Pythonで世界の人口データを分析する

import griddb_python as griddb
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="darkgrid")

dataset = pd.read_csv(r"/mnt/d/Datasets/world_population.csv")
print(dataset.shape)
dataset.head()

dataset.columns = dataset.columns.str.replace('[^a-zA-Z0-9]', '_', regex=True)
dataset.dtypes

factory = griddb.StoreFactory.get_instance()

DB_HOST = "127.0.0.1:10001"
DB_CLUSTER = "myCluster"
DB_USER = "admin"
DB_PASS = "admin"

try:
    gridstore = factory.get_store(
        notification_member = DB_HOST,
        cluster_name = DB_CLUSTER,
        username = DB_USER,
        password = DB_PASS
    )

    container1 = gridstore.get_container("container1")
    if container1 == None:
        print("Container does not exist")
    print("Successfully connected to GridDB")

except griddb.GSException as e:
    for i in range(e.get_error_stack_size()):
        print("[", i, "]")
        print(e.get_error_code(i))
        print(e.get_location(i))
        print(e.get_message(i))

# see all GridDB data types: https://docs.griddb.net/architecture/data-model/#data-type

def map_pandas_dtype_to_griddb(dtype):
    if dtype == 'int64':
        return griddb.Type.LONG
    elif type == 'float64':
        return griddb.Type.FLOAT
    elif dtype == 'object':
        return griddb.Type.STRING
    # Add more column types if you want
    else:
        raise ValueError(f'Unsupported pandas type: {dtype}')

container_columns = []
for column_name, dtype in dataset.dtypes.items():
    griddb_dtype = map_pandas_dtype_to_griddb(str(dtype))
    container_columns.append([column_name, griddb_dtype])

container_info = griddb.ContainerInfo("PopulationStats",
                                      container_columns,
                                      griddb.ContainerType.COLLECTION, True)

try:
    cont = grid store.put_container(container_info)
    for index, row in dataset.iterrows():
        cont.put(row.tolist())
    print("All rows have been successfully stored in the GridDB container.")

except griddb.GSException as e:
    for i in range(e.get_error_stack_size()):
        print("[", i, "]")
        print(e.get_error_code(i))
        print(e.get_location(i))
        print(e.get_message(i))

population_container = gridstore.get_container("PopulationStats")
query = population_container.query("select *")
rs = query.fetch()
population_data = rs.fetch_rows()

print(population_data.shape)
population_data.head()

population_by_continent = population_data.groupby('Continent')['2022_Population'].sum()

plt.figure(figsize=(6,6))
plt.pie(population_by_continent,
        labels=population_by_continent.index,
        autopct='%1.1f%%', startangle=140)
plt.title('World Population by Continent in 2022')
plt.show()

top_countries = population_data.sort_values('World_Population_Percentage', ascending=False).head(10)

plt.figure(figsize=(10, 8))
plt.barh(top_countries['Country_Territory'],
         top_countries['World_Population_Percentage'],
         color='skyblue')

plt.xlabel('% of world population')
plt.title('Top 10 Countries by World Population %')
plt.gca().invert_yaxis()  # Ensure the largest value is at the top
plt.show()

top_density_countries = population_data.nlargest(10, 'Density__per_km__')

plt.figure(figsize=(8, 6))
sns.barplot(x='Country_Territory', y='Density__per_km__', data=top_density_countries)
plt.xticks(rotation=45)
plt.title('Top 10 Countries/Territories by Population Density per Sq-km')
plt.xlabel('Country')
plt.ylabel('Density (per km²)')
plt.show()

europe = population_data[population_data['Continent'] == 'Europe'].sort_values('Density__per_km__', ascending=False).head(10)
south_america = population_data[population_data['Continent'] == 'South America'].sort_values('Density__per_km__', ascending=False).head(10)

fig, axes = plt.subplots(1, 2, figsize=(14, 6))

axes[0].barh(europe['Country_Territory'], europe['Density__per_km__'], color='skyblue')
axes[0].set_title('Top 10 Densely Populated Countries/Territories in Europe')
axes[0].invert_yaxis()

axes[1].barh(south_america['Country_Territory'], south_america['Density__per_km__'], color='lightgreen')
axes[1].set_title('Top 10 Densely Populated Countries/Territories in South America')
axes[1].invert_yaxis()  

plt.tight_layout()
plt.show()

top_countries = population_data.sort_values(by='World_Population_Percentage', ascending=False).head(10)

data = pd.melt(top_countries,
               id_vars=['Country_Territory'],
               value_vars=['1970_Population', '1980_Population', '1990_Population', '2000_Population', '2010_Population', '2015_Population', '2020_Population', '2022_Population'],
               var_name='Year',
               value_name='Population')

data['Year'] = data['Year'].str.extract('(\d+)').astype(int)


plt.figure(figsize=(9, 6))
sns.line plot(x='Year',
             y='Population',
             hue='Country_Territory',
             data=data, marker='o')

plt.title('Population Growth from 1970 to 2022 for Top 10 Most Populous Countries')
plt.legend(title='Country')
plt.show()

population_container.set_auto_commit(False)
query = population_container.query("SELECT * WHERE Country_Territory = 'Afghanistan'")
rs = query.fetch(True)  

if rs.has_next():
    data = rs.next()
    capital_index = population_data.columns.get_loc('Capital')

    data[capital_index] = 'Kabool'
    rs.update(data)

population_container.commit()
print("Capital name updated successfully.")

query = population_container.query("select *")
rs = query.fetch()
population_data = rs.fetch_rows()
population_data.head()

population_container.set_auto_commit(False)

query = population_container.query("SELECT * WHERE Continent = 'Europe'")

rs = query.fetch(True)

while rs.has_next():
    data = rs.next()
    rs.remove()


population_container.commit()
print("Records where Continent is 'Europe' have been successfully deleted.")

query = population_container.query("select *")
rs = query.fetch()
population_data = rs.fetch_rows()
population_data.head()