- Updated dependencies.

- Upgraded Python to 3.9+. - Tweaked some validators. - Updated README.
mrcagney · Jul 10, 2024 · 0adf4a0 · 0adf4a0
1 parent c1dc96b
commit 0adf4a0
Show file tree

Hide file tree

Showing 13 changed files with 2,781 additions and 2,459 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,15 +1,15 @@
 repos:
 - repo: https://github.com/kynan/nbstripout
-  rev: 0.6.1
+  rev: 0.7.1
   hooks:
     - id: nbstripout
       files: ".ipynb"
 - repo: https://github.com/psf/black
-  rev: 23.1.0
+  rev: 24.4.2
   hooks:
     - id: black
 - repo: https://github.com/charliermarsh/ruff-pre-commit
   # Ruff version.
-  rev: 'v0.0.259'
+  rev: 'v0.5.1'
   hooks:
     - id: ruff
diff --git a/README.rst b/README.rst
@@ -2,14 +2,20 @@ Make GTFS
 ***********
 .. image:: https://github.com/mrcagney/gtfs_kit/actions/workflows/test.yml/badge.svg
 
-A Python 3.8+ library to build GTFS feeds from basic route information.
+A Python 3.9+ library to build GTFS feeds from basic route information.
 Inspired by Conveyal's `geom2gtfs <https://github.com/conveyal/geom2gtfs>`_.
 Makes naive timetables, but they are often good enough for preliminary work.
 
+Contributors
+============
+- Alex Raichev (maintainer), 2014-09
+
 
 Installation
 =============
-Create a Python 3.8+ virtual environment and run ``poetry add make_gtfs``.
+To use as a library in your own project (called something other than ``make_gtfs``), make a Python 3.9+ virtual environment for your project, then run ``poetry add make_gtfs``.
+
+To develop the ``make_gtfs`` repo, Git clone it, make a Python 3.9+ virtual environment, then run ``poetry install --no-root && pre-commit install``.
 
 
 Usage
@@ -129,12 +135,6 @@ Documentation
 On Github pages `here <https://mrcagney.github.io/make_gtfs_docs>`_.
 
 
-Contributors
-============
-- Alex Raichev (maintainer), 2014-09
-- Danielle Gatland (reviewer), 2021-10
-
-
 Notes
 ======
 - This project's development status is Alpha.
@@ -146,6 +146,13 @@ Notes
 Changes
 ========
 
+4.0.7, 2024-07-10
+-----------------
+- Updated dependencies.
+- Upgraded Python to 3.9+.
+- Tweaked some validators.
+- Updated README.
+
 4.0.6, 2023-03-29
 -----------------
 - Updated dependencies and pre-commit hooks.

diff --git a/make_gtfs/__init__.py b/make_gtfs/__init__.py
@@ -4,4 +4,4 @@
 from .hashables import *
 from .main import *
 
-__version__ = "4.0.6"
+__version__ = "4.0.7"
diff --git a/make_gtfs/main.py b/make_gtfs/main.py
@@ -1,7 +1,9 @@
 """
 This module contains the main logic.
 """
-from typing import Optional
+
+from __future__ import annotations
+
 from functools import lru_cache
 import math
 
@@ -161,7 +163,7 @@ def make_stop_points(
     offset: float,
     side: str,
     n: int = 2,
-    spacing: Optional[float] = None,
+    spacing: float | None = None,
 ) -> gpd.GeoDataFrame:
     """
     Given a GeoDataFrame of lines with at least the columns
@@ -252,10 +254,10 @@ def get_dists(L, δ):
 
 def build_stops(
     pfeed: pf.ProtoFeed,
-    shapes: Optional[pd.DataFrame] = None,
+    shapes: pd.DataFrame | None = None,
     offset: float = cs.STOP_OFFSET,
     n: int = 2,
-    spacing: Optional[float] = None,
+    spacing: float | None = None,
 ) -> pd.DataFrame:
     """
     Given a ProtoFeed, return a DataFrame representing ``stops.txt``.
@@ -477,7 +479,9 @@ def compute_dists(group):
     shapes_g = (
         gk.geometrize_shapes_0(shapes)
         .to_crs(utm_crs)
-        .assign(boundary_points=lambda x: x.intersection(speed_zones.boundary))
+        .assign(
+            boundary_points=lambda x: x.intersection(speed_zones.boundary, align=True)
+        )
     )
 
