enhanced timeline, improved handling of odd cases
This commit is contained in:
Florian Förster
parent
578c543a3e
commit
9197146d2c
@ -9,6 +9,7 @@ from lang_main.analysis.graphs import (
|
||||
save_to_GraphML,
|
||||
)
|
||||
from lang_main.constants import (
|
||||
CYTO_BASE_NETWORK_NAME,
|
||||
PATH_TO_DATASET,
|
||||
SAVE_PATH_FOLDER,
|
||||
SKIP_GRAPH_POSTPROCESSING,
|
||||
@ -26,7 +27,7 @@ from lang_main.pipelines.predefined import (
|
||||
build_timeline_pipe,
|
||||
build_tk_graph_pipe,
|
||||
build_tk_graph_post_pipe,
|
||||
build_tk_graph_rendering_pipe,
|
||||
build_tk_graph_render_pipe,
|
||||
build_tk_graph_rescaling_pipe,
|
||||
)
|
||||
from lang_main.types import (
|
||||
@ -42,8 +43,14 @@ pipe_target_feat = build_base_target_feature_pipe()
|
||||
pipe_merge = build_merge_duplicates_pipe()
|
||||
pipe_token_analysis = build_tk_graph_pipe()
|
||||
pipe_graph_postprocessing = build_tk_graph_post_pipe()
|
||||
pipe_graph_rescaling = build_tk_graph_rescaling_pipe()
|
||||
pipe_static_graph_rendering = build_tk_graph_rendering_pipe()
|
||||
pipe_graph_rescaling = build_tk_graph_rescaling_pipe(
|
||||
save_result=True,
|
||||
exit_point=EntryPoints.TK_GRAPH_ANALYSIS_RESCALED,
|
||||
)
|
||||
pipe_static_graph_rendering = build_tk_graph_render_pipe(
|
||||
with_subgraphs=True,
|
||||
base_network_name=CYTO_BASE_NETWORK_NAME,
|
||||
)
|
||||
pipe_timeline = build_timeline_pipe()
|
||||
|
||||
|
||||
@ -98,11 +105,11 @@ def run_graph_edge_rescaling() -> None:
|
||||
load_pickle(entry_point_path),
|
||||
)
|
||||
tk_graph = loaded_results[0]
|
||||
ret = cast(
|
||||
tk_graph_rescaled, tk_graph_rescaled_undirected = cast(
|
||||
tuple[TokenGraph, Graph], pipe_graph_rescaling.run(starting_values=(tk_graph,))
|
||||
)
|
||||
tk_graph_rescaled = ret[0]
|
||||
tk_graph_rescaled_undirected = ret[1]
|
||||
# tk_graph_rescaled = ret[0]
|
||||
# tk_graph_rescaled_undirected = ret[1]
|
||||
tk_graph_rescaled.to_GraphML(
|
||||
SAVE_PATH_FOLDER, filename='TokenGraph-directed-rescaled', directed=False
|
||||
)
|
||||
|
||||
@ -20,13 +20,15 @@ from pandas import DataFrame
|
||||
|
||||
import lang_main.io
|
||||
from lang_main.analysis import graphs, tokens
|
||||
from lang_main.constants import SPCY_MODEL
|
||||
from lang_main.types import ObjectID, TimelineCandidates
|
||||
from lang_main.constants import SAVE_PATH_FOLDER, SPCY_MODEL
|
||||
from lang_main.types import EntryPoints, ObjectID, TimelineCandidates
|
||||
|
||||
# ** data
|
||||
p_df = Path(r'../results/test_20240619/TIMELINE.pkl').resolve()
|
||||
# p_df = Path(r'../results/test_20240619/TIMELINE.pkl').resolve()
|
||||
p_df = lang_main.io.get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TIMELINE)
|
||||
(data,) = cast(tuple[DataFrame], lang_main.io.load_pickle(p_df))
|
||||
p_tl = Path(r'../results/test_20240619/TIMELINE_POSTPROCESSING.pkl').resolve()
|
||||
# p_tl = Path(r'../results/test_20240619/TIMELINE_POSTPROCESSING.pkl').resolve()
|
||||
p_tl = lang_main.io.get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TIMELINE_POST)
|
||||
cands, texts = cast(
|
||||
tuple[TimelineCandidates, dict[ObjectID, str]], lang_main.io.load_pickle(p_tl)
|
||||
)
|
||||
@ -58,9 +60,10 @@ HOVER_DATA: Final[dict[str, Any]] = {
|
||||
}
|
||||
|
||||
# ** graph
|
||||
target = '../results/test_20240529/Pipe-Token_Analysis_Step-1_build_token_graph.pkl'
|
||||
p = Path(target).resolve()
|
||||
ret = lang_main.io.load_pickle(p)
|
||||
# target = '../results/test_20240529/Pipe-Token_Analysis_Step-1_build_token_graph.pkl'
|
||||
# p = Path(target).resolve()
|
||||
p_tk_graph = lang_main.io.get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TK_GRAPH_POST)
|
||||
ret = lang_main.io.load_pickle(p_tk_graph)
|
||||
tk_graph = cast(graphs.TokenGraph, ret[0])
|
||||
tk_graph_filtered = graphs.filter_graph_by_edge_weight(tk_graph, 150, None)
|
||||
tk_graph_filtered = graphs.filter_graph_by_node_degree(tk_graph_filtered, 1, None)
|
||||
413
scripts/dash_timeline_static.py
Normal file
413
scripts/dash_timeline_static.py
Normal file
@ -0,0 +1,413 @@
|
||||
import time
|
||||
import webbrowser
|
||||
from pathlib import Path
|
||||
from threading import Thread
|
||||
from typing import Any, Final, cast
|
||||
|
||||
# import dash_cytoscape as cyto
|
||||
import plotly.express as px
|
||||
from dash import (
|
||||
Dash,
|
||||
Input,
|
||||
Output,
|
||||
State,
|
||||
callback,
|
||||
dash_table,
|
||||
dcc,
|
||||
html,
|
||||
)
|
||||
from pandas import DataFrame
|
||||
from plotly.graph_objects import Figure
|
||||
|
||||
import lang_main.io
|
||||
from lang_main.analysis import graphs, tokens
|
||||
from lang_main.constants import SAVE_PATH_FOLDER, SPCY_MODEL
|
||||
from lang_main.errors import EmptyEdgesError, EmptyGraphError
|
||||
from lang_main.pipelines.predefined import (
|
||||
build_tk_graph_render_pipe,
|
||||
build_tk_graph_rescaling_pipe,
|
||||
)
|
||||
from lang_main.types import EntryPoints, ObjectID, TimelineCandidates
|
||||
|
||||
# ** data
|
||||
# p_df = Path(r'../results/test_20240619/TIMELINE.pkl').resolve()
|
||||
p_df = lang_main.io.get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TIMELINE)
|
||||
(data,) = cast(tuple[DataFrame], lang_main.io.load_pickle(p_df))
|
||||
# p_tl = Path(r'../results/test_20240619/TIMELINE_POSTPROCESSING.pkl').resolve()
|
