def test_parquet(gp_point, gp_multipoint, gp_multiline, tmp_path):
# Build dataframe
n = min(len(gp_multipoint), len(gp_multiline))
df = GeoDataFrame({
'point': GeoSeries(gp_point[:n]),
'multipoint': GeoSeries(gp_multipoint[:n]),
'multiline': GeoSeries(gp_multiline[:n]),
'a': list(range(n))
})
path = tmp_path / 'df.parq'
to_parquet(df, path)
df_read = read_parquet(path)
assert isinstance(df_read, GeoDataFrame)
assert all(df == df_read)
def test_parquet_columns(gp_point, gp_multipoint, gp_multiline, tmp_path):
# Build dataframe
n = min(len(gp_multipoint), len(gp_multiline))
df = GeoDataFrame({
'point': GeoSeries(gp_point[:n]),
'multipoint': GeoSeries(gp_multipoint[:n]),
'multiline': GeoSeries(gp_multiline[:n]),
'a': list(range(n))
})
path = tmp_path / 'df.parq'
to_parquet(df, path)
columns = ['a', 'multiline']
df_read = read_parquet(str(path), columns=columns)
assert isinstance(df_read, GeoDataFrame)
pd.testing.assert_frame_equal(df[columns], df_read)
def test_parquet(gp_point, gp_multipoint, gp_multiline, tmp_path):
# Build dataframe
n = min(len(gp_multipoint), len(gp_multiline))
df = GeoDataFrame({
'point': GeoSeries(gp_point[:n]),
'multipoint': GeoSeries(gp_multipoint[:n]),
'multiline': GeoSeries(gp_multiline[:n]),
'a': list(range(n))
})
df.index.name = 'range_idx'
path = tmp_path / 'df.parq'
to_parquet(df, path)
df_read = read_parquet(str(path),
columns=['point', 'multipoint', 'multiline', 'a'])
assert isinstance(df_read, GeoDataFrame)
pd.testing.assert_frame_equal(df, df_read)
assert df_read.index.name == df.index.name
def split_device_trajectories(
file: str,
output: str,
study: gpd.GeoDataFrame,
split_opts: Dict[str, Any],
min_length: float,
min_duration: float,
) -> None:
"""Split device trajectories."""
out = f"{output}/device_{file.split('.')[-2]}.parquet"
if exists(out):
return None
df = read_parquet(file)[[
"device_id", "latitude", "longitude", "timestamp"
]]
if len(df) < 2:
return None
tc = split_trajectories(df, **split_opts)
gdf = extract_traj_info(tc)
gdf = gdf[(gdf["length"] >= min_length)
& (gdf["duration"] >= min_duration)]
gdf = gpd.sjoin(gdf, study).drop(columns=["index_right"])
sdf = spd.GeoDataFrame(gdf)
to_parquet(sdf, out)