#df_trips.drop([df_trips["origin_commune_id"]=="aaaaa"], inplace=True) #df_trips.drop([df_trips["destination_commune_id"]=="aaaaa"], inplace=True) #df_trips = df_trips[~df_trips["origin_commune_id"].isin(["aaaaa"]) | ~df_trips["destination_commune_id"].isin(["aaaaa"])] df_trips = df_trips[~df_trips["origin_commune_id"].isin(["aaaaa"])] df_trips = df_trips[~df_trips["destination_commune_id"].isin(["aaaaa"])] # Clean employment df_persons["employed"] = df_persons["P9"].isin([1, 2, 3] )##1: temps plein, 2: temps partiel et 3: apprentit, # stage, formation # Studies df_persons["studies"] = df_persons["P9"].isin([4, 5] )##4:etudiant 5: scolaire jusqu'au BAC # 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") # Socioprofessional class df_persons["socioprofessional_class"] = df_persons["PCSD"].fillna(00).astype(int) # Number of vehicles df_households["number_of_vehicles"] = df_households["M6"] + df_households["M14" ]##M6: Voiture particulière # M14: Nbre de 2/3 roues motorisées df_households["number_of_vehicles"] = df_households["number_of_vehicles"].astype(np.int) df_households["number_of_bikes"] = df_households["M21"].astype(np.int) # License df_persons["has_license"] = df_persons["P7"] == 1 # Car availability df_persons = pd.merge(
def execute(context):
df_individu, df_tcm_individu, df_menage, df_tcm_menage, df_deploc, df_comm = context.stage(
"data.hts.entd.raw")
# Make copies
df_persons = pd.DataFrame(df_tcm_individu, copy=True)
df_households = pd.DataFrame(df_tcm_menage, copy=True)
df_trips = pd.DataFrame(df_deploc, copy=True)
# Get weights for persons that actually have trips
df_persons = pd.merge(df_persons,
df_trips[["IDENT_IND",
"PONDKI"]].drop_duplicates("IDENT_IND"),
on="IDENT_IND",
how="left")
df_persons["is_kish"] = ~df_persons["PONDKI"].isna()
df_persons["trip_weight"] = df_persons["PONDKI"].fillna(0.0)
# Important: If someone did not have any trips on the reference day, ENTD asked
# for another day. With this flag we make sure that we only cover "reference days".
f = df_trips["V2_MOBILREF"] == 1
df_trips = df_trips[f]
print("Filtering out %d non-reference day trips" % np.count_nonzero(~f))
# Merge in additional information from ENTD
df_households = pd.merge(df_households,
df_menage[[
"idENT_MEN", "V1_JNBVEH", "V1_JNBMOTO",
"V1_JNBCYCLO", "V1_JNBVELOADT"
]],
on="idENT_MEN",
how="left")
df_persons = pd.merge(df_persons,
df_individu[[
"IDENT_IND", "V1_GPERMIS", "V1_GPERMIS2R",
"V1_ICARTABON"
]],
on="IDENT_IND",
how="left")
# Transform original IDs to integer (they are hierarchichal)
df_persons["entd_person_id"] = df_persons["IDENT_IND"].astype(np.int)
df_persons["entd_household_id"] = df_persons["IDENT_MEN"].astype(np.int)
df_households["entd_household_id"] = df_households["idENT_MEN"].astype(
np.int)
df_trips["entd_person_id"] = df_trips["IDENT_IND"].astype(np.int)
# Construct new IDs for households, persons and trips (which are unique globally)
df_households["household_id"] = np.arange(len(df_households))
df_persons = pd.merge(df_persons,
df_households[["entd_household_id", "household_id"]],
on="entd_household_id")
df_persons["person_id"] = np.arange(len(df_persons))
df_trips = pd.merge(
df_trips,
df_persons[["entd_person_id", "person_id", "household_id"]],
on=["entd_person_id"])
df_trips["trip_id"] = np.arange(len(df_trips))
# Weight
df_persons["person_weight"] = df_persons["PONDV1"].astype(np.float)
df_households["household_weight"] = df_households["PONDV1"].astype(
np.float)
# Clean age
df_persons.loc[:, "age"] = df_persons["AGE"]
# Clean sex
df_persons.loc[df_persons["SEXE"] == 1, "sex"] = "male"
df_persons.loc[df_persons["SEXE"] == 2, "sex"] = "female"
df_persons["sex"] = df_persons["sex"].astype("category")
# Household size
df_households["household_size"] = df_households["NPERS"]
