import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
%matplotlib inline

# 한글폰트 적용
import matplotlib.font_manager as fm

font_location = '/usr/share/fonts/truetype/nanum/NanumBarunGothic.ttf'
font_name = fm.FontProperties(fname=font_location).get_name()

from matplotlib import rc
rc('font', family=font_name)

population = pd.read_excel('./data_science/05. population_raw_data.xlsx', header=1)
population.head()

# Nan 부분을  채우기
population.fillna(
    method='pad',
    inplace=True
)

# column 제목 바꾸기 
population.rename(
    columns = {
        '행정구역(동읍면)별(1)' : '광역시도',
        '행정구역(동읍면)별(2)' : '시도',
        '계' : '인구수'
    },
    inplace=True
)

population.head()

# '소계'  부분 없애기
population = population[ population['시도'] != '소계' ]
population.head()

population.loc[ population['항목'] == '총인구수 (명)', '항목' ] = '합계'

population.loc[ population['항목'] == '여자인구수 (명)', '항목' ] = '여자'
population.loc[ population['항목'] == '남자인구수 (명)', '항목' ] = '남자'

population.head()

population['20-39세'] = population['20 - 24세'] + population['25 - 29세'] + population['30 - 34세'] + population['35 - 39세']
population['65세 이상'] = population['65 - 69세']  + population['70 - 74세']  + population['75 - 79세'] + population['80 - 84세']  \
                                      + population['85 - 89세'] + population['90 - 94세']  + population['95 - 99세']  + population['100+'] 

population.head()    

pop = pd.pivot_table(
    population,
    index=['광역시도', '시도'],
    columns=['항목'],
    values=['인구수', '20-39세', '65세 이상']
)

pop.head()

pop['소멸비율'] = 2 * pop['20-39세', '여자'] / ( pop['65세 이상', '합계'] ) 
pop.head()

pop['소멸위기지역'] = pop['소멸비율'] < 1.0
pop.head()

pop.reset_index( inplace=True )
pop.head()

# coloumn title 다듬기
tmp_columns = [ 
    pop.columns.get_level_values(0)[n] + pop.columns.get_level_values(1)[n] 
    for n in range(0, len(pop.columns.get_level_values(0)))
            ]

tmp_columns

pop.columns = tmp_columns

pop.head()

len(pop['시도'])

si_name = []
tmp_gu_list = ['장안구', '권선구', '팔달구', '영통구', 
               '수정구', '중원구', '분당구', 
               '만안구', '동안구',
                   '상록구', '단원구', 
               '덕양구', '일산동구', '일산서구', 
               '처인구', '기흥구', '수지구', 
               '상당구', '서원구', '흥덕구', '청원구', 
               '동남구', '서북구', 
               '완산구', '덕진구', 
               '남구', '북구', 
               '의창구', '성산구', '진해구', 
               '마산합포구', '마산회원구', 
               '오정구', '원미구', '소사구']

for n in pop.index:
    if pop['광역시도'][n][-3:] not in ['광역시', '특별시', '자치시']:
        if pop['시도'][n] in tmp_gu_list:
            #['장안구', '권선구', '팔달구', '영통구']:
            if pop['시도'][n] in tmp_gu_list[:4]:                
                si_name.append('수원' + ' ' + pop['시도'][n][:-1])
            
            #['수정구', '중원구', '분당구']:
            elif pop['시도'][n] in tmp_gu_list[4:7]:
                si_name.append('성남' + ' ' + pop['시도'][n][:-1])
                    
            #['만안구', '동안구']:
            elif pop['시도'][n] in tmp_gu_list[7:9]: 
                si_name.append('안양' + ' ' + pop['시도'][n][:-1])
                
            #['상록구', '단원구']:
            elif pop['시도'][n] in tmp_gu_list[9:11]: 
                si_name.append('안산' + ' ' + pop['시도'][n][:-1])

             #['덕양구', '일산동구', '일산서구']:
            elif pop['시도'][n] in tmp_gu_list[11:14]: 
                si_name.append('고양' + ' ' + pop['시도'][n][:-1])
    
