什么是数据分析?
数据分析是指运用适当的统计分析方法或者工具对收集来的大量数据进行整理和归纳,将它们加以汇总和理解并消化,提取有价值信息,从中发现因果关系、内部联系和业务规律,以求最大化地开发数据的功能,形成有效结论的过程,发挥数据的作用。
去博客设置页面,选择一款你喜欢的代码片高亮样式,下面展示同样高亮的 代码片
.
#!/usr/bin/python3
# -*- coding:utf-8 -*-
# author: 恒仔仔
# ====================================================
# 内容描述:爬取豆瓣电影评论数据
# ====================================================
import urllib.request
from bs4 import BeautifulSoup
import random
import time
import csv
from tqdm import tqdm
import string
def getHTML(url,movieid):
"""获取url页面"""
id = movieid
user_agents = list({
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60',
'Opera/8.0 (Windows NT 5.1; U; en)',
'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0',
'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2 ',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36",
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0) ',
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14"})
headers = {
# 注意:使用登陆账号的cookie最多能爬取500条数据,使用不登录账号的cookie最多只能爬取200条数据
# 防止账号被永久封禁,请自行添加 IP 代理,或者不登陆账号,爬取少量数据做分析即可
'Cookie': '你自己的cookie',
'User-Agent': str(random.choice(user_agents)),
'Referer': 'https: // movie.douban.com / subject / ' + id + '/ comments?status = P',
'Connection': 'keep-alive'
}
request = urllib.request.Request(url, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
return content
def getComment(url,movieid):
"""解析HTML页面"""
html = getHTML(url,movieid)
bs = BeautifulSoup(html, 'html.parser')
# 评论作者
one_page_authors = []
authors = bs.select(".comment-info a")
for author in authors:
one_page_authors.append(author.text)
# 评论内容
one_page_comments = []
comments = bs.select(".comment .short")
for comment in comments:
# 去掉所有标点符号
content_str = ''.join(c for c in comment.text if c not in string.punctuation) \
.replace(" ", "").replace("\n", "")
one_page_comments.append(content_str)
# 评论评分
one_page_rates = []
rates = bs.select(".rating")
for rate in rates:
rate_str = str(rate.get("class")).split(" ")[0]
rate_score = int([int(i) for i in rate_str if i.isdigit()][0])
one_page_rates.append(rate_score)
# 评论title
one_page_titles = []
titles = bs.select(".rating")
for title in titles:
one_page_titles.append(title.get("title"))
# 评论日期
one_page_dates = []
dates = bs.select(".comment-time")
for date in dates:
one_page_dates.append(date.get("title"))
# 评论是否有用
one_page_uses = []
uses = bs.select(".votes")
for u in uses:
one_page_uses.append(u.text)
return [one_page_authors, one_page_comments, one_page_rates, one_page_titles, one_page_dates, one_page_uses]
def generateURL(movieid):
""" 生成所有的 待爬取的 URL """
urls = []
id = movieid
# 好评数据
page_number = 25
for page in range(page_number):
url = 'https://movie.douban.com/subject/' + id + '/comments?start=' + str(20 * page) + '&limit=20&sort=new_score&status=P&percent_type=h'
urls.append(url)
page_number = 25
# 中评论数据
for page in range(page_number):
url = 'https://movie.douban.com/subject/' + id + '/comments?start=' + str(20 * page) + '&limit=20&sort=new_score&status=P&percent_type=m'
urls.append(url)
page_number = 25
# 差评数据
for page in range(page_number):
url = 'https://movie.douban.com/subject/' + id + '/comments?start='+ str(20 * page) + '&limit=20&sort=new_score&status=P&percent_type=l'
urls.append(url)
page_number = 5
# 最新数据
for page in range(page_number):
url = 'https://movie.douban.com/subject/' + id + '/comments?start=' + str(20 * page) + '&limit=20&sort=time&status=P&percent_type=l'
