+\nr3hmYoIlfhMdEyfCxo2uSSHW9enjJosbPbrgj9m2zV0L0LMnnHSSa9r597+LF0flyq7Z55VX3Kyl\nzZu7D5Pi2r0bbrvNTZdxxBGuaatjx+KXa2KWJX4TeRkZbnHzli1ds0Ksq1fPtc2PHw8bNuR//Hff\nuTUEJk6EBx+EWbOgYUP/4uneHb7+Gho0gPPOc8tS7t2b/+PC+eUXOPVUePpp1+T2+eduGUpTqlni\nN5H3/vuwbJlb9SqvK0FjyR13wK5d8Fwecwyqwrhxrj1/0yaX8B95xM366bemTWHhQrc05dCh0Lat\nu8q4MF5/3c2A+ssvMG2aa9dPSPA/VhNzLPGbyBs50nVulqTmhGbNXO36mWfcB0B2//wDXbu6RHzq\nqa5p58wzg42pUiVISYFXX4Vvv3VNP++9l//jdu1yzVedOsHRR7tYL7kk2FhNTLHEbyLrm2/cqJbb\nb4fy5aMdTeH06wdr18LkyVm3p6W5ZqspU2DgQPjvf+GggyIXV5curumnUSO46CK4667crzZetgxO\nPhnGjnXPZ+5cN8GYiSu29KKJrO7dXbPC779DjRrRjqZwVN249r/+cm3qjRu7Wv3kyVCrlvt5xhnR\ni2/XLtdZPnas61C+8krXIb1qlYv1ggtcx3BCgrs+4MILoxerCURMzM5ZVJb4S6nVq+GQQ9z48MKM\nkIkVkyZBr145a9PHHuva8+vVi05c2U2d6oZ97tyZc9+RR7pYGzWKeFgmeLbmrok9zzzjRvTcfnu0\nIyma/v3DN6Fs2RI7SR9c231uU0nv2mVJ31jiNxGybRs8/7wbK37IIdGOpmhWrQq/vbCjaSLhr7/C\nb4/FWE3EWeI3kfHyy7B5s+tQLKkaNy7c9mgqSbGaiLPEb4KXnu7a9Fu3diNKSqqSNBd7SYrVRJwl\nfhO8d96BX38t2bV9cOP0U1Lc8EcR9zMlxW2PNSUpVhNxNqrHBK9NG7eA+c8/B3MVqzEGsFE9JlYs\nXOjmf7n9dkv6xsQIS/wmWCNHQvXqbvy7MSYmWOI3wVmxAt54A3r3hqpVox2NMcZjid8E56mn3PKF\nt90W7UiMMSEs8ZtgbNnipiju1KngywwaYyKiCGvAlRxt27bNsa1Tp0706dOHHTt2cH6Yxa579OhB\njx492LBhAx3DTBt800030blzZ37//Xe6d++eY3+/fv246KKLWLp0KTfccEOO/QMGDODss88mLS2N\nvmHWmh08eDCnnHIK8+fP5/7778+xf/To0TRv3pxZs2YxaNCgHPuff/55jjrqKKZPn86IMOvETpw4\nkUaNGjFlyhTGjh2bY/8bb7xBnTp1GD9+POPHj8+x//333ycxMZExY8YwderUHPvnzJkDwPBu3Xjv\nn3/cMn7e36FSpUrMnDkTgEcffZTZs2dneWzt2rV58803AbjvvvtYsGBBlv1JSUmkpqYC0LdvX9LS\n0rLsP/LII0lJSQGgd+/eLFu2LMv+5s2bM9qbI6hbt26sXr06y/7WrVszZMgQADp06MDGjRuz7D/r\nrLN44IEHADjvvPPYmW0unAsvvJC77roLsP+9qP7vDR/Oe9mmpy5J/3uRYDV+4799++Czz1ynrrXt\nGxNzbBy/8d+UKW5K4HfecYupG2MiIqrj+EWkuojMFJGPRORtEUnwto8RkYuCOKeJEaowYoRbtNvm\nezcmJgXV1NMVGKmq5wBrgPYichpwkKpOD+icJhZ8/jl89ZVbo7aMtSQaE4sCeWeq6hhV/ci7WxfY\nBLwArBARW9yzNBsxwq1Gdc010Y7EGJOLQKtkItIaqAkcCfwIPAGcKCK3hjm2t4gsEpFF69evDzIs\nE5Tly127/k035ZwZ0hgTMwJL/CJSC3ga6AUcD6So6hogFWiX/XhVTVHVVqraqm7dukGFZYL05JNu\nAfWbb452JMaYPATVuZsATAXuU9WVwHLgUG93K2BlEOc1UfT33/DSS3DVVdCgQbSjMcbkIaga/7VA\nS6C/iMzBtfG3E5G5QB9geEDnNdGSkgI7drhOXWNMTLNx/Kb49uxx6+gecwx8+GG0ozEmbhV0HH+p\nnrLBRMiUKW6hlRdfjHYkxpgCsIHWpngyL9hq1gzOPTfa0RhjCsBq/KZ4PvkE/vc/NxOnSLSjMcYU\ngNX4TfGMHAn16tki3saUIJb4TdH99BPMmOHG7VesGO1ojDEFZInfFN3o0VChgrtS1xhTYljiN0Wz\nfj288gpcfTXYldbGlCiW+E3RjB0Lu3bZBVvGlECFTvwiYksqlQSTJkGTJm5q5CZN3H2/yk1Ohoce\ngkqVYPFif8qNc0H9uYJQkmINQql4/qqa5w1oBHwKVPDunwfMBRrm99ii3lq2bKmmGFJTVRMTVd0o\ne3dLTHTbY7HcOFeSXtaSFGsQYv35A4u0ADk23ykbRORV4AlVTQvZdjpwv6q2D+LDyKZsKKYmTWBl\nmHnwatWCoUOLXu4997jJ2LJLToYVK4pebpzL7c8Viy9rSYo1CLH+/As6ZUNBEv88VW0TZvsi4CRV\nTS96mOFZ4i+mMmVcZSRSRCAjI3LnK2Vyu+4tFl/WkhRrEHJ7a8XK8/dzrh4RkfKqujdkQ1kgEYiB\np2pyaNw4fLXk4IPhiy+KXu7JJ8Mff4Q/nymSb7+FcuVg376c+xo1inw8efn5Z0hIcHPyZZeUFPl4\noqFWLdi4Mef2kvYWKEjn7mjgRRGpASAiFYARwPua39cFEx2dO+fclpjomnmSkop+Gzo058paiYnw\n2GOReV6liKqbyfrEE6FKFXc5RHYJCeE/v6PhtdegZUsXU0JCzv0isHRp5OOKlG3b3GqiGzfmXEq6\nRL4FCtJqqDZBAAAgAElEQVQRAPwbeAfXyTsf6A+ULchji3Kzzt1i2LxZNSlJtWFD1caNVUVUk5P9\n631KTXXl+V1uHNmyRfXKK13H4L//rbp2bc6X9ZZbVKtWVa1ZU3XatOjFumOHau/eLtZTTlFduTJn\nrP/5j2qdOqqVK6tOnBi9WIPy7beqTZu65/vQQ6qvvBK7bwEK2LmbX8K/FGhfkIL8vFniL4ZevVTL\nlFFduDDakZgwFi9WPfxw1bJlVQcPVk1Pz/3Y5ctVW7Rw79K+fVV3745cnKqqS5ao/t//ufPfc4/q\nnj25H7t6terpp7tje/ZU3b49cnEGJSND9YUXVCtWVK1fX3X27GhHlD+/Ev8MoFtBCvLzZom/iGbM\ncH/S++6LdiQmm4wM1WeeUU1IUD34YNXPPivY43btUr31VvdnPeEE1V9/DTbOTBMnuhp8nTqq779f\nsMfs3as6YICrCTdrpvrDD8HGGKStW1Wvusq97medpfrXX9GOqGD8Svz1geSCFOTnzRJ/Efz9t2ve\nOeYYly1MzNi0SbVjR/duO/981fXrC1/Gm2+qVq/ubm++6X+MmbZvd18aQfW001xNvrA+/FC1Xj3V\nSpVUX3rJfeiVJN98o3rkke6L86OPqu7bF+2ICs6vxN8dSCpIQX7eLPEXwTXXuPaDRYuiHYkJ8eWX\nqocc4v40TzyRd9NOfn791dX6wfUB+P35/sMPrqYuotq/v6vBF9Wff6q2a+di7d5d9Z9//IszKBkZ\nqmPGqFao4OpQc+ZEO6LC8yvxlweuB+4F6hakQD9ulvgL6d133Z9ywIBoR2I8GRmqo0erli/v+tjn\nz/en3N27Ve+4w/25W7RQ/flnf8p9+WVXQ69Xz9XY/bBvn+rDD7sPkqZNXSdprNq8WbVTJ/e6nnuu\n6rp10Y6oaHxJ/PsPcmP2bwX6AdUL8pji3CzxF8LGjaoNGrheuEj3/pmw/v5b9dJL3bvr4ovdn8hv\n77zjRvxUrao6ZUrRy/nnH9Wrr3axtmvnaup++/hj1YMOcp2kKSmx1/SzaJHqYYe5b2VDhhTvW1m0\n+Zr49x8M1b3kfyuQWJjHFuZmib8QunVTLVfODRcxUbdggRviV7686siRwSa5FStUTz7ZvYtvuMEN\nvSyM7MMUg2zLXrNG9ZxzXKxdurjO02jLyFB96inX4Z6UpDpvXrQjKr5AEv/+B0Fdr/mnTlEen9/N\nEn8BTZvm/oQPPRTtSOJeerrqsGHuM7hJk8iNpt2zx42jB/elb8mS/B+TkeFq3hUrupp4pIYppqer\nDhrkOk0PPzy6dZVNm1Qvv9y9bhdcoLphQ/Ri8VOgiX//g6FdcR6f280SfwFs2OAGFx93nDXxRNmG\nDS55gEsmmzZFPob33lOtXdsNwczrgqKtW12NG1TPPtvVxCPt009d52mFCq4zNdJNPwsXug/ncuXc\nh3VJbtrJzq/O3bLAW14n7zvetjIh+z/L5XHVgZnAR8DbQIK3vT7wTX5BWeIvgC5d3H9uWlq0I4kr\n2a9affBB10yQkKD69NPRbb/+/XfVNm3cu/raa1VffDFrrIMGuZp2mTLu92gmvHXrVNu3d7FecYX7\nBhLE1bChf6/GjVW7dnXNcMnJrlmutPGtxg+8DwwEfgTuBCYBHYBKwNRcHtMHOMf7fSxwsff7RGBJ\nfue0xJ+PN990f7qBA6MdSVwJNxc7uJEwsTKKdu9ed/0euGSXPdaaNV2NOxakp6s+/rj7IMoea1DL\nR4Bqy5auA740KmjiL8i0zO8Bo4CHgW+BhsDXwPHAR6r6XD6PfwMY7o0M6gQ0VdW2eT3GpmXOw/r1\ncMwxburGL76A8uWjHVHcyG0u9kaNYNWqiIeTp/r1Yd26nNuTkuD33yMfT14OOgjWrs25vU4dt8Jn\nUd10E2zYkHN7bpPXlgbFnpZZRMoD7wG7VXW2iNwC/AE0AF7BjewZkk8QrYGawGLgQ9zcP9NyObY3\n0BugcUmb4zSSbrkFNm+G2bMt6UdYbsl99erIxlEQ69eH3x5uVu1oC/cBBS5pX3GF/+eLtQ++aMg1\n8avqXhG5DRguIi8DLYCqwG4gBegKXAaErZqLSC3gaVyz0L3As6q6WXJZyUFVU7xyadWqlU33HM7r\nr8PUqW4O2GOPjXY0cSU9HapVgy1bcu6LxXpKbrXakhRrgwbw4YdFL/ff/4a//gp/vriXX1sQ8C7Q\nBFdjTwb+y4HO2km5PCYBmMWBdv65wBzvthkYl9c5rY0/jLVr3YxZrVoV71p6U2hr1riJusBd5BOr\n662GivW1YUPZEtH+wcfO3dlAU+ABoB5wYsi+Mbk85iZgU0iy7xyyb05+57TEn01GhmqHDm7oyPff\nRzuauDJ7ths1W7Gim6J34sTYnYs9u5K0dEJQsZak18APBU38BencHQek41brqghUwzX5rAaeU9X5\nRfuukTvr3M1myhS48kp4/HG34LkJXHo6DBwIjz4KRx3lWtisdc3EOt/W3FXV63I5wdHAIUWIzRTG\nmjXQp49bo69fv2hHExf+/BO6doU5c9xye88+C5UrRzsqY/xTkMXWARCRaqq61fu9HG60z/uBRWZc\ns+RNN8H27TB+vFuV2wTqww+hWzf3kr/8MvToEe2IjPFfnouti0gNEanr3Z0Xsutk4AMRuT6wyAxM\nngzTprn2hqOPjnY0pdq+fdC/P7RvD/XqwVdfWdI3pVeeiR94HDjF+z09c6OqzgNGAkcGFJf56y83\nZv/kk+HOO6MdTam2ejWceSYMHgy9esGXX0KzZtGOypjg5Nd28DHugi0ABRCR2sDtwElAx+BCi2Oq\ncMMNsHOna+IpWzbaEZVa778PV18Nu3ZBaqpr2zemtMuvxv8LcKGI9AMOFpFZuLl6lgDtVfWfoAOM\nS6mpMH26u1DrqKOiHU2ptHcv3H03XHABHHwwfP21JX0TP/Kr8W/Ajd3/BXfh1UWqulNEymh+40BN\n0fzxB9x2G5x6Ktx+e7SjKZVWrXKjYxcscF+sRo2CSpWiHZUxkZNfjX8rsFFVpwE7VHWnt/1VETkp\n2NDikCr07g27d7shJdbE47t334XmzeH77+G11+C55yzpm/iTX+LfCTQUkRZAJRFp4f0+ERjjTeRm\nimvSJDf1Y5kyrtG5Qwc44ohoR1Xihb6syclw3nlwySVu2+LF0LlztCM0JjrybOpR1V0isgw3E+cC\n7+f+3UB7YHpw4cWBSZNcLX/HjgPb3nzTjSu0Ruciy/6yrlrlbuec42r9FStGNz5joinXKRvETaN5\nvKou9u6fCKQBZTObfETk/CAu4oqrKRtym+Q9ORlWrIh0NKWGvawmHhV0yoa8mnrKABNF5DIRuRy4\nAzgL+FlEXhKRK4Cr/Ak3juW2IkSsrexRwtjLakzu8pqPP11EygBXAsfi5t2vgxvK+S5uMZbzIxFk\nqbVwoevATU/Puc8mDS+yX36BhATYsyfnPntZjcm/c3cNbvWstbg59X/GzcnfEDdV872S28oqJneq\nMGIEtGkDtWpBhQpZ9ycmujH8ptBefx1atHDTGiUkZN1nL6sxTn6JvzJuHH9lXG2/LG6e/cNxq2Xd\nbeP5C2njRrj4YrjrLvdz2TJ48UXX+CzifqakWMduIe3a5SYx7dTJTbfw44/w0kv2shoTTl5r7pbB\nJf0twAygJbAcN7YfoDxwFPBjwDGWHp9/7q4cWrcOnn4abr7ZZaWuXS0jFcOyZS7h/+9/7vN08GC3\nHHFysr2sxoSTX43/FuBzYBAwBvgd+AL4ATeU89RAoystMjLcIipnnOGadebPdxOwWStZsb36KrRs\n6RbQfu89GDbM1qA3Jj95de5miMhxwOm4hdb/BVTHtfXXAPoC0yIRZIm2fr2bBeyDD1y1NCUFqleP\ndlQl3s6dbmaLcePc7BaTJ0OjRtGOypiSIb8a/wJcB+8i4CXgCOAv734aMDzQ6Eq6uXPd/ACffAJj\nx7o5AizpF9uSJW5BsnHj4L773EpZlvSNKbj8rtz9WES2A1953wBuB35R1d8ARKRLJIIscdLTYcgQ\neOghOOwwmDHDfQCYYnvlFbcoWWKi+xJ17rnRjsiYkqcga+4uDPl9VrZ9vwURVIm2dq1bu2/WLLjq\nKjcLWNWq0Y6qxNu+3XWLjB8Pp5/u2vYPPjjaURlTMuXX1GMK4+OPXc1+3jx44QU3r74l/WL74QfX\ntDNhAjzwAMyebUnfmOKwxO+H9HR4+GE4+2yoUcOt3XfddTZqp5hU3Vj8E05wlz98+CEMHGhrzhtT\nXKX6LdS2bdsc2zp16kSfPn3YsWMH55+fc8aJHj160KNHDzZs2EDHjjlXlrzpppvo3Lkzv//+O927\nd3fzAvz0E2zeDPXr0++RR7jo2GNZunQpN9xwQ47HDxgwgLPPPpu0tDT69u2bY//gwYM55ZRTmD9/\nPvfff3+O/aNHj6Z58+bMmjWLQYMG5dj//PPPc9RRRzF9+nRGjBiRY//EiRNp1KgRU6ZMYezYsTn2\nv/HGG9SpU4fx48czfvz4HPvff/99EhMTGTNmDFOnTs2xf86cOQAMHz6c9957L8u+SpUqMXPmTAAe\nffRRZs+enWV/7dq1efPNNwHo1+8+UlMXsG6d+yw99FAYPz6Js89OBaBv376kpaVlefyRRx5JSkoK\nAL1792bZsmVZ9jdv3pzRo0cD0K1bN1avXp1lf+vWrRkyZAgAHTp0YOPGjVn2n3XWWTzwwAMAnHfe\neezcuTPL/gsvvJC77roLiND/Xjb9+vXjoosusv+9Yv7v3XfffSxYsCDL/qSkJFJTI/O/FwmlOvEH\nbtMml/TT090SiQcdZKt6+ODbb11b/t9/u1k2Gze2L0/G+EpVfb/hxvvPBD4C3g5zPyGvx7ds2VKL\nJTVVNTlZVcT9TE0tXnnZywXVatVc+ccco/rDD/6UH6dCX9ZatVTLl1dt0ED1k0+iHZkxJQuwSAuQ\no4Oq8XcFRqrqRyIyFrgm2/32uBk+/Zd9BY6VK117+2+/uSWYimrmTDfD165d7v7WrW5mzTvvdJPD\nmCLJ/uf6+2+3YtaAARCmtcQY44NcF2Lx7QQibwDDVfWLcPfDKdZCLLmtwBEUW9mjWGzBFGP8U9CF\nWAJt4xeR1kDNkKSf5X62Y3sDvQEaF2fS9LxW2ni3GF8yLr648Ocz+crt5bOX1ZjgBJb4RaQW8DTQ\nIdz97FQ1BTfVM61atSr615DGjXOvQl50UZGLJTk5fLm2skexNGwIf/yRc7u9rMYEJ5Bx/CKSAEwF\n7lPVldnvB3HO/R57zF3PH8qPFTiCKjeOqbqhmtnZy2pMsIK6gOta3Pz9/UVkDnBf6H0R6RzQed0E\n7Ckp/q/AEVS5cez5591VuT172stqTCQF3rlbFMXq3DUlwm+/wbHHQuvW7opcG6dvTPEVtHPXpmww\nEZeRAdde64ZtvviiJX1jIs2u3DURN3asW6LghResE9eYaLAav4moX36Bu+928+hfe220ozEmPlni\nNxGTkQG9erk1cceNsyYeY6LFmnpMxDzzjFuN8qWXICkp2tEYE7+sxm8iYvlyuPdeOP986NEj2tEY\nE98s8ZvApae7ZF+hghujb008xkSXNfWYwD31FHz+uVs60ZZMNCb6rMZvArVsGdx/v5smKcyiUcaY\nKLDEbwKT2cRTqZKbnsGaeIyJDdbUYwIzahQsWACpqdCgQbSjMcZkshq/CcSSJW4VrUsvhauuinY0\nxphQlviN7zKbeCpXdtMzWBOPMbHFmnqM70aMgIULYfJkOOigaEdjjMnOavzGVz/+CA88AB06QOfg\nVl0wxhSDJX7jm3374JproFo1GDPGmniMiVXW1GN8M2wYLFoEU6dCvXrRjsYYkxur8RtffP89PPQQ\ndOoEV1wR7WiMMXmxxG+Kbe9eN4qnRg03A6cxJrZZU48ptqFD4euv4Y03oG7daEdjjMmP1fhNsXz7\nLQwcCF26uJE8xpjYZ4nfFNnevW4UT61a8PTT0Y7GGFNQ1tRjimzwYEhLg2nToHbtaEdjjCkoq/Gb\nIklLg0GDoGtXuOSSaEdjjCmMQBK/iFQXkZki8pGIvC0iCSLyoojMF5EBQZzTRMakSZCcDMcfD6pw\n2mnRjsgYU1hB1fi7AiNV9RxgDXAlUFZVTwEaisgRAZ3XBGjSJOjdG1atcvfT0+HOO912Y0zJEUji\nV9UxqvqRd7cu0A2Y6t3/GGgTxHlNsO6/H3bsyLptxw7o3z868RhjiibQNn4RaQ3UBH4H/vA2bwXq\nhzm2t4gsEpFF69evDzIsUwR//32gpp9dbtuNMbEpsMQvIrWAp4FewDagkrerSrjzqmqKqrZS1VZ1\n7SqgmPLFF65NPzeNG0cuFmNM8QXVuZuAa9q5T1VXAl9zoHnnOGBFEOc1/srIgOHDXQdu2bLwyCOQ\nmJj1mMREeOyx6MRnjCmaoGr81wItgf4iMgcQoLuIjAQ6ATMCOq/xycaNcPHF8J//uOGaixfDgw9C\nSoob1SPifqakuCGdxpiSQ1Q1MicSqQmcA8xV1TV5HduqVStdtGhRROIyOX3+OVx5JaxbByNHQp8+\nNre+MSWBiHytqq3yOy5iF3Cp6iZVnZpf0jfRk5EBjz8OZ5wBFSrAggVw882W9I0pbWzKBgPA+vVw\n9dXwwQduycSUFLeSljGm9LHEb/j0U7jqKteu/9xz7iItq+UbU3rZXD1xLD0dHn0UzjwTqlSBhQvh\nhhss6RtT2lmNP06tXetG48ye7X6OHQtVq0Y7KmNMJFjij0Mff+yadrZuhXHjoFcvq+UbE0+sqSeO\npKe7BdHPPtstnvLll3DttZb0jYk3VuOPE3/+6Zp05sxxq2Y9+yxUrhztqIwx0VAqa/yTJkGTJlCm\njPvp17TBQZUbhNBY69eHo492Nfzx493Nkr4x8avU1fgz54zPnD545Uq4/np3cVJxphaYNMmNeNm5\n80C5vXu732NtyoLsr8G6da455/HHXW3fGBPfIjZlQ2EUZ8qGJk1cUo6U5GRYsSJy5yuI3F6DWIzV\nGOOfgk7ZUOpq/HnNDf/II0Uv96GHCn++aMntgy8WYzXGRF6pS/yNG+de233wwaKX+9JL4cutUgV2\n7YKKFYtetl/27s17NSybN98YA6Wwc/exx4KZMz5cueXKwT//wCmnwPLlxSu/uFatcpOrDRsGZ50F\nlSpl3W/z5htjMpW6xN+1azBzxocrd/x4ePdd127eogVMmeLHMyi8d9+F5s3h++9dDLNmwQsv2Lz5\nxpjwSl3nbjSsWgVdusD8+W7kz6hROWvcQdizB+69150v84Pn8MODP68xJjbF3Hz8pVnjxu7CqLvv\nhuefh5NPhqVLgz3nb7+5JRFHjYJbbnEfOpb0jTEFYYm/CLZv384JJ5zACm9sZN++ffn3v9sxb96p\njBnzPX/+CS1bBneB19tvu8XPly6FN96Ap592C6cYY0xBWOIvpO3bt9OhQwc2bNgAwPfff8+ePXv4\n5JNPGDlyJHPmPEpammt66dYNrrvuwIVUxbV7N9x2G1x+ORx5JHzzDXTo4E/Zxpj4YYm/kESEiRMn\nkpycDEC1atVYunQpW7du5YsvvuDII4/k4IPdDJj9+7thoCeeCD/+WLzz/vILnHqqq9337Qvz5sEh\nh/jwhIwxcccSfyElJiZSt27d/fcbNGhAjRo1ePLJJ1m0aBGXX3454IZ6DhoE//2vmzLhhBPcKKCi\neP119w3il19g2jTXrp+Q4MOTMcbEJUv8xTRhwgTOOOMMHnjgASZMmMBtt92WZf8558D//gcnnQQ9\ne7q5crZtK1jZu3ZBnz7QqRM0awZpaXDJJQE8CWNMXLHEX0zbt2/nu+++Q1VZvHgxW7ZsyXFMgwbw\n0Udu2oeJE13t/7vv8i7355+hdWu3MtZ//gNz57rx+MYYU1yW+Ivp6quvZuXKlVStWpUrrriCoUOH\nhj2ubFl4+GF3cdXmza7df9w4CHcZxeTJrmnn99/hvffgiSegfPlgn4cxJn4EdgGXiNQH3lDV00Sk\nJjAJqAr8oKo35vXYknYBV2GtXetG/Mya5ZZAbNfO9QesXOnm/tm2Ddq0cR8ASUnRjtYYU1JE9QIu\nL9FPADKX++gOpKrqaUBVEck3sNKsfn344AOX7CdPdnPnZ04At22b6xi+/npL+saYYATV1JMOdAa2\nevc3AkeJSA2gERD3EwSXLeuGe9arl7O5Z9++4s0kaowxeQkk8avqVlUN7eWcBxwB3AYsATZlf4yI\n9BaRRSKyaP369UGEFZPWrQu/3ebON8YEJVKdu4OBG1V1IC7x98x+gKqmqGorVW0VOk6+tMttjnyb\nO98YE5RIJf5E4FgRKQucBMTelKBREtT6AcYYk5tIJf4hQAqwBagFTI7QeWNeUOsHGGNMbmw+fmOM\nKSVsPn5jjDFhWeI3xpg4Y4nfGGPijCV+Y4yJM5b4jTEmzljiN8aYOGOJ3xhj4owlfmOMiTMxeQGX\niKwHVvpQVB1ggw/llORyLVaL1WItWbEWR7Kq5jvZWUwmfr+IyKKCXMVWmsu1WC1Wi7VkxRoJ1tRj\njDFxxhK/McbEmdKe+FOsXIs1oHItVos1qFgDV6rb+I0xxuRU2mv8JYKI1BKRc0SkTrRjMaa0svfZ\nAaU68YtIfRH5zMfyqovITBH5SETeFpEEH8psAMwATgQ+ERFf1530XoNvfCqrnIisEpE53u1YP8oN\nKX+MiFzkY3k3hcSaJiLP+1BmTRF5X0Q+E5HnfIrzEBGZ4ZU5wo8yg5L9PeXHeyy0DD/fY9nK9eV9\nFu75+vkei5RSm/hFpCYwAajsY7FdgZGqeg6wBmjvQ5nHAHeo6mPAf4EWPpQZajhQyaey/g+YrKpt\nvdt3PpWLiJwGHKSq0/0qU1XHZsYKfAa84EOx3YFUVT0NqCoifgznGwo86pWZJCJti1tgmAT9oojM\nF5EBxSgzy3vKj/dYmDJ8eY+FKbfY77M8nq+f77GIKLWJH0gHOgNb/SpQVceo6kfe3brAOh/KnKWq\nX4jI6bjayILilplJRM4EtuPeQH44GbhMROaJyCQRKedHoSJSHpeUV4jIJX6Uma38g3EfKn4s67YR\nOEpEagCNgFU+lHkksNj7fR1QvTiFhUnQlwNlVfUUoKGIHFHEorO/p/x4j2Upw8f3WPZy/Xif5Xi+\nAbzHIqLUJn5V3aqqW4IoW0RaAzVV9QufyhPcP9Re3D+XH2UmAA8C9/pRnucr4AxVbQNsBs73qdyr\ngR+BJ4ATReRWn8rNdDMw1qey5gFHALcBS4BNPpT5BvCQ18zVHphdzPKyJ6i2wFTv94+BNkUpNPt7\nyo/3WG5lFPc9Fq7c4r7PspcZ0HssIkpt4g+KiNQCngZ6+VWmOjcD84ELfSr2XuBZVd3sU3kA36rq\nX97vS3AJ0A/HAymqugZIBdr5VC4iUgY4E/jEpyIHAzeq6kDca9CzuAWq6iBgJnAdMEFVtxWzvOxJ\nrzLwh/f7VqB+ccoPWhDvMQjkfRbEeywiLPEXgvcJPxW4T1X9mEsIEblHRK727tbA1aT9cDZws4jM\nAZqLyDgfypwoIseJSFngMuB/PpQJsBw41Pu9Ff7M05TpNOAL9W/cciJwrPcanAT4VW4a0BgY6VN5\nobZxoA26CjH8vg/iPeaVG8T7LIj3WETE7D9AjLoWaAn090aKdPahzBSgu4jMBcoCH/pQJqp6ekjH\nZpqqXudDsQOBibgktUBVZ/lQJsCLQDvvNeiD6yzzy7nAXB/LG4L7m20BagGTfSr3P7hOzR0+lRfq\naw407xwHrAjgHH4J4j0GAbzPAnqPRYRdwGVMKSUic1S1rYhUw41qmg2cB5wcVP+XKRks8RsTB7yR\nPucAc72+FBPHLPEbY0ycsTZ+Y4yJM5b4jQnDm56ibC7b/bpwLfBzGBOOJX5TKonIIBHJ8wIzEbld\nRHIbidEJ+Ny7Svln7zYPdwHXJSFlDBSRtiLymIjcKyJVReS/4RK6d3yCiFxTmHMY4zdr4zelhogM\nAk7Aja0/HDdWewNQAXhKVd/2Jmpr6h3TEMjAXW4vuAvUclw1nPnhoKrjsm2vAtwIJACHeGU8CTyi\nqpd7F4+hqhkhj+kNfKCqq7KVFfYcxgTBvk6aUkNV909AJiIP4y7c+iDbYbfhpoiYCnQBduGu6r2I\nwi+sUR2oDdyCu7ZhPm56iMO98eKHA5cCX3oxVQbqZE/6xkSaJX5TKnhNKxpau862PwHYp6q7ReQn\n4E4gc/qJe4HnVXWPd2wd3IfBbm9/XW/7jd79CkA3YC3QBBiB+xZxEG4G0/64q5FvUNUvQ8K4Fnex\nWoHPoap+XR1tzH7W1GNKBW+Cs1twTTg1cTMw7uTAVbvlgSm4aZV3e/cP947/GTdpV3lgSPZvCSLy\nXyBBVdtl256EmwKhOzANN/nXYFwNfwFwlKo+5R1bA7heVYflEn/YcxgTBKvxm1LBm8d/ujca5m3g\nXVxTzOuq+mLIoSkAIvIyrsZfG/ifqt4VrlwR+T9cP8DXInK5qr4VsjsZGISbrO44oDmurT/zmJkh\nx14HhG2/z+ccxvjOEr8pNbzO1lTcNMeH4KaR7u1dtTpKVdO9JqHRwG+4ud53AS1EJBXoq6obQsqr\nD7yG6xP4BZglIqsy5/VX1c9FZCpunYKZwA+quldEFuNG5Qz0yqkH7FXVHFM453cOY4JgwzlNqeDN\n3/45MElVJ3ib03FDJg8GfvIW4fgC2OxNqywAqpo5t/7PInKGiJQRkStwwyoHqOoiL2l3AV4SkcEi\ncoh3judwc+AMAP7lbT8G2MOBVZ72t+2HxFuYcxjjK6vxm9LiG+DikKl8qwDlVHU3cIe4tWzXA/eq\nauZCJ4l4C3Ko6iAReRX3TeAc4ArgPFVdnnkCVV0mIqcAtwK1RWQzboGXX3G1/mbAy8BduI7fN0Tk\nKuDFMHPsn12Qc3jxGOMr69w1phhEpJyq7vN+F6CMqqZn3vdxHQBjfGOJ3xhj4oy18RtjTJyxxG+M\nMc9AaZwAAAAaSURBVHHGEr8xxsQZS/zGGBNnLPEbY0yc+X94sp4Lm1cLngAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d67db8d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[3.0, 0, 0, 0, 0, 3.2, 3.0, 4.0]\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAARQAAAEYCAYAAACdsgkCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x2c4d6886f60>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'多云': 4, '阴': 2, '多云转阵雨': 1, '阵雨转多云': 1, '雨': 2, '雨转阴': 1, '阴转晴': 1, '晴': 1, '多云转晴': 1}\n"
     ]
    },
    {
     "ename": "TypeError",
     "evalue": "float() argument must be a string or a number, not 'dict_values'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-3-e3afdcfcaeea>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m    130\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    131\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0m__name__\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m'__main__'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 132\u001b[1;33m     \u001b[0mmain\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    133\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-3-e3afdcfcaeea>\u001b[0m in \u001b[0;36mmain\u001b[1;34m()\u001b[0m\n\u001b[0;32m    126\u001b[0m     \u001b[0mtem_curve\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata14\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    127\u001b[0m     \u001b[0mwind_radar\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata14\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 128\u001b[1;33m     \u001b[0mweather_pie\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata14\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    129\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    130\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m<ipython-input-3-e3afdcfcaeea>\u001b[0m in \u001b[0;36mweather_pie\u001b[1;34m(data)\u001b[0m\n\u001b[0;32m    114\u001b[0m     \u001b[0mexplode\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;36m0.01\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m*\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdic_wea\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    115\u001b[0m     \u001b[0mcolor\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;34m'lightskyblue'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'silver'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'yellow'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'salmon'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'grey'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'lime'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'gold'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'red'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'green'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'pink'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 116\u001b[1;33m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpie\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdic_wea\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexplode\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mexplode\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdic_wea\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mautopct\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'%1.1f%%'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolors\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcolor\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    117\u001b[0m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'未来14天气候分布饼图'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    118\u001b[0m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\Users\\ymwy\\Anaconda3\\lib\\site-packages\\matplotlib\\pyplot.py\u001b[0m in \u001b[0;36mpie\u001b[1;34m(x, explode, labels, colors, autopct, pctdistance, shadow, labeldistance, startangle, radius, counterclock, wedgeprops, textprops, center, frame, hold, data)\u001b[0m\n\u001b[0;32m   3294\u001b[0m                      \u001b[0mradius\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mradius\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcounterclock\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcounterclock\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3295\u001b[0m                      \u001b[0mwedgeprops\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mwedgeprops\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtextprops\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtextprops\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcenter\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcenter\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3296\u001b[1;33m                      frame=frame, data=data)\n\u001b[0m\u001b[0;32m   3297\u001b[0m     \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3298\u001b[0m         \u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_hold\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwashold\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\Users\\ymwy\\Anaconda3\\lib\\site-packages\\matplotlib\\__init__.py\u001b[0m in \u001b[0;36minner\u001b[1;34m(ax, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1895\u001b[0m                     warnings.warn(msg % (label_namer, func.__name__),\n\u001b[0;32m   1896\u001b[0m                                   RuntimeWarning, stacklevel=2)\n\u001b[1;32m-> 1897\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1898\u001b[0m         \u001b[0mpre_doc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0minner\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__doc__\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1899\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mpre_doc\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\Users\\ymwy\\Anaconda3\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001b[0m in \u001b[0;36mpie\u001b[1;34m(self, x, explode, labels, colors, autopct, pctdistance, shadow, labeldistance, startangle, radius, counterclock, wedgeprops, textprops, center, frame)\u001b[0m\n\u001b[0;32m   2570\u001b[0m         \"\"\"\n\u001b[0;32m   2571\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2572\u001b[1;33m         \u001b[0mx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfloat32\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   2573\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2574\u001b[0m         \u001b[0msx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfloat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msum\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mTypeError\u001b[0m: float() argument must be a string or a number, not 'dict_values'"
     ]
    }
   ],
   "source": [
    "# data14_analysis.py\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import math\n",
    "\n",
    "\n",
    "def tem_curve(data):\n",
    "    \"\"\"温度曲线绘制\"\"\"\n",
    "    date = list(data['日期'])\n",
    "    tem_low = list(data['最低气温'])\n",
    "    tem_high = list(data['最高气温'])\n",
    "    for i in range(0, 14):\n",
    "        if math.isnan(tem_low[i]) == True:\n",
    "            tem_low[i] = tem_low[i - 1]\n",
    "        if math.isnan(tem_high[i]) == True:\n",
    "            tem_high[i] = tem_high[i - 1]\n",
    "\n",
    "    tem_high_ave = sum(tem_high) / 14  # 求平均高温\n",
    "    tem_low_ave = sum(tem_low) / 14  # 求平均低温\n",
    "\n",
    "    tem_max = max(tem_high)\n",
    "    tem_max_date = tem_high.index(tem_max)  # 求最高温度\n",
    "    tem_min = min(tem_low)\n",
    "    tem_min_date = tem_low.index(tem_min)  # 求最低温度\n",
    "\n",
    "    x = range(1, 15)\n",
    "    plt.figure(1)\n",
    "    plt.plot(x, tem_high, color='red', label='高温')  # 画出高温度曲线\n",
    "    plt.scatter(x, tem_high, color='red')  # 点出每个时刻的温度点\n",
    "    plt.plot(x, tem_low, color='blue', label='低温')  # 画出低温度曲线\n",
    "    plt.scatter(x, tem_low, color='blue')  # 点出每个时刻的温度点\n",
    "\n",
    "    plt.plot([1, 15], [tem_high_ave, tem_high_ave], c='black', linestyle='--')  # 画出平均温度虚线\n",
    "    plt.plot([1, 15], [tem_low_ave, tem_low_ave], c='black', linestyle='--')  # 画出平均温度虚线\n",
    "    plt.legend()\n",
    "    plt.text(tem_max_date + 0.15, tem_max + 0.15, str(tem_max), ha='center', va='bottom', fontsize=10.5)  # 标出最高温度\n",
    "    plt.text(tem_min_date + 0.15, tem_min + 0.15, str(tem_min), ha='center', va='bottom', fontsize=10.5)  # 标出最低温度\n",
    "    plt.xticks(x)\n",
    "    plt.title('未来14天高温低温变化曲线图')\n",
    "    plt.xlabel('未来天数/天')\n",
    "    plt.ylabel('摄氏度/℃')\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def change_wind(wind):\n",
    "    \"\"\"改变风向\"\"\"\n",