# Clean departement
df_households["departement_id"] = pd.to_numeric(
df_households["DEP"], errors="coerce").fillna(-1).astype(np.int)
df_persons["departement_id"] = pd.to_numeric(
df_persons["DEP"], errors="coerce").fillna(-1).astype(np.int)
df_trips["origin_departement_id"] = pd.to_numeric(
df_trips["V2_MORIDEP"], errors="coerce").fillna(-1).astype(np.int)
df_trips["destination_departement_id"] = pd.to_numeric(
df_trips["V2_MDESDEP"], errors="coerce").fillna(-1).astype(np.int)
# Clean employment
df_persons["employed"] = df_persons["SITUA"].isin([1, 2])
# Studies
# Many < 14 year old have NaN
df_persons["studies"] = df_persons["ETUDES"].fillna(1) == 1
# 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["V1_JNBAUTVEH"]
#df_households["number_of_vehicles"] += df_households["V1_JNBCCVUL"]
df_households["number_of_vehicles"] = df_households[
"number_of_vehicles"].astype(np.int)
df_households["number_of_bikes"] = df_households["V1_JNBVELOADT"].fillna(
0).astype(np.int)
# License
df_persons["has_license"] = (df_persons["V1_GPERMIS"]
== 1) | (df_persons["V1_GPERMIS2R"] == 1)
# Has subscription
df_persons["has_pt_subscription"] = df_persons["V1_ICARTABON"] == 1
# Household income
df_households["income_class"] = -1
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("Moins de 400"),
"income_class"] = 0
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 400"),
"income_class"] = 1
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 600"),
"income_class"] = 2
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 800"),
"income_class"] = 3
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 1 000"),
"income_class"] = 4
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 1 200"),
"income_class"] = 5
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 1 500"),
"income_class"] = 6
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 1 800"),
"income_class"] = 7
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 2 000"),
"income_class"] = 8
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 2 500"),
"income_class"] = 9
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 3 000"),
"income_class"] = 10
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 4 000"),
"income_class"] = 11
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("De 6 000"),
"income_class"] = 12
df_households.loc[
df_households["TrancheRevenuMensuel"].str.startswith("10 000"),
"income_class"] = 13
df_households["income_class"] = df_households["income_class"].astype(
np.int)
# Trip purpose
df_trips["following_purpose"] = "other"
df_trips["preceeding_purpose"] = "other"
for prefix, activity_type in PURPOSE_MAP:
df_trips.loc[
df_trips["V2_MMOTIFDES"].astype(np.str).str.startswith(prefix),
"following_purpose"] = activity_type
df_trips.loc[
df_trips["V2_MMOTIFORI"].astype(np.str).str.startswith(prefix),
"preceeding_purpose"] = activity_type
df_trips["following_purpose"] = df_trips["following_purpose"].astype(
"category")
df_trips["preceeding_purpose"] = df_trips["preceeding_purpose"].astype(
"category")
# Trip mode
df_trips["mode"] = "pt"
for prefix, mode in MODES_MAP:
df_trips.loc[df_trips["V2_MTP"].astype(np.str).str.startswith(prefix),
"mode"] = mode
df_trips["mode"] = df_trips["mode"].astype("category")
# Further trip attributes
df_trips["routed_distance"] = df_trips["V2_MDISTTOT"] * 1000.0
df_trips["routed_distance"] = df_trips["routed_distance"].fillna(
0.0) # This should be just one within Île-de-France
# Only leave weekday trips
f = df_trips["V2_TYPJOUR"] == 1
print("Removing %d trips on weekends" % np.count_nonzero(~f))
df_trips = df_trips[f]
# Only leave one day per person
initial_count = len(df_trips)
df_first_day = df_trips[[
"person_id", "IDENT_JOUR"