     # Assign distances to those boundary points
@@ -746,7 +750,7 @@ def build_stop_times(
         # Convert seconds back to time strings
         f[["arrival_time", "departure_time"]] = f[
             ["arrival_time", "departure_time"]
-        ].applymap(lambda x: gk.timestr_to_seconds(x, inverse=True))
+        ].map(lambda x: gk.timestr_to_seconds(x, inverse=True))
 
     # Free memory
     _build_stop_times_for_trip.cache_clear()
@@ -759,7 +763,7 @@ def build_feed(
     buffer: float = cs.BUFFER,
     stop_offset: float = cs.STOP_OFFSET,
     num_stops_per_shape: int = 2,
-    stop_spacing: Optional[float] = None,
+    stop_spacing: float | None = None,
 ) -> gk.Feed:
     """
     Convert the given ProtoFeed to a GTFS Feed with meter distance units.

diff --git a/make_gtfs/protofeed.py b/make_gtfs/protofeed.py
@@ -1,5 +1,5 @@
 from __future__ import annotations
-from typing import Optional
+
 import pathlib as pl
 from dataclasses import dataclass
 
@@ -39,8 +39,8 @@ class ProtoFeed:
     service_windows: pd.DataFrame
     shapes: gpd.GeoDataFrame
     frequencies: pd.DataFrame
-    stops: Optional[pd.DataFrame] = None
-    speed_zones: Optional[gpd.GeoDataFrame] = None
+    stops: pd.DataFrame | None = None
+    speed_zones: gpd.GeoDataFrame | None = None
 
     @staticmethod
     def clean_speed_zones(
@@ -55,8 +55,10 @@ def clean_speed_zones(
         ``default_speed_zone_id`` and the speed there will be set to ``default_speed``.
         Return the resulting service area of (Multi)Polygons, now partitioned into speed
         zones.
+        The result is a GeoDataFrame with the columns 'speed_zone_id', 'speed',
+        'geometry'.
         """
-        if service_area.geom_equals(speed_zones.unary_union).all():
+        if service_area.geom_equals(speed_zones.union_all()).all():
             # Speed zones already partition the study area, so good
             result = speed_zones
         else:
@@ -68,12 +70,13 @@ def clean_speed_zones(
                 # Union chunks
                 .overlay(service_area, how="union")
                 .assign(
-                    speed_zone_id=lambda x: x.speed_zone_id.fillna(
+                    route_type=lambda x: x["route_type"].ffill().astype(int),
+                    speed_zone_id=lambda x: x["speed_zone_id"].fillna(
                         default_speed_zone_id
                     ),
-                    speed=lambda x: x.speed.fillna(default_speed),
+                    speed=lambda x: x["speed"].fillna(default_speed),
                 )
-                .filter(["speed_zone_id", "speed", "geometry"])
+                .filter(["route_type", "speed_zone_id", "speed", "geometry"])
                 .sort_values("speed_zone_id", ignore_index=True)
             )
         return result
@@ -91,7 +94,7 @@ def __post_init__(self):
         # <shape ID> -> <trip directions using the shape (0, 1, or 2)>
         def my_agg(group):
             d = {}
-            dirs = group.direction.unique()
+            dirs = group["direction"].unique()
             if len(dirs) > 1 or 2 in dirs:
                 d["direction"] = 2
             else:
@@ -114,7 +117,7 @@ def my_agg(group):
             # it infinite speed so it won't override route speeds present in
             # ``self.frequencies``.
             frames = []
-            for route_type in self.frequencies.route_type.unique():
+            for route_type in self.frequencies["route_type"].unique():
                 g = service_area.assign(
                     route_type=route_type,
                     speed_zone_id=f"default{cs.SEP}{route_type}",
@@ -132,15 +135,25 @@ def my_apply(group):
                 )
 
             self.speed_zones = (
-                self.speed_zones.groupby("route_type")
+                self.speed_zones.groupby("route_type", group_keys=False)
                 .apply(my_apply)
-                .reset_index()
                 .filter(["route_type", "speed_zone_id", "speed", "geometry"])
             )
 
         lon, lat = self.shapes.geometry.iat[0].coords[0]
         self.utm_crs = gk.get_utm_crs(lat, lon)
 
