Amazon Bedrock と Amazon Location Service による地理空間生成系 AI

Your Role: You are a geospatial data analyzer designed to analyze data schema from arbitrary geospatial datasets.
Your Task: You are provided a set of file URLs. You need to generate a Python function that meets the following:
    Read each file using geopandas. Each file could be CSV, shape file, or GeoJSON.
    Use built-in function resolved_file_url= get_data_file_url(file_url, session_id) to get downloadable URLs.

import geopandas as gpd
import pandas as pd
import numpy as np
 
def analyze_geospatial_data(file_urls):
    dataframes = []
    for file_url in file_urls:
        resolved_file_url = get_data_file_url(file_url, 'a5b188fe-91f7-4f92-92fe-c4030721a427', 'local')
        if file_url.endswith('.csv'):
            df = pd.read_csv(resolved_file_url)
        elif file_url.endswith('.shp'):
            df = gpd.read_file(resolved_file_url)
        elif file_url.endswith('.parquet'):
            df = pd.read_parquet(resolved_file_url)
        elif file_url.endswith('.geojson'):
            df = gpd.read_file(resolved_file_url)
        else:
            raise ValueError('Unsupported file format')
 
        df = df.sample(n=3, random_state=42)
        dataframes.append({
            'file_url': file_url, 
            'resolved_file_url': resolved_file_url,
            'data_frame': df,
            'column_names': list(df.columns)
        })
    return dataframes
 
file_urls = ['agent://airbnb_listings_price.csv']
dataframes = analyze_geospatial_data(file_urls)

Your Role: You are a geospatial data analyzer designed to analyze data schema from arbitrary geospatial data sets.
Your Task: You are provided with a table with some rows data. Your task is to generate a summary that describes the data in the table following the requirements below.
    The first sentence should be summary of the data in the table from the aspect of the user action.
    If there is no geometry column in the table, the second sentence should note column names that can be used to generate a geometry column in geopandas.

Summary: The table contains columns for listing id, name, host id, host name, location details like neighborhood, latitude, and longitude that can be used to generate a geometry column for plotting. Price column contains listing price that can be used to generate a heatmap of listing prices.

Your Role: You are a geospatial data scientist and an expert Python developer.
Your Task: A series of consecutive steps.
Your Reply needs to meet these requirements:
    Create a single NetworkX graph.
    No disconnected components allowed.
    First operations are data loading.
    Use geopandas for spatial data.

import networkx as nx
G = nx.DiGraph()
# Load the data
G.add_node("airbnb_data_url", node_type="data", data_path="agent://airbnb_listings_price.csv", 
           description="URL for Airbnb listing price data")
G.add_node("load_data", node_type="operation", operation_type="load",
           description="Load the Airbnb listing price data")
G.add_edge("airbnb_data_url", "load_data")
G.add_node("airbnb_df", node_type="data", 
           description="Pandas DataFrame containing Airbnb listing prices")
G.add_edge("load_data", "airbnb_df")
# Transform the data
G.add_node("add_geometry", node_type="operation", operation_type="transform",
           description="Create a geometry column using latitude and longitude")
G.add_edge("airbnb_df", "add_geometry")
G.add_node("airbnb_gdf", node_type="data",
           description="GeoDataFrame with geometry column added")
G.add_edge("add_geometry", "airbnb_gdf")
# Visualize the data
G.add_node("plot_heatmap", node_type="operation", operation_type="visualization",
           description="Generate a heatmap of listing prices")
G.add_edge("airbnb_gdf", "plot_heatmap")
G.add_node("price_heatmap", node_type="data", 
           description="The heatmap plot showing Airbnb listing prices")
G.add_edge("plot_heatmap", "price_heatmap")

Your Role: You are a geospatial data scientist and an expert Python developer.
Operation_task: You need to generate a Python function to do: Load Airbnb data.
Your Reply needs to meet these requirements:
    The function definition is: 
    load_data(airbnb_data_url='agent://airbnb_listings_price.csv').
    When doing spatial joins, retain at least 1 geometry column.
    Point function requires importing shapely library.

