카르토그램

1. 배경

• 목표
  • 1. 인구 소멸 위기 지역 파악
  • 2. 인구 소멸 위기 지역의 지도 표현
  • 3. 지도 표현에 대한 카르토그램 표현

---

2. 데이터 읽고 인구 소멸 지역 계산하기

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import platform
import seaborn as sns
from matplotlib import font_manager, rc

# %matplotlib inline
get_ipython().run_line_magic('matplotlib', 'inline')

path = 'C:/Windows/Fonts/malgun.ttf'

if platform.system() == 'Darwin':
    rc('font', family='Arial Unicode MS')
elif platform.system() == 'Windows':
    font_name = font_manager.FontProperties(fname=path).get_name()
    rc('font', family=font_name)
else:
    print('Unknown system. sorry')
    
import warnings
warnings.filterwarnings(action='ignore') # Warning 무시해줌

population = pd.read_excel('../data/07_population_raw_data.xlsx', header=1)
population.fillna(method='pad', inplace=True)
population

위의 데이터를 다듬어 새로운 데이터프레임 생성한 후, 소멸비율을 계산하여 소멸비율 컬럼과 소멸위기지역 컬럼을 생성해주기!

# pivot_table

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

pop

# 소멸 비율 계산

pop['소멸비율'] = pop['20-39세', '여자'] / (pop['65세이상', '합계'] / 2)
pop.tail()

# 소멸위기지역 컬럼 생성

pop['소멸위기지역'] = pop['소멸비율'] < 1.0
pop

---

3. 지도 시각화를 위한 지역별 ID 만들기

for idx, row in pop.iterrows():
    if row['광역시도'][-3:] not in ['광역시', '특별시', '자치시']:
        si_name[idx] = row['시도'][:-1]
    
    elif row['광역시도'] == '세종특별자치시':
        si_name[idx] = '세종'
    
    else:
        if len(row['시도']) == 2:
            si_name[idx] = row['광역시도'][:2] + ' ' + row['시도']
        else:
            si_name[idx] = row['광역시도'][:2] + ' ' + row['시도'][:-1]

for idx, row in pop.iterrows():
    if row['광역시도'][-3:] not in ['광역시', '특별시', '자치시']:
        for keys, values in tmp_gu_dict.items():
            if row['시도'] in values:
                if len(row['시도']) == 2:
                    si_name[idx] = keys + ' ' + row['시도']
                
                elif row['시도'] in ['마산합포구', '마산회원구']:
                        si_name[idx] = keys + ' ' + row['시도'][2:-1]
                
                else:
                    si_name[idx] = keys + ' ' + row['시도'][:-1]

for idx, row in pop.iterrows():
    if row['광역시도'][-3:] not in ['광역시', '특별시', '자치시']:
        if row['시도'][:-1] == '고성' and row['광역시도'] == '강원도':
            si_name[idx] = '고성(강원)'
        elif row['시도'][:-1] == '고성' and row['광역시도'] == '경상남도':
            si_name[idx] = '고성(경남)'

---

4. 지도 그리기(카르토그램)

위의 한반도 모형의 데이터에 직접 시, 도 경계선 그려주기

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

카르토그램 테스트

def plot_text_simple(draw_korea):
    for idx, row in draw_korea.iterrows():
        if len(row['ID'].split()) == 2:
            dispname = '{}\n{}'.format(row['ID'].split()[0], row['ID'].split()[1])
        elif row['ID'][:2] == '고성':
            dispname = '고성'
        else:
            dispname = row['ID']
        if len(dispname.split()[-1]) >= 3:
            fontsize, linespacing = 9.5, 1.5
        else:
            fontsize, linespacing = 11, 1.2
            
    

        plt.annotate(
            dispname, 
            (row['x'] + 0.5, row['y'] + 0.5),
            weight='bold',
            fontsize=fontsize,
            linespacing=linespacing,
            ha = 'center', # 수평 정렬
            va = 'center', # 수직 정렬

        )

def simpleDraw(draw_korea):
    plt.figure(figsize=(8, 11))
    
    plot_text_simple(draw_korea)
    
    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()

simpleDraw(draw_korea)

이제 pop데이터의 수치들에 색 적용하여 카르토그램 완성해보기!

def get_data_info(targetData, blockedMap):
    whitelabelmin = (
        max(blockedMap[targetData]) - min(blockedMap[targetData])
    ) * 0.25 + min(blockedMap[targetData])
    vmin = min(blockedMap[targetData])
    vmax = max(blockedMap[targetData])
    
    mapdata = blockedMap.pivot_table(index='y', columns='x', values=targetData)

    return mapdata, vmax, vmin, whitelabelmin

def get_data_info_for_zero_center(targetData, blockedMap):
    whitelabelmin = 5
    tmp_max = max(
        np.abs(min(blockedMap[targetData])), np.abs(max(blockedMap[targetData])) 
    )
    vmin, vmax = -tmp_max, tmp_max
    mapdata = blockedMap.pivot_table(index='y', columns='x', values=targetData) 
    return mapdata, vmax, vmin, whitelabelmin

def plot_text(targetData, blockedMap, whitelabelmin):
    for idx, row in blockedMap.iterrows():
        if len(row['ID'].split()) == 2:
            dispname = '{}\n{}'.format(row['ID'].split()[0], row['ID'].split()[1])
        elif row['ID'][:2] == '고성':
            dispname = '고성'
        else:
            dispname = row['ID']
        if len(dispname.split()[-1]) >= 3:
            fontsize, linespacing = 9.5, 1.5
        else:
            fontsize, linespacing = 11, 1.2
            
    
        annocolor = 'white' if np.abs(row[targetData]) > whitelabelmin else 'black'
        plt.annotate(
            dispname, 
            (row['x'] + 0.5, row['y'] + 0.5),
            weight='bold',
            color=annocolor,
            fontsize=fontsize,
            linespacing=linespacing,
            ha = 'center', # 수평 정렬
            va = 'center', # 수직 정렬

        )

def drawKorea(targetData, blockedMap, cmapname, zeroCenter=False):
    if zeroCenter:
        masked_mapdata, vmax, vmin, whitelabelmin = get_data_info_for_zero_center(targetData, blockedMap)
    
    if not zeroCenter:
        masked_mapdata, vmax, vmin, whitelabelmin = get_data_info(targetData, blockedMap)
    
    plt.figure(figsize=(8, 11))
    plt.pcolor(masked_mapdata, vmin=vmin, vmax=vmax, cmap=cmapname, edgecolor='#aaaaaa', linewidth=0.5)    
    
    plot_text(targetData, blockedMap, whitelabelmin)
    
    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()
    cb = plt.colorbar(shrink=0.1, aspect=10)
    cb.set_label(targetData)
    plt.show()

인구수 합계 카르토그램

drawKorea('인구수합계', pop, 'Blues')

소멸위기지역 카르토그램

pop['소멸위기지역'] = [1 if con else 0 for con in pop['소멸위기지역']]
drawKorea('소멸위기지역', pop, 'Reds')

---

Folium을 통한 시각화

import folium
import json

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

geo_path = '../data/07_skorea_municipalities_geo_simple.json'
geo_str = json.load(open(geo_path, encoding='utf-8'))


# 인구수합계 지도 시각화
mymap = folium.Map(location=[36.002, 127.054], zoom_start=7)
mymap.choropleth(
    geo_data=geo_str,
    data=pop_folium['인구수합계'],
    key_on='feature.id',
    columns=[pop_folium.index, pop_folium['인구수합계']],
    fill_color='YlGnBu'
)

mymap

# 소멸위기지역 시각화

mymap = folium.Map(location=[36.002, 127.054], zoom_start=7)
mymap.choropleth(
    geo_data=geo_str,
    data=pop_folium['소멸위기지역'],
    key_on='feature.id',
    columns=[pop_folium.index, pop_folium['소멸위기지역']],
    fill_color='PuRd'
)

mymap