PowerPoint 프레젠테이션

Size: px

Start display at page:

Download "PowerPoint 프레젠테이션"

강우 증
6 years ago
Views:

1 파이썬을이용한빅데이터수집. 분석과시각화 Part 2. 데이터시각화 이원하

2 목 차 WordCloud 자연어처리 Matplotlib 그래프 Folium 지도시각화 Seabean - Heatmap

3 1 WORDCLOUD - 자연어처리

KoNLPy 형태소기반자연어처리 http://www.oracle.com/technetwork/java/javase/downloads/index.html http://www.lfd.uci.edu/~gohlke/pythonlibs/#jpype >>> from konlpy.

4 KoNLPy 형태소기반자연어처리 >>> from konlpy.tag import Kkma >>> from konlpy.utils import pprint >>> kkma = Kkma() >>> pprint(kkma.nouns(u' 명사만을추출하여워드클라우드를그려봅니다 ')) [' 명사 ', ' 추출 ', ' 워드 ', ' 워드클라우드 ', ' 클라우드 '] 4

5 KoNLPy 내부객체 5

$KoNLPy & pytagcloud >>> from collections import Counter >>> color = ['red', 'blue', 'red', 'red'] >>> counter_color = Counter(color) >>> print(counter_color_a) Counter({'red': 3, 'blue': 1}) 6$

6 KoNLPy & pytagcloud >>> from collections import Counter >>> color = ['red', 'blue', 'red', 'red'] >>> counter_color = Counter(color) >>> print(counter_color_a) Counter({'red': 3, 'blue': 1}) 6 jtbcnews_facebook_ _ txt >>> from konlpy.tag import Twitter >>> from collections import Counter >>> import pytagcloud >>> import webbrowser >>> import re >>> openfilename = "c:/python_sample/jtbcnews_facebook_ _ txt" >>> cloudimagepath = openfilename + ".jpg" >>> rfile = open(openfilename, 'r', encoding='utf-8').read() >>> data = re.sub(r'[^\w]', ' ', rfile) >>> nlp = Twitter() >>> nouns = nlp.nouns(data) >>> count = Counter(nouns) >>> wordinfo = dict() >>> for tags, counts in count.most_common(50): if (len(str(tags)) > 1): wordinfo[tags] = counts print ("%s : %d" % (tags, counts)) >>> taglist = pytagcloud.make_tags(dict(wordinfo).items(), maxsize=80) >>> pytagcloud.create_tag_image(taglist, cloudimagepath, size=(640, 480), fontname='korean', rectangular=false) >>> webbrowser.open(cloudimagepath)

7 21 MATPLOTLIB 그래프

8 Matplotlib 그래프 Package [ 파이썬설치경로 ]>pip install matplotlib >>> from matplotlib import pyplot >>> pyplot.plot([1,2,3,4],[10,30,20,40]) >>> pyplot.show() 8

9 Matplotlib 그래프 Package File "C:\python\lib\site-packages\matplotlib\font_manager.py", line 1412, in <module> fontmanager = pickle_load(_fmcache) def win32installedfonts(directory=none, fontext='ttf'): 중략 key, direc, any = winreg.enumvalue( local, j) if not is_string_like(direc): continue if not os.path.dirname(direc): direc = os.path.join(directory, direc) direc = direc.split( \0, 1)[0] # 파이썬경로문제해결 direc = os.path.abspath(direc).lower() 9

10 Matplotlib 그래프 Package >>> import matplotlib.pyplot as plt >>> plt.plot([1,2,3,4]) >>> plt.xlabel('x-axis label ) #x 축라벨타이틀설정 >>> plt.ylabel('y-axis label') #y 축라벨타이틀설정 >>> plt.show() >>> plt.plot([1,2,3,4],[1,2,3,4]) >>> plt.show() 10

11 Matplotlib 그래프 Package >>> plt.plot([1,2,3,4], [1,2,3,4], 'ro') >>> plt.show() 11

12 Matplotlib 그래프 Package >>> plt.plot([1,2,3,4],[1,2,3,4],'r-', [1,2,3,4],[3,4,5,6],'v-') >>> plt.show() >>> from matplotlib import font_manager, rc >>> import matplotlib >>> font_location = "c:/windows/fonts/malgun.ttf" >>> font_name = font_manager.fontproperties(fname=font_location).get_name() >>> matplotlib.rc('font', family=font_name) >>> plt.plot([1,2,3,4]) >>> plt.xlabel('x축한글표시 ') >>> plt.show() 12

13 Matplotlib 그래프 Package >>> plt.figure() >>> plt.subplot(1, 2, 1) >>> plt.plot([1,2,3,4], [1,2,3,4]) >>> plt.subplot(1, 2, 2) >>> plt.plot([5,6,7,8],[5,6,7,8]) >>> plt.show() 13

14 Matplotlib 그래프 Package >>> plt.plot([1,2,3,4], [1,2,3,4]) >>> plt.xlabel('x축 ') >>> plt.ylabel('y축 ') >>> plt.title('matplotlib 활용 ') >>> plt.text(3.5, 3.0, ' 평균 :2.5') >>> plt.grid(true) >>> plt.show() 14

Matplotlib 그래프 Package jtbcnews_facebook_2017-01-01_2017-06-30.txt >>> from konlpy.