import pandas as pd
def load_data(airbnb_data_url='agent://airbnb_listings_price.csv'):
    """ Load Airbnb listing price data """
    file_url = get_data_file_url(airbnb_data_url, session_id, storage_mode) 
    airbnb_df = pd.read_csv(file_url)
    return airbnb_df

Your Role: You are a geospatial data scientist and an expert Python developer.
Operation_task: You need to generate a Python function to do: 
    Add geometry column from latitude/longitude.
    Your Reply needs to meet these requirements:
    The function definition is: add_geometry(filtered_df).
    The function return line is: return airbnb_gdf.

import geopandas as gpd
from shapely.geometry import Point
def add_geometry(airbnb_df):
    """ Add geometry column from latitude and longitude """
    airbnb_df['geometry'] = airbnb_df.apply(lambda row: Point(row['longitude'], row['latitude']), axis=1)
    airbnb_gdf = gpd.GeoDataFrame(airbnb_df, geometry='geometry')
 
    return airbnb_gdf

Your Role: You are a geospatial data scientist and an expert Python developer.
Operation_task: You need to generate a Python function to do: Generate heatmap from price.
Your Reply needs to meet these requirements:
    The function definition is: generate_heatmap(airbnb_gdf).
    The function return line is: return airbnb_heatmap.

import pandas as pd
import geopandas as gpd
import pydeck as pdk
 
def plot_heatmap(airbnb_gdf):
    """ Plot heatmap of listing prices """
    price_heatmap = pdk.Deck(
        map_style=location_map_style(),
        initial_view_state=pdk.ViewState(
            latitude=airbnb_gdf['latitude'].mean(),
            longitude=airbnb_gdf['longitude'].mean(),
            zoom=11,
            pitch=50,
        ),
        layers=[
            pdk.Layer(
                'HexagonLayer',
                data=airbnb_gdf,
                get_position=['longitude', 'latitude'],
                radius=100,
                elevation_scale=4,
                elevation_range=[0, 1000],
                pickable=True,
                extruded=True,
            ),
            pdk.Layer(
                'ScatterplotLayer',
                data=airbnb_gdf,
                get_position=['longitude', 'latitude'],
                get_color='[200, 30, 0, 160]',
                get_radius=200,
            ),
        ],
    )
 
    # Save heatmap HTML
    price_heatmap.to_html(get_local_file_path('airbnb_heatmap.html', session_id, task_name))
 
    return price_heatmap

session_id = "a5b188fe-91f7-4f92-92fe-c4030721a427"
task_name = "1694813661_airbnb_listings_price_heatmap"
storage_mode = "local"
# Sequentially invoke the functions
airbnb_df = load_data(airbnb_data_url='agent://airbnb_listings_price.csv')
airbnb_gdf = add_geometry(airbnb_df)
price_heatmap = plot_heatmap(airbnb_gdf)

Agent: Hi! I'm Agent Smith, your conversational geospatial assistant. How can I assist you today?
You: >? Hello, can you give me the coordinates for 112 E 11th St, Austin, TX 78701?
Agent: The coordinates for 112 E 11th St, Austin, TX 78701 are longitude -97.740590981087 and latitude 30.274118017533.

git clone https://github.com/aws-samples/amazon-location-geospatial-agent/

cd amazon-location-geospatial-agent

vim .env

API_KEY_NAME=AgentAPIKey
MAP_NAME=AgentMap
PLACE_INDEX_NAME=AgentPlaceIndex

docker build -t agent .

docker run --rm -it -v ~/.aws:/root/.aws --entrypoint bash agent

apt install -y wget
wget http://data.insideairbnb.com/united-states/ny/new-york-city/2023-10-01/visualisations/listings.csv
cp listings.csv data/listings.csv

SESSION_ID="3c18d48c-9c9b-488f-8229-e2e8016fa851" FILE_NAME="listings.csv" make create-session

poetry run agent --session-id 3c18d48c-9c9b-488f-8229-e2e8016fa851 --profile <profilename>

I've uploaded the file listings.csv. Draw a heatmap of Airbnb listing price.