]].sort_values(by=["person_id", "IDENT_JOUR"]).drop_duplicates("person_id")
df_trips = pd.merge(df_trips,
df_first_day,
how="inner",
on=["person_id", "IDENT_JOUR"])
final_count = len(df_trips)
print("Removed %d trips for non-primary days" %
(initial_count - final_count))
# Trip flags
df_trips = hts.compute_first_last(df_trips)
# Trip times
df_trips["departure_time"] = df_trips["V2_MORIHDEP"].apply(
convert_time).astype(np.float)
df_trips["arrival_time"] = df_trips["V2_MDESHARR"].apply(
convert_time).astype(np.float)
df_trips = hts.fix_trip_times(df_trips)
# Durations
df_trips["trip_duration"] = df_trips["arrival_time"] - df_trips[
"departure_time"]
hts.compute_activity_duration(df_trips)
# Add weight to trips
df_trips["trip_weight"] = df_trips["PONDKI"]
# Chain length
df_persons = pd.merge(df_persons,
df_trips[["person_id", "NDEP"
]].drop_duplicates("person_id").rename(
columns={"NDEP": "number_of_trips"}),
on="person_id",
how="left")
df_persons["number_of_trips"] = df_persons["number_of_trips"].fillna(
-1).astype(np.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")
# Socioprofessional class
df_persons["socioprofessional_class"] = df_persons["CS24"].fillna(
80).astype(int) // 10
return df_households, df_persons, df_trips
def execute(context):
df_households, df_persons, df_trips = context.stage("data.hts.egt.raw")
# Make copies
df_households = pd.DataFrame(df_households, copy=True)
df_persons = pd.DataFrame(df_persons, copy=True)
df_trips = pd.DataFrame(df_trips, copy=True)
# Transform original IDs to integer (they are hierarchichal)
df_households["egt_household_id"] = df_households["NQUEST"].astype(np.int)
df_persons["egt_person_id"] = df_persons["NP"].astype(np.int)
df_persons["egt_household_id"] = df_persons["NQUEST"].astype(np.int)
df_trips["egt_person_id"] = df_trips["NP"].astype(np.int)
df_trips["egt_household_id"] = df_trips["NQUEST"].astype(np.int)
df_trips["egt_trip_id"] = df_trips["ND"].astype(np.int)
# Construct new IDs for households, persons and trips (which are unique globally)
df_households["household_id"] = np.arange(len(df_households))
df_persons = pd.merge(df_persons,
df_households[["egt_household_id", "household_id"]],
on="egt_household_id")
df_persons["person_id"] = np.arange(len(df_persons))
df_trips = pd.merge(df_trips,
df_persons[[
"egt_person_id", "egt_household_id", "person_id",
"household_id"
]],
on=["egt_person_id", "egt_household_id"])
df_trips["trip_id"] = np.arange(len(df_trips))
# Trip flags
df_trips = hts.compute_first_last(df_trips)
# Weight
df_persons["person_weight"] = df_persons["POIDSP"].astype(np.float)
df_households["household_weight"] = df_households["POIDSM"].astype(
np.float)
# Clean age
df_persons["age"] = df_persons["AGE"].astype(np.int)
# Clean sex
df_persons.loc[df_persons["SEXE"] == 1, "sex"] = "male"
df_persons.loc[df_persons["SEXE"] == 2, "sex"] = "female"
df_persons["sex"] = df_persons["sex"].astype("category")
# Household size
df_households["household_size"] = df_households["MNP"].astype(np.int)
# Clean departement
df_persons["departement_id"] = df_persons["RESDEP"].astype(str).astype(
"category")
df_households["departement_id"] = df_households["RESDEP"].astype(
str).astype("category")
df_trips["origin_departement_id"] = df_trips["ORDEP"].astype(str).astype(
"category")
df_trips["destination_departement_id"] = df_trips["DESTDEP"].astype(
str).astype("category")
# Clean employment
df_persons["employed"] = df_persons["OCCP"].isin([1.0, 2.0])
# Studies
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(np.int)
df_households["number_of_bikes"] = df_households["NB_VELO"].astype(np.int)
# License
df_persons["has_license"] = (df_persons["PERMVP"]
== 1) | (df_persons["PERM2RM"] == 1)
# Has subscription
df_persons["has_pt_subscription"] = df_persons["ABONTC"] > 1