urls.append(url)
# 想看
page_number = 25
for page in range(page_number):
url = 'https://movie.douban.com/subject/' + id + '/comments?start=' + str(20 * page) + '&limit=20&sort=new_score&status=F'
urls.append(url)
return urls
if __name__ == '__main__':
file = open('movie.csv', mode="w", encoding="utf-8", newline="")
csv_writer = csv.writer(file)
movieid = str() #输入电影id号
# 拿到所有的待爬取的URL
urls = generateURL(movieid)
print(urls)
times = list(range(8, 16))
for url in tqdm(urls):
print(url)
# 每个URL就是一页评论数据
[authors, comments, rates, titles, dates, uses] = getComment(url,movieid)
result_list = []
# 输出结果到文件中
for i in range(len(authors)):
result_list.append([authors[i], comments[i], rates[i], titles[i], dates[i], uses[i]])
csv_writer.writerows(result_list)
time.sleep(random.choice(times))
导入需要的库
import jieba
import wordcloud
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
为了解决matplotlib显示中文问题,仅适用于Windows
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
plt.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题
filepath = "movie.csv"
data = pd.read_csv(filepath, names=["date", "rate", "title", "uses", "name", "comment"], usecols=[0, 1, 2, 3, 4, 5])
display("数据集有{}条记录。".format(len(data)))
display(data.head())
进行设置即可
# 如果部分列的信息没显示出来,可以这么做
pd.set_option("max_columns", 20)
display(data.head())
data.info()
data[data["rate"].isnull()].head()
data.dropna(axis=0, inplace=True)
data.sample(10)
data.info()
display(data.columns)
data.describe()
对评分进行简单的频次统计
data["rate"].plot(kind="hist")
data["rate"].plot(kind="kde")
data.groupby("rate").size().plot(kind="bar")
data["date"] = data["date"].apply(lambda x: str(x).split(" ")[0])
data.head()
data["title"].value_counts()
输入自己需要截止的日期
data[data["date"] > "2020-10-08"].sample(30)
data[data["date"] > "2020-10-08"]["date"].value_counts()
按照每天统计评论数
data[data["date"] > "2019-07-26"].groupby("date").size().plot(kind="bar")
import pandas as pd
import matplotlib.pyplot as plt
# 读取文件
df = pd.read_csv("c:/movie.csv",
names=["date", "rate", "title", "uses", "name", "comment"],
usecols=[0, 1, 2, 3, 4, 5])
# 去掉带null字段的数据
df.dropna(axis=0, inplace=True)
# 处理日期字段,保留年月日,去掉时分秒
df["date"] = df["date"].apply(lambda x: str(x).split(" ")[0])
df["count"] = 1
# 筛选出上映之后的评论数据
df1 = df[df["date"] > "2019-10-08"]
# 按天统计评论的个数,并且按照天数排序
# df_result = df1.groupby("date")["count"].agg(["count"]).sort_values("count", ascending=False)
# 按天统计评论的个数
df_result = df1.groupby("date")["count"].agg(["count"])
df_result.plot(kind='bar')
plt.show()
["rate"].agg(["mean"]).sort_values("mean", ascending=False)
# 统计每天评论的平均分
df_result = df1.groupby("date")["rate"].agg(["mean"])
df_result.plot(kind='bar')
plt.show()
# 绘图
df_result.plot.pie(subplots=True, figsize=(6, 6), fontsize=18, counterclock=False, startangle=-270)
plt.title("评分饼图", fontsize=16, fontweight="bold")
plt.ylabel("", fontsize=12, fontweight="bold")
plt.show()
filepath = "c:/nezha.csv"
file = open(filepath, mode="r", encoding="utf-8")
content = file.read().replace("推荐", "").replace("力荐", "")
file.close()
# 分词,并生成词云图
ls = jieba.lcut(content)
txt = " ".join(ls)
w = wordcloud.WordCloud(font_path='c:\windows\Fonts\STZHONGS.TTF', width=1200, height=500, background_color='white')
w.generate(txt)
w.to_file('movie.png')
import matplotlib.image as imgplt
x = imgplt.imread("movie.png")
plt.imshow(x)
数据分析流程