Kakao Arena 3 EDA on Google Colab

%config InlineBackend.figure_format = 'retina'
!sudo apt-get -qq -y install fonts-nanum

from datetime import timedelta, datetime
import glob
from itertools import chain
import json
import os
import re

import numpy as np
import pandas as pd

from wordcloud import WordCloud
import nltk
from nltk.corpus import stopwords
from collections import Counter
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer

from pandas.plotting import register_matplotlib_converters
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib as mpl
import matplotlib.pyplot as plt
import matplotlib.font_manager as fm

fontpath = '/usr/share/fonts/truetype/nanum/NanumBarunGothic.ttf'
font = fm.FontProperties(fname=fontpath, size=9)
plt.rc('font', family='NanumBarunGothic') 
plt.rcParams["figure.figsize"] = (20, 10)
register_matplotlib_converters()
mpl.font_manager._rebuild()
mpl.pyplot.rc('font', family='NanumGothic')
fm._rebuild()

# Mount Google Drive
from google.colab import drive # import drive from google colab

ROOT = "/content/drive"     # default location for the drive
print(ROOT)                 # print content of ROOT (Optional)
drive.mount(ROOT)           # we mount the google drive at /content/drive

import os, sys
my_path = '/content/notebooks'
os.symlink('/content/drive/My Drive/Colab Notebooks/competition/pkgs_folder', my_path)
sys.path.insert(0,my_path)

from konlpy.tag import Twitter

pd.options.mode.chained_assignment = None

# import join used to join ROOT path and MY_GOOGLE_DRIVE_PATH
from os.path import join  

# path to your project on Google Drive
MY_GOOGLE_DRIVE_PATH = 'My Drive/Colab Notebooks/competition'

PROJECT_PATH = join(ROOT, MY_GOOGLE_DRIVE_PATH)

%cd "{PROJECT_PATH}"

!git status

!ls

# genre_gn_all.json
genre_gn_all = pd.read_json('kakao_arena_3/data/genre_gn_all.json', typ = 'series')
# 장르코드 : gnr_code, 장르명 : gnr_name
genre_gn_all = pd.DataFrame(genre_gn_all, columns = ['gnr_name']).reset_index().rename(columns = {'index' : 'gnr_code'})
print(genre_gn_all.head())

# 장르코드 뒷자리 두 자리가 00이 아닌 코드를 필터링
dtl_gnr_code = genre_gn_all[genre_gn_all['gnr_code'].str[-2:] != '00']
dtl_gnr_code.rename(columns = {'gnr_code' : 'dtl_gnr_code', 'gnr_name' : 'dtl_gnr_name'}, inplace = True)
print(dtl_gnr_code.head())

# Plotting a bar graph of the number of stores in each city, for the first ten cities listed
# in the column 'City'
dtl_gnr_name_count  = dtl_gnr_code['dtl_gnr_name'].value_counts()
dtl_gnr_name_count = dtl_gnr_name_count[:10,]
plt.figure(figsize=(10,5))
sns.barplot(dtl_gnr_name_count.index, dtl_gnr_name_count.values, alpha=0.8)
plt.title('한글 시각화 테스트')
plt.ylabel('Number of Occurrences', fontsize=12)
plt.xlabel('세부장르', fontsize=12)
plt.show()

# Clone github repository setup
# import join used to join ROOT path and MY_GOOGLE_DRIVE_PATH
from os.path import join  

# path to your project on Google Drive
MY_GOOGLE_DRIVE_PATH = 'My Drive/Colab Notebooks/'

# replace with your github username
GIT_USERNAME = "chloevan"

# definitely replace with your
GIT_TOKEN = "your_token" # this is temporary, whenever you add, need to get token number

# Replace with your github repository in this case we want 
# to clone deep-learning-v2-pytorch repository
GIT_REPOSITORY = "competition"

PROJECT_PATH = join(ROOT, MY_GOOGLE_DRIVE_PATH)

# It's good to print out the value if you are not sure 
print("PROJECT_PATH: ", PROJECT_PATH)  

# In case we haven't created the folder already; we will create a folder in the project path 
# !mkdir "{PROJECT_PATH}"    

#GIT_PATH = "https://{GIT_TOKEN}@github.com/{GIT_USERNAME}/{GIT_REPOSITORY}.git" this return 400 Bad Request for me
GIT_PATH = "https://" + GIT_TOKEN + "@github.com/" + GIT_USERNAME + "/" + GIT_REPOSITORY + ".git"
print("GIT_PATH: ", GIT_PATH)

!git remote set-url origin "{GIT_PATH}"

!git add .

# Linked to account
!git config --global user.email "your_email_address"
!git config --global user.name "your_username"

# Git commit
!git commit -m "finally updated"

!git push