feat: model update 2024

analysis/marginals.py

@@ -8,14 +8,14 @@
 HOUSEHOLD_SIZE_BOUNDS = [1, 3, np.inf]
 HOUSEHOLD_SIZE_LABELS = ["1", "2-3", "4+"]
 
-NUMBER_OF_VEHICLES_BOUNDS = [0, 1, 2, np.inf]
-NUMBER_OF_VEHICLES_LABELS = ["0", "1", "2", "3+"]
+NUMBER_OF_CARS_BOUNDS = [0, 1, 2, np.inf]
+NUMBER_OF_CARS_LABELS = ["0", "1", "2", "3+"]
 
-NUMBER_OF_BIKES_BOUNDS = [0, 1, 2, np.inf]
-NUMBER_OF_BIKES_LABELS = ["0", "1", "2", "3+"]
+NUMBER_OF_BICYCLES_BOUNDS = [0, 1, 2, np.inf]
+NUMBER_OF_BICYCLES_LABELS = ["0", "1", "2", "3+"]
 
 GENERAL_PERSON_MARGINALS = [("age_class",), ("sex",), ("employed",), ("studies",)]
-GENERAL_HOUSEHOLD_MARGINALS = [("household_size_class",), ("number_of_vehicles_class",)]
+GENERAL_HOUSEHOLD_MARGINALS = [("household_size_class",), ("number_of_cars_class",)]
 
 CENSUS_PERSON_MARGINALS = GENERAL_PERSON_MARGINALS + [("socioprofessional_class",)]
 CENSUS_HOUSEHOLD_MARGINALS = GENERAL_HOUSEHOLD_MARGINALS
@@ -34,11 +34,11 @@ def prepare_classes(df):
     if "household_size" in df:
         df["household_size_class"] = np.digitize(df["household_size"], HOUSEHOLD_SIZE_BOUNDS, right = True)
 
-    if "number_of_vehicles" in df:
-        df["number_of_vehicles_class"] = np.digitize(df["number_of_vehicles"], NUMBER_OF_VEHICLES_BOUNDS, right = True)
+    if "number_of_cars" in df:
+        df["number_of_cars_class"] = np.digitize(df["number_of_cars"], NUMBER_OF_CARS_BOUNDS, right = True)
 
-    if "number_of_bikes" in df:
-        df["number_of_bikes_class"] = np.digitize(df["number_of_bikes"], NUMBER_OF_BIKES_BOUNDS, right = True)
+    if "number_of_bicycles" in df:
+        df["number_of_bicycles_class"] = np.digitize(df["number_of_bicycles"], NUMBER_OF_BICYCLES_BOUNDS, right = True)
 
 def cross(*marginals):
     result = []

analysis/reference/hts/mode_distances.py

@@ -20,7 +20,7 @@ def execute(context):
 
     data = dict()
 
-    for mode in ["car", "car_passenger", "pt", "bike", "walk"]:
+    for mode in ["car", "car_passenger", "pt", "bicycle", "walk"]:
         f = df["mode"] == mode
 
         if np.count_nonzero(f) > 0:

analysis/synthesis/mode_distances.py

@@ -15,7 +15,7 @@ def execute(context):
     acquisition_sample_size = context.config("acquisition_sample_size")
 
     probabilities = np.linspace(0.0, 1.0, 20)
-    modes = ["car", "car_passenger", "pt", "bike", "walk"]
+    modes = ["car", "car_passenger", "pt", "bicycle", "walk"]
 
     quantiles = { mode : [] for mode in modes }
 

data/census/cleaned.py

@@ -60,9 +60,10 @@ def execute(context):
     # Clean TRANS
     df.loc[df["TRANS"] == "1", "commute_mode"] = np.nan
     df.loc[df["TRANS"] == "2", "commute_mode"] = "walk"
-    df.loc[df["TRANS"] == "3", "commute_mode"] = "bike"
+    df.loc[df["TRANS"] == "3", "commute_mode"] = "bicycle"
     df.loc[df["TRANS"] == "4", "commute_mode"] = "car"
-    df.loc[df["TRANS"] == "5", "commute_mode"] = "pt"
+    df.loc[df["TRANS"] == "5", "commute_mode"] = "car"
+    df.loc[df["TRANS"] == "6", "commute_mode"] = "pt"
     df.loc[df["TRANS"] == "Z", "commute_mode"] = np.nan
     df["commute_mode"] = df["commute_mode"].astype("category")
 