15 Matplotlib 그래프 Package jtbcnews_facebook_ _ txt >>> from konlpy.tag import Twitter >>> from collections import Counter >>> import pytagcloud >>> import webbrowser >>> import re >>> openfilename = "c:/python_sample/jtbcnews_facebook_ _ txt" >>> cloudimagepath = openfilename + ".jpg" >>> rfile = open(openfilename, 'r', encoding='utf-8').read() >>> data = re.sub(r'[^\w]', ' ', rfile) >>> nlp = Twitter() >>> nouns = nlp.nouns(data) >>> count = Counter(nouns) >>> wordinfo = dict() >>> for tags, counts in count.most_common(50): if (len(str(tags)) > 1): wordinfo[tags] = counts print ("%s : %d" % (tags, counts)) >>> import matplotlib.pyplot as plt >>> from matplotlib import font_manager, rc >>> import matplotlib >>> font_location = "c:/windows/fonts/malgun.ttf" >>> font_name = font_manager.fontproperties(fname=font_location).get_name() matplotlib.rc('font', family=font_name) >>> plt.xlabel(' 주요단어 ') >>> plt.ylabel(' 빈도수 ') >>> plt.grid(true) >>> Sorted_Dict_Values = sorted(wordinfo.values(), reverse=true) >>> Sorted_Dict_Keys = sorted(wordinfo, key=wordinfo.get, reverse=true) >>> plt.bar(range(len(wordinfo)), Sorted_Dict_Values, align='center') >>> plt.xticks(range(len(wordinfo)), list(sorted_dict_keys), rotation='70') >>> plt.show() 15

16 21 FOLIUM 지도시각화

17 Folium 지도시각화 Package [ 파이썬설치경로 ]>pip install folium >>> import folium >>> map_osm = folium.map(location=[ , ]) >>> map_osm.save( c:/python_sample/map1.html') 17

Folium 지도시각화 Package >>> import folium >>> map_osm = folium.map(location=[37.

html') >>> import folium >>> map_osm = folium.map(location=[37.566345, 126.

save('c:/python_sample/map3.html') >>> map_osm = folium.map(location=[37.

18 Folium 지도시각화 Package >>> import folium >>> map_osm = folium.map(location=[ , ], zoom_st art=17) >>> map_osm.save( c:/python_sample/map2.html') >>> import folium >>> map_osm = folium.map(location=[ , ], zoom_st art=17, tiles='stamen Terrain') >>> map_osm.save('c:/python_sample/map3.html') >>> map_osm = folium.map(location=[ , ], zoom_st art=17, tiles='stamen Toner') >>> map_osm.save('c:/python_sample/map4.html') 18

19 Folium 지도시각화 Package >>> map_osm = folium.map(location=[ , ], zoom_start=17) >>> folium.marker([ , ], popup=' 서울특별시청 ').add_to(map_osm) >>> folium.marker([ , ], popup=' 덕수궁 ').add_to(map_osm) >>> map_osm.save(c:/python_sample/map5.html')

20 Folium 지도시각화 Package import urllib.request import json import folium import webbrowser if (retdata == None): return None else: return json.loads(retdata) def get_request_url(url): client_id = "PIKKM1p_iFKvlrgZdyk3" client_secret = "scxkesjyib" req = urllib.request.request(url) req.add_header("x-naver-client-id", client_id) req.add_header("x-naver-client-secret", client_secret) try: response = urllib.request.urlopen(req) if response.getcode() == 200: return response.read().decode('utf-8') except Exception as e: print(e) return None def getgeodata(address): base = " parameters = "?query=%s" % urllib.parse.quote(address) url = base + parameters retdata = get_request_url(url) def main(): address = input(" 주소를입력하세요 : ") jsonresult = getgeodata(address) if (jsonresult == None): print (" 주소검색결과가없습니다 ") elif 'result' in jsonresult.keys(): lattitude = jsonresult['result']['items'][0]['point']['y'] longitude = jsonresult['result']['items'][0]['point']['x'] map_osm = folium.map(location=[lattitude, longitude], zoom_start=17) folium.marker(location=[lattitude, longitude], popup=address).add_to(map_osm) map_osm.save('c:/python_sample/address.html') webbrowser.open('c:/python_sample/address.html') else: print (" 주소검색결과가없습니다 ") if name == ' main ': main()

데이터 시각화

데이터 시각화 데이터시각화 박창이 서울시립대학교통계학과 박창이 ( 서울시립대학교통계학과 ) 데이터시각화 1 / 22 학습내용 matplotlib 막대그래프히스토그램선그래프산점도참고 박창이 ( 서울시립대학교통계학과 ) 데이터시각화 2 / 22 matplotlib I 간단한막대그래프, 선그래프, 산점도등을그릴때유용 http://matplotlib.org 에서설치방법참고윈도우의경우명령프롬프트를관리자권한으로실행한후아래의코드실행