# Household income
df_households["income_class"] = df_households["REVENU"] - 1
df_households.loc[df_households["income_class"].isin([10.0, 11.0, np.nan]),
"income_class"] = -1
df_households["income_class"] = df_households["income_class"].astype(
np.int)
# Trip purpose
df_trips["following_purpose"] = "other"
df_trips["preceding_purpose"] = "other"
for category, purpose in PURPOSE_MAP.items():
df_trips.loc[df_trips["DESTMOT_H9"] == category,
"following_purpose"] = purpose
df_trips.loc[df_trips["ORMOT_H9"] == category,
"preceding_purpose"] = purpose
df_trips["following_purpose"] = df_trips["following_purpose"].astype(
"category")
df_trips["preceding_purpose"] = df_trips["preceding_purpose"].astype(
"category")
# Trip mode
df_trips["mode"] = "pt"
for category, mode in MODES_MAP.items():
df_trips.loc[df_trips["MODP_H7"] == category, "mode"] = mode
df_trips["mode"] = df_trips["mode"].astype("category")
# Further trip attributes
df_trips["euclidean_distance"] = df_trips["DPORTEE"] * 1000.0
# Trip times
df_trips[
"departure_time"] = df_trips["ORH"] * 3600.0 + df_trips["ORM"] * 60.0
df_trips[
"arrival_time"] = df_trips["DESTH"] * 3600.0 + df_trips["DESTM"] * 60.0
df_trips = hts.fix_trip_times(df_trips)
# Durations
df_trips["trip_duration"] = df_trips["arrival_time"] - df_trips[
"departure_time"]
hts.compute_activity_duration(df_trips)
# Add weight to trips
df_trips = pd.merge(
df_trips,
df_persons[["person_id", "person_weight"]],
on="person_id",
how="left").rename(columns={"person_weight": "trip_weight"})
df_persons["trip_weight"] = df_persons["person_weight"]
# Chain length
df_persons["number_of_trips"] = df_persons["NBDEPL"].fillna(0).astype(
np.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")
# Socioprofessional class
df_persons["socioprofessional_class"] = df_persons["CS8"].fillna(8).astype(
int)
# Drop people that have NaN departure or arrival times in trips
# Filter for people with NaN departure or arrival times in trips
f = df_trips["departure_time"].isna()
f |= df_trips["arrival_time"].isna()
f = df_persons["person_id"].isin(df_trips[f]["person_id"])
nan_count = np.count_nonzero(f)
total_count = len(df_persons)
print(
"Dropping %d/%d persons because of NaN values in departure and arrival times"
% (nan_count, total_count))
df_persons = df_persons[~f]
df_trips = df_trips[df_trips["person_id"].isin(
df_persons["person_id"].unique())]
df_households = df_households[df_households["household_id"].isin(
df_persons["household_id"])]
# Fix activity types (because of inconsistent EGT data and removing in the timing fixing step)
hts.fix_activity_types(df_trips)
return df_households, df_persons, df_trips
def execute(context):
df_households, df_persons, df_trips = context.stage("data.hts.emc2.raw")
# Make copies
df_households = pd.DataFrame(df_households, copy=True)
df_persons = pd.DataFrame(df_persons, copy=True)
df_trips = pd.DataFrame(df_trips, copy=True)
df_households['ZFM'] = df_households['ZFM'].map(lambda x: int(x) // 100)
df_persons['ZFP'] = df_persons['ZFP'].map(lambda x: int(x) // 100)
df_trips['ZFD'] = df_trips['ZFD'].map(lambda x: int(x) // 100)
df_trips['D3'] = df_trips['D3'].map(lambda x: int(x // 100))
df_trips['D7'] = df_trips['D7'].map(lambda x: int(x // 100))
# Construct new IDs for households, persons and trips (which are unique globally)
df_households["household_id"] = np.arange(len(df_households))
df_persons = pd.merge(df_persons,
df_households[["MID", "household_id"]],
on="MID")
df_persons["person_id"] = np.arange(len(df_persons))
df_trips = pd.merge(df_trips,
df_persons[["PER", "MID", "person_id",
"household_id"]],
on=["PER", "MID"])
df_trips["trip_id"] = np.arange(len(df_trips))
# Trip flags
df_trips = hts.compute_first_last(df_trips)
