초보 파이썬 3주차

< 변화구간 파악하기 >

import pandas as pd

enroll = pd.read_csv('./data/enrolleds_detail.csv')

enroll_detail = enroll.groupby('lecture_id')['user_id'].count()

import matplotlib.pyplot as plt
plt.rcParams['font.family'] = 'AppleGothic'

plt.figure(figsize=(22,5))
plt.bar(enroll_detail.index, enroll_detail)
plt.title('강의에 따른 수강완료 수의 합계')
plt.xticks(rotation=90)
plt.show()

# 두 데이터 조인하여 강의명 나타내기

lectures = pd.read_csv('./data/lectures.csv')

lecture_count = pd.DataFrame(enroll_detail).reset_index()
lecture_count = lecture_count.rename(columns={'user_id':'count'})

lectures = lectures.set_index('lecture_id')

full_lecture = lecture_count.join(lectures, on='lecture_id')

plt.figure(figsize=(22,5))
plt.bar(full_lecture['title'], full_lecture['count'])
plt.title('강의에 따른 수강완료 수의 합계')
plt.xlabel('강의명')
plt.xticks(rotation=90)
plt.show()

# 여러 스크립트 반복분으로 읽어오기

result = ""

for number in range(1,15):
    index = '{:02}'.format(number)
    filename = "Sequence_" + index + ".txt"
    print(filename)
    text = open('./data/'+filename, 'r', encoding='utf-8-sig')
    result += text.read().replace("\n", " ")

result

하나씩 나열해서 열 경우

text = open('./data/Sequence_01.txt')
text = text.read()
text = text.replace('\n', " ")
text

text2 = open('./data/Sequence_02.txt')
text2 = text2.read()
text2 = text2.replace('\n', " ")
text2

특수 문자 없애기

import re

pattern = '[^\w\s]'
text = re.sub (pattern=pattern, repl='', string=result)

text

# 워드 클라우드 라이브러리 열기

import numpy as np
from PIL import Image
from wordcloud import WordCloud
import matplotlib.pyplot as plt

워드 클라우드 폰트 설정 및 표현하기

import matplotlib.font_manager as fm

for f in fm.fontManager.ttflist:
if 'Gothic' in f.name:
print(f.fname)

font_path = '/Library/Fonts/AppleGothic.ttf'

wc = WordCloud(font_path=font_path, background_color='white')
wc.generate(text)

plt.figure(figsize=(50,50))
plt.axis("off")
plt.imshow(wc)
plt.show()

// 예시 Generate a word cloud image
mask = np.array(Image.open('./data/sparta.png'))
wc = WordCloud(font_path=font_path, background_color="white", mask=mask)
wc.generate(text)
f = plt.figure(figsize=(50,50))
f.add_subplot(1,2, 1)
plt.imshow(mask, cmap=plt.cm.gray)
plt.title('Original Stencil', size=40)
plt.axis("off")
f.add_subplot(1,2, 2)
plt.imshow(wc, interpolation='bilinear')
plt.title('Sparta Cloud', size=40)
plt.axis("off")
plt.show()

워드 입혀서 그림으로 저장하기

mask = np.array(Image.open('./data/sparta.png'))
wc = WordCloud(font_path=font_path, background_color='white', mask=mask)
wc.generate(text)

f = plt.figure(figsize=(50,50))
plt.imshow(wc, interpolation='bilinear')
plt.title('나만의 워드클라우드', size = 40)
plt.axis("off")
plt.show()
f.savefig('./data/myWordCloud.png')

수강완료가 가장 많은 요일 및 시간은?

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
plt.rcParams['font.family']='AppleGothic'

sparta_data = pd.read_csv('./data/enrolleds_detail.csv')


format = '%Y-%m-%dT%H:%M:%S.%f'

sparta_data['done_date_time'] = pd.to_datetime(sparta_data['done_date'], format=format)
sparta_data['done_date_time_weekday'] = sparta_data['done_date_time'].dt.day_name()


weekdata = sparta_data.groupby('done_date_time_weekday')['user_id'].count()

weeks = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
weekdata = weekdata.agg(weeks) 


plt.figure(figsize=(8,5))
plt.bar(weekdata.index, weekdata)
plt.title('요일별 수강완료 수강생 수')
plt.xlabel('요일')
plt.ylabel('수강생(명)')
plt.xticks(rotation=45)
plt.show()


sparta_data['done_date_time_hour'] = sparta_data['done_date_time'].dt.hour

hourdata = sparta_data.groupby('done_date_time_hour')['user_id'].count()
hourdata = hourdata.sort_index()


plt.figure(figsize=(10,5))
plt.plot(hourdata.index, hourdata)
plt.title('시간별 수강 완료 수강생 수')
plt.xlabel('시간')
plt.ylabel('사용자(명)')
plt.xticks(np.arange(24))
plt.show()


sparta_data_pivot_table = pd.pivot_table(sparta_data, values='user_id', aggfunc='count',
              index=['done_date_time_weekday'],
              columns=['done_date_time_hour']).agg(weeks)


plt.figure(figsize=(14,5))
plt.pcolor(sparta_data_pivot_table)
plt.xticks(np.arange(0.5, len(sparta_data_pivot_table.columns), 1), sparta_data_pivot_table.columns)
plt.yticks(np.arange(0.5, len(sparta_data_pivot_table.index), 1), sparta_data_pivot_table.index)
plt.title('요일별 종료 시간 히트맵')
plt.xlabel('시간')
plt.ylabel('요일')
plt.colorbar()
plt.show()

plt.xticks(np.arange(24)) 는
plt.xticks([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24])
의 줄임표현

숙제

lyrics = open('./data/mysong.txt')
lyrics = lyrics.read()
lyrics = lyrics.replace('\n', " ")

import re
pattern = '[^\w\s]'
lyrics = re.sub(pattern=pattern, repl='', string=lyrics)

import numpy as np
from PIL import Image
from wordcloud import WordCloud
import matplotlib.pyplot as plt

import matplotlib.font_manager as fm

for f in fm.fontManager.ttflist:
    if 'Gothic' in f.name:
        print(f.fname)

        
font_path = '/Library/Fonts/AppleGothic.ttf'

word_cloud = WordCloud(font_path=font_path, background_color = 'white')
word_cloud.generate(lyrics)

plt.figure(figsize=(50,50))
plt.axis("off")
plt.imshow(word_cloud)


mask = np.array(Image.open('./data/myimage.png'))
word_cloud = WordCloud(font_path=font_path, background_color='white', mask=mask)
word_cloud.generate(lyrics)

f = plt.figure(figsize=(50,50))
plt.imshow(word_cloud, interpolation='bilinear')
plt.title('최애곡 가사 워드 클라우드', size=40)
plt.axis("off")
plt.show()
f.savefig('./data/homework.png')

##############################

sparta_data_Monday = sparta_data[ sparta_data['done_date_time_weekday'] == 'Monday' ]
sparta_data_Monday = sparta_data_Monday.groupby('done_date_time_hour')['user_id'].count()

sparta_data_Tuesday = sparta_data[ sparta_data['done_date_time_weekday'] == 'Tuesday' ]
sparta_data_Tuesday = sparta_data_Tuesday.groupby('done_date_time_hour')['user_id'].count()

plt.figure(figsize=(10,5))
plt.plot(sparta_data_Monday.index, sparta_data_Monday)
plt.plot(sparta_data_Tuesday.index, sparta_data_Tuesday)
plt.title('시간별 수강 완료자 수')
plt.xticks(np.arange(24))
plt.show()