||||
p_tl = lang_main.io.get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TIMELINE_POST)
|
||||
cands, texts = cast(
|
||||
tuple[TimelineCandidates, dict[ObjectID, str]], lang_main.io.load_pickle(p_tl)
|
||||
)
|
||||
# ** necessary pipelines
|
||||
rescaling_pipe = build_tk_graph_rescaling_pipe(
|
||||
exit_point=EntryPoints.TIMELINE_TK_GRAPH_RESCALED,
|
||||
save_result=False,
|
||||
)
|
||||
BASE_NETWORK_NAME: Final[str] = 'test_timeline'
|
||||
# RENDER_FOLDER: Final[Path] = Path.cwd() / 'assets/'
|
||||
graph_render_pipe = build_tk_graph_render_pipe(
|
||||
with_subgraphs=False,
|
||||
base_network_name=BASE_NETWORK_NAME,
|
||||
)
|
||||
# PTH_RENDERED_GRAPH = f'assets/{BASE_NETWORK_NAME}.svg'
|
||||
PTH_RENDERED_GRAPH = lang_main.io.get_entry_point(
|
||||
SAVE_PATH_FOLDER,
|
||||
BASE_NETWORK_NAME,
|
||||
file_ext='.svg',
|
||||
)
|
||||
|
||||
|
||||
TABLE_FEATS: Final[list[str]] = [
|
||||
'ErstellungsDatum',
|
||||
'ErledigungsDatum',
|
||||
'VorgangsTypName',
|
||||
'VorgangsBeschreibung',
|
||||
]
|
||||
TABLE_FEATS_DATES: Final[list[str]] = [
|
||||
'ErstellungsDatum',
|
||||
'ErledigungsDatum',
|
||||
]
|
||||
|
||||
# ** figure config
|
||||
MARKERS_OCCURRENCES: Final[dict[str, Any]] = {
|
||||
'size': 12,
|
||||
'color': 'yellow',
|
||||
'line': {
|
||||
'width': 2,
|
||||
'color': 'red',
|
||||
},
|
||||
}
|
||||
MARKERS_DELTA: Final[dict[str, Any]] = {
|
||||
'size': 8,
|
||||
'color': 'red',
|
||||
'symbol': 'cross',
|
||||
}
|
||||
HOVER_DATA: Final[dict[str, Any]] = {
|
||||
'ErstellungsDatum': '|%d.%m.%Y',
|
||||
'ErledigungsDatum': '|%d.%m.%Y',
|
||||
'VorgangsBeschreibung': True,
|
||||
}
|
||||
HOVER_DATA_DELTA: Final[dict[str, Any]] = {
|
||||
'ErstellungsDatum': '|%d.%m.%Y',
|
||||
'ErledigungsDatum': '|%d.%m.%Y',
|
||||
'VorgangsDatum': '|%d.%m.%Y',
|
||||
'delta': True,
|
||||
'VorgangsBeschreibung': True,
|
||||
}
|
||||
|
||||
# ** graph
|
||||
p_tk_graph = lang_main.io.get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TK_GRAPH_POST)
|
||||
ret = lang_main.io.load_pickle(p_tk_graph)
|
||||
tk_graph = cast(graphs.TokenGraph, ret[0])
|
||||
tk_graph_filtered = graphs.filter_graph_by_edge_weight(tk_graph, 150, None)
|
||||
tk_graph_filtered = graphs.filter_graph_by_node_degree(tk_graph_filtered, 1, None)
|
||||
|
||||
|
||||
graph_layout = html.Div(
|
||||
[
|
||||
dcc.Store(id='graph-store', storage_type='memory'),
|
||||
# dcc.Store(id='graph-store-cyto-curr_cands', storage_type='memory'),
|
||||
html.Div(id='output'),
|
||||
html.Div(
|
||||
[
|
||||
html.H2('Token Graph', style={'margin': 0}),
|
||||
],
|
||||
style={
|
||||
'display': 'flex',
|
||||
'marginBottom': '1em',
|
||||
},
|
||||
),
|
||||
html.Div(
|
||||
[
|
||||
html.H3('Graph'),
|
||||
html.Button(
|
||||
'Download Bild',
|
||||
id='bt-reset',
|
||||
style={
|
||||
'marginLeft': 'auto',
|
||||
'width': '300px',
|
||||
},
|
||||
),
|
||||
dcc.Download(id='static-graph-download'),
|
||||
dcc.Loading(
|
||||
id='loading-graph-render',
|
||||
children=html.Div(
|
||||
[
|
||||
html.Img(
|
||||
id='static-graph-img',
|
||||
alt='static rendered graph',
|
||||
# style={
|
||||
# 'width': 'auto',
|
||||
# 'height': 'auto',
|
||||
# },
|
||||
),
|
||||
html.P(id='info-graph-errors', children=[]),
|
||||
],
|
||||
style={
|
||||
'border': '3px solid black',
|
||||
'borderRadius': '25px',
|
||||
'marginTop': '1em',
|
||||
'marginBottom': '2em',
|
||||
'padding': '7px',
|
||||
},
|
||||
),
|
||||
),
|
||||
],
|
||||
style={'marginTop': '1em'},
|
||||
),
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
# ** app
|
||||
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
|
||||
app = Dash(__name__, external_stylesheets=external_stylesheets)
|
||||
|
||||
|
||||
app.layout = html.Div(
|
||||
[
|
||||
html.H1(children='Demo Zeitreihenanalyse', style={'textAlign': 'center'}),
|
||||
html.Div(
|
||||
children=[
|
||||
html.H2('Wählen Sie ein Objekt aus (ObjektID):'),
|
||||
dcc.Dropdown(
|
||||
list(cands.keys()),
|
||||
id='selector-obj_id',
|
||||
placeholder='ObjektID auswählen...',
|
||||
),
|
||||
]
|
||||
),
|
||||
html.Div(
|
||||
children=[
|
||||
html.H3(id='object-text'),
|
||||
dcc.Dropdown(id='selector-candidates'),
|
||||
dcc.Graph(id='figure-occurrences'),
|
||||
dcc.Graph(id='figure-delta'),
|
||||
]
|
||||
),
|
||||
html.Div(
|
||||
[dash_table.DataTable(id='table-candidates')], style={'marginBottom': '2em'}
|
||||
),
|
||||
graph_layout,
|
||||
],
|
||||
style={'margin': '2em'},
|
||||
)
|
||||
|
||||
|
||||
# ** selectors of candidates
|
||||
@callback(
|
||||
Output('object-text', 'children'),
|
||||
Input('selector-obj_id', 'value'),
|
||||
prevent_initial_call=True,
|
||||
)
|
||||
def update_obj_text(obj_id):
|
||||
obj_id = int(obj_id)
|
||||
obj_text = texts[obj_id]
|
||||
headline = f'HObjektText: {obj_text}'
|
||||
return headline
|
||||
|
||||
|
||||
@callback(
|
||||
[
|
||||
Output('selector-candidates', 'options'),
|
||||
Output('selector-candidates', 'value'),
|
||||
],
|
||||
Input('selector-obj_id', 'value'),
|
||||
prevent_initial_call=True,
|
||||
)
|
||||
def update_choice_candidates(obj_id):
|
||||
obj_id = int(obj_id)
|
||||
choices = list(range(1, len(cands[obj_id]) + 1))
|
||||
return choices, choices[0]
|
||||
|
||||
|
||||