@@ -81,11 +82,11 @@ def execute(context):
     df["studies"] = df["ETUD"] == "1"
 
     # Number of vehicles
-    df["number_of_vehicles"] = df["VOIT"].apply(
+    df["number_of_cars"] = df["VOIT"].apply(
         lambda x: str(x).replace("Z", "0").replace("X", "0")
     ).astype(int)
 
-    df["number_of_vehicles"] += df["DEROU"].apply(
+    df["number_of_cars"] += df["DEROU"].apply(
         lambda x: str(x).replace("U", "0").replace("Z", "0").replace("X", "0")
     ).astype(int)
 
@@ -104,7 +105,7 @@ def execute(context):
         "iris_id", "commune_id", "departement_id",
         "age", "sex", "couple",
         "commute_mode", "employed",
-        "studies", "number_of_vehicles", "household_size",
+        "studies", "number_of_cars", "household_size",
         "consumption_units", "socioprofessional_class"
     ]]
 

data/hts/edgt_44/cleaned.py

@@ -22,7 +22,8 @@ def configure(context):
     "car": [13, 15, 21, 81],
     "car_passenger": [14, 16, 22, 82],
     "pt": [30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 51, 52, 53, 61, 71, 72, 73, 91, 92, 94, 95],
-    "bike": [11, 17, 12, 18, 93, 19],
+    "bicycle": [11, 17, 12, 18, 93, 19],
+    # "motorbike": [13, 15],
     "walk": [1, 2] # Actually, 2 is not really explained, but we assume it is walk
 }
 
@@ -90,9 +91,9 @@ def execute(context):
     df_persons["studies"] = df_persons["P7"].isin(["3", "4", "5"])
 
     # Number of vehicles
-    df_households["number_of_vehicles"] = df_households["M6"] + df_households["M5"]
-    df_households["number_of_vehicles"] = df_households["number_of_vehicles"].astype(int)
-    df_households["number_of_bikes"] = df_households["M7"].astype(int)
+    df_households["number_of_cars"] = df_households["M6"].astype(int)
+    df_households["number_of_cars"] += df_households["M5"].astype(int) # motorbikes
+    df_households["number_of_bicycles"] = df_households["M7"].astype(int)
 
     # License
     df_persons["has_license"] = df_persons["P5"] == "1"
@@ -166,11 +167,6 @@ def execute(context):
     # Nonrespondent of travel questionary section (number_of_trips = -1)
     df_persons["number_of_trips"] = df_persons["number_of_trips"].fillna(-1).astype(int)
 
-    # Passenger attribute
-    df_persons["is_passenger"] = df_persons["person_id"].isin(
-        df_trips[df_trips["mode"] == "car_passenger"]["person_id"].unique()
-    )
-
     # Calculate consumption units
     hts.check_household_size(df_households, df_persons)
     df_households = pd.merge(df_households, hts.calculate_consumption_units(df_persons), on = "household_id")

data/hts/edgt_lyon/cleaned_adisp.py

@@ -23,7 +23,8 @@ def configure(context):
     "car": [13, 15, 21, 81],
     "car_passenger": [14, 16, 22, 82],
     "pt": [31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 51, 52, 53, 61, 71, 91, 92, 94, 95],
-    "bike": [11, 17, 12, 18, 93],
+    "bicycle": [11, 17, 12, 18, 93],
+    # "motorbike": [13, 15],
     "walk": [1, 2] # Actually, 2 is not really explained, but we assume it is walk
 }
 
@@ -106,9 +107,9 @@ def execute(context):
     df_persons["studies"] = df_persons["P9"].isin(["3", "4", "5"])
 
     # Number of vehicles
-    df_households["number_of_vehicles"] = df_households["M6"] + df_households["M14"]
-    df_households["number_of_vehicles"] = df_households["number_of_vehicles"].astype(int)
-    df_households["number_of_bikes"] = df_households["M21"].astype(int)
+    df_households["number_of_cars"] = df_households["M6"].astype(int)
+    df_households["number_of_cars"] += df_households["M14"].astype(int) # motorbikes
+    df_households["number_of_bicycles"] = df_households["M21"].astype(int)
 
     # License
     df_persons["has_license"] = df_persons["P7"] == "1"
@@ -179,11 +180,6 @@ def execute(context):
     # Nonrespondent of travel questionary section (number_of_trips = -1)
     df_persons["number_of_trips"] = df_persons["number_of_trips"].fillna(-1).astype(int)
 