# Weight
df_households["household_weight"] = df_households["COEM"]
df_persons["person_weight"] = df_persons["COE2"]
# Clean age
df_persons["age"] = df_persons["P4"].astype(np.int)
# Clean sex
df_persons.loc[df_persons["P2"] == 1, "sex"] = "male"
df_persons.loc[df_persons["P2"] == 2, "sex"] = "female"
df_persons["sex"] = df_persons["sex"].astype("category")
# Household size
df_households["household_size"] = df_persons.groupby("household_id").size()
# Clean commune
df_persons = df_persons.merge(
df_zone, left_on='ZFP', right_on='ZF',
how='left').rename(columns={'INSEE': 'commune_id'})
df_households = df_households.merge(
df_zone, left_on='ZFM', right_on='ZF',
how='left').rename(columns={'INSEE': 'commune_id'})
df_persons['commune_id'].fillna(0, inplace=True)
df_households['commune_id'].fillna(0, inplace=True)
df_trips = df_trips.merge(
df_zone, left_on='D3', right_on='ZF',
how='left').rename(columns={'INSEE': 'origin_commune_id'})
df_trips = df_trips.merge(
df_zone, left_on='D7', right_on='ZF',
how='left').rename(columns={'INSEE': 'destination_commune_id'})
df_trips['origin_commune_id'].fillna(0, inplace=True)
df_trips['destination_commune_id'].fillna(0, inplace=True)
df_persons["commune_id"] = df_persons["commune_id"].astype("category")
df_households["commune_id"] = df_households["commune_id"].astype(
"category")
df_trips["origin_commune_id"] = df_trips["origin_commune_id"].astype(
"category")
df_trips["destination_commune_id"] = df_trips[
"destination_commune_id"].astype("category")
# Clean departement
df_persons["departement_id"] = (
df_persons["commune_id"].astype(int) /
1000).astype(int).astype(str).astype("category")
df_households["departement_id"] = (
df_households["commune_id"].astype(int) /
1000).astype(int).astype(str).astype("category")
df_trips["origin_departement_id"] = (
df_trips["origin_commune_id"].astype(int) /
1000).astype(int).astype(str).astype("category")
df_trips["destination_departement_id"] = (
df_trips["destination_commune_id"].astype(int) /
1000).astype(int).astype(str).astype("category")
# Clean employment
df_persons["employed"] = df_persons["P9"].astype('Float32').isin(
[1.0, 2.0])
# Studies
df_persons["studies"] = df_persons["P9"].astype('Float32').isin(
[3.0, 4.0, 5.0])
# 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(np.int)
df_households["number_of_bikes"] = df_households["M21"].astype(np.int)
# License
df_persons["has_license"] = (df_persons["P7"] == 1)
# Has subscription
df_persons["has_pt_subscription"] = (df_persons["P12"] != 4)
# # Household income
# df_households["income_class"] = df_households["REVENU"] - 1
# df_households.loc[df_households["income_class"].isin([10.0, 11.0, np.nan]), "income_class"] = -1
# df_households["income_class"] = df_households["income_class"].astype(np.int)
df_households[
"income_class"] = 0 # np.random.randint(0, 10, size=(len(df_households), 1)).astype(int)
# Trip purpose
df_trips["following_purpose"] = "other"
df_trips["preceding_purpose"] = "other"
for purpose, category in PURPOSE_MAP.items():
df_trips.loc[df_trips["D2A"].isin(category),
"preceding_purpose"] = purpose
df_trips.loc[df_trips["D5A"].isin(category),
"following_purpose"] = purpose
df_trips["preceding_purpose"] = df_trips["preceding_purpose"].astype(
"category")
df_trips["following_purpose"] = df_trips["following_purpose"].astype(
"category")
# Trip mode
df_trips["mode"] = "walk"
for mode, category in MODES_MAP.items():
df_trips.loc[df_trips["MODP"].isin(category), "mode"] = mode
df_trips["mode"] = df_trips["mode"].astype("category")
# Further trip attributes
df_trips["euclidean_distance"] = df_trips["DOIB"]
# Trip times
df_trips["departure_time"] = df_trips["D4A"] * 3600 + df_trips["D4B"] * 60