# ** helpers to filter DataFrame
|
||||
def pre_filter_data(
|
||||
data: DataFrame,
|
||||
idx: int,
|
||||
obj_id: ObjectID,
|
||||
) -> DataFrame:
|
||||
idx = int(idx)
|
||||
obj_id = int(obj_id)
|
||||
# data = data.copy()
|
||||
cands_for_obj_id = cands[obj_id]
|
||||
cands_choice = cands_for_obj_id[int(idx) - 1]
|
||||
# data
|
||||
data = data.loc[list(cands_choice)].sort_index() # type: ignore
|
||||
data['delta'] = data['ErledigungsDatum'] - data['ErstellungsDatum']
|
||||
data['delta'] = data['delta'].dt.days
|
||||
|
||||
return data
|
||||
|
||||
|
||||
# ** figure generation
|
||||
# TODO check possible storage of pre-filtered result
|
||||
# TODO change input of ``update_table_candidates`` and ``display_candidates_as_graph``
|
||||
# TODO to storage component
|
||||
@callback(
|
||||
[
|
||||
Output('figure-occurrences', 'figure'),
|
||||
Output('figure-delta', 'figure'),
|
||||
],
|
||||
Input('selector-candidates', 'value'),
|
||||
State('selector-obj_id', 'value'),
|
||||
prevent_initial_call=True,
|
||||
)
|
||||
def update_timeline(index, obj_id):
|
||||
obj_id = int(obj_id)
|
||||
obj_text = texts[obj_id]
|
||||
title_occurrences = f'HObjektText: {obj_text}'
|
||||
title_delta = f'HObjektText: {obj_text}, Differenz Erstellung und Erledigung'
|
||||
df = pre_filter_data(data, idx=index, obj_id=obj_id)
|
||||
# figure
|
||||
fig_occurrences = fig_timeline_occurrences(df, title_occurrences)
|
||||
fig_delta = fig_timeline_delta(df, title_delta)
|
||||
|
||||
return fig_occurrences, fig_delta
|
||||
|
||||
|
||||
def fig_timeline_occurrences(
|
||||
df: DataFrame,
|
||||
title: str,
|
||||
) -> Figure:
|
||||
fig = px.line(
|
||||
data_frame=df,
|
||||
x='ErstellungsDatum',
|
||||
y='ObjektID',
|
||||
title=title,
|
||||
hover_data=HOVER_DATA,
|
||||
)
|
||||
fig.update_traces(
|
||||
mode='markers+lines', marker=MARKERS_OCCURRENCES, marker_symbol='diamond'
|
||||
)
|
||||
fig.update_xaxes(
|
||||
tickformat='%B\n%Y',
|
||||
rangeslider_visible=True,
|
||||
)
|
||||
fig.update_yaxes(type='category')
|
||||
fig.update_layout(hovermode='x unified')
|
||||
|
||||
return fig
|
||||
|
||||
|
||||
def fig_timeline_delta(
|
||||
df: DataFrame,
|
||||
title: str,
|
||||
) -> Figure:
|
||||
fig = px.scatter(
|
||||
data_frame=df,
|
||||
x='ErstellungsDatum',
|
||||
y='delta',
|
||||
title=title,
|
||||
hover_data=HOVER_DATA_DELTA,
|
||||
)
|
||||
fig.update_traces(marker=MARKERS_DELTA)
|
||||
fig.update_xaxes(tickformat='%B\n%Y')
|
||||
fig.update_yaxes(dtick=1)
|
||||
fig.update_layout(hovermode='x unified')
|
||||
|
||||
return fig
|
||||
|
||||
|
||||
# ** HTML table
|
||||
@callback(
|
||||
[Output('table-candidates', 'data'), Output('table-candidates', 'columns')],
|
||||
Input('selector-candidates', 'value'),
|
||||
State('selector-obj_id', 'value'),
|
||||
prevent_initial_call=True,
|
||||
)
|
||||
def update_table_candidates(index, obj_id):
|
||||
df = pre_filter_data(data, idx=index, obj_id=obj_id)
|
||||
df = df.filter(items=TABLE_FEATS, axis=1).sort_values(
|
||||
by='ErstellungsDatum', ascending=True
|
||||
)
|
||||
cols = [{'name': i, 'id': i} for i in df.columns]
|
||||
# convert dates to strings
|
||||
for col in TABLE_FEATS_DATES:
|
||||
df[col] = df[col].dt.strftime(r'%Y-%m-%d')
|
||||
|
||||
table_data = df.to_dict('records')
|
||||
return table_data, cols
|
||||
|
||||
|
||||
# ** graph callbacks
|
||||
@app.callback(
|
||||
[
|
||||
Output('graph-store', 'data'),
|
||||
Output('static-graph-img', 'src'),
|
||||
Output('info-graph-errors', 'children'),
|
||||
],
|
||||
# Input('graph-build-btn', 'n_clicks'),
|
||||
Input('selector-candidates', 'value'),
|
||||
State('selector-obj_id', 'value'),
|
||||
prevent_initial_call=True,
|
||||
)
|
||||
def display_candidates_as_graph(index, obj_id):
|
||||
error_msg = ''
|
||||
t1 = time.perf_counter()
|
||||
df = pre_filter_data(data, idx=index, obj_id=obj_id)
|
||||
t2 = time.perf_counter()
|
||||
print(f'Time for filtering: {t2 - t1} s')
|
||||
|
||||
t1 = time.perf_counter()
|
||||
tk_graph_cands, _ = tokens.build_token_graph(
|
||||
data=df,
|
||||
model=SPCY_MODEL,
|
||||
target_feature='VorgangsBeschreibung',
|
||||
build_map=False,
|
||||
logging_graph=False,
|
||||
)
|
||||
t2 = time.perf_counter()
|
||||
print(f'Time for graph building: {t2 - t1} s')
|
||||
|
||||
# ** now start rendering pipeline in Cytoscape
|
||||
# rescale graph
|
||||
try:
|
||||
t1 = time.perf_counter()
|
||||
_, tk_graph_rescaled_undirected = cast(
|
||||
tuple[graphs.TokenGraph, graphs.Graph],
|
||||
rescaling_pipe.run(starting_values=(tk_graph_cands,)),
|
||||
)
|
||||
# render graph in Cytoscape and export image
|
||||
_ = graph_render_pipe.run(starting_values=(tk_graph_rescaled_undirected,))
|
||||
# load image as b64 encoded string
|
||||
b64_img = lang_main.io.encode_file_to_base64_str(PTH_RENDERED_GRAPH)
|
||||
static_img = f'data:image/svg+xml;base64,{b64_img}'
|
||||
graph_to_store = lang_main.io.encode_to_base64_str(tk_graph_cands)
|
||||
|
||||
# place image in browser
|
||||
t2 = time.perf_counter()
|
||||
print(f'Time for graph rescaling and rendering: {t2 - t1} s')
|
||||
except (EmptyGraphError, EmptyEdgesError):
|
||||
graph_to_store = ''
|
||||
static_img = ''
|
||||
error_msg = 'Graph ist leer und konnte nicht generiert werden!'