-    # Passenger attribute
-    df_persons["is_passenger"] = df_persons["person_id"].isin(
-        df_trips[df_trips["mode"] == "car_passenger"]["person_id"].unique()
-    )
-
     # Calculate consumption units
     hts.check_household_size(df_households, df_persons)
     df_households = pd.merge(df_households, hts.calculate_consumption_units(df_persons), on = "household_id")

data/hts/edgt_lyon/cleaned_cerema.py

@@ -22,7 +22,8 @@ def configure(context):
     "car": [13, 15, 21, 81],
     "car_passenger": [14, 16, 22, 82],
     "pt": [31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 51, 52, 53, 61, 71, 91, 92, 94, 95],
-    "bike": [11, 17, 12, 18, 93],
+    "bicycle": [11, 17, 12, 18, 93],
+    # "motorbike": [13, 15],
     "walk": [1, 2] # Actually, 2 is not really explained, but we assume it is walk
 }
 
@@ -105,9 +106,9 @@ def execute(context):
     df_persons["studies"] = df_persons["P7"].isin(["3", "4", "5"])
 
     # Number of vehicles
-    df_households["number_of_vehicles"] = df_households["M6"] + df_households["M5"]
-    df_households["number_of_vehicles"] = df_households["number_of_vehicles"].astype(int)
-    df_households["number_of_bikes"] = df_households["M7"].astype(int)
+    df_households["number_of_cars"] = df_households["M6"].astype(int)
+    df_households["number_of_cars"] += df_households["M5"].astype(int) # motorbikes
+    df_households["number_of_bicycles"] = df_households["M7"].astype(int)
 
     # License
     df_persons["has_license"] = df_persons["P5"] == "1"
@@ -180,11 +181,6 @@ def execute(context):
     # Nonrespondent of travel questionary section (number_of_trips = -1)
     df_persons["number_of_trips"] = df_persons["number_of_trips"].fillna(-1).astype(int)
 
-    # Passenger attribute
-    df_persons["is_passenger"] = df_persons["person_id"].isin(
-        df_trips[df_trips["mode"] == "car_passenger"]["person_id"].unique()
-    )
-
     # Calculate consumption units
     hts.check_household_size(df_households, df_persons)
     df_households = pd.merge(df_households, hts.calculate_consumption_units(df_persons), on = "household_id")

data/hts/edgt_lyon/raw_adisp.py

@@ -15,7 +15,7 @@ def configure(context):
 
 HOUSEHOLD_COLUMNS = {
     "ECH": str, "ZFM": str, # id
-    "M6": int, "M21": int, "M14": int,  # number_of_cars, number_of_bikes, number_of_motorbikes
+    "M6": int, "M21": int, "M14": int,  # number_of_cars, number_of_bicycles, number_of_motorbikes
     "COE0": float # weights
 }
 

data/hts/egt/cleaned.py

@@ -31,8 +31,8 @@ def configure(context):
     1 : "pt",
     2 : "car",
     3 : "car_passenger",
-    4 : "car",
-    5 : "bike",
+    4 : "car", # motorbike
+    5 : "bicycle",
     #6 : "pt", # default (other)
     7 : "walk"
 }
@@ -99,9 +99,9 @@ def execute(context):
     df_persons["studies"] = df_persons["OCCP"].isin([3.0, 4.0, 5.0])
 
     # Number of vehicles
-    df_households["number_of_vehicles"] = df_households["NB_2RM"] + df_households["NB_VD"]
-    df_households["number_of_vehicles"] = df_households["number_of_vehicles"].astype(int)
-    df_households["number_of_bikes"] = df_households["NB_VELO"].astype(int)
+    df_households["number_of_cars"] = df_households["NB_VD"].astype(int)
+    df_households["number_of_cars"] += df_households["NB_2RM"].astype(int) # motorbikes
+    df_households["number_of_bicycles"] = df_households["NB_VELO"].astype(int)
 
     # License
     df_persons["has_license"] = (df_persons["PERMVP"] == 1) | (df_persons["PERM2RM"] == 1)
@@ -172,11 +172,6 @@ def execute(context):
     # Chain length
     df_persons["number_of_trips"] = df_persons["NBDEPL"].fillna(0).astype(int)
 