df_trips["arrival_time"] = df_trips["D8A"] * 3600 + df_trips["D8B"] * 60
df_trips = hts.fix_trip_times(df_trips)
# Durations
df_trips["trip_duration"] = df_trips["arrival_time"] - df_trips[
"departure_time"]
hts.compute_activity_duration(df_trips)
# Add weight to trips
df_trips = pd.merge(
df_trips,
df_persons[["person_id", "person_weight"]],
on="person_id",
how="left").rename(columns={"person_weight": "trip_weight"})
df_persons["trip_weight"] = df_persons["person_weight"]
# Chain length
df_persons["number_of_trips"] = df_trips.groupby("person_id").size()
# 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")
# Socioprofessional class
df_persons["socioprofessional_class"] = df_persons["P11"].fillna(8).astype(
int)
df_persons.loc[df_persons["socioprofessional_class"].isin([7, 8, 9]),
"socioprofessional_class"] = 8
df_persons.loc[df_persons["P9"] == 7, "socioprofessional_class"] = 7
# Drop people that have NaN departure or arrival times in trips
# Filter for people with NaN departure or arrival times in trips
f = df_trips["departure_time"].isna()
f |= df_trips["arrival_time"].isna()
f = df_persons["person_id"].isin(df_trips[f]["person_id"])
nan_count = np.count_nonzero(f)
total_count = len(df_persons)
print(
"Dropping %d/%d persons because of NaN values in departure and arrival times"
% (nan_count, total_count))
df_persons = df_persons[~f]
df_trips = df_trips[df_trips["person_id"].isin(
df_persons["person_id"].unique())]
df_households = df_households[df_households["household_id"].isin(
df_persons["household_id"])]
# Fix activity types (because of inconsistent EGT data and removing in the timing fixing step)
hts.fix_activity_types(df_trips)
return df_households, df_persons, df_trips
def execute(context):
df = pd.read_hdf("%s/census.hdf" % context.path("data.census.raw"))
# Construct household IDs for persons with NUMMI != Z
df_household_ids = df[["CANTVILLE", "NUMMI"]]
df_household_ids = df_household_ids[df_household_ids["NUMMI"] != "Z"]
df_household_ids["temporary"] = df_household_ids[
"CANTVILLE"] + df_household_ids["NUMMI"]
df_household_ids = df_household_ids.drop_duplicates("temporary")
df_household_ids["household_id"] = np.arange(len(df_household_ids))
df = pd.merge(df, df_household_ids, on=["CANTVILLE", "NUMMI"], how="left")
# Fill up undefined household ids (those where NUMMI == Z)
f = np.isnan(df["household_id"])
df.loc[f, "household_id"] = np.arange(
np.count_nonzero(f)) + df["household_id"].max()
df["household_id"] = df["household_id"].astype(np.int)
# Put person IDs
df["person_id"] = np.arange(len(df))
# Sorting
df = df.sort_values(by=["household_id", "person_id"])
# Spatial information
df["departement_id"] = df["DEPT"].astype("category")
df["commune_id"] = df["IRIS"].str[:5]
f_undefined = df["commune_id"].str.contains("Z")
df.loc[f_undefined, "commune_id"] = "undefined"
df["commune_id"] = df["commune_id"].astype("category")
df["iris_id"] = df["IRIS"]
f_undefined = df["iris_id"].str.contains("Z") | df["iris_id"].str.contains(
"X")
df.loc[f_undefined, "iris_id"] = "undefined"
df["iris_id"] = df["iris_id"].astype("category")
# Verify with requested codes
df_codes = context.stage("data.spatial.codes")
excess_communes = set(df["commune_id"].unique()) - set(
df_codes["commune_id"].unique())
if not excess_communes == {"undefined"}:
raise RuntimeError("Found additional communes: %s" % excess_communes)
excess_iris = set(df["iris_id"].unique()) - set(
df_codes["iris_id"].unique())
if not excess_iris == {"undefined"}:
raise RuntimeError("Found additional IRIS: %s" % excess_iris)
# Age
df["age"] = df["AGED"].apply(
lambda x: "0" if x == "000" else x.lstrip("0")).astype(np.int)
# Clean COUPLE
df["couple"] = df["COUPLE"] == "1"
# 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"] == "4", "commute_mode"] = "car"
df.loc[df["TRANS"] == "5", "commute_mode"] = "pt"