|
||||
finally:
|
||||
return graph_to_store, static_img, error_msg
|
||||
|
||||
|
||||
@callback(
|
||||
Output('static-graph-download', 'data'),
|
||||
Input('bt-reset', 'n_clicks'),
|
||||
prevent_initial_call=True,
|
||||
)
|
||||
def func(n_clicks):
|
||||
return dcc.send_file(path=PTH_RENDERED_GRAPH)
|
||||
|
||||
|
||||
def _start_webbrowser():
|
||||
host = '127.0.0.1'
|
||||
port = '8050'
|
||||
adress = f'http://{host}:{port}/'
|
||||
time.sleep(2)
|
||||
webbrowser.open_new(adress)
|
||||
|
||||
|
||||
def main():
|
||||
webbrowser_thread = Thread(target=_start_webbrowser, daemon=True)
|
||||
webbrowser_thread.start()
|
||||
app.run(debug=True)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -1,56 +0,0 @@
|
||||
# lang_main: Config file
|
||||
|
||||
[paths]
|
||||
inputs = './inputs/'
|
||||
results = './results/test_new2/'
|
||||
dataset = './01_2_Rohdaten_neu/Export4.csv'
|
||||
#results = './results/Export7/'
|
||||
#dataset = './01_03_Rohdaten_202403/Export7_59499_Zeilen.csv'
|
||||
#results = './results/Export7_trunc/'
|
||||
#dataset = './01_03_Rohdaten_202403/Export7_trunc.csv'
|
||||
|
||||
[control]
|
||||
preprocessing = true
|
||||
preprocessing_skip = false
|
||||
token_analysis = false
|
||||
token_analysis_skip = false
|
||||
graph_postprocessing = false
|
||||
graph_postprocessing_skip = false
|
||||
time_analysis = false
|
||||
time_analysis_skip = false
|
||||
|
||||
#[export_filenames]
|
||||
#filename_cossim_filter_candidates = 'CosSim-FilterCandidates'
|
||||
|
||||
[preprocess]
|
||||
filename_cossim_filter_candidates = 'CosSim-FilterCandidates'
|
||||
date_cols = [
|
||||
"VorgangsDatum",
|
||||
"ErledigungsDatum",
|
||||
"Arbeitsbeginn",
|
||||
"ErstellungsDatum",
|
||||
]
|
||||
threshold_amount_characters = 5
|
||||
threshold_similarity = 0.8
|
||||
|
||||
[graph_postprocessing]
|
||||
threshold_edge_weight = 150
|
||||
|
||||
[time_analysis.uniqueness]
|
||||
threshold_unique_texts = 4
|
||||
criterion_feature = 'HObjektText'
|
||||
feature_name_obj_id = 'ObjektID'
|
||||
|
||||
[time_analysis.model_input]
|
||||
input_features = [
|
||||
'VorgangsTypName',
|
||||
'VorgangsArtText',
|
||||
'VorgangsBeschreibung',
|
||||
]
|
||||
activity_feature = 'VorgangsTypName'
|
||||
activity_types = [
|
||||
'Reparaturauftrag (Portal)',
|
||||
'Störungsmeldung',
|
||||
]
|
||||
threshold_num_acitivities = 1
|
||||
threshold_similarity = 0.8
|
||||
Binary file not shown.
Binary file not shown.
@ -1,18 +0,0 @@
|
||||
from pathlib import Path
|
||||
from typing import cast
|
||||
import statistics
|
||||
|
||||
import lang_main.io
|
||||
from lang_main.analysis import graphs
|
||||
|
||||
# target = '../results/test_20240529/Pipe-Token_Analysis_Step-1_build_token_graph.pkl'
|
||||
# p = Path(target).resolve()
|
||||
# ret = lang_main.io.load_pickle(p)
|
||||
# tk_graph = cast(graphs.TokenGraph, ret[0])
|
||||
# tk_graph_filtered = tk_graph.filter_by_edge_weight(150, None)
|
||||
# tk_graph_filtered = tk_graph_filtered.filter_by_node_degree(1, None)
|
||||
# cyto_data_base, weight_data, all_weights = graphs.convert_graph_to_cytoscape(tk_graph_filtered)
|
||||
|
||||
|
||||
test = [1, 1, 1, 2, 2, 3, 3, 4, 4, 1000]
|
||||
print(statistics.mean(test))
|
||||
@ -17,7 +17,7 @@ from lang_main.constants import (
|
||||
EDGE_WEIGHT_DECIMALS,
|
||||
PROPERTY_NAME_DEGREE_WEIGHTED,
|
||||
)
|
||||
from lang_main.errors import EdgePropertyNotContainedError
|
||||
from lang_main.errors import EdgePropertyNotContainedError, EmptyEdgesError, EmptyGraphError
|
||||
from lang_main.io import load_pickle, save_pickle
|
||||
from lang_main.loggers import logger_graphs as logger
|
||||
from lang_main.types import (
|
||||
@ -381,9 +381,12 @@ def normalise_array_linear(
|
||||
npt.NDArray[np.float32]
|
||||
min/max normalised array
|
||||
"""
|
||||
arr_norm = (array - array.min()) / (array.max() - array.min())
|
||||
|
||||
div = array.max() - array.min()
|
||||
if div != 0:
|
||||
arr_norm = (array - array.min()) / div
|
||||
return arr_norm.astype(np.float32)
|
||||
else:
|
||||
return np.zeros(shape=array.shape, dtype=np.float32)
|
||||
|
||||
|
||||
def weight_scaling(
|
||||
@ -459,6 +462,8 @@ def rescale_edge_weights(
|
||||
weight_property: str = 'weight',
|
||||
) -> Graph | DiGraph | TokenGraph:
|
||||
graph = graph.copy()
|
||||
# check non-emptiness
|
||||
verify_non_empty_graph(graph, including_edges=True)
|
||||
# check if all edges contain weight property
|
||||
verify_property(graph, property=weight_property)
|
||||
|
||||
@ -473,6 +478,33 @@ def rescale_edge_weights(
|
||||
return graph
|
||||
|
||||
|
||||
def verify_non_empty_graph(
|
||||
graph: DiGraph | Graph,
|
||||
including_edges: bool = True,
|
||||
) -> None:
|
||||
"""check if the given graph is empty, presence of nodes is checked first,
|
||||
then of edges
|
||||
|
||||
Parameters
|
||||
----------
|
||||
graph : DiGraph | Graph
|
||||
graph to check for emptiness
|
||||
including_edges : bool, optional
|
||||
whether to check for non-existence of edges, by default True
|
||||
|
||||
Raises
|
||||
------
|
||||
EmptyGraphError
|
||||
if graph does not contain any nodes and therefore edges
|
||||
EmptyEdgesError
|
||||
if graph does not contain any edges
|
||||
"""
|
||||
if not tuple(graph.nodes):
|
||||
raise EmptyGraphError(f'Graph object >>{graph}<< does not contain any nodes.')
|
||||
elif including_edges and not tuple(graph.edges):
|
||||
raise EmptyEdgesError(f'Graph object >>{graph}<< does not contain any edges.')