-    # Passenger attribute
-    df_persons["is_passenger"] = df_persons["person_id"].isin(
-        df_trips[df_trips["mode"] == "car_passenger"]["person_id"].unique()
-    )
-
     # Calculate consumption units
     hts.check_household_size(df_households, df_persons)
     df_households = pd.merge(df_households, hts.calculate_consumption_units(df_persons), on = "household_id")

data/hts/entd/cleaned.py

@@ -28,7 +28,7 @@ def configure(context):
 MODES_MAP = [
     ("1", "walk"),
     ("2", "car"), #
-    ("2.20", "bike"), # bike
+    ("2.20", "bicycle"), # bike
     ("2.23", "car_passenger"), # motorcycle passenger
     ("2.25", "car_passenger"), # same
     ("3", "car"),
@@ -135,13 +135,12 @@ def execute(context):
     df_persons.loc[df_persons["age"] < 5, "studies"] = False
 
     # Number of vehicles
-    df_households["number_of_vehicles"] = 0
-    df_households["number_of_vehicles"] += df_households["V1_JNBVEH"].fillna(0)
-    df_households["number_of_vehicles"] += df_households["V1_JNBMOTO"].fillna(0)
-    df_households["number_of_vehicles"] += df_households["V1_JNBCYCLO"].fillna(0)
-    df_households["number_of_vehicles"] = df_households["number_of_vehicles"].astype(int)
+    df_households["number_of_cars"] = df_households["V1_JNBVEH"].fillna(0)
+    df_households["number_of_cars"] += df_households["V1_JNBMOTO"].fillna(0) # motorbike
+    df_households["number_of_cars"] += df_households["V1_JNBCYCLO"].fillna(0) # motorbike
+    df_households["number_of_cars"] = df_households["number_of_cars"].astype(int)
 
-    df_households["number_of_bikes"] = df_households["V1_JNBVELOADT"].fillna(0).astype(int)
+    df_households["number_of_bicycles"] = df_households["V1_JNBVELOADT"].fillna(0).astype(int)
 
     # License
     df_persons["has_license"] = (df_persons["V1_GPERMIS"] == 1) | (df_persons["V1_GPERMIS2R"] == 1)
@@ -236,11 +235,6 @@ def execute(context):
     df_persons["number_of_trips"] = df_persons["number_of_trips"].fillna(-1).astype(int)
     df_persons.loc[(df_persons["number_of_trips"] == -1) & df_persons["is_kish"], "number_of_trips"] = 0
 
-    # Passenger attribute
-    df_persons["is_passenger"] = df_persons["person_id"].isin(
-        df_trips[df_trips["mode"] == "car_passenger"]["person_id"].unique()
-    )
-
     # Calculate consumption units
     hts.check_household_size(df_households, df_persons)
     df_households = pd.merge(df_households, hts.calculate_consumption_units(df_persons), on = "household_id")

data/hts/hts.py

@@ -222,7 +222,7 @@ def calculate_consumption_units(df_persons):
 
 HOUSEHOLD_COLUMNS = [
     "household_id", "household_weight", "household_size",
-    "number_of_vehicles", "number_of_bikes", "departement_id",
+    "number_of_cars", "number_of_bicycles", "departement_id",
     "consumption_units", # "income_class"
 ]
 
@@ -231,7 +231,7 @@ def calculate_consumption_units(df_persons):
     "age", "sex", "employed", "studies",
     "has_license", "has_pt_subscription",
     "number_of_trips", "departement_id", "trip_weight",
-    "is_passenger", "socioprofessional_class"
+    "socioprofessional_class"
 ]
 
 TRIP_COLUMNS = [

data/od/cleaned.py

@@ -50,8 +50,8 @@ def execute(context):
     df_work["commute_mode"] = np.nan
     df_work.loc[df_work["TRANS"] == 1, "commute_mode"] = "no transport"
     df_work.loc[df_work["TRANS"] == 2, "commute_mode"] = "walk"
-    df_work.loc[df_work["TRANS"] == 3, "commute_mode"] = "bike"
-    df_work.loc[df_work["TRANS"] == 4, "commute_mode"] = "car"
+    df_work.loc[df_work["TRANS"] == 3, "commute_mode"] = "bicycle"
+    df_work.loc[df_work["TRANS"] == 4, "commute_mode"] = "car" # motorbike
     df_work.loc[df_work["TRANS"] == 5, "commute_mode"] = "car"
     df_work.loc[df_work["TRANS"] == 6, "commute_mode"] = "pt"
     df_work["commute_mode"] = df_work["commute_mode"].astype("category")

