Collisions Study - Pipeline¶

This notebook uses UrbanPipeline to efficiently analyse collision data, counting collisions per intersection.

Data Sources¶

NYC DOT Motor Vehicle Collisions

In [1]:

Copied!





import urban_mapper as um
from urban_mapper.pipeline import UrbanPipeline

# Note: For the documentation interactive mode, we only query 5000 records from the dataset.  Feel free to remove for a more realistic analysis.
data = (
    um.UrbanMapper()
    .loader
    .from_huggingface("oscur/NYC_vehicle_collisions", number_of_rows=5000, streaming=True)
    .with_columns(longitude_column="LONGITUDE", latitude_column="LATITUDE")
    .load()
)

data['LONGITUDE'] = data['LONGITUDE'].astype(float)
data['LATITUDE'] = data['LATITUDE'].astype(float)

data.to_csv("./NYC_Motor_Vehicle_Collisions_Mar_12_2025.csv")
import urban_mapper as um
from urban_mapper.pipeline import UrbanPipeline

# Note: For the documentation interactive mode, we only query 5000 records from the dataset.  Feel free to remove for a more realistic analysis.
data = (
    um.UrbanMapper()
    .loader
    .from_huggingface("oscur/NYC_vehicle_collisions", number_of_rows=5000, streaming=True)
    .with_columns(longitude_column="LONGITUDE", latitude_column="LATITUDE")
    .load()
)

data['LONGITUDE'] = data['LONGITUDE'].astype(float)
data['LATITUDE'] = data['LATITUDE'].astype(float)

data.to_csv("./NYC_Motor_Vehicle_Collisions_Mar_12_2025.csv")

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[1], line 1
----> 1 import urban_mapper as um
      2 from urban_mapper.pipeline import UrbanPipeline
      4 # Note: For the documentation interactive mode, we only query 5000 records from the dataset.  Feel free to remove for a more realistic analysis.

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/__init__.py:3
      1 from loguru import logger
----> 3 from .mixins import (
      4     LoaderMixin,
      5     EnricherMixin,
      6     VisualMixin,
      7     TableVisMixin,
      8     AuctusSearchMixin,
      9     PipelineGeneratorMixin,
     10     UrbanPipelineMixin,
     11 )
     12 from .modules import (
     13     LoaderBase,
     14     CSVLoader,
   (...)
     30     PipelineGeneratorFactory,
     31 )
     33 from .urban_mapper import UrbanMapper

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/mixins/__init__.py:1
----> 1 from .loader import LoaderMixin
      2 from .enricher import EnricherMixin
      3 from .visual import VisualMixin

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/mixins/loader.py:1
----> 1 from urban_mapper.modules.loader.loader_factory import LoaderFactory
      4 class LoaderMixin(LoaderFactory):
      5     def __init__(self):

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/modules/__init__.py:1
----> 1 from .loader import LoaderBase, CSVLoader, ShapefileLoader, ParquetLoader
      2 from .imputer import (
      3     GeoImputerBase,
      4     SimpleGeoImputer,
      5     AddressGeoImputer,
      6 )
      7 from .filter import (
      8     GeoFilterBase,
      9     BoundingBoxFilter,
     10 )

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/modules/loader/__init__.py:3
      1 from .abc_loader import LoaderBase
      2 from .loaders import CSVLoader, ShapefileLoader, ParquetLoader
----> 3 from .loader_factory import LoaderFactory
      5 __all__ = [
      6     "LoaderBase",
      7     "CSVLoader",
   (...)
     10     "LoaderFactory",
     11 ]

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/modules/loader/loader_factory.py:19
     17 from urban_mapper.modules.loader.loaders.csv_loader import CSVLoader
     18 from urban_mapper.modules.loader.loaders.parquet_loader import ParquetLoader
---> 19 from urban_mapper.modules.loader.loaders.raster_loader import RasterLoader  # Importing RasterLoader of the new raster loader module
     20 from urban_mapper.modules.loader.loaders.shapefile_loader import ShapefileLoader
     21 from urban_mapper.utils import require_attributes