|
||||
|
||||
|
||||
# ** ---------------------------------------
|
||||
class TokenGraph(DiGraph):
|
||||
def __init__(
|
||||
|
||||
@ -1,128 +1,128 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<vizmap id="VizMap-2024_07_12-08_08" documentVersion="3.1">
|
||||
<vizmap id="VizMap-2024_07_24-08_54" documentVersion="3.1">
|
||||
<visualStyle name="lang_main">
|
||||
<network>
|
||||
<visualProperty default="0.0" name="NETWORK_CENTER_X_LOCATION"/>
|
||||
<visualProperty default="0.0" name="NETWORK_CENTER_Y_LOCATION"/>
|
||||
<visualProperty default="0.0" name="NETWORK_CENTER_Z_LOCATION"/>
|
||||
<visualProperty default="false" name="NETWORK_ANNOTATION_SELECTION"/>
|
||||
<visualProperty default="1.0" name="NETWORK_SCALE_FACTOR"/>
|
||||
<visualProperty default="false" name="NETWORK_NODE_LABEL_SELECTION"/>
|
||||
<visualProperty default="400.0" name="NETWORK_HEIGHT"/>
|
||||
<visualProperty default="true" name="NETWORK_NODE_SELECTION"/>
|
||||
<visualProperty default="550.0" name="NETWORK_WIDTH"/>
|
||||
<visualProperty default="0.0" name="NETWORK_DEPTH"/>
|
||||
<visualProperty default="false" name="NETWORK_FORCE_HIGH_DETAIL"/>
|
||||
<visualProperty default="" name="NETWORK_TITLE"/>
|
||||
<visualProperty default="true" name="NETWORK_EDGE_SELECTION"/>
|
||||
<visualProperty default="#F7FFFF" name="NETWORK_BACKGROUND_PAINT"/>
|
||||
<visualProperty default="0.0" name="NETWORK_DEPTH"/>
|
||||
<visualProperty default="0.0" name="NETWORK_CENTER_Z_LOCATION"/>
|
||||
<visualProperty default="true" name="NETWORK_EDGE_SELECTION"/>
|
||||
<visualProperty default="false" name="NETWORK_ANNOTATION_SELECTION"/>
|
||||
<visualProperty default="" name="NETWORK_TITLE"/>
|
||||
<visualProperty default="false" name="NETWORK_FORCE_HIGH_DETAIL"/>
|
||||
<visualProperty default="true" name="NETWORK_NODE_SELECTION"/>
|
||||
<visualProperty default="0.0" name="NETWORK_CENTER_Y_LOCATION"/>
|
||||
<visualProperty default="0.0" name="NETWORK_CENTER_X_LOCATION"/>
|
||||
<visualProperty default="false" name="NETWORK_NODE_LABEL_SELECTION"/>
|
||||
<visualProperty default="550.0" name="NETWORK_WIDTH"/>
|
||||
<visualProperty default="400.0" name="NETWORK_HEIGHT"/>
|
||||
</network>
|
||||
<node>
|
||||
<dependency value="true" name="nodeCustomGraphicsSizeSync"/>
|
||||
<dependency value="true" name="nodeSizeLocked"/>
|
||||
<visualProperty default="ROUND_RECTANGLE" name="NODE_LABEL_BACKGROUND_SHAPE"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_9"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_7"/>
|
||||
<visualProperty default="true" name="NODE_NESTED_NETWORK_IMAGE_VISIBLE"/>
|
||||
<visualProperty default="0.0" name="NODE_LABEL_ROTATION"/>
|
||||
<visualProperty default="175" name="NODE_LABEL_BACKGROUND_TRANSPARENCY"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_8"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_2"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_6"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_7"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_1"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_4"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_9"/>
|
||||
<visualProperty default="ROUND_RECTANGLE" name="COMPOUND_NODE_SHAPE"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_5"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_9"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_5"/>
|
||||
<visualProperty default="10.0" name="COMPOUND_NODE_PADDING"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_3"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_6"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_8"/>
|
||||
<visualProperty default="SE,NW,c,-2.00,3.00" name="NODE_LABEL_POSITION"/>
|
||||
<visualProperty default="ELLIPSE" name="NODE_SHAPE"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_3"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_4"/>
|
||||
<visualProperty default="SansSerif.plain,plain,12" name="NODE_LABEL_FONT_FACE"/>
|
||||
<visualProperty default="#D1F5BE" name="NODE_BORDER_PAINT"/>
|
||||
<visualProperty default="40.0" name="NODE_HEIGHT"/>
|
||||
<visualProperty default="255" name="NODE_LABEL_TRANSPARENCY"/>
|
||||
<visualProperty default="#E1E1E1" name="NODE_LABEL_BACKGROUND_COLOR"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_6"/>
|
||||
<visualProperty default="false" name="NODE_SELECTED"/>
|
||||
<visualProperty default="0.0" name="NODE_DEPTH"/>
|
||||
<visualProperty default="SOLID" name="NODE_BORDER_STROKE"/>
|
||||
<visualProperty default="" name="NODE_TOOLTIP"/>
|
||||
<visualProperty default="7.0" name="NODE_BORDER_WIDTH"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_2"/>
|
||||
<visualProperty default="#A63C06" name="NODE_LABEL_COLOR"/>
|
||||
<visualProperty default="0.0" name="NODE_X_LOCATION"/>
|
||||
<visualProperty default="18.0" name="NODE_SIZE"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_8"/>
|
||||
<visualProperty default="0.0" name="NODE_Z_LOCATION"/>
|
||||
<visualProperty default="#FE9929" name="NODE_FILL_COLOR"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_1"/>
|
||||
<visualProperty default="255" name="NODE_BORDER_TRANSPARENCY"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_1"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_2"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_3"/>
|
||||
<visualProperty default="60.0" name="NODE_WIDTH"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_6"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_9"/>
|
||||
<visualProperty default="18.0" name="NODE_SIZE"/>
|
||||
<visualProperty default="#A63C06" name="NODE_LABEL_COLOR"/>
|
||||
<visualProperty default="0.0" name="NODE_LABEL_ROTATION"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_3"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_3"/>
|
||||
<visualProperty default="#E1E1E1" name="NODE_LABEL_BACKGROUND_COLOR"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_4"/>
|
||||
<visualProperty default="#D1F5BE" name="NODE_BORDER_PAINT"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_8"/>
|
||||
<visualProperty default="40.0" name="NODE_HEIGHT"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_7"/>
|
||||
<visualProperty default="255" name="NODE_LABEL_TRANSPARENCY"/>
|
||||
<visualProperty default="" name="NODE_TOOLTIP"/>
|
||||
<visualProperty default="false" name="NODE_SELECTED"/>
|
||||
<visualProperty default="255" name="NODE_BORDER_TRANSPARENCY"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_5"/>
|
||||
<visualProperty default="14" name="NODE_LABEL_FONT_SIZE"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_2"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_6"/>
|
||||
<visualProperty default="" name="NODE_LABEL">
|
||||
<passthroughMapping attributeName="name" attributeType="string"/>
|
||||
</visualProperty>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_5"/>
|
||||
<visualProperty default="500.0" name="NODE_LABEL_WIDTH"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_4"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_7"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_2"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_2"/>
|
||||
<visualProperty default="#FE9929" name="NODE_FILL_COLOR"/>
|
||||
<visualProperty default="#FFFF00" name="NODE_SELECTED_PAINT"/>
|
||||
<visualProperty default="0.0" name="NODE_Y_LOCATION"/>
|
||||
<visualProperty default="true" name="NODE_VISIBLE"/>
