Taxi Trips Study - Step-by-Step¶

This notebook analyzes taxi trip data, mapping pickups and dropoffs to street segments and visualizing counts.

Data Sources¶

Yellow NYC Taxis 2015: Sample taxi trip data for NYC.

In [1]:

Copied!





import urban_mapper as um

# Initialise UrbanMapper
mapper = um.UrbanMapper()

# Step 1: Create urban layer for street segments
layer = (
    mapper.urban_layer
    .with_type("streets_roads")
    .from_place("Downtown Brooklyn, New York City, USA", network_type="drive")
    .build()
)
import urban_mapper as um

# Initialise UrbanMapper
mapper = um.UrbanMapper()

# Step 1: Create urban layer for street segments
layer = (
    mapper.urban_layer
    .with_type("streets_roads")
    .from_place("Downtown Brooklyn, New York City, USA", network_type="drive")
    .build()
)

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[1], line 1
----> 1 import urban_mapper as um
      3 # Initialise UrbanMapper
      4 mapper = um.UrbanMapper()

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!





# Step 2: Load taxi trip data
# Note: For the documentation interactive mode, we only query 5000 records from the dataset.  Feel free to remove for a more realistic analysis.    
data = (
    mapper.loader
    .from_huggingface("oscur/taxisvis1M", number_of_rows=5000, streaming=True)
    .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)
# Step 2: Load taxi trip data
# Note: For the documentation interactive mode, we only query 5000 records from the dataset.  Feel free to remove for a more realistic analysis.    
data = (
    mapper.loader
    .from_huggingface("oscur/taxisvis1M", number_of_rows=5000, streaming=True)
    .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)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[2], line 4
      1 # Step 2: Load taxi trip data
      2 # Note: For the documentation interactive mode, we only query 5000 records from the dataset.  Feel free to remove for a more realistic analysis.    
      3 data = (
----> 4     mapper.loader
      5     .from_huggingface("oscur/taxisvis1M", number_of_rows=5000, streaming=True)
      6     .with_columns(longitude_column="pickup_longitude", latitude_column="pickup_latitude")
      7     .load()
      8 )
     10 data['pickup_longitude'] = data['pickup_longitude'].astype(float)
     11 data['pickup_latitude'] = data['pickup_latitude'].astype(float)

NameError: name 'mapper' is not defined

In [3]:

Copied!





# Step 3: Impute missing coordinates
imputer_pickup = (
    mapper.imputer
    .with_type("SimpleGeoImputer")
    .on_columns("pickup_longitude", "pickup_latitude")
    .build()
)
data = imputer_pickup.transform(data, layer)

imputer_dropoff = (
    mapper.imputer
    .with_type("SimpleGeoImputer")
    .on_columns("dropoff_longitude", "dropoff_latitude")
    .build()
)
data = imputer_dropoff.transform(data, layer)
# Step 3: Impute missing coordinates
imputer_pickup = (
    mapper.imputer
    .with_type("SimpleGeoImputer")
    .on_columns("pickup_longitude", "pickup_latitude")
    .build()
)
data = imputer_pickup.transform(data, layer)

imputer_dropoff = (
    mapper.imputer
    .with_type("SimpleGeoImputer")
    .on_columns("dropoff_longitude", "dropoff_latitude")
    .build()
)
data = imputer_dropoff.transform(data, layer)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[3], line 3
      1 # Step 3: Impute missing coordinates
      2 imputer_pickup = (
----> 3     mapper.imputer
      4     .with_type("SimpleGeoImputer")
      5     .on_columns("pickup_longitude", "pickup_latitude")
      6     .build()
      7 )
      8 data = imputer_pickup.transform(data, layer)
     10 imputer_dropoff = (
     11     mapper.imputer
     12     .with_type("SimpleGeoImputer")
     13     .on_columns("dropoff_longitude", "dropoff_latitude")
     14     .build()
     15 )

NameError: name 'mapper' is not defined

In [4]:

Copied!

# Step 4: Filter to bounding box
filter_step = mapper.filter.with_type("BoundingBoxFilter").build()
data = filter_step.transform(data, layer)
# Step 4: Filter to bounding box
filter_step = mapper.filter.with_type("BoundingBoxFilter").build()
data = filter_step.transform(data, layer)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 2
      1 # Step 4: Filter to bounding box
----> 2 filter_step = mapper.filter.with_type("BoundingBoxFilter").build()
      3 data = filter_step.transform(data, layer)

NameError: name 'mapper' is not defined

In [5]:

Copied!





