Taxi Trips Study - Advanced Pipeline¶

import urban_mapper as um

data = (
    um.UrbanMapper()
    .loader
    .from_huggingface("oscur/taxisvis1M")
    .with_columns(longitude_column="pickup_longitude", latitude_column="pickup_latitude")
    .load()
)

data['pickup_longitude'] = data['pickup_longitude'].astype(float)
data['pickup_latitude'] = data['pickup_latitude'].astype(float)

data['dropoff_longitude'] = data['dropoff_longitude'].astype(float)
data['dropoff_latitude'] = data['dropoff_latitude'].astype(float)

data.to_csv("./taxisvis1M.csv")

import urban_mapper as um
from urban_mapper.pipeline import UrbanPipeline

# Define the pipeline
pipeline = UrbanPipeline([
    ("urban_layer", (
        um.UrbanMapper().urban_layer
        .with_type("streets_roads")
        .from_place("Downtown Brooklyn, New York City, USA", network_type="drive")
        .with_mapping(
            longitude_column="pickup_longitude",
            latitude_column="pickup_latitude",
            output_column="pickup_segment"
        )
        .with_mapping(
            longitude_column="dropoff_longitude",
            latitude_column="dropoff_latitude",
            output_column="dropoff_segment"
        )
        .build()
    )),
    ("loader", (
        um.UrbanMapper().loader
        .from_file("./taxisvis1M.csv")
        .with_columns(longitude_column="pickup_longitude", latitude_column="pickup_latitude")
        .build()
    )),
    ("impute_pickup", (
        um.UrbanMapper().imputer
        .with_type("SimpleGeoImputer")
        .on_columns("pickup_longitude", "pickup_latitude")
        .build()
    )),
    ("impute_dropoff", (
        um.UrbanMapper().imputer
        .with_type("SimpleGeoImputer")
        .on_columns("dropoff_longitude", "dropoff_latitude")
        .build()
    )),
    ("filter", um.UrbanMapper().filter.with_type("BoundingBoxFilter").build()),
    ("enrich_pickups", (
        um.UrbanMapper().enricher
        .with_data(group_by="pickup_segment")
        .count_by(output_column="pickup_count")
        .build()
    )),
    ("enrich_dropoffs", (
        um.UrbanMapper().enricher
        .with_data(group_by="dropoff_segment")
        .count_by(output_column="dropoff_count")
        .build()
    )),
    ("enrich_fare_amount", (
        um.UrbanMapper().enricher
        .with_data(group_by="pickup_segment", values_from="fare_amount")
        .aggregate_by(method="mean", output_column="avg_fare_amount")
        .build()
    )),
    ("visualiser", (
        um.UrbanMapper().visual
        .with_type("Interactive")
        .with_style({"tiles": "CartoDB dark_matter", "colorbar_text_color": "white"})
        .build()
    ))
])

# Execute the pipeline
mapped_data, enriched_layer = pipeline.compose_transform()

# Visualize results
fig = pipeline.visualise(["pickup_count", "dropoff_count", "avg_fare_amount"])
fig

# Save the pipeline
pipeline.save("./taxi_advanced_pipeline.dill")