|
||||
<visualProperty default="255" name="NODE_TRANSPARENCY"/>
|
||||
<visualProperty default="14" name="NODE_LABEL_FONT_SIZE"/>
|
||||
<visualProperty default="500.0" name="NODE_LABEL_WIDTH"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_8"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_5"/>
|
||||
<visualProperty default="60.0" name="NODE_WIDTH"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_4"/>
|
||||
<visualProperty default="10.0" name="COMPOUND_NODE_PADDING"/>
|
||||
<visualProperty default="SansSerif.plain,plain,12" name="NODE_LABEL_FONT_FACE"/>
|
||||
<visualProperty default="0.0" name="NODE_Y_LOCATION"/>
|
||||
<visualProperty default="ELLIPSE" name="NODE_SHAPE"/>
|
||||
<visualProperty default="SE,NW,c,-2.00,3.00" name="NODE_LABEL_POSITION"/>
|
||||
<visualProperty default="true" name="NODE_VISIBLE"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_1"/>
|
||||
<visualProperty default="ROUND_RECTANGLE" name="NODE_LABEL_BACKGROUND_SHAPE"/>
|
||||
<visualProperty default="0.0" name="NODE_Z_LOCATION"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_6"/>
|
||||
<visualProperty default="ROUND_RECTANGLE" name="COMPOUND_NODE_SHAPE"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_9"/>
|
||||
<visualProperty default="SOLID" name="NODE_BORDER_STROKE"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_5"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_7"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_8"/>
|
||||
<visualProperty default="0.0" name="NODE_X_LOCATION"/>
|
||||
<visualProperty default="5.0" name="NODE_BORDER_WIDTH"/>
|
||||
<visualProperty default="true" name="NODE_NESTED_NETWORK_IMAGE_VISIBLE"/>
|
||||
<visualProperty default="org.cytoscape.cg.model.NullCustomGraphics,0,[ Remove Graphics ]," name="NODE_CUSTOMGRAPHICS_3"/>
|
||||
<visualProperty default="175" name="NODE_LABEL_BACKGROUND_TRANSPARENCY"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_1"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="NODE_CUSTOMGRAPHICS_POSITION_4"/>
|
||||
<visualProperty default="0.0" name="NODE_DEPTH"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_7"/>
|
||||
<visualProperty default="0.0" name="NODE_CUSTOMGRAPHICS_SIZE_9"/>
|
||||
</node>
|
||||
<edge>
|
||||
<dependency value="true" name="arrowColorMatchesEdge"/>
|
||||
<visualProperty default="false" name="EDGE_SELECTED"/>
|
||||
<visualProperty default="255" name="EDGE_TRANSPARENCY"/>
|
||||
<visualProperty default="10" name="EDGE_LABEL_FONT_SIZE"/>
|
||||
<visualProperty default="#577399" name="EDGE_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="" name="EDGE_LABEL"/>
|
||||
<visualProperty default="#FFFFFF" name="EDGE_STROKE_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="200.0" name="EDGE_LABEL_WIDTH"/>
|
||||
<visualProperty default="#000000" name="EDGE_LABEL_COLOR"/>
|
||||
<visualProperty default="SansSerif.plain,plain,10" name="EDGE_LABEL_FONT_FACE"/>
|
||||
<visualProperty default="0.728545744495502,-0.684997151948455,0.6456513365424503" name="EDGE_BEND"/>
|
||||
<visualProperty default="#B6B6B6" name="EDGE_LABEL_BACKGROUND_COLOR"/>
|
||||
<visualProperty default="AUTO_BEND" name="EDGE_STACKING"/>
|
||||
<visualProperty default="#000000" name="EDGE_TARGET_ARROW_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="0.5" name="EDGE_STACKING_DENSITY"/>
|
||||
<visualProperty default="NONE" name="EDGE_TARGET_ARROW_SHAPE"/>
|
||||
<visualProperty default="true" name="EDGE_VISIBLE"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="EDGE_LABEL_POSITION"/>
|
||||
<visualProperty default="0.0" name="EDGE_LABEL_ROTATION"/>
|
||||
<visualProperty default="" name="EDGE_TOOLTIP"/>
|
||||
<visualProperty default="0.0" name="EDGE_Z_ORDER"/>
|
||||
<visualProperty default="#FFFF00" name="EDGE_TARGET_ARROW_SELECTED_PAINT"/>
|
||||
<visualProperty default="#FF0000" name="EDGE_STROKE_SELECTED_PAINT"/>
|
||||
<visualProperty default="NONE" name="EDGE_SOURCE_ARROW_SHAPE"/>
|
||||
<visualProperty default="#FFFF00" name="EDGE_SOURCE_ARROW_SELECTED_PAINT"/>
|
||||
<visualProperty default="false" name="EDGE_LABEL_AUTOROTATE"/>
|
||||
<visualProperty default="true" name="EDGE_CURVED"/>
|
||||
<visualProperty default="#000000" name="EDGE_SOURCE_ARROW_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="255" name="EDGE_LABEL_TRANSPARENCY"/>
|
||||
<visualProperty default="6.0" name="EDGE_TARGET_ARROW_SIZE"/>
|
||||
<visualProperty default="NONE" name="EDGE_LABEL_BACKGROUND_SHAPE"/>
|
||||
<visualProperty default="255" name="EDGE_LABEL_BACKGROUND_TRANSPARENCY"/>
|
||||
<visualProperty default="SOLID" name="EDGE_LINE_TYPE"/>
|
||||
<visualProperty default="6.0" name="EDGE_SOURCE_ARROW_SIZE"/>
|
||||
<visualProperty default="" name="EDGE_TOOLTIP"/>
|
||||
<visualProperty default="10" name="EDGE_LABEL_FONT_SIZE"/>
|
||||
<visualProperty default="255" name="EDGE_TRANSPARENCY"/>
|
||||
<visualProperty default="#000000" name="EDGE_TARGET_ARROW_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="200.0" name="EDGE_LABEL_WIDTH"/>
|
||||
<visualProperty default="SansSerif.plain,plain,10" name="EDGE_LABEL_FONT_FACE"/>
|
||||
<visualProperty default="0.728545744495502,-0.684997151948455,0.6456513365424503" name="EDGE_BEND"/>
|
||||
<visualProperty default="0.5" name="EDGE_STACKING_DENSITY"/>
|
||||
<visualProperty default="false" name="EDGE_SELECTED"/>
|
||||
<visualProperty default="3.0" name="EDGE_WIDTH">
|
||||
<continuousMapping attributeName="weight" attributeType="float">
|
||||
<continuousMappingPoint attrValue="0.09520000219345093" equalValue="2.0" greaterValue="2.0" lesserValue="1.0"/>
|
||||
<continuousMappingPoint attrValue="1.0" equalValue="10.0" greaterValue="1.0" lesserValue="10.0"/>
|
||||
</continuousMapping>
|
||||
</visualProperty>
|
||||
<visualProperty default="#577399" name="EDGE_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="6.0" name="EDGE_SOURCE_ARROW_SIZE"/>
|
||||
<visualProperty default="255" name="EDGE_LABEL_BACKGROUND_TRANSPARENCY"/>
|
||||
<visualProperty default="#000000" name="EDGE_LABEL_COLOR"/>
|
||||
<visualProperty default="SOLID" name="EDGE_LINE_TYPE"/>
|
||||
<visualProperty default="#FF0000" name="EDGE_STROKE_SELECTED_PAINT"/>
|
||||
<visualProperty default="" name="EDGE_LABEL"/>
|
||||
<visualProperty default="true" name="EDGE_VISIBLE"/>
|
||||
<visualProperty default="255" name="EDGE_LABEL_TRANSPARENCY"/>
|
||||
<visualProperty default="#000000" name="EDGE_SOURCE_ARROW_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="#B6B6B6" name="EDGE_LABEL_BACKGROUND_COLOR"/>
|
||||
<visualProperty default="true" name="EDGE_CURVED"/>
|
||||
<visualProperty default="#FFFFFF" name="EDGE_STROKE_UNSELECTED_PAINT"/>
|
||||
<visualProperty default="0.0" name="EDGE_LABEL_ROTATION"/>
|
||||
<visualProperty default="AUTO_BEND" name="EDGE_STACKING"/>
|
||||
<visualProperty default="#FFFF00" name="EDGE_SOURCE_ARROW_SELECTED_PAINT"/>
|
||||
<visualProperty default="NONE" name="EDGE_TARGET_ARROW_SHAPE"/>
|
||||
<visualProperty default="NONE" name="EDGE_SOURCE_ARROW_SHAPE"/>
|
||||
<visualProperty default="6.0" name="EDGE_TARGET_ARROW_SIZE"/>
|
||||
<visualProperty default="NONE" name="EDGE_LABEL_BACKGROUND_SHAPE"/>
|
||||
<visualProperty default="false" name="EDGE_LABEL_AUTOROTATE"/>
|
||||
<visualProperty default="C,C,c,0.00,0.00" name="EDGE_LABEL_POSITION"/>
|
||||
</edge>
|
||||
</visualStyle>
|
||||
</vizmap>
|
||||
|
||||
Binary file not shown.
@ -1,2 +1,12 @@
|
||||
class EdgePropertyNotContainedError(Exception):
|
||||
"""Error raised if a needed edge property is not contained in graph edges"""
|
||||
|
||||
|
||||
class EmptyGraphError(Exception):
|
||||
"""Error raised if an operation should be performed on the graph,
|
||||
but it does not contain any nodes or edges"""
|
||||
|
||||
|
||||
class EmptyEdgesError(EmptyGraphError):
|
||||
"""Error raised if action should be performed on a graph's edges, but
|
||||
it does not contain any"""
|
||||
|
||||
@ -71,6 +71,15 @@ def encode_to_base64_str(
|
||||
return b64_bytes.decode(encoding=encoding)
|
||||
|
||||
|
||||
def encode_file_to_base64_str(
|
||||
path: Path,
|
||||
encoding: str = 'utf-8',
|
||||
) -> str:
|
||||
with open(path, 'rb') as file:
|
||||
b64_bytes = base64.b64encode(file.read())
|
||||
return b64_bytes.decode(encoding=encoding)
|
||||
|
||||
|
||||
def decode_from_base64_str(
|
||||
b64_str: str,
|
||||
encoding: str = 'utf-8',
|
||||
@ -83,8 +92,9 @@ def decode_from_base64_str(
|
||||
def get_entry_point(
|
||||
saving_path: Path,
|
||||
filename: str,
|
||||
file_ext: str = '.pkl',
|
||||
) -> Path:
|
||||
entry_point_path = (saving_path / filename).with_suffix('.pkl')
|
||||
entry_point_path = (saving_path / filename).with_suffix(file_ext)
|
||||
if not entry_point_path.exists():
|
||||
raise FileNotFoundError(
|
||||
f'Could not find provided entry data under path: >>{entry_point_path}<<'
|
||||
|
||||
@ -1,3 +1,5 @@
|
||||
from pathlib import Path
|
||||
|
||||
from lang_main.analysis import graphs
|
||||
from lang_main.analysis.preprocessing import (
|
||||
analyse_feature,
|
||||
@ -168,37 +170,75 @@ def build_tk_graph_post_pipe() -> Pipeline:
|
||||
return pipe_graph_postprocessing
|
||||
|
||||
|
||||
def build_tk_graph_rescaling_pipe() -> Pipeline:
|
||||
def build_tk_graph_rescaling_pipe(
|
||||
save_result: bool,
|
||||
exit_point: EntryPoints,
|
||||
) -> Pipeline:
|
||||
pipe_graph_rescaling = Pipeline(name='Graph_Rescaling', working_dir=SAVE_PATH_FOLDER)
|
||||
pipe_graph_rescaling.add(
|
||||
graphs.pipe_rescale_graph_edge_weights,
|
||||
)
|
||||
pipe_graph_rescaling.add(
|
||||
graphs.pipe_add_graph_metrics,
|
||||
save_result=True,
|
||||
filename=EntryPoints.TK_GRAPH_ANALYSIS_RESCALED,
|
||||
save_result=save_result,
|
||||
filename=exit_point,
|
||||
# filename=EntryPoints.TK_GRAPH_ANALYSIS_RESCALED,
|
||||
)
|
||||
|
||||
return pipe_graph_rescaling
|
||||
|
||||
|
||||
# ** token analysis: rendering
|
||||
def build_tk_graph_rendering_pipe() -> Pipeline:
|
||||
def build_tk_graph_render_pipe(
|
||||
with_subgraphs: bool,
|
||||
export_folder: Path = SAVE_PATH_FOLDER,
|
||||
base_network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
) -> Pipeline:
|
||||
pipe_graph_rendering = Pipeline(
|
||||
name='Graph_Static-Rendering',
|
||||
working_dir=SAVE_PATH_FOLDER,
|
||||
)
|
||||
pipe_graph_rendering.add(cyto.import_to_cytoscape)
|
||||
pipe_graph_rendering.add(cyto.layout_network)
|
||||
pipe_graph_rendering.add(cyto.apply_style_to_network)
|
||||
pipe_graph_rendering.add(
|
||||
cyto.import_to_cytoscape,
|
||||
{
|
||||
'network_name': base_network_name,
|
||||
},
|
||||
)
|
||||
pipe_graph_rendering.add(
|
||||
cyto.layout_network,
|
||||
{
|
||||
'network_name': base_network_name,
|
||||
},
|
||||
)
|
||||
pipe_graph_rendering.add(
|
||||
cyto.apply_style_to_network,
|
||||
{
|
||||
'network_name': base_network_name,
|
||||
},
|
||||
)
|
||||
pipe_graph_rendering.add(
|
||||
cyto.export_network_to_image,
|
||||
{'filename': CYTO_BASE_NETWORK_NAME},
|
||||
{
|
||||
'filename': base_network_name,
|
||||
'target_folder': export_folder,
|
||||
'network_name': base_network_name,
|
||||
},
|
||||
)
|
||||
|
||||
if with_subgraphs:
|
||||
pipe_graph_rendering.add(
|
||||
cyto.get_subgraph_node_selection,
|
||||
{
|
||||
'network_name': base_network_name,
|
||||
},
|
||||
)
|
||||
pipe_graph_rendering.add(cyto.get_subgraph_node_selection)
|
||||
pipe_graph_rendering.add(
|
||||
cyto.build_subnetworks,
|
||||
{'export_image': True},
|
||||
{
|
||||
'export_image': True,
|
||||
'target_folder': export_folder,
|
||||
'network_name': base_network_name,
|
||||
},
|
||||
)
|
||||
|
||||
return pipe_graph_rendering
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
import time
|
||||
from collections.abc import Iterable
|
||||
from pathlib import Path
|
||||
from typing import cast
|
||||
from typing import Literal, cast
|
||||
|
||||
import py4cytoscape as p4c
|
||||
from networkx import DiGraph, Graph
|
||||
@ -55,6 +55,7 @@ def verify_connection():
|
||||
|
||||
def import_to_cytoscape(
|
||||
graph: DiGraph | Graph,
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
) -> None:
|
||||
"""Cytoscape: import NetworkX graph as new network collection
|
||||
|
||||
@ -65,15 +66,49 @@ def import_to_cytoscape(
|
||||
"""
|
||||
logger.debug('Checking Cytoscape connection...')