            #['처인구', '기흥구', '수지구']:
            elif pop['시도'][n] in tmp_gu_list[14:17]: 
                si_name.append('용인' + ' ' + pop['시도'][n][:-1])
                
           #['상당구', '서원구', '흥덕구', '청원구']:
            elif pop['시도'][n] in tmp_gu_list[17:21]: 
                si_name.append('청주' + ' ' + pop['시도'][n][:-1])

            #['동남구', '서북구']:
            elif pop['시도'][n] in tmp_gu_list[21:23]: 
                si_name.append('천안' + ' ' + pop['시도'][n][:-1])
                  
            #['완산구', '덕진구']:
            elif pop['시도'][n] in tmp_gu_list[23:25]: 
                si_name.append('전주' + ' ' + pop['시도'][n][:-1])
                
            #['남구', '북구']:
            elif pop['시도'][n] in tmp_gu_list[25:27]: 
                si_name.append('포항' + ' ' + pop['시도'][n])
                
            #['의창구', '성산구', '진해구']:
            elif pop['시도'][n] in tmp_gu_list[27:30]: 
                si_name.append('창원' + ' ' + pop['시도'][n][:-1])
 
           #['마산합포구', '마산회원구']:
            elif pop['시도'][n] in tmp_gu_list[30:32]: 
                si_name.append('창원' + ' ' + pop['시도'][n][2:-1])
  
            #['소사구', '오정구', '원미구']:
            elif pop['시도'][n] in tmp_gu_list[32:35]: 
                si_name.append('부천' + ' ' + pop['시도'][n][:-1])
  
        else:
            if pop['시도'][n][:-1]=='고성' and pop['광역시도'][n]=='강원도':
                si_name.append('고성(강원)')
            elif pop['시도'][n][:-1]=='고성' and pop['광역시도'][n]=='경상남도':
                si_name.append('고성(경남)')
            else:
                si_name.append(pop['시도'][n][:-1])
 
    elif pop['광역시도'][n] == '세종특별자치시':
        si_name.append('세종')
  
    else:
        if len(pop['시도'][n])==2:
            si_name.append(pop['광역시도'][n][:2] + ' ' + pop['시도'][n])
        else:
            si_name.append(pop['광역시도'][n][:2] + ' ' + pop['시도'][n][:-1])  

len(si_name)

pop.tail()

pop['ID'] = si_name

pop.head()

draw_korea_raw = pd.read_excel(
    './data_science/05. draw_korea_raw.xlsx',
    encoding='EUC-KR'
)

draw_korea_raw

# 행정구역상 좌표 얻기 :  .stack()

draw_korea_raw_stacked = pd.DataFrame( draw_korea_raw.stack() )

draw_korea_raw_stacked.head()

# 인덱스 재설정

draw_korea_raw_stacked.reset_index( inplace=True )

draw_korea_raw_stacked.head()

# column 이름 재설정

draw_korea_raw_stacked.rename(
    columns = {
        'level_0' : 'y',
        'level_1' : 'x',
        0 : 'ID'
    },
    inplace=True
)

draw_korea = draw_korea_raw_stacked

draw_korea.head()

# 저장
draw_korea.to_csv('./data_ouput/05.draw_korea.csv', encoding='utf-8', sep=',' )

BORDER_LINES = [
    # 인천
    [(5, 1), (5,2), (7,2), (7,3), (11,3), (11,0)], 
    # 서울
    [(5,4), (5,5), (2,5), (2,7), (4,7), (4,9), (7,9), 
     (7,7), (9,7), (9,5), (10,5), (10,4), (5,4)], 
    # 경기도
    [(1,7), (1,8), (3,8), (3,10), (10,10), (10,7), 
     (12,7), (12,6), (11,6), (11,5), (12, 5), (12,4), 
     (11,4), (11,3)], 
    # 강원도
    [(8,10), (8,11), (6,11), (6,12)], 
    # 충청북도
    [(12,5), (13,5), (13,4), (14,4), (14,5), (15,5), 
     (15,4), (16,4), (16,2)], 
    # 전라북도
    [(16,4), (17,4), (17,5), (16,5), (16,6), (19,6),
     (19,5), (20,5), (20,4), (21,4), (21,3), (19,3), (19,1)], 
    # 대전시
    [(13,5), (13,6), (16,6)],
    #세종시
    [(13,5), (14,5)], 
     #광주
    [(21,2), (21,3), (22,3), (22,4), (24,4), (24,2), (21,2)],
    #전라남도
    [(20,5), (21,5), (21,6), (23,6)],
    #충청북도
    [(10,8), (12,8), (12,9), (14,9), (14,8), (16,8), (16,6)],
    #경상북도
    [(14,9), (14,11), (14,12), (13,12), (13,13)],
    #대구
    [(15,8), (17,8), (17,10), (16,10), (16,11), (14,11)],
    #부산
    [(17,9), (18,9), (18,8), (19,8), (19,9), (20,9), (20,10), (21,10)], 
    #울산
    [(16,11), (16,13)], 
    
