2017年12月_castingA3T

原创 matplotlib条形图

from matplotlib import pyplot as pltimport numpy as npfig=plt.figure()ax=fig.add_subplot(111)x=np.arange(4)data=np.array([15,20,18,25])rect=ax.bar(x,data,width=0.5,color="lightblue")for rec in r

2017-12-31 10:48:39 344

原创 KMeans基础代码

import numpy as npimport matplotlib.pyplot as plt#给定x,y两组数据x=np.array([1,7,4,6,2,9,3,5,7,3,5,9,7,8,2,4,3,1,2,4,4,2])y=np.array([8,3,10,5,12,2,9,11,1,20,4,7,8,4,3,2,5,1,6,5,15,15])#plt.scatter(x,y)#

2017-12-29 21:13:18 423

原创 matplotlib绘制sin、cos曲线

import numpy as npimport matplotlib.pyplot as pltplt.rcParams['font.sans-serif']=['SimHei']#用来正常显示中文标签plt.rcParams['axes.unicode_minus']=False#用来正常显示负号x = np.linspace(0, 10, 1000)y = np.sin(x) + 1

2017-12-29 21:02:24 9796

原创 pandas层次化索引

import pandas as pdimport numpy as npfrom numpy import nan as NAdf=pd.DataFrame(np.random.randn(7,3),index=['a','b','c','d','e','f','g'],columns=['q','w','t'])In [106]:dfOut[120]: q

2017-12-29 18:03:12 363

原创链家网二手房数据分析（承接上篇爬虫）

import pandas as pdimport numpy as npimport matplotlib.pyplot as pltplt.rcParams['font.sans-serif']=['SimHei']#用来正常显示中文标签path='F:/python/从零开始学python网络爬虫/链家网/lianjia-3.xls'lj=pd.read_excel(path)

2017-12-28 22:43:05 3740

原创 python爬取链家网40页二手房信息

import requestsfrom bs4 import BeautifulSoupimport reimport timeheaders={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/

2017-12-28 22:38:57 727

原创 pandas过滤缺失值

import pandas as pdimport numpy as npobj=pd.Series(range(5),index=['a','a','b','b','c'])print(obj)print(obj.index.is_unique)#是够是唯一值print(obj['b'])print(obj['c'])print(obj[['a','b']])#输出多个列print

2017-12-28 18:59:14 2624

原创 KMeans与MiniBatchKMeans

#首先随机创建一些二维数据作为训练集，选择二维特征数据，主要是方便可视化from numpy import concatenate,column_stack,row_stackimport numpy as npimport matplotlib.pyplot as plt#%matplotlib inlinefrom sklearn.datasets.samples_generator

2017-12-26 23:04:04 3081

原创 scatter绘制散点图

import numpy as np import matplotlib.pyplot as plt x = np.arange(1,10) y = x fig = plt.figure() ax1 = fig.add_subplot(111) ax1.set_title('Scatter Plot') plt.xlabel('X') plt.ylabel('Y')

2017-12-26 13:04:36 2554

原创 matplotlib绘制函数曲线

import numpy as np import matplotlib.pyplot as pltplt.rcParams['axes.unicode_minus']=Falsex = np.linspace(-30, 30, 10000) y = (x**2-5*x+10)#方程式 z = (2*x-5)#导数方程 z = (-5*x+10)#二次函数的0点切线方程plt.figure(

2017-12-25 23:42:25 5921

原创 polyfit及poly1d多项式拟合

#多项式拟合(从给定的x,y中解析出最接近数据的方程式)#要拟合的x,y数据x = np.arange(1, 17, 1)y = np.array([4.00, 6.40, 8.00, 8.80, 9.22, 9.50, 9.70, 9.86, 10.00, 10.20, 10.32, 10.42, 10.50, 10.55, 10.58, 10.60])z1 = np.polyfit(x,

2017-12-25 18:17:08 9228

原创 pandas运算、排序、排名

import pandas as pdimport numpy as np#Series运算s1=pd.Series([7.3,-2.5,3.4,1.5],index=['a','c','d','e'])s2=pd.Series([-2.1,3.6,-1.5,4,3.1],index=['a','c','e','f','g'])print(s1+s2)print(s1.add(s2,fi

2017-12-25 14:27:08 1536

原创抓取淘宝评论

import requestsheaders={ 'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' }'''url='https://rate.tmall.com/l