df.loc[df["TRANS"] == "Z", "commute_mode"] = np.nan
df["commute_mode"] = df["commute_mode"].astype("category")
# Weight
df["weight"] = df["IPONDI"].astype(np.float)
# Clean SEXE
df.loc[df["SEXE"] == "1", "sex"] = "male"
df.loc[df["SEXE"] == "2", "sex"] = "female"
df["sex"] = df["sex"].astype("category")
# Clean employment
df["employed"] = df["TACT"] == "11"
# Studies
df["studies"] = df["ETUD"] == "1"
# Number of vehicles
df["number_of_vehicles"] = df["VOIT"].apply(
lambda x: str(x).replace("Z", "0").replace("X", "0")).astype(np.int)
df["number_of_vehicles"] += df["DEROU"].apply(lambda x: str(x).replace(
"U", "0").replace("Z", "0").replace("X", "0")).astype(np.int)
# Household size
df_size = df[[
"household_id"
]].groupby("household_id").size().reset_index(name="household_size")
df = pd.merge(df, df_size)
# Socioprofessional category
df["socioprofessional_class"] = df["CS1"].astype(np.int)
# Place of work or education
df["work_outside_region"] = df["ILT"].isin(("4", "5", "6"))
df["education_outside_region"] = df["ILETUD"].isin(("4", "5", "6"))
# Consumption units
df = pd.merge(df, hts.calculate_consumption_units(df), on="household_id")
return df[[
"person_id", "household_id", "weight", "iris_id", "commune_id",
"departement_id", "age", "sex", "couple", "commute_mode", "employed",
"studies", "number_of_vehicles", "household_size",
"work_outside_region", "education_outside_region", "consumption_units",
"socioprofessional_class"
]]
def execute(context):
df_households, df_persons, df_trips, df_spatial = context.stage(
"data.hts.edgt_lyon.raw_cerema")
# Merge departement into households
df_spatial = df_spatial[["ZF__2015", "DepCom"]].copy()
df_spatial["MP2"] = df_spatial["ZF__2015"].astype(str)
df_spatial["departement_id"] = df_spatial["DepCom"].str[:2]
df_spatial = df_spatial[["MP2", "departement_id"]]
# Attention, some households get lost here!
df_households = pd.merge(df_households, df_spatial, on="MP2", how="left")
df_households["departement_id"] = df_households["departement_id"].fillna(
"unknown")
# Transform original IDs to integer (they are hierarchichal)
df_households["edgt_household_id"] = (df_households["ECH"] +
df_households["MP2"]).astype(int)
df_persons["edgt_person_id"] = df_persons["PER"].astype(np.int)
df_persons["edgt_household_id"] = (df_persons["ECH"] +
df_persons["PP2"]).astype(int)
df_trips["edgt_person_id"] = df_trips["PER"].astype(np.int)
df_trips["edgt_household_id"] = (df_trips["ECH"] +
df_trips["DP2"]).astype(int)
df_trips["edgt_trip_id"] = df_trips["NDEP"].astype(np.int)
# Construct new IDs for households, persons and trips (which are unique globally)
df_households["household_id"] = np.arange(len(df_households))
df_persons = pd.merge(
df_persons,
df_households[["edgt_household_id", "household_id", "departement_id"]],
on=["edgt_household_id"
]).sort_values(by=["household_id", "edgt_person_id"])
df_persons["person_id"] = np.arange(len(df_persons))
df_trips = pd.merge(
df_trips,
df_persons[[
"edgt_person_id", "edgt_household_id", "person_id", "household_id"
]],
on=["edgt_person_id", "edgt_household_id"
]).sort_values(by=["household_id", "person_id", "edgt_trip_id"])
df_trips["trip_id"] = np.arange(len(df_trips))
# Trip flags
df_trips = hts.compute_first_last(df_trips)
# Weight
df_persons["person_weight"] = df_persons["COEP"].astype(np.float)
df_households["household_weight"] = df_households["COEM"].astype(np.float)
# Clean age
df_persons["age"] = df_persons["P4"].astype(np.int)
# Clean sex
df_persons.loc[df_persons["P2"] == 1, "sex"] = "male"
df_persons.loc[df_persons["P2"] == 2, "sex"] = "female"
df_persons["sex"] = df_persons["sex"].astype("category")
# Household size
df_size = df_persons.groupby("household_id").size().reset_index(