    # [(9,14), (9,15)], 
    [(27,5), (27,6), (25,6)],
]

plt.figure( figsize=(8, 11) )

# 지역 이름 표시
for idx, row in draw_korea.iterrows():
    
    # 광역시는 구 이름이 겹치는 경우가 많아서 시단위 이름을 같이 표시한다. 
    if len( row['ID'].split() ) ==2:
        display_name = '{}\n{}'.format(row['ID'].split()[0], row['ID'].split()[1])
    elif row['ID'][:2] =='고성':
        display_name = '고성'
    else:
        display_name = row['ID']
        
    # 서대문구, 서귀포시 같이 이름이 3자 이상인 경우에 작은 글자로 표시한다
    if len(display_name.splitlines()[-1]) >= 3:
        fontsize, linespacing = 9.5, 1.5
    else:
        fontsize, linespacing = 11, 1.2
        
    plt.annotate(
        display_name, 
        (row['x']+0.5, row['y']+0.5), 
        weight='bold',
        fontsize=fontsize, 
        ha='center', 
        va='center',
        linespacing=linespacing
    ) 
    
# 시도 경계를 그린다. 
for path in BORDER_LINES:
    ys, xs = zip(*path)
    plt.plot(xs, ys, c='black', lw=1.5)

plt.gca().invert_yaxis()
plt.axis('off')
plt.tight_layout()
plt.show()

# 지역 ID 고유성 유지
set(draw_korea['ID'].unique()) - set(pop['ID'].unique())

set(pop['ID'].unique()) - set(draw_korea['ID'].unique()) 

tmp_list = list(
    set(pop['ID'].unique()) - set(draw_korea['ID'].unique()) 
)

for tmp in tmp_list:
    pop = pop.drop(
        pop[ pop['ID'] == tmp ].index
    )

pop.head()    

# pop와 draw_korea를 merge함
pop = pd.merge(
    pop, draw_korea,
    how='left',
    on=['ID']
)

pop.head()

map_data = pop.pivot_table(
    index='y',
    columns='x',
    values='인구수합계'
)

masked_map_data = np.ma.masked_where(
    np.isnan(map_data),
    map_data
)

map_data

def draw_Korea(target_data, blocked_map, c_map_name):
    gamma = 0.75
    white_label_min = (
        max(blocked_map[target_data]) - min(blocked_map[target_data]) * 0.25 + min( blocked_map[target_data] )        
    )
    data_label = target_data
    vmin = min( blocked_map[target_data] )
    vmax = max( blocked_map[target_data] )
    
