【不動産情報ライブラリ】Pythonを使った国土交通省APIからの人口データ取得と年齢分布グラフの作成方法

import json
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import requests
from matplotlib.font_manager import FontProperties

API_KEY = '****'  # 自分のAPIキーに置き換えてください

url = 'https://www.reinfolib.mlit.go.jp/ex-api/external/XKT013?'

# APIリクエストの設定（XYZ座標を使用してデータ取得範囲を指定）
headers = {"Ocp-Apim-Subscription-Key": API_KEY}
params = {
    'response_format': 'geojson',  # データ形式を指定
    'z': 15,  # ズームレベル
    'x': 28730,  # X座標
    'y': 13015   # Y座標
}

# APIリクエストの送信と応答の取得
response = requests.get(url, headers=headers, params=params)

if response.status_code == 200:
    geojson_data = response.json()
else:
    print(f"Error: {response.status_code}, Message: {response.text}")

def flatten_json(y):
    """ネストされたJSONをフラットにするヘルパー関数"""
    out = {}
    def flatten(x, name=''):
        if isinstance(x, dict):
            for a in x:
                flatten(x[a], name + a + '_')
        elif isinstance(x, list):
            i = 0
            for a in x:
                flatten(a, name + str(i) + '_')
                i += 1
        else:
            out[name[:-1]] = x
    flatten(y)
    return out

flattened_data = [flatten_json(feature) for feature in geojson_data['features']]
df = pd.DataFrame(flattened_data)
df_data = df

target_years = ['2020', '2025', '2035', '2040', '2045', '2050']  # 必要な年
age_groups = {
    '0-4': 'properties_PT1', '5-9': 'properties_PT2', '10-14': 'properties_PT3', '15-19': 'properties_PT4',
    '20-24': 'properties_PT5', '25-29': 'properties_PT6', '30-34': 'properties_PT7', '35-39': 'properties_PT8',
    '40-44': 'properties_PT9', '45-49': 'properties_PT10', '50-54': 'properties_PT11', '55-59': 'properties_PT12',
    '60-64': 'properties_PT13', '65-69': 'properties_PT14', '70-74': 'properties_PT15', '75-79': 'properties_PT16',
    '80-84': 'properties_PT17', '85-89': 'properties_PT18', '90+': 'properties_PT19'
}

# グラフの描画設定
fig, ax = plt.subplots(figsize=(15, 8))
x = np.arange(len(age_groups))
colors = plt.cm.viridis(np.linspace(0, 1, len(target_years)))

for i, year in enumerate(target_years):
    population_counts = []
    for age_group_key, age_group_column in age_groups.items():
        column_name = f'{age_group_column}_{year}'
        if column_name in df.columns:
            population_counts.append(df[column_name].sum())
        else:
            population_counts.append(0)

    # 散布図としてプロットし、線で結ぶ
    ax.plot(age_groups.keys(), population_counts, marker='o', color=colors[i], label=f'{year}', linestyle='-', markersize=6)

# グラフの装飾
ax.set_xlabel('Age Group', fontsize=14)
ax.set_ylabel('Population (thousands)', fontsize=14)
ax.set_title('Population by Age Group in Multiple Years', fontsize=16)
ax.legend(title='Year')
ax.grid(True, linestyle='--', linewidth=0.5, axis='y')

plt.tight_layout()
plt.show()

for year_idx in range(1, len(target_years)):
    prev_year = target_years[year_idx - 1]
    curr_year = target_years[year_idx]
    
    print(f"--- {prev_year}年から{curr_year}年の増減率 ---")
    for age_group_key, age_group_column in age_groups.items():
        prev_column = f'{age_group_column}_{prev_year}'
        curr_column = f'{age_group_column}_{curr_year}'
        
        if prev_column in df.columns and curr_column in df.columns:
            prev_sum = df[prev_column].sum()
            curr_sum = df[curr_column].sum()
            rate_change = ((curr_sum - prev_sum) / prev_sum) * 100 if prev_sum > 0 else 0
            print(f"{age_group_key}: {rate_change:.2f}%")
        else:
            print(f"{age_group_key}: データなし")