matplotlib => line_chart + excel
import pandas as pd
import matplotlib.pyplot as plt
class LineChart:
def __init__(self):
self._xlsx = LineChart.getConfig()
self._xvalues = list()
self._yvalues = list()
def doLine(self):
for i in self._xlsx.index:
rowData = self._xlsx["날짜"][i], self._xlsx["방문자수"][i]
self._xvalues.append(rowData[0])
self._yvalues.append(rowData[1])
df = pd.DataFrame({"xvalues" : self._xvalues, "yvalues" : self._yvalues})
# plot
plt.plot("xvalues", "yvalues", data=df, color="g")
plt.xlabel("year")
plt.ylabel("count")
plt.title("tistory my count")
plt.show()
@classmethod
def getConfig(cls):
PATH = "/home/kim/Desktop/PY.dir/stu_01.dir/KimJH_uv.xlsx"
SHEETNAME = "uv"
xlxsObj = pd.read_excel(PATH, sheet_name=SHEETNAME)
return xlxsObj
def main():
obj = LineChart()
obj.doLine()
if __name__ == "__main__":
main()
'python > matplolib' 카테고리의 다른 글
| matplotlib => pie_chart + xlsx (0) | 2019.11.02 |
|---|
matplotlib => pie_chart + xlsx
import pandas as pd
import matplotlib.pyplot as plt
class PIE:
def __init__(self):
self._xlsx = PIE.getConfig()
self._category = {"남자" : 0, "여자" : 0}
def doPie(self):
for i in self._xlsx.index:
rowData = self._xlsx["성별"][i], self._xlsx["방문자수"][i]
self._category[rowData[0]] += rowData[1]
category = ["man", "woman"]
categorySize = [self._category["남자"], self._category["여자"]]
categoryColors = ["yellow", "green"]
categoryExplodes = (0.1, 0)
plt.pie(categorySize,
explode = categoryExplodes,
labels = category,
colors = categoryColors,
autopct = '%1.2f%%',
shadow = True,
startangle = 90,
textprops = {"fontsize" : 14}) # text font size
plt.axis("equal")
plt.show()
@classmethod
def getConfig(cls):
PATH = "/home/kim/Desktop/PY.dir/stu_01.dir/KimJH.xlsx"
SHEETNAME = "demographicsDashboard"
xlxsObj = pd.read_excel(PATH, sheet_name=SHEETNAME)
return xlxsObj
def main():
obj = PIE()
obj.doPie()
if __name__ == "__main__":
main()
'python > matplolib' 카테고리의 다른 글
| matplotlib => line_chart + excel (0) | 2019.11.02 |
|---|
데이트를 위해 맛집 크롤링 중
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import xlsxwriter # 엑셀
from bs4 import BeautifulSoup
from urllib.request import urlretrieve
import time
import os
# =====================================================
class Crawling(object):
def __init__(self, search_data):
# 작업 위치
os.chdir(r'C:\Users\sleep\Desktop\date_info')
self.search_data = search_data
self.target_url = "https://www.naver.com/"
self.chrome_options = Options() # 객체 생성
self.chrome_options.add_argument("--headless")
self.driver = webdriver.Chrome(r'C:\Users\sleep\Desktop\chrom_driver\chromedriver.exe',
chrome_options=self.chrome_options)
# 엑셀___________________________________________
self.wb = None
self.ws = None
# ______________________________________________
self.food_info_list = list()
self.index_list = ['title', 'url', 'latitude','longitude']
self.width_list = [87.5, 47.7, 15.8, 15.8]
self.index_num = [2, 3, 4, 5]
# func (1)
def URLrequest(self):
self.driver.get("https://www.naver.com/")
assert "NAVER" in self.driver.title
print ("title : {}".format(self.driver.title))
self.driver.find_element_by_name('query').send_keys(self.search_data)
self.driver.find_element_by_id('search_btn').click()
# scroll bar
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight/2);")
self.driver.find_element_by_xpath('//*[@id="main_pack"]/div[2]/div[2]/a').click()
page = 1
x = 10
while True:
print ("{} 페이지 작업 중 ==========================".format(page))
# scroll bar
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
html = BeautifulSoup(self.driver.page_source, "html.parser")
time.sleep(3)
li_list = html.select('ul.type01 > li') # list
for i in li_list:
# =============================================
t_data = {"thum_name_url":None,
"title":None,
"url":None,
"page":page}
# =============================================
thumb_nail = i.select_one('div.review_thumb > a')
try:
thumb_nail_url = thumb_nail.attrs['href']
except AttributeError as e:
print (e)
else:
t_data['thum_name_url'] = thumb_nail_url
# ---------------------------------------------
title_list = i.select_one('div.review_content > a')
try:
title = title_list.attrs['title']
except AttributeError as e:
print (e)
else:
t_data['title'] = title
# ---------------------------------------------
try:
url = title_list.attrs['href']
except AttributeError as e:
print (e)
else:
t_data['url'] = url
# ---------------------------------------------
self.food_info_list.append(t_data)
print (t_data)
# =============================================
try:
self.driver.find_element_by_xpath('//*[@id="main_pack"]/div[3]/a[{}]'.format(x)).click()
except:
print ("page _end")
break
else:
x = 11
page += 1
time.sleep(1)
# func (2)
def XLwrite(self):
self.wb = xlsxwriter.Workbook(self.search_data+'_.xlsx')
self.cell_format = self.wb.add_format()
self.cell_format.set_bottom() # 테두리 : 바닥
self.cell_format.set_top() # 테두리 : 천장
self.cell_format.set_left() # 테두리 : 왼쪽
self.cell_format.set_right() # 테두리 : 오른쪽
self.ws = self.wb.add_worksheet()
# 셀 열너비
for i ,w in zip(self.index_num, self.width_list):
self.ws.set_column(i, i, w)
r = 3
c = 2
for i in self.index_list:
self.ws.write_string(row=r, col=c,
string=i,
cell_format=self.cell_format)
c = c + 1
r += 1 # 행
c = 2
for i in self.food_info_list:
for j in i.keys():
if j == 'title':
self.ws.write_string(row=r,col=c,
string=i['title'],
cell_format=self.cell_format)
c = c + 1
elif j == 'url':
self.ws.write_string(row=r, col=c,
string=i['url'],
cell_format=self.cell_format)
c = c + 1
c = 2
r += 1 # 행
self.wb.close()
print ("엑셀 적재 완료")
def main():
node = Crawling("여의도 데이트 음식점") # 객체 생성
node.URLrequest()
node.XLwrite()
if __name__ == "__main__":
main()
'python > request + bs4' 카테고리의 다른 글
| python3 request (0) | 2018.03.11 |
|---|
python3 request
import requests
# HTML 소스 가져오기
def HTMLsouceGet(p):
print (p.text)
# HTTP 헤더 정보
def HTTPheaderGet(p):
retV = p.headers
return retV
def HTTPstatusGet(p):
print (p.status_code)
def main():
# GET방식으로 요청
req = requests.get(url='http://www.kitri.re.kr/academy/it_education/job_status2009.web')
is_ok = req.ok
print ("is_ok => {result}".format(result = is_ok))
if req.ok:
HTTPstatusGet(req)
d = HTTPheaderGet(req)
for i in d.keys():
print (i, d[i], sep='=> ')
else:
print ("요청 에러")
if __name__ == "__main__":
main()
is_ok => True
200
Date=> Sun, 11 Mar 2018 06:17:49 GMT
Server=> Apache/2.2.15 (CentOS)
Set-Cookie=> JSESSIONID=B27FC1FD587B1967B6F36A6A8755CA45; Path=/; HttpOnly
Content-Language=> ko-KR
Connection=> close
Transfer-Encoding=> chunked
Content-Type=> text/html;charset=UTF-8
'python > request + bs4' 카테고리의 다른 글
| 데이트를 위해 맛집 크롤링 중 (0) | 2018.11.22 |
|---|
python numpy 01
"""
Numerical Python
고성능의 과학계산 컴퓨팅과 데이터 분석에 필요한 기본 패키지
제공하는 기능
1) 빠르고 메모리를 효율적으로 사용하며 벡터 산술연산과 세련된
브로드캐스팅 기능을 제공하는 다차원 배열인 ndarray
2) 반복문을 작성할 필요없이 전체 데이터 배열에 대해 빠른 연산을
제공하는 표준 수학 함수
3) 배열 데이터를 디스크에 쓰거나 읽을 수 있는 도구와 메모리에 올려진
파일을 사용하는 도구
4) 선형대수(linear algebra), 난수 발생기, 푸리에 변환 기능
5) c, c++, 포트란으로 쓰여진 코드를 통합하는 도구
"""
import numpy as np
data = np.random.randn(3, 3)
print (data)
[[ 0.07353147 0.2299053 -1.40381414]
[ 0.28591902 -0.13944514 -0.2153317 ]
[-0.82442217 -0.94539717 0.30150343]]
random.randn 함수는 Return a sample (or samples) from the “standard normal” distribution. (표준 정규 분포)
# 벡터의 모양 출력
print (data.shape)
=> data 가 3x3 행렬 이기 때문에 (3,3) return
# 벡터의 원소들 데이터 타입 출력
print (data.dtype)
=> float64
# 차원
print (data.ndim)
=> 2차원
# ndarray 생성
import numpy as np
import pprint as ppr
s = [n for n in range(3, 20)]
vec = np.array(s)
ppr.pprint (vec)
# 자료형
s = [n for n in range(3, 20)] # 요 녀석은 파이썬의 list 타입
vec = np.array(s, dtype=np.float32)
# 새로운 배열을 생성
[1] zeros
import numpy as np
import pprint as ppr
np = np.zeros(shape=(4, 4))
ppr.pprint(np)
=>
array([[0., 0., 0., 0.],
[0., 0., 0., 0.],
[0., 0., 0., 0.],
[0., 0., 0., 0.]])
[2] arange
import numpy as np
v = np.arange(start=10, stop=30, step=1, dtype=np.int16)
print (v)
=>
[10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29]
