Coverage for .tox/p311/lib/python3.10/site-packages/scicom/historicalletters/utils.py: 100%
39 statements
« prev ^ index » next coverage.py v7.4.4, created at 2024-04-26 17:45 +0200
« prev ^ index » next coverage.py v7.4.4, created at 2024-04-26 17:45 +0200
1"""Utility functions for HistoricalLetters."""
2import random
4import geopandas as gpd
5import mesa
6import numpy as np
7import pandas as pd
8import shapely
9from shapely import LineString, contains
12def createData(population: int, populationDistribution: str) -> gpd.GeoDataFrame:
13 """Create random coordinates of historically motivated choices.
15 The routine samples a population sample based on estimated
16 population density of that coordinate.
18 The original CSV dataset is retrieved from
19 https://doi.org/10.1371/journal.pone.0162678.s003
20 """
21 initial_population_choices = pd.read_csv(
22 populationDistribution,
23 encoding="latin1", index_col=0,
24 )
26 # Calculate relative population ratio to estimated settlement area.
27 # This will correspont to the probabilities to draw an agent from
28 # these coordinates.
29 relPop = []
31 for _, row in initial_population_choices.iterrows():
32 relPop.append(
33 row["Area"] / row["Pop"],
34 )
36 initial_population_choices.insert(0, "relPop", relPop)
38 # Four costal cities can not be considered, since the modern NUTS regions
39 # give zero overlap to their coordinates, leading to potential errors when
40 # agents move.
41 excludeCoastal = ["Great Yarmouth", "Kingston-upon-Hull", "Calais", "Toulon"]
42 initial_population_choices = initial_population_choices.query("~Settlement.isin(@excludeCoastal)")
44 loc_probabilities = []
45 loc_values = []
46 for _, row in initial_population_choices.iterrows():
47 loc_probabilities.append(row["relPop"])
48 loc_values.append(
49 (row["longitude"], row["latitude"]),
50 )
52 coordinates = random.choices(
53 loc_values,
54 loc_probabilities,
55 k=population,
56 )
58 data = pd.DataFrame(
59 coordinates,
60 columns=["longitude", "latitude"],
61 )
63 data.insert(
64 0,
65 "unique_id",
66 [
67 "P" + str(x) for x in list(range(population))
68 ],
69 )
71 # Read the Geodataframe with EPSG:4326 projection.
72 geodf = gpd.GeoDataFrame(
73 data,
74 geometry=gpd.points_from_xy(data.longitude, data.latitude),
75 crs="EPSG:4326",
76 )
78 # Transform to EPSG:3857, since the NUTS shape files are in
79 # that projection.
80 return geodf.to_crs("EPSG:3857")
83def getRegion(geometry: shapely.geometry.point.Point, model:mesa.Model) -> str:
84 """Get region ID overlaping with input geometry.
86 Might e.g. fail if line of connection crosses international
87 waters, since there is no NUTS region assigned then.
88 """
89 regionID = [
90 x.unique_id for x in model.regions if contains(x.geometry, geometry)
91 ]
92 if regionID:
93 return regionID[0]
94 text = f"Can not find overlaping region to geometry {geometry}"
95 raise IndexError(text)
98def getPositionOnLine(start:shapely.Point, target:shapely.Point) -> shapely.Point:
99 """Interpolate movement along line between two given points.
101 The amount of moving from start to target is random.
102 """
103 segment = LineString([start, target])
104 return segment.interpolate(random.uniform(0.0, 1.0), normalized=True)
106def getNewTopic(start: tuple, target:tuple) -> tuple:
107 """Interpolate new topic between two topics.
109 The amount of moving from start to target is random.
110 """
111 p1 = np.array(start)
112 p2 = np.array(target)
113 p3 = p1 + random.uniform(0, 1) * (p2 -p1)
114 return tuple(p3)