猫眼电影-分析及展示（Python+pycharts）

  此篇文章承接（猫眼电影-爬取）。

  将电影数据储存到MySQL中后，发现评论人数和票房的数据当中存在汉字，后期不好分析，所以需要将汉字转化为数值。

  保险起见，我先将films表里面的结构和数据复制了成了一个新表films_copy，然后新增了2列，people和box_price。

将数据转化为便于分析的数据，代码如下：

import pymysql


def get_data():
    data1 = []
    data2 = []
    db = pymysql.connect(host='localhost', user='root', passwd='password', db='maoyan', port=3306)
    cursor = db.cursor()
    sql = "SELECT score_hum,box_office FROM films_copy"
    try:
        cursor.execute(sql)
        results = cursor.fetchall()
        for item in results:
            if '万' in item[0]:
                change0 = item[0]
                change1 = int(float(item[0].replace('万', '')) * 10000)
                data1.append((change1, change0))
            else:
                change0 = item[0]
                change1 = item[0]
                data1.append((change1, change0))
            if '万' in item[1]:
                if '美元' in item[1]:
                    change0 = item[1]
                    change2 = int(float(item[1].replace('万美元', '')) * 10000 * 6.8)
                    data2.append((change2, change0))
                else:
                    change0 = item[1]
                    change2 = int(float(item[1].replace('万', '')) * 10000)
                    data2.append((change2, change0))
            elif '亿' in item[1]:
                if '美元' in item[1]:
                    change0 = item[1]
                    change2 = int(float(item[1].replace('亿美元', '')) * 100000000 * 6.8)
                    data2.append((change2, change0))
                else:
                    change0 = item[1]
                    change2 = int(float(item[1].replace('亿', '')) * 100000000)
                    data2.append((change2, change0))
            else:
                change0 = item[1]
                data2.append((item[1], change0))
    except:
        print("something wrong")
    db.close()
    return data1,data2

def change_hum(data1)
    for i in range(len(data1)):
        db = pymysql.connect(host='localhost', user='root', passwd='password', db='maoyan', port=3306)
        cursor = db.cursor()
        sql1 = "UPDATE films_copy SET people = '%s' WHERE score_hum = '%s'" %(data1[i][0], data1[i][1])
        print(data1[i][0], data1[i][1])
        try:
            if cursor.execute(sql1):
                print('Successful')
                db.commit()
        except:
            db.rollback()
            print('Falied')
        db.close()
 
def change_prices(data2):    
    for i in range(len(data2)):
        db = pymysql.connect(host='localhost', user='root', passwd='password', db='maoyan', port=3306)
        cursor = db.cursor()
        sql2 = "UPDATE films_copy SET box_price = '%s' WHERE box_office = '%s'" %(data2[i][0], data2[i][1])
        try:
            if cursor.execute(sql2):
                print('Successful')
                db.commit()
        except:
            db.rollback()
            print('Falied')
        db.close()

def main():
    data1 = get_data()[0]
    data2 = get_data()[1]
    change_hum(data1)
    change_prices(data2)

if '__name__' == '__main__':
    main()
    
    

现在开始分析数据：（按照公众号作者的代码操作，一直没有出现作者文章中的效果，所以找解决方法找了很久）

1，2018年电影评分TOP10

 

from pyecharts import Bar
import pandas as pd
import numpy as np
import pymysql

co