Handling of mexico-city survey data for scenario generation

matsim/scenariogen/__main__.py

@@ -3,14 +3,14 @@
 
 import argparse
 
-from .data import run_create_ref_data
-from .data import run_extract_activities
-from .data import run_lookup_regiostar
-from .network import run_collect_results
-from .network import run_edges as sumo_edges
-from .network import run_intersections as sumo_intersections
-from .network import run_routes as sumo_routes
-from .network import run_train_model
+from matsim.scenariogen.data import run_create_ref_data
+from data import run_extract_activities
+from matsim.scenariogen.data import run_lookup_regiostar
+from matsim.scenariogen.network import run_collect_results
+from matsim.scenariogen.network import run_edges as sumo_edges
+from matsim.scenariogen.network import run_intersections as sumo_intersections
+from matsim.scenariogen.network import run_routes as sumo_routes
+from matsim.scenariogen.network import run_train_model
 
 
 def _add(subparsers, m):

matsim/scenariogen/data/__init__.py

@@ -30,7 +30,7 @@ def _batch(iterable: list, max_batch_size: int):
 def read_all(dirs: Union[str, List[str]], regio=None) -> Tuple[pd.DataFrame]:
     """ Scan directories and read everything into one dataframe """
 
-    from .formats import srv, mid
+    from .formats import srv, mid, eodmx
 
     hh = []
     pp = []
@@ -42,7 +42,7 @@ def read_all(dirs: Union[str, List[str]], regio=None) -> Tuple[pd.DataFrame]:
 
     for d in dirs:
 
-        for format in (srv, mid):
+        for format in (srv, mid, eodmx):
 
             files = []
 
@@ -112,12 +112,14 @@ class HouseholdType(AutoNameLowerStrEnum):
     MULTI_W_CHILDREN = auto()
     MULTI_WO_CHILDREN = auto()
     SINGLE = auto()
+    UNKNOWN = auto()
 
 
 class EconomicStatus(AutoNameLowerStrEnum):
     VERY_LOW = auto()
     LOW = auto()
-    MEDIUM = auto()
+    MEDIUM_LOW = auto()
+    MEDIUM_HIGH = auto()
     HIGH = auto()
     VERY_HIGH = auto()
     UNKNOWN = auto()
@@ -179,6 +181,7 @@ class Purpose(AutoNameLowerStrEnum):
     HOME = auto()
     WAYBACK = auto()
     OTHER = auto()
+    ACCOMP_OTHER = auto()
 
 
 class TripMode(AutoNameLowerStrEnum):
@@ -189,6 +192,8 @@ class TripMode(AutoNameLowerStrEnum):
     PT = auto()
     MOTORCYCLE = auto()
     OTHER = auto()
+    # This transport mode represents what in english is known as shared taxi / taxibus / minibus / colectivo in spanish:
+    TAXIBUS = auto()
 
 
 class DistanceGroup(AutoNameLowerStrEnum):
@@ -262,6 +267,7 @@ class SourceDestinationGroup(AutoNameLowerStrEnum):
     OTHER_WORK = auto()
     WORK_OTHER = auto()
     OTHER_OTHER = auto()
+    VISIT_OTHER = auto()
 
     UNKNOWN = auto()
 
@@ -309,6 +315,7 @@ class Person:
     present_on_day: bool
     reporting_day: int
     n_trips: int
+    home_district: str = None
 
 
 @dataclass
@@ -327,11 +334,14 @@ class Trip:
     purpose: Purpose
     sd_group: SourceDestinationGroup
     valid: bool
+    dep_district: str = None
+    arr_district: str = None
 
 
 @dataclass
 class Activity:
-    """ Activity information (including leg) """
+    """ Activity information (including leg)
+    all leg information relates to the leg leading to the activity """
     a_id: str
     p_id: str
     n: int
@@ -340,3 +350,7 @@ class Activity:
     leg_dist: float
     leg_duration: float
     leg_mode: TripMode
+    leg_dep_district: str = None
+    leg_arr_district: str = None
+    leg_departure: int = 0
+    start_time: int = 0

matsim/scenariogen/data/formats/__init__.py

@@ -1,3 +1,3 @@
 # -*- coding: utf-8 -*-
 
-__all__ = ["srv", "mid"]
+__all__ = ["srv", "mid", "eodmx"]