File ~/checkouts/readthedocs.org/user_builds/urbanmapper/checkouts/70/src/urban_mapper/modules/loader/loaders/raster_loader.py:2
      1 from ..abc_loader import LoaderBase
----> 2 import rasterio
      3 from typing import Any
      4 import numpy as np

ModuleNotFoundError: No module named 'rasterio'

In [2]:

Copied!





mapper = um.UrbanMapper()

# Define the pipeline
pipeline = UrbanPipeline([
    ("urban_layer", (
        mapper
        .urban_layer
        .with_type("streets_intersections")
        .from_place("Downtown Brooklyn, New York City, USA", network_type="drive")
        .with_mapping(
            longitude_column="LONGITUDE",
            latitude_column="LATITUDE",
            output_column="nearest_intersection"
        )
        .build()
    )),
    ("loader", (
        mapper
        .loader
        .from_file("./NYC_Motor_Vehicle_Collisions_Mar_12_2025.csv")
        .with_columns(longitude_column="LONGITUDE", latitude_column="LATITUDE")
        .build()
    )),
    ("imputer", (
        mapper
        .imputer
        .with_type("SimpleGeoImputer")
        .on_columns("LONGITUDE", "LATITUDE")
        .build()
    )),
    ("filter", um.UrbanMapper().filter.with_type("BoundingBoxFilter").build()),
    ("enricher", (
        mapper
        .enricher
        .with_data(group_by="nearest_intersection")
        .count_by(output_column="collision_count")
        .build()
    )),
    ("visualiser", (
        mapper
        .visual
        .with_type("Interactive")
        .with_style({"tiles": "CartoDB dark_matter", "colorbar_text_color": "white"})
        .build()
    ))
])
mapper = um.UrbanMapper()

# Define the pipeline
pipeline = UrbanPipeline([
    ("urban_layer", (
        mapper
        .urban_layer
        .with_type("streets_intersections")
        .from_place("Downtown Brooklyn, New York City, USA", network_type="drive")
        .with_mapping(
            longitude_column="LONGITUDE",
            latitude_column="LATITUDE",
            output_column="nearest_intersection"
        )
        .build()
    )),
    ("loader", (
        mapper
        .loader
        .from_file("./NYC_Motor_Vehicle_Collisions_Mar_12_2025.csv")
        .with_columns(longitude_column="LONGITUDE", latitude_column="LATITUDE")
        .build()
    )),
    ("imputer", (
        mapper
        .imputer
        .with_type("SimpleGeoImputer")
        .on_columns("LONGITUDE", "LATITUDE")
        .build()
    )),
    ("filter", um.UrbanMapper().filter.with_type("BoundingBoxFilter").build()),
    ("enricher", (
        mapper
        .enricher
        .with_data(group_by="nearest_intersection")
        .count_by(output_column="collision_count")
        .build()
    )),
    ("visualiser", (
        mapper
        .visual
        .with_type("Interactive")
        .with_style({"tiles": "CartoDB dark_matter", "colorbar_text_color": "white"})
        .build()
    ))
])

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[2], line 1
----> 1 mapper = um.UrbanMapper()
      3 # Define the pipeline
      4 pipeline = UrbanPipeline([
      5     ("urban_layer", (
      6         mapper
   (...)
     45     ))
     46 ])

NameError: name 'um' is not defined

In [3]:

Copied!

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

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[3], line 2
      1 # Execute the pipeline
----> 2 mapped_data, enriched_layer = pipeline.compose_transform()

NameError: name 'pipeline' is not defined

In [4]:

Copied!

# Visualize results
pipeline.visualise(["collision_count"])
# Visualize results
pipeline.visualise(["collision_count"])

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 2
      1 # Visualize results
----> 2 pipeline.visualise(["collision_count"])

NameError: name 'pipeline' is not defined

In [5]:

Copied!

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

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 2
      1 # Save the pipeline
----> 2 pipeline.save("./collisions_pipeline.dill")

NameError: name 'pipeline' is not defined