name="household_size")
df_households = pd.merge(df_households, df_size, on="household_id")
# Clean departement
df_trips = pd.merge(
df_trips,
df_spatial.rename(columns={
"MP2": "D3",
"departement_id": "origin_departement_id"
}),
on="D3",
how="left")
df_trips = pd.merge(
df_trips,
df_spatial.rename(columns={
"MP2": "D7",
"departement_id": "destination_departement_id"
}),
on="D7",
how="left")
df_trips["origin_departement_id"] = df_trips[
"origin_departement_id"].fillna("unknown")
df_trips["destination_departement_id"] = df_trips[
"destination_departement_id"].fillna("unknown")
df_households["departement_id"] = df_households["departement_id"].astype(
"category")
df_persons["departement_id"] = df_persons["departement_id"].astype(
"category")
df_trips["origin_departement_id"] = df_trips[
"origin_departement_id"].astype("category")
df_trips["destination_departement_id"] = df_trips[
"destination_departement_id"].astype("category")
# Clean employment
df_persons["employed"] = df_persons["P7"].isin(["1", "2"])
# Studies
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(np.int)
df_households["number_of_bikes"] = df_households["M7"].astype(np.int)
# License
df_persons["has_license"] = df_persons["P5"] == "1"
# Has subscription
df_persons["has_pt_subscription"] = df_persons["P10"].isin(["1", "2", "3"])
# Trip purpose
df_trips["following_purpose"] = "invalid"
df_trips["preceding_purpose"] = "invalid"
for purpose, values in PURPOSE_MAP.items():
df_trips.loc[df_trips["D5A"].isin(values),
"following_purpose"] = purpose
df_trips.loc[df_trips["D2A"].isin(values),
"preceding_purpose"] = purpose
assert np.count_nonzero(df_trips["following_purpose"] == "invalid") == 0
assert np.count_nonzero(df_trips["preceding_purpose"] == "invalid") == 0
df_trips["following_purpose"] = df_trips["following_purpose"].astype(
"category")
df_trips["preceding_purpose"] = df_trips["preceding_purpose"].astype(
"category")
# Trip mode
for mode, values in MODES_MAP.items():
df_trips.loc[df_trips["MODP"].isin(values), "mode"] = mode
assert np.count_nonzero(df_trips["following_purpose"] == "invalid") == 0
df_trips["mode"] = df_trips["mode"].astype("category")
# Further trip attributes
df_trips["euclidean_distance"] = df_trips["DOIB"]
df_trips["routed_distance"] = df_trips["DIST"]
# Trip times
df_trips["departure_time"] = 3600.0 * (df_trips["D4"] // 100) # hour
df_trips["departure_time"] += 60.0 * (df_trips["D4"] % 100) # minute
df_trips["arrival_time"] = 3600.0 * (df_trips["D8"] // 100) # hour
df_trips["arrival_time"] += 60.0 * (df_trips["D8"] % 100) # minute
df_trips = df_trips.sort_values(
by=["household_id", "person_id", "trip_id"])
df_trips = hts.fix_trip_times(df_trips)
# Durations
df_trips["trip_duration"] = df_trips["arrival_time"] - df_trips[
"departure_time"]
hts.compute_activity_duration(df_trips)
# Add weight to trips
df_trips = pd.merge(df_trips,
df_persons[["person_id", "COEQ"]],
on="person_id",
how="left").rename(columns={"COEQ": "trip_weight"})
df_persons["trip_weight"] = df_persons["COEQ"]
# Chain length
df_count = df_trips[[
"person_id"
]].groupby("person_id").size().reset_index(name="number_of_trips")
df_persons = pd.merge(df_persons, df_count, on="person_id", how="left")
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")
# Socioprofessional class
df_persons["socioprofessional_class"] = df_persons["P9"].fillna(8).astype(
int)
# Check departure and arrival times
assert np.count_nonzero(df_trips["departure_time"].isna()) == 0
assert np.count_nonzero(df_trips["arrival_time"].isna()) == 0
# Fix activity types (because of inconsistent EGT data and removing in the timing fixing step)
hts.fix_activity_types(df_trips)
return df_households, df_persons, df_trips