2017-12-21 20:11:04 1194

原创 meshgrid计算函数sqrt(x^2+y^2)

import numpy as nppoints=np.arange(-5,5,0.01)#1000个间隔相同的点xs,ys=np.meshgrid(points,points)#生成两个二维矩阵print(ys)import matplotlib.pyplot as pltz=np.sqrt(xs ** 2 + ys ** 2)#计算函数print(z)plt.imshow(z

2017-12-21 12:18:46 1824

原创诸葛找房房源信息爬取

import requestsfrom bs4 import BeautifulSoupimport pymongoimport datetimeimport re lg = '15001927982ttcc'lgttcc = re.sub("\D", "", lg)headers={ 'UserAgent':'Mozilla/5.0 (Windows NT 6.1; WOW

2017-12-20 22:44:16 1298

原创前程无忧python工作薪资爬取及数据分析

# -*- coding: utf-8 -*-"""Created on Fri Dec 15 15:31:51 2017@author: Administrator"""'''获取前程无忧python相关工作地点、薪水、公司、职位'''import requestsfrom bs4 import BeautifulSoupheaders={ 'UserAgent':

2017-12-17 21:33:50 6706 1

原创爬取斗破苍穹整本小说

import requestsfrom bs4 import BeautifulSoupheaders={ 'UserAgent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' }url='

2017-12-15 12:30:30 1602

原创链家网爬虫

import requestsfrom bs4 import BeautifulSoupheaders={ 'UserAgent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}def get_detai

2017-12-13 22:41:40 1263

原创 python爬取起点中文网，原创榜单

import requestsfrom bs4 import BeautifulSoupheaders={ 'UserAgent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' }total

2017-12-13 18:24:10 4025

原创爬取酷狗top500

import requestsfrom bs4 import BeautifulSoupheaders={ 'UserAgent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36' }def

2017-12-13 12:19:24 1821

原创 if name == "main":

文件名：const.pyPI = 3.14def main(): return PIif __name__ == "__main__": print("PI:", main())结果：PI: 3.14文件名：area.pyfrom const import PIdef calc_round_area(radius): return PI * (radius **

2017-12-13 10:12:43 408

原创 python抓取博客正文

import requestsfrom bs4 import BeautifulSouplink = "http://www.santostang.com/2017/10/22/%E5%9B%BD%E5%86%85%E4%B8%8B%E8%BD%BDanaconda%E9%80%9F%E5%BA%A6%E6%85%A2%EF%BC%8C%E8%AF%B7%E4%BD%BF%E7%94%A8%E6

2017-12-10 21:43:16 590

原创 python爬虫——获取新浪新闻前两页新闻信息

import requestsimport jsonfrom bs4 import BeautifulSoupimport reimport jsonfrom datetime import datetimecommentURL='http://comment5.news.sina.com.cn/page/info?version=1&\ format=j

2017-12-10 20:33:51 731

原创获取新浪新闻信息

'''import requestsfrom bs4 import BeautifulSoupres=requests.get('http://news.sina.com.cn/china/')res.encoding='utf-8'soup=BeautifulSoup(res.text,'html.parser')for news in soup.select('.news-item'

2017-12-10 11:39:48 513

原创条件结构及函数

条件表达式的值只要不是False,0,空值None,空列表，空元组，空集合，空字典，空字符串，空range对象或其他空迭代对象，均认为与True等价。条件表达式中不允许使用赋值运算符‘=’。 1、单分支结构，2、双分支结构，3、多分枝结构，4、选择结构的嵌套 split():拆分字符串，通过指定分隔符对字符串进行切片，并返回分割后的字符串列表。 lower()转换字符串中所有大写字符为小写

2017-12-05 17:56:53 425

原创 python猜数字游戏

猜随机数字import randomy = random.randint(1,10)print('猜数字游戏')z = input('输入数字')guess = int(z)if guess > y: print('大了')else: print('小了')while guess != y: z = input('重新输入数字') guess = in

2017-12-04 22:12:00 529

原创 2017.12.03.学习日记（集合）

集合：无序可变序列，界定符大括号，分隔符逗号，元素唯一不能重复。 a=set([0,1,2,1,2]) print(a) del a hash(‘1,2,3’) import time print(time.time())集合中只能包含数字、字符串、元组等不可变类型，不能包含列表、集合、字典等可变类型数据。调用hash()函数时抛出异常都不能作为集合元素。 add():为集合增加新元素

2017-12-03 18:31:27 232

原创 hello world

print(‘hello world’)

2017-12-03 11:29:24 165

castingA3T的博客