# Step 5: Map pickups and dropoffs
import copy
tmp_layer = copy.deepcopy(layer)

_, mapped_pickups = layer.map_nearest_layer(
    data,
    longitude_column="pickup_longitude",
    latitude_column="pickup_latitude",
    output_column="pickup_segment"
)

_, mapped_dropoffs = tmp_layer.map_nearest_layer(
    data,
    longitude_column="dropoff_longitude",
    latitude_column="dropoff_latitude",
    output_column="dropoff_segment"
)
# Step 5: Map pickups and dropoffs
import copy
tmp_layer = copy.deepcopy(layer)

_, mapped_pickups = layer.map_nearest_layer(
    data,
    longitude_column="pickup_longitude",
    latitude_column="pickup_latitude",
    output_column="pickup_segment"
)

_, mapped_dropoffs = tmp_layer.map_nearest_layer(
    data,
    longitude_column="dropoff_longitude",
    latitude_column="dropoff_latitude",
    output_column="dropoff_segment"
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 3
      1 # Step 5: Map pickups and dropoffs
      2 import copy
----> 3 tmp_layer = copy.deepcopy(layer)
      5 _, mapped_pickups = layer.map_nearest_layer(
      6     data,
      7     longitude_column="pickup_longitude",
      8     latitude_column="pickup_latitude",
      9     output_column="pickup_segment"
     10 )
     12 _, mapped_dropoffs = tmp_layer.map_nearest_layer(
     13     data,
     14     longitude_column="dropoff_longitude",
     15     latitude_column="dropoff_latitude",
     16     output_column="dropoff_segment"
     17 )

NameError: name 'layer' is not defined

In [6]:

Copied!





# Step 6: Enrich with counts
enricher_pickup = (
    mapper.enricher
    .with_data(group_by="pickup_segment")
    .count_by(output_column="pickup_count")
    .build()
)
enriched_layer_pickup = enricher_pickup.enrich(mapped_pickups, layer)

enricher_dropoff = (
    mapper.enricher
    .with_data(group_by="dropoff_segment")
    .count_by(output_column="dropoff_count")
    .build()
)
enriched_layer = enricher_dropoff.enrich(mapped_dropoffs, enriched_layer_pickup)
# Step 6: Enrich with counts
enricher_pickup = (
    mapper.enricher
    .with_data(group_by="pickup_segment")
    .count_by(output_column="pickup_count")
    .build()
)
enriched_layer_pickup = enricher_pickup.enrich(mapped_pickups, layer)

enricher_dropoff = (
    mapper.enricher
    .with_data(group_by="dropoff_segment")
    .count_by(output_column="dropoff_count")
    .build()
)
enriched_layer = enricher_dropoff.enrich(mapped_dropoffs, enriched_layer_pickup)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[6], line 3
      1 # Step 6: Enrich with counts
      2 enricher_pickup = (
----> 3     mapper.enricher
      4     .with_data(group_by="pickup_segment")
      5     .count_by(output_column="pickup_count")
      6     .build()
      7 )
      8 enriched_layer_pickup = enricher_pickup.enrich(mapped_pickups, layer)
     10 enricher_dropoff = (
     11     mapper.enricher
     12     .with_data(group_by="dropoff_segment")
     13     .count_by(output_column="dropoff_count")
     14     .build()
     15 )

NameError: name 'mapper' is not defined

In [7]:

Copied!





# Step 7: Visualize interactively
visualiser = (
    mapper.visual
    .with_type("Interactive")
    .with_style({"tiles": "CartoDB dark_matter", "colorbar_text_color": "white"})
    .build()
)
fig = visualiser.render(enriched_layer.get_layer(), columns=["pickup_count", "dropoff_count"])
fig
# Step 7: Visualize interactively
visualiser = (
    mapper.visual
    .with_type("Interactive")
    .with_style({"tiles": "CartoDB dark_matter", "colorbar_text_color": "white"})
    .build()
)
fig = visualiser.render(enriched_layer.get_layer(), columns=["pickup_count", "dropoff_count"])
fig

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[7], line 3
      1 # Step 7: Visualize interactively
      2 visualiser = (
----> 3     mapper.visual
      4     .with_type("Interactive")
      5     .with_style({"tiles": "CartoDB dark_matter", "colorbar_text_color": "white"})
      6     .build()
      7 )
      8 fig = visualiser.render(enriched_layer.get_layer(), columns=["pickup_count", "dropoff_count"])
      9 fig

NameError: name 'mapper' is not defined