Network analysis
The NetworkInspector provides tools for quickly analyzing the created network.
First, let us create an example network:
[1]:
import pop2net as p2n
env = p2n.Environment()
creator = p2n.Creator(env=env)
for _ in range(20):
actor = p2n.Actor()
actor.status = "pupil"
env.add_actor(actor)
for _ in range(4):
actor = p2n.Actor()
actor.status = "teacher"
env.add_actor(actor)
class School(p2n.LocationDesigner):
n_locations = 2
overcrowding = False
def weight(self, actor):
return 0.1
def stick_together(self, actor):
return actor.Classroom
class PupilsInClassroom(p2n.MeltLocationDesigner):
n_actors = 5
def filter(self, actor):
return actor.status == "pupil"
class TeacherInClassroom(p2n.MeltLocationDesigner):
n_actors = 1
def filter(self, actor):
return actor.status == "teacher"
class Classroom(p2n.LocationDesigner):
def melt(self):
return PupilsInClassroom, TeacherInClassroom
creator.create_locations(
location_designers=[
Classroom,
School,
]
)
[1]:
[<pop2net.creator.Location object at 0x0000012A35789550>,
<pop2net.creator.Location object at 0x0000012A35789A90>,
<pop2net.creator.Location object at 0x0000012A35789400>,
<pop2net.creator.Location object at 0x0000012A35789940>,
<pop2net.creator.Location object at 0x0000012A35789BE0>,
<pop2net.creator.Location object at 0x0000012A357897F0>]
In the following, we initialize an instance of the NetworkInspector and bind it to our model:
[2]:
inspector = p2n.NetworkInspector(env=env)
Network visualization
The method plot_bipartite_network() plots the biparte network. Actors are displayed as circles and locations are displayed as squares. Using the arguments actor_color and location_color, actor and location attributes can be displayed as colors in the plot. With the arguments actor_attrs and location_attrs you can add attributes that should be displayed in the tooltips for each node when you move the mouse pointer over it.
In the following example I display the actor attribute status as color and add id_p2n to the list of shown attribute values per actor node.
[3]:
inspector.plot_bipartite_network(actor_color="status", actor_attrs=["id_p2n"])
You may have noticed that the weight between nodes is automatically reflected in the alpha (transparency) of the edge connecting them.
Using plot_actor_network(), the actor-level network is shown:
[4]:
inspector.plot_actor_network(actor_color="status", actor_attrs=["id_p2n"])
Using plot_networks(), both network types are plotted:
[5]:
inspector.plot_networks(actor_color="status", actor_attrs=["id_p2n"])
Evaluate affiliations
Using eval_affiliations(), the number of locations per label, the number of actors per location and the number of locations per actor can be displayed:
[6]:
inspector.eval_affiliations()
______________________________________
Number of locations
______________________________________
count
location_label
Classroom 4
School 2
______________________________________
Number of actors per location
______________________________________
mean std min 25% 50% 75% max
location_label
Classroom 6.0 0.0 6.0 6.0 6.0 6.0 6.0
School 12.0 0.0 12.0 12.0 12.0 12.0 12.0
______________________________________
Number of affiliated locations per actor
______________________________________
n_affiliated_locations
mean 2.0
std 0.0
min 2.0
25% 2.0
50% 2.0
75% 2.0
max 2.0
Network measures
Using inspector.network_measures(), common network measures are calculated for the actor-level network. If there are unconnected components within the network, the network measures are calculated for each component.
[7]:
inspector.network_measures()
[7]:
[{'n_nodes': 12,
'diameter': 0.2,
'density': 1.0,
'transitivity': 1.0,
'avg_clustering': 0.3472381885547425,
'avg_path_length': 0.14545454545454548},
{'n_nodes': 12,
'diameter': 0.2,
'density': 1.0,
'transitivity': 1.0,
'avg_clustering': 0.3472381885547425,
'avg_path_length': 0.14545454545454548}]
Location information
The method
inspector.location_information() provides detailed information about the actors assigned to each location instance.You can specify which location types to include using the
location_labels argument, and which actor attributes to display using the actor_attributes argument.The output can be shown as a formatted table (default) or returned as a pandas DataFrame by setting
output_format="df".Below, we display the status and id of each actor in every Classroom and School location:
[14]:
inspector.location_information(
location_labels=["Classroom", "School"], actor_attributes=["status", "id_p2n"]
)
1.Location: Classroom
╒════╤══════════╤══════════╤═════════════════╕
│ │ status │ id_p2n │ location_type │
╞════╪══════════╪══════════╪═════════════════╡
│ 0 │ pupil │ 0 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 1 │ pupil │ 1 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 2 │ pupil │ 2 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 3 │ pupil │ 3 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 4 │ pupil │ 4 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 5 │ teacher │ 20 │ Classroom │
╘════╧══════════╧══════════╧═════════════════╛
2.Location: Classroom
╒════╤══════════╤══════════╤═════════════════╕
│ │ status │ id_p2n │ location_type │
╞════╪══════════╪══════════╪═════════════════╡
│ 0 │ pupil │ 5 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 1 │ pupil │ 6 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 2 │ pupil │ 7 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 3 │ pupil │ 8 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 4 │ pupil │ 9 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 5 │ teacher │ 21 │ Classroom │
╘════╧══════════╧══════════╧═════════════════╛
3.Location: Classroom
╒════╤══════════╤══════════╤═════════════════╕
│ │ status │ id_p2n │ location_type │
╞════╪══════════╪══════════╪═════════════════╡
│ 0 │ pupil │ 10 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 1 │ pupil │ 11 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 2 │ pupil │ 12 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 3 │ pupil │ 13 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 4 │ pupil │ 14 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 5 │ teacher │ 22 │ Classroom │
╘════╧══════════╧══════════╧═════════════════╛
4.Location: Classroom
╒════╤══════════╤══════════╤═════════════════╕
│ │ status │ id_p2n │ location_type │
╞════╪══════════╪══════════╪═════════════════╡
│ 0 │ pupil │ 15 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 1 │ pupil │ 16 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 2 │ pupil │ 17 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 3 │ pupil │ 18 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 4 │ pupil │ 19 │ Classroom │
├────┼──────────┼──────────┼─────────────────┤
│ 5 │ teacher │ 23 │ Classroom │
╘════╧══════════╧══════════╧═════════════════╛
5.Location: School
╒════╤══════════╤══════════╤═════════════════╕
│ │ status │ id_p2n │ location_type │
╞════╪══════════╪══════════╪═════════════════╡
│ 0 │ pupil │ 15 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 1 │ pupil │ 16 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 2 │ pupil │ 17 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 3 │ pupil │ 18 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 4 │ pupil │ 19 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 5 │ teacher │ 23 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 6 │ pupil │ 5 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 7 │ pupil │ 6 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 8 │ pupil │ 7 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 9 │ pupil │ 8 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 10 │ pupil │ 9 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 11 │ teacher │ 21 │ School │
╘════╧══════════╧══════════╧═════════════════╛
6.Location: School
╒════╤══════════╤══════════╤═════════════════╕
│ │ status │ id_p2n │ location_type │
╞════╪══════════╪══════════╪═════════════════╡
│ 0 │ pupil │ 0 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 1 │ pupil │ 1 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 2 │ pupil │ 2 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 3 │ pupil │ 3 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 4 │ pupil │ 4 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 5 │ teacher │ 20 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 6 │ pupil │ 10 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 7 │ pupil │ 11 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 8 │ pupil │ 12 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 9 │ pupil │ 13 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 10 │ pupil │ 14 │ School │
├────┼──────────┼──────────┼─────────────────┤
│ 11 │ teacher │ 22 │ School │
╘════╧══════════╧══════════╧═════════════════╛
You can also retrieve the information as a DataFrame for further analysis:
[15]:
loc_inf_df = inspector.location_information(
location_labels=["Classroom", "School"],
actor_attributes=["status", "id_p2n"],
output_format="df",
)
loc_inf_df.head()
[15]:
| location_id | status | id_p2n | location_type | |
|---|---|---|---|---|
| 0 | 0 | pupil | 0 | Classroom |
| 1 | 0 | pupil | 1 | Classroom |
| 2 | 0 | pupil | 2 | Classroom |
| 3 | 0 | pupil | 3 | Classroom |
| 4 | 0 | pupil | 4 | Classroom |
Coming soon …
The inspector offers several additional methods for analyzing the created network. Detailed documentation will be added soon.