大乐透数据分析

数据爬取

导包

import requests
from lxml import etree
import csv

爬取信息

def get_info(url):
    headers = {
        'UserAgent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    resp = requests.get(url=url, headers=headers)
    resp.encoding = 'utf-8'
    # print(resp.text)
    html = etree.HTML(resp.text)
    tr_list = html.xpath('//table[@id="chartsTable"]/tr[position()>2 and position()<122 and not (@class="tdbck")]')
    # 去除不需要的tr标签
    # tr_list = html.xpath('//table[@id="chartsTable"]/tr[position()>2]')
    f = open('./大乐透.csv', mode='w', encoding='utf-8')
    csv_writer = csv.writer(f)
    for tr in tr_list:
        qi_shu = tr.xpath('./td[@align="center"]/text()')
        red_ball = tr.xpath('./td[@class="chartBall01"]/text()')
        blue_ball = tr.xpath('./td[@class="chartBall02"]/text()')
        info_list = qi_shu + red_ball + blue_ball
        csv_writer.writerow(info_list)
        print(qi_shu[0], 'over')
    f.close()

主程序

if __name__ == '__main__':
    url = 'https://datachart.500.com/dlt/zoushi/newinc/jbzs_foreback.php?expect=100'
    get_info(url)

可视化分析

导包

import pandas as pd
import matplotlib.pylab as plt
import numpy as np

数据处理

df = pd.read_csv('大乐透.csv', header=None, index_col=0)
# 读取数据,对表头和第一列进行设置
# print(df)
red_ball = df.loc[:, 1:5]
blue_ball = df.loc[:, 6:7]
# pandas的loc公式截取数据[行,列]
red_ball_count = pd.value_counts(red_ball.values.flatten())
# 把红球的数据区变成一个一位的顺序排列的数据(flatten()),然后统计
# print(red_ball_count)
blue_ball_count = pd.value_counts(blue_ball.values.flatten())
# 有行有列的时候才使用flatten()函数,如果只有一列,可以直接把值丢进去不用加 flatten()
# print(blue_ball_count)

matplotlib进行数据展示

# 可视化展示

# fig,ax = plt.subplots(2,1)
# 一次创建多个图标,两行 一列
# print(fig)
# print(ax)
# ax[0].pie(red_ball_count,labels=red_ball_count.index,radius=1,wedgeprops={'width':0.3})
# ax[0].pie(blue_ball_count,labels=blue_ball_count.index,radius=0.5,wedgeprops={'width':0.2})
# pie 表示饼图,labels图片旁边索引,radius 饼图的半径,wedgeprops 表示中间挖空,ax[i]里面的i一样时,两个图形就会重叠
colors = {}
# 另一种写法
plt.pie(red_ball_count, colors=np.random.choice([colors[i] for i in colors], len(red_ball_count)),labels=red_ball_count.index, radius=1, wedgeprops={'width': 0.3})
plt.pie(blue_ball_count, colors=np.random.choice([colors[i] for i in colors], len(blue_ball_count)),labels=blue_ball_count.index, radius=0.5, wedgeprops={'width': 0.2})