    BORDER_LINES = [
        # 인천
        [(5, 1), (5,2), (7,2), (7,3), (11,3), (11,0)], 
        # 서울
        [(5,4), (5,5), (2,5), (2,7), (4,7), (4,9), (7,9), (7,7), (9,7), (9,5), (10,5), (10,4), (5,4)], 
        # 경기도
        [(1,7), (1,8), (3,8), (3,10), (10,10), (10,7), (12,7), (12,6), (11,6), (11,5), (12, 5), (12,4), (11,4), (11,3)], 
        # 강원도
        [(8,10), (8,11), (6,11), (6,12)], 
        # 충청북도
        [(12,5), (13,5), (13,4), (14,4), (14,5), (15,5), (15,4), (16,4), (16,2)], 
        # 전라북도
        [(16,4), (17,4), (17,5), (16,5), (16,6), (19,6), (19,5), (20,5), (20,4), (21,4), (21,3), (19,3), (19,1)], 
        # 대전시
        [(13,5), (13,6), (16,6)],
        #세종시
        [(13,5), (14,5)], 
        #광주
        [(21,2), (21,3), (22,3), (22,4), (24,4), (24,2), (21,2)],
        #전라남도
        [(20,5), (21,5), (21,6), (23,6)],
        #충청북도
        [(10,8), (12,8), (12,9), (14,9), (14,8), (16,8), (16,6)],
        #경상북도
        [(14,9), (14,11), (14,12), (13,12), (13,13)],
        #대구
        [(15,8), (17,8), (17,10), (16,10), (16,11), (14,11)],
        #부산
        [(17,9), (18,9), (18,8), (19,8), (19,9), (20,9), (20,10), (21,10)], 
        #울산
        [(16,11), (16,13)], 
        # [(9,14), (9,15)], 
        [(27,5), (27,6), (25,6)], 
    ]
    
    map_data = blocked_map.pivot_table(
        index='y',
        columns='x',
        values=target_data
        )
    masked_map_data = np.ma.masked_where(
        np.isnan(map_data),
        map_data
        )
    plt.figure( figsize=(9, 11) )
    plt.pcolor(masked_map_data, vmin=vmin, vmax=vmax, cmap=c_map_name, edgecolor='#aaaaaa', linewidth=0.5 )
    
    # 지역 이름 표시
    for idx, row in blocked_map.iterrows():
        # 광역시는 구 이름이 겹치는 경우가 많아서 시단위 이름을 같이 표시한다. 
        if len( row['ID'].split() ) ==2:
            display_name = '{}\n{}'.format(row['ID'].split()[0], row['ID'].split()[1])
        elif row['ID'][:2] =='고성':
            display_name = '고성'
        else:
            display_name = row['ID']
        # 서대문구, 서귀포시 같이 이름이 3자 이상인 경우에 작은 글자로 표시한다
        if len(display_name.splitlines()[-1]) >= 3:
            fontsize, linespacing = 9.5, 1.5
        else:
            fontsize, linespacing = 11, 1.2
        annocolor = 'white' if row[target_data] > white_label_min else 'black'
        plt.annotate(
            display_name, 
            (row['x']+0.5, row['y']+0.5), 
            weight='bold',
            fontsize=fontsize, 
            ha='center', 
            va='center',
            color=annocolor,
            linespacing=linespacing
        ) 
        
        # 시도 경계를 그린다. 
        for path in BORDER_LINES:
            ys, xs = zip(*path)
            plt.plot(xs, ys, c='black', lw=2)

    plt.gca().invert_yaxis()
    plt.axis('off')
    plt.tight_layout()
    plt.show()

draw_Korea('인구수합계', pop, 'Blues')

pop['소멸위기지역'] = [ 1 if con else 0 for con in pop['소멸위기지역'] ]

draw_Korea('소멸위기지역', pop, 'Reds')

pop[ pop['ID'] == '청주 서원' ]

# 청주 서원 index 삭제
pop_folium = pop.drop( pop[ pop['ID'] == '청주 서원' ].index )

pop_folium = pop_folium.set_index('ID')
pop_folium.head()

import folium
import json
import warnings
warnings.simplefilter(
    action='ignore',
    category=FutureWarning
)

geo_path = './data_science/05. skorea_municipalities_geo_simple.json'
geo_string = json.load(
    open(geo_path, encoding='utf-8')
)

fmap = folium.Map(
    location=[36.2002, 127.054],
    zoom_start=7
)

fmap.choropleth(
    geo_data = geo_string,
    data=pop_folium['소멸위기지역'],
    columns = [ pop_folium.index, pop_folium['소멸위기지역'] ],
    fill_color = 'PuRd',
    key_on = 'feature.id'
)

fmap

# 파일 저장
draw_korea.to_csv("./data_output/05.draw_korea.csv", encoding='utf-8', sep=',')