+    def __eq__(self, other) -> bool:
+        for k in self.__dataclass_fields__:
+            v1 = getattr(self, k)
+            v2 = getattr(other, k)
+            if isinstance(v1, (pd.DataFrame, gpd.GeoDataFrame)):
+                if not v1.equals(v2):
+                    return False
+            elif not isinstance(v2, type(v1)) or v1 != v2:
+                return False
+        return True
+
     def copy(self) -> ProtoFeed:
         """
         Return a copy of this ProtoFeed, that is, a feed with all the
@@ -293,8 +306,10 @@ def read_protofeed(path: str | pl.Path) -> ProtoFeed:
     d["speed_zones"] = None
     if (path / "speed_zones.geojson").exists():
         g = gpd.read_file(path / "speed_zones.geojson")
+        if "route_type" in g.columns:
+            g["route_type"] = g["route_type"].astype(int)
         if "speed_zone_id" in g.columns:
-            g["speed_zone_id"] = g.speed_zone_id.astype(str)
+            g["speed_zone_id"] = g["speed_zone_id"].astype(str)
         d["speed_zones"] = g
 
     pfeed = ProtoFeed(**d)

diff --git a/make_gtfs/validators.py b/make_gtfs/validators.py
@@ -1,6 +1,7 @@
 """
 ProtoFeed validators.
 """
+
 import re
 import pytz
 
@@ -163,29 +164,33 @@
 def check_meta(pfeed: pf.ProtoFeed) -> pd.DataFrame:
     """
     Return `pfeed.meta` if it is valid.
-    Otherwise, raise a Pandera SchemaError.
+    Otherwise, raise a ValueError or a Pandera SchemaError.
     """
+    if not isinstance(pfeed.meta, pd.DataFrame):
+        raise ValueError("Meta must be a DataFrame")
+
     return SCHEMA_META.validate(pfeed.meta)
 
 
 def check_shapes(pfeed: pf.ProtoFeed) -> pd.DataFrame:
     """
     Return `pfeed.shapes` if it is valid.
-    Otherwise, raise a Pandera SchemaError.
+    Otherwise, raise a ValueError or a Pandera SchemaError.
     """
-    result = SCHEMA_SHAPES.validate(pfeed.shapes)
-
     if not isinstance(pfeed.shapes, gpd.GeoDataFrame):
         raise ValueError("Shapes must be a GeoDataFrame")
 
-    return result
+    return SCHEMA_SHAPES.validate(pfeed.shapes)
 
 
 def check_service_windows(pfeed: pf.ProtoFeed) -> pd.DataFrame:
     """
     Return `pfeed.service_windows` if it is valid.
     Otherwise, raise a Pandera SchemaError.
     """
+    if not isinstance(pfeed.service_windows, pd.DataFrame):
+        raise ValueError("Service windows must be a DataFrame")
+
     return SCHEMA_SERVICE_WINDOWS.validate(pfeed.service_windows)
 
 
@@ -194,6 +199,9 @@ def check_frequencies(pfeed: pf.ProtoFeed) -> pd.DataFrame:
     Return `pfeed.frequencies` if it is valid.
     Otherwise, raise a Pandera SchemaError.
     """
+    if not isinstance(pfeed.frequencies, pd.DataFrame):
+        raise ValueError("Frequencies must be a DataFrame")
+
     return SCHEMA_FREQUENCIES.validate(pfeed.frequencies)
 
 

diff --git a/notebooks/examples.ipynb b/notebooks/examples.ipynb
@@ -92,7 +92,7 @@
    "source": [
     "# Map some trips\n",
     "tids = [feed.trips.trip_id.iat[0], feed.trips.trip_id.iat[-1]]\n",
-    "feed.map_trips(tids, include_arrows=True, include_stops=True)\n",
+    "feed.map_trips(tids, show_direction=True, show_stops=True)\n",
     "    "
    ]
   },
@@ -120,9 +120,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }
diff --git a/notebooks/prototype_speed_zones.ipynb b/notebooks/prototype_speed_zones.ipynb
@@ -17,8 +17,8 @@
     "import gtfs_kit as gk\n",
     "import shapely\n",
     "import shapely.geometry as sg\n",
-    "import geo_kit as geo\n",
     "import folium as fl\n",
+    "import geo_kit as geo  # Only works for MRCagney staff\n",
     "\n",
     "sys.path.append('../')\n",
     "\n",
@@ -232,9 +232,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }