인구 분석 (2)

지도 그리기 (카르토그램)

draw_korea_raw = pd.read_excel("../data/07_draw_korea_raw.xlsx")
draw_korea_raw

draw_korea_raw.stack()

0   7         철원
    8         화천
    9         양구
    10    고성(강원)
1   3         양주
           ...  
24  2         장흥
    3         보성
25  2         완도
    5         제주
26  5        서귀포
Length: 252, dtype: object

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

draw_korea_raw_stacked.reset_index(inplace=True)
draw_korea_raw_stacked

# 컬럼 이름 변경
draw_korea_raw_stacked.rename(
    columns={
        "level_0" : "y",
        "level_1" : "x",
        0 : "ID"
    }, inplace=True)
draw_korea_raw_stacked

draw_korea = draw_korea_raw_stacked

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)], 
    [(13, 5), (14, 5)], # 대전시 # 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)]
]

BORDER_LINES

[[(5, 1), (5, 2), (7, 2), (7, 3), (11, 3), (11, 0)],
 [(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)],
 [(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)],
 [(8, 10), (8, 11), (6, 11), (6, 12)],
 [(12, 5),
  (13, 5),
  (13, 4),
  (14, 4),
  (14, 5),
  (15, 5),
  (15, 4),
  (16, 4),
  (16, 2)],
 [(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)],
 [(13, 5), (13, 6), (16, 6)],
 [(13, 5), (14, 5)],
 [(21, 2), (21, 3), (22, 3), (22, 4), (24, 4), (24, 2), (21, 2)],
 [(20, 5), (21, 5), (21, 6), (23, 6)],
 [(10, 8), (12, 8), (12, 9), (14, 9), (14, 8), (16, 8), (16, 6)],
 [(14, 9), (14, 11), (14, 12), (13, 12), (13, 13)],
 [(15, 8), (17, 8), (17, 10), (16, 10), (16, 11), (14, 11)],
 [(17, 9), (18, 9), (18, 8), (19, 8), (19, 9), (20, 9), (20, 10), (21, 10)],
 [(16, 11), (16, 13)],
 [(27, 5), (27, 6), (25, 6)]]

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.splitlines()[-1]) >= 3:
            fontsize, linespacing = 9.5, 1.5
        else:
            fontsize, linespacing = 11, 1.2
    
        plt.annotate(# matplotlib 주석 다는 기능
            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)

pop.head()

draw_korea.head()  # pop 과 draw_korea에 공통된 "ID"

검증작업

set(draw_korea["ID"].unique()) - set(pop["ID"].unique())  # 차집합 확인

{'고양 덕양', '고양 일산동', '고양 일산서', '용인 기흥', '용인 수지', '용인 처인'}

set(pop["ID"].unique()) - set(draw_korea["ID"].unique())  # 차집합 확인

{'고양',
 '고양 기흥',
 '고양 수지',
 '고양 처인',
 '부천',
 '성남',
 '수원',
 '안산',
 '안양',
 '용인',
 '일산 덕양',
 '일산 일산동',
 '일산 일산서',
 '전주',
 '창원',
 '천안',
 '청주',
 '포항'}

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)
print(set(pop["ID"].unique()) - set(draw_korea["ID"].unique()))

set()

tmp2_list = list(set(draw_korea["ID"].unique()) - set(pop["ID"].unique()))

for tmp in tmp2_list:
    draw_korea = draw_korea.drop(draw_korea[draw_korea["ID"]== tmp].index)
print(set(draw_korea["ID"].unique()) - set(pop["ID"].unique()))

set()

공통 컬럼 "ID"로 merge`

pop = pd.merge(pop,draw_korea, how="left", on="ID")
pop.head()

그림을 그리기 위한 데이터를 계산하는 함수

• 색상을 만들 때, 최소값을 흰색으로
• blockedMap : 인구현황 (pop)
• targetData : 그리고싶은 컬럼

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.splitlines()[-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()
    
drawKorea("인구수합계", pop, "Blues")

pop["소멸 위기 지역"]

pop["소멸 위기 지역"] = [1 if con else 0 for con in pop["소멸 위기 지역"]]  # True/False 로 된 데이터 --> 0 /1 
drawKorea("소멸 위기 지역", pop, "Reds")

# 여성 비 컬럼 만들기 
pop["여성비"] = (pop["인구수여자"] / pop["인구수합계"] - 0.5 ) * 100
drawKorea("여성비", pop, "RdBu", zeroCenter=True)

pop["2030여성비"] = (pop["20-39세여자"] / pop["20-39세합계"] - 0.5 ) * 100
drawKorea("2030여성비", pop, "RdBu", zeroCenter=True)

folium으로 지도 시각화

import folium
import json 

pop_folium = pop.set_index("ID")  #지도 그릴 때 ID값 기준으로 하기 위해
pop_folium.head()

# 인구수 합계 시각화
geo_path = "../data/07_skorea_municipalities_geo_simple.json"
geo_str = json.load(open(geo_path, encoding="utf-8"))

myMap = folium.Map(location=[36.2002, 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

# 소멸위기 지역 시각화

myMap = folium.Map(location=[36.2002, 127.054], zoom_start=7)
myMap.choropleth(
    geo_data=geo_str,
    data=pop_folium["소멸 위기 지역"],
    key_on="feature.id",
    columns=[pop_folium.index, pop_folium["소멸 위기 지역"]],
    fill_color="PuRd"
)
myMap

# 데이터 저장 

draw_korea.to_csv("../data/07_draw_korea2.csv", encoding="utf-8", sep=",")