documentation/plots/secondary_locations.py

@@ -21,7 +21,6 @@ def execute(context):
     plt.figure()
 
     modes = list(context.stage("analysis.reference.hts.mode_distances").keys())
-    #modes = ["car", "car_passenger", "pt", "bike", "walk"]
 
     for index, mode in enumerate(modes):
         mode_distribution = distributions[mode]
@@ -71,10 +70,10 @@ def execute(context):
 
     limits = dict(
         car = 20 * 1e3, car_passenger = 20 * 1e3, pt = 20 * 1e3,
-        bike = 6 * 1e3, walk = 1 * 1e3
+        bicycle = 6 * 1e3, walk = 1 * 1e3
     )
 
-    modes = ["car", "bike" if "bike" in modes else "walk" ]
+    modes = ["car", "bicycle" if "bicycle" in modes else "walk" ]
 
     for index, mode in enumerate(modes):
         plt.subplot(1, 2, index + 1)

documentation/plots/sociodemographics/general.py

@@ -79,11 +79,11 @@ def label(row):
     elif row["attribute"] == "household_size_class":
         return "Household size %s" % analysis.marginals.HOUSEHOLD_SIZE_LABELS[row["value"]]
 
-    elif row["attribute"] == "number_of_vehicles_class":
-        return "No. vehicles %s" % analysis.marginals.NUMBER_OF_VEHICLES_LABELS[row["value"]]
+    elif row["attribute"] == "number_of_cars_class":
+        return "No. vehicles %s" % analysis.marginals.NUMBER_OF_CARS_LABELS[row["value"]]
 
-    elif row["attribute"] == "number_of_bikes_class":
-        return "No. bicycles %s" % analysis.marginals.NUMBER_OF_BIKES_LABELS[row["value"]]
+    elif row["attribute"] == "number_of_bicycles_class":
+        return "No. bicycles %s" % analysis.marginals.NUMBER_OF_BICYCLES_LABELS[row["value"]]
 
 def add_labels(df_figure):
     df_figure["label"] = df_figure.apply(label, axis = 1, raw = False)
@@ -115,7 +115,7 @@ def execute(context):
         ),
         dict(
             level = "household", label = "Number of households", size = plotting.WIDE_FIGSIZE,
-            marginals = ["household_size_class", "number_of_vehicles_class", "number_of_bikes_class"]
+            marginals = ["household_size_class", "number_of_cars_class", "number_of_bikes_class"]
         )
     ]
 

documentation/plotting.py

@@ -23,7 +23,7 @@
     car = "Car driver",
     car_passenger = "Car passenger",
     pt = "Public transport",
-    bike = "Bicycle",
+    bicycle = "Bicycle",
     walk = "Walking"
 )
 

matsim/runtime/eqasim.py

@@ -6,8 +6,8 @@
 import matsim.runtime.maven as maven
 
 DEFAULT_EQASIM_VERSION = "1.5.0"
-DEFAULT_EQASIM_BRANCH = "develop"
-DEFAULT_EQASIM_COMMIT = "ece4932"
+DEFAULT_EQASIM_BRANCH = "feat/model-2024"
+DEFAULT_EQASIM_COMMIT = "c0645372"
 
 def configure(context):
     context.stage("matsim.runtime.git")

matsim/scenario/households.py

@@ -8,15 +8,15 @@
 def configure(context):
     context.stage("synthesis.population.enriched")
 
-FIELDS = ["household_id", "person_id", "household_income", "car_availability", "bike_availability", "census_household_id"]
+FIELDS = ["household_id", "person_id", "household_income", "car_availability", "bicycle_availability", "census_household_id"]
 
 def add_household(writer, household, member_ids):
     writer.start_household(household[FIELDS.index("household_id")])
     writer.add_members(member_ids)
 
     writer.start_attributes()
     writer.add_attribute("carAvailability", "java.lang.String", household[FIELDS.index("car_availability")])
-    writer.add_attribute("bikeAvailability", "java.lang.String", household[FIELDS.index("bike_availability")])
+    writer.add_attribute("bicycleAvailability", "java.lang.String", household[FIELDS.index("bicycle_availability")])
     writer.add_attribute("household_income", "java.lang.Double", household[FIELDS.index("household_income")])
     writer.add_attribute("censusId", "java.lang.Long", household[FIELDS.index("census_household_id")])
     writer.end_attributes()