# plt.pie(red_ball_count,labels=red_ball.count.index)
# plt.pie(blue_ball_count,labels=blue_ball.count.index)
plt.show()

备注:常用的颜色列表

colors = {
‘aliceblue’: ‘#F0F8FF’,
‘antiquewhite’: ‘#FAEBD7’,
‘aqua’: ‘#00FFFF’,
‘aquamarine’: ‘#7FFFD4’,
‘azure’: ‘#F0FFFF’,
‘beige’: ‘#F5F5DC’,
‘bisque’: ‘#FFE4C4’,
‘black’: ‘#000000’,
‘blanchedalmond’: ‘#FFEBCD’,
‘blue’: ‘#0000FF’,
‘blueviolet’: ‘#8A2BE2’,
‘brown’: ‘#A52A2A’,
‘burlywood’: ‘#DEB887’,
‘cadetblue’: ‘#5F9EA0’,
‘chartreuse’: ‘#7FFF00’,
‘chocolate’: ‘#D2691E’,
‘coral’: ‘#FF7F50’,
‘cornflowerblue’: ‘#6495ED’,
‘cornsilk’: ‘#FFF8DC’,
‘crimson’: ‘#DC143C’,
‘cyan’: ‘#00FFFF’,
‘darkblue’: ‘#00008B’,
‘darkcyan’: ‘#008B8B’,
‘darkgoldenrod’: ‘#B8860B’,
‘darkgray’: ‘#A9A9A9’,
‘darkgreen’: ‘#006400’,
‘darkkhaki’: ‘#BDB76B’,
‘darkmagenta’: ‘#8B008B’,
‘darkolivegreen’: ‘#556B2F’,
‘darkorange’: ‘#FF8C00’,
‘darkorchid’: ‘#9932CC’,
‘darkred’: ‘#8B0000’,
‘darksalmon’: ‘#E9967A’,
‘darkseagreen’: ‘#8FBC8F’,
‘darkslateblue’: ‘#483D8B’,
‘darkslategray’: ‘#2F4F4F’,
‘darkturquoise’: ‘#00CED1’,
‘darkviolet’: ‘#9400D3’,
‘deeppink’: ‘#FF1493’,
‘deepskyblue’: ‘#00BFFF’,
‘dimgray’: ‘#696969’,
‘dodgerblue’: ‘#1E90FF’,
‘firebrick’: ‘#B22222’,
‘floralwhite’: ‘#FFFAF0’,
‘forestgreen’: ‘#228B22’,
‘fuchsia’: ‘#FF00FF’,
‘gainsboro’: ‘#DCDCDC’,
‘ghostwhite’: ‘#F8F8FF’,
‘gold’: ‘#FFD700’,
‘goldenrod’: ‘#DAA520’,
‘gray’: ‘#808080’,
‘green’: ‘#008000’,
‘greenyellow’: ‘#ADFF2F’,
‘honeydew’: ‘#F0FFF0’,
‘hotpink’: ‘#FF69B4’,
‘indianred’: ‘#CD5C5C’,
‘indigo’: ‘#4B0082’,
‘ivory’: ‘#FFFFF0’,
‘khaki’: ‘#F0E68C’,
‘lavender’: ‘#E6E6FA’,
‘lavenderblush’: ‘#FFF0F5’,
‘lawngreen’: ‘#7CFC00’,
‘lemonchiffon’: ‘#FFFACD’,
‘lightblue’: ‘#ADD8E6’,
‘lightcoral’: ‘#F08080’,
‘lightcyan’: ‘#E0FFFF’,
‘lightgoldenrodyellow’: ‘#FAFAD2’,
‘lightgreen’: ‘#90EE90’,
‘lightgray’: ‘#D3D3D3’,
‘lightpink’: ‘#FFB6C1’,
‘lightsalmon’: ‘#FFA07A’,
‘lightseagreen’: ‘#20B2AA’,
‘lightskyblue’: ‘#87CEFA’,
‘lightslategray’: ‘#778899’,
‘lightsteelblue’: ‘#B0C4DE’,
‘lightyellow’: ‘#FFFFE0’,
‘lime’: ‘#00FF00’,
‘limegreen’: ‘#32CD32’,
‘linen’: ‘#FAF0E6’,
‘magenta’: ‘#FF00FF’,
‘maroon’: ‘#800000’,
‘mediumaquamarine’: ‘#66CDAA’,
‘mediumblue’: ‘#0000CD’,
‘mediumorchid’: ‘#BA55D3’,
‘mediumpurple’: ‘#9370DB’,
‘mediumseagreen’: ‘#3CB371’,
‘mediumslateblue’: ‘#7B68EE’,
‘mediumspringgreen’: ‘#00FA9A’,
‘mediumturquoise’: ‘#48D1CC’,
‘mediumvioletred’: ‘#C71585’,
‘midnightblue’: ‘#191970’,
‘mintcream’: ‘#F5FFFA’,
‘mistyrose’: ‘#FFE4E1’,
‘moccasin’: ‘#FFE4B5’,
‘navajowhite’: ‘#FFDEAD’,
‘navy’: ‘#000080’,
‘oldlace’: ‘#FDF5E6’,
‘olive’: ‘#808000’,
‘olivedrab’: ‘#6B8E23’,
‘orange’: ‘#FFA500’,
‘orangered’: ‘#FF4500’,
‘orchid’: ‘#DA70D6’,
‘palegoldenrod’: ‘#EEE8AA’,
‘palegreen’: ‘#98FB98’,
‘paleturquoise’: ‘#AFEEEE’,
‘palevioletred’: ‘#DB7093’,
‘papayawhip’: ‘#FFEFD5’,
‘peachpuff’: ‘#FFDAB9’,
‘peru’: ‘#CD853F’,
‘pink’: ‘#FFC0CB’,
‘plum’: ‘#DDA0DD’,
‘powderblue’: ‘#B0E0E6’,
‘purple’: ‘#800080’,
‘red’: ‘#FF0000’,
‘rosybrown’: ‘#BC8F8F’,
‘royalblue’: ‘#4169E1’,
‘saddlebrown’: ‘#8B4513’,
‘salmon’: ‘#FA8072’,
‘sandybrown’: ‘#FAA460’,
‘seagreen’: ‘#2E8B57’,
‘seashell’: ‘#FFF5EE’,
‘sienna’: ‘#A0522D’,
‘silver’: ‘#C0C0C0’,
‘skyblue’: ‘#87CEEB’,
‘slateblue’: ‘#6A5ACD’,
‘slategray’: ‘#708090’,
‘snow’: ‘#FFFAFA’,
‘springgreen’: ‘#00FF7F’,
‘steelblue’: ‘#4682B4’,
‘tan’: ‘#D2B48C’,
‘teal’: ‘#008080’,
‘thistle’: ‘#D8BFD8’,
‘tomato’: ‘#FF6347’,
‘turquoise’: ‘#40E0D0’,
‘violet’: ‘#EE82EE’,
‘wheat’: ‘#F5DEB3’,
‘white’: ‘#FFFFFF’,
‘whitesmoke’: ‘#F5F5F5’,
‘yellow’: ‘#FFFF00’,
‘yellowgreen’: ‘#9ACD32’}

你可能感兴趣的:(matplotlib数据分析)