    "    for i in range(0, 14):\n",
    "        if wind[i] == \"北风\":\n",
    "            wind[i] = 90\n",
    "        elif wind[i] == \"南风\":\n",
    "            wind[i] = 270\n",
    "        elif wind[i] == \"西风\":\n",
    "            wind[i] = 180\n",
    "        elif wind[i] == \"东风\":\n",
    "            wind[i] = 360\n",
    "        elif wind[i] == \"东北风\":\n",
    "            wind[i] = 45\n",
    "        elif wind[i] == \"西北风\":\n",
    "            wind[i] = 135\n",
    "        elif wind[i] == \"西南风\":\n",
    "            wind[i] = 225\n",
    "        elif wind[i] == \"东南风\":\n",
    "            wind[i] = 315\n",
    "    return wind\n",
    "\n",
    "\n",
    "def wind_radar(data):\n",
    "    \"\"\"风向雷达图\"\"\"\n",
    "    wind1 = list(data['风向1'])\n",
    "    wind2 = list(data['风向2'])\n",
    "    wind_speed = list(data['风级'])\n",
    "    wind1 = change_wind(wind1)\n",
    "    wind2 = change_wind(wind2)\n",
    "\n",
    "    degs = np.arange(45, 361, 45)\n",
    "    temp = []\n",
    "    for deg in degs:\n",
    "        speed = []\n",
    "        # 获取 wind_deg 在指定范围的风速平均值数据\n",
    "        for i in range(0, 14):\n",
    "            if wind1[i] == deg:\n",
    "                speed.append(wind_speed[i])\n",
    "            if wind2[i] == deg:\n",
    "                speed.append(wind_speed[i])\n",
    "        if len(speed) == 0:\n",
    "            temp.append(0)\n",
    "        else:\n",
    "            temp.append(sum(speed) / len(speed))\n",
    "    print(temp)\n",
    "    N = 8\n",
    "    theta = np.arange(0. + np.pi / 8, 2 * np.pi + np.pi / 8, 2 * np.pi / 8)\n",
    "    # 数据极径\n",
    "    radii = np.array(temp)\n",
    "    # 绘制极区图坐标系\n",
    "    plt.axes(polar=True)\n",
    "    # 定义每个扇区的RGB值（R,G,B），x越大，对应的颜色越接近蓝色\n",
    "    colors = [(1 - x / max(temp), 1 - x / max(temp), 0.6) for x in radii]\n",
    "    plt.bar(theta, radii, width=(2 * np.pi / N), bottom=0.0, color=colors)\n",
    "    plt.title('未来14天风级图', x=0.2, fontsize=20)\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def weather_pie(data):\n",
    "    \"\"\"绘制天气饼图\"\"\"\n",
    "    weather = list(data['天气'])\n",
    "    dic_wea = {}\n",
    "    for i in range(0, 14):\n",
    "        if weather[i] in dic_wea.keys():\n",
    "            dic_wea[weather[i]] += 1\n",
    "        else:\n",
    "            dic_wea[weather[i]] = 1\n",
    "    print(dic_wea)\n",
    "    explode = [0.01] * len(dic_wea.keys())\n",
    "    color = ['lightskyblue', 'silver', 'yellow', 'salmon', 'grey', 'lime', 'gold', 'red', 'green', 'pink']\n",
    "    plt.pie(dic_wea.values(), explode=explode, labels=dic_wea.keys(), autopct='%1.1f%%', colors=color)\n",
    "    plt.title('未来14天气候分布饼图')\n",
    "    plt.show()\n",
    "\n",
    "\n",
    "def main():\n",
    "    plt.rcParams['font.sans-serif'] = ['SimHei']  # 解决中文显示问题\n",
    "    plt.rcParams['axes.unicode_minus'] = False  # 解决负号显示问题\n",
    "    data14 = pd.read_csv('weather14.csv', encoding='gb2312')\n",
    "    print(data14)\n",
    "    tem_curve(data14)\n",
    "    wind_radar(data14)\n",
    "    weather_pie(data14)\n",
    "\n",
    "\n",
    "if __name__ == '__main__':\n",
    "    main()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}