def _trackintel_model(gdf, set_names=None, geom_col=None, crs=None, tz_cols=None, tz=None):
"""Help function to assure the trackintel model on a GeoDataFrame.
Parameters
----------
gdf : GeoDataFrame
Input GeoDataFrame
set_names : dict, optional
Renaming dictionary for the columns of the GeoDataFrame.
set_geometry : str, optional
Set geometry of GeoDataFrame.
crs : pyproj.crs or str, optional
Set coordinate reference system. The value can be anything accepted
by pyproj.CRS.from_user_input(), such as an authority string
(eg "EPSG:4326") or a WKT string.
tz_cols : list, optional
List of timezone aware datetime columns.
tz : str, optional
pytz compatible timezone string. If None UTC will be assumed
Returns
-------
gdf : GeoDataFrame
The input GeoDataFrame transformed to match the trackintel format.
"""
if set_names is not None:
gdf = gdf.rename(columns=set_names)
if tz_cols is not None:
for col in tz_cols:
if not pd.api.types.is_datetime64tz_dtype(gdf[col]):
try:
gdf[col] = _localize_timestamp(dt_series=gdf[col], pytz_tzinfo=tz, col_name=col)
except ValueError:
# Taken if column contains datetimes with different timezone informations.
# Cast them to UTC in this case.
gdf[col] = pd.to_datetime(gdf[col], utc=True)
# If is not GeoDataFrame and no geom_col is set end early.
# That allows us to handle DataFrames and GeoDataFrames in one function.
if not isinstance(gdf, gpd.GeoDataFrame) and geom_col is None:
return gdf
if geom_col is not None:
gdf = gdf.set_geometry(geom_col)
else:
try:
gdf.geometry
except AttributeError:
raise AttributeError("GeoDataFrame has no geometry, set it with keyword argument.")
if crs is not None:
gdf = gdf.set_crs(crs)
return gdf
def read_positionfixes_gpd(gdf,
tracked_at="tracked_at",
user_id="user_id",
geom="geom",
tz=None,
mapper={}):
"""
Read positionfixes from GeoDataFrames.
Warps the pd.rename function to simplify the import of GeoDataFrames.
Parameters
----------
gdf : GeoDataFrame
GeoDataFrame with valid point geometry, containing the positionfixes to import
tracked_at : str, default 'tracked_at'
name of the column storing the timestamps.
user_id : str, default 'user_id'
name of the column storing the user_id.
geom : str, default 'geom'
name of the column storing the geometry.
tz : str, optional
pytz compatible timezone string. If None UTC will be assumed
mapper : dict, optional
further columns that should be renamed.
Returns
-------
pfs : GeoDataFrame (as trackintel positionfixes)
A GeoDataFrame containing the positionfixes.
Examples
--------
>>> trackintel.read_positionfixes_gpd(gdf, user_id='User', geom='geometry', tz='utc')
"""
columns = {tracked_at: "tracked_at", user_id: "user_id", geom: "geom"}
columns.update(mapper)
pfs = gdf.rename(columns=columns)
pfs = pfs.set_geometry("geom")
# check and/or set timezone
for col in ["tracked_at"]:
if not pd.api.types.is_datetime64tz_dtype(pfs[col]):
pfs[col] = _localize_timestamp(dt_series=pfs[col],
pytz_tzinfo=tz,
col_name=col)
# assert validity of positionfixes
pfs.as_positionfixes
return pfs
def read_staypoints_gpd(gdf,
started_at="started_at",
finished_at="finished_at",
user_id="user_id",
geom="geom",
tz=None,
mapper={}):
"""
Read staypoints from GeoDataFrames.
Warps the pd.rename function to simplify the import of GeoDataFrames.
Parameters
----------
gdf : GeoDataFrame
GeoDataFrame with valid point geometry, containing the staypoints to import
started_at : str, default 'started_at'
name of the column storing the starttime of the staypoints.
finished_at : str, default 'finished_at'
name of the column storing the endtime of the staypoints.
user_id : str, default 'user_id'
name of the column storing the user_id.
geom : str, default 'geom'
name of the column storing the geometry.
tz : str, optional
pytz compatible timezone string. If None UTC is assumed.
mapper : dict, optional
further columns that should be renamed.
Returns
-------
stps : GeoDataFrame (as trackintel staypoints)
A GeoDataFrame containing the staypoints
Examples
--------
>>> trackintel.read_staypoints_gpd(gdf, started_at='start_time', finished_at='end_time', tz='utc')
"""
columns = {
started_at: "started_at",
finished_at: "finished_at",
user_id: "user_id",
geom: "geom"
}
columns.update(mapper)
stps = gdf.rename(columns=columns)
stps = stps.set_geometry("geom")
# check and/or set timezone
for col in ["started_at", "finished_at"]:
if not pd.api.types.is_datetime64tz_dtype(stps[col]):
stps[col] = _localize_timestamp(dt_series=stps[col],
pytz_tzinfo=tz,
col_name=col)
# assert validity of staypoints
stps.as_staypoints
return stps
def read_trips_gpd(
gdf,
started_at="started_at",
finished_at="finished_at",
user_id="user_id",
origin_staypoint_id="origin_staypoint_id",
destination_staypoint_id="destination_staypoint_id",
tz=None,
mapper={},
):
"""
Read trips from GeoDataFrames/DataFrames.
Warps the pd.rename function to simplify the import of GeoDataFrames (DataFrames).
Parameters
----------
gdf : GeoDataFrame or DataFrame
GeoDataFrame/DataFrame containing the trips to import.
started_at : str, default 'started_at'
name of the column storing the starttime of the staypoints.
finished_at : str, default 'finished_at'
name of the column storing the endtime of the staypoints.
user_id : str, default 'user_id'
name of the column storing the user_id.
origin_staypoint_id : str, default 'origin_staypoint_id'
name of the column storing the staypoint_id of the start of the tripleg
destination_staypoint_id : str, default 'destination_staypoint_id'
name of the column storing the staypoint_id of the end of the tripleg
tz : str, optional
pytz compatible timezone string. If None UTC is assumed.
mapper : dict, optional
further columns that should be renamed.
Returns
-------
trips : GeoDataFrame/DataFrame (as trackintel trips)
A GeoDataFrame/DataFrame containing the trips.
Examples
--------
>>> trackintel.read_trips_gpd(df, tz='utc')
"""
columns = {
started_at: "started_at",
finished_at: "finished_at",
user_id: "user_id",
origin_staypoint_id: "origin_staypoint_id",
destination_staypoint_id: "destination_staypoint_id",
}
columns.update(mapper)
trips = gdf.rename(columns=columns)
# check and/or set timezone
for col in ["started_at", "finished_at"]:
if not pd.api.types.is_datetime64tz_dtype(trips[col]):
trips[col] = _localize_timestamp(dt_series=trips[col],
pytz_tzinfo=tz,
col_name=col)
# assert validity of trips
trips.as_trips
return trips