|
||||
verify_connection()
|
||||
logger.debug('Importing network to Cytoscape...')
|
||||
logger.debug('Importing to and analysing network in Cytoscape...')
|
||||
p4c.delete_all_networks()
|
||||
p4c.create_network_from_networkx(
|
||||
graph,
|
||||
title=CYTO_BASE_NETWORK_NAME,
|
||||
title=network_name,
|
||||
collection=CYTO_COLLECTION_NAME,
|
||||
)
|
||||
analyse_network(network_name=network_name)
|
||||
logger.debug('Import and analysis of network to Cytoscape successful.')
|
||||
|
||||
|
||||
def verify_table_property(
|
||||
property: str,
|
||||
table_type: Literal['node', 'edge', 'network'] = 'node',
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
) -> bool:
|
||||
table = p4c.get_table_columns(table=table_type, network=network_name)
|
||||
|
||||
return property in table.columns
|
||||
|
||||
|
||||
def analyse_network(
|
||||
property_degree_weighted: str = PROPERTY_NAME_DEGREE_WEIGHTED,
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
) -> None:
|
||||
node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||
net_analyse_possible: bool = True
|
||||
if len(node_table) < 4:
|
||||
net_analyse_possible = False
|
||||
|
||||
if net_analyse_possible:
|
||||
p4c.analyze_network(directed=False)
|
||||
logger.debug('Importing network to Cytoscape successful.')
|
||||
node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||
node_table['stress_norm'] = node_table['Stress'] / node_table['Stress'].max()
|
||||
node_table[CYTO_SELECTION_PROPERTY] = (
|
||||
node_table[property_degree_weighted]
|
||||
* node_table['BetweennessCentrality']
|
||||
* node_table['stress_norm']
|
||||
)
|
||||
else:
|
||||
node_table[CYTO_SELECTION_PROPERTY] = 1
|
||||
|
||||
p4c.load_table_data(node_table, data_key_column='name', network=network_name)
|
||||
|
||||
|
||||
def reset_current_network_to_base() -> None:
|
||||
@ -83,6 +118,7 @@ def reset_current_network_to_base() -> None:
|
||||
|
||||
def export_network_to_image(
|
||||
filename: str,
|
||||
target_folder: Path = SAVE_PATH_FOLDER,
|
||||
filetype: CytoExportFileTypes = 'SVG',
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
pdf_export_page_size: CytoExportPageSizes = 'A4',
|
||||
@ -102,7 +138,6 @@ def export_network_to_image(
|
||||
by default 'A4'
|
||||
"""
|
||||
logger.debug('Exporting image to file...')
|
||||
target_folder = SAVE_PATH_FOLDER
|
||||
if not target_folder.exists():
|
||||
target_folder.mkdir(parents=True)
|
||||
file_pth = target_folder / filename
|
||||
@ -138,7 +173,8 @@ def layout_network(
|
||||
necessarily match the name in the Cytoscape UI),
|
||||
by default CYTO_LAYOUT_NAME
|
||||
layout_properties : CytoLayoutProperties, optional
|
||||
configuration of parameters for the given layout algorithm, by default CYTO_LAYOUT_PROPERTIES
|
||||
configuration of parameters for the given layout algorithm,
|
||||
by default CYTO_LAYOUT_PROPERTIES
|
||||
network_name : str, optional
|
||||
network to apply the layout algorithm on, by default CYTO_BASE_NETWORK_NAME
|
||||
"""
|
||||
@ -153,6 +189,9 @@ def apply_style_to_network(
|
||||
style_name: str = CYTO_STYLESHEET_NAME,
|
||||
pth_to_stylesheet: Path = CYTO_PATH_STYLESHEET,
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
node_size_property: str = 'node_selection',
|
||||
min_node_size: int = 15,
|
||||
max_node_size: int = 40,
|
||||
) -> None:
|
||||
"""Cytoscape: apply a chosen Cytoscape style to the defined network
|
||||
|
||||
@ -185,14 +224,36 @@ def apply_style_to_network(
|
||||
p4c.import_visual_styles(str(pth_to_stylesheet))
|
||||
|
||||
p4c.set_visual_style(style_name, network=network_name)
|
||||
time.sleep(1) # if not waited image export could be without applied style
|
||||
# node size mapping, only if needed property is available
|
||||
# TODO check removal
|
||||
# size_prop_available = verify_table_property(
|
||||
# property=node_size_property,
|
||||
# network_name=network_name,
|
||||
# )
|
||||
# if size_prop_available:
|
||||
scheme = p4c.scheme_c_number_continuous(
|
||||
start_value=min_node_size, end_value=max_node_size
|
||||
)
|
||||
node_size_map = p4c.gen_node_size_map(
|
||||
node_size_property,
|
||||
number_scheme=scheme,
|
||||
mapping_type='c',
|
||||
style_name='lang_main',
|
||||
default_number=min_node_size,
|
||||
)
|
||||
p4c.set_node_size_mapping(**node_size_map)
|
||||
# else:
|
||||
# node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||
# nodes_SUID = node_table['SUID'].to_list()
|
||||
# p4c.set_node_size_bypass(nodes_SUID, new_sizes=min_node_size, network=network_name)
|
||||
# p4c.set_visual_style(style_name, network=network_name)
|
||||
# time.sleep(1) # if not waited image export could be without applied style
|
||||
p4c.fit_content(selected_only=False, network=network_name)
|
||||
logger.debug('Style application to network successful.')
|
||||
|
||||
|
||||
def get_subgraph_node_selection(
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
property_degree_weighted: str = PROPERTY_NAME_DEGREE_WEIGHTED,
|
||||
num_subgraphs: int = CYTO_NUMBER_SUBGRAPHS,
|
||||
) -> list[CytoNodeID]:
|
||||
"""Cytoscape: obtain the relevant nodes for iterative subgraph generation
|
||||
@ -214,14 +275,9 @@ def get_subgraph_node_selection(
|
||||
list containing all relevant Cytoscape nodes
|
||||
"""
|
||||
logger.debug('Selecting nodes for subgraph generation...')
|
||||
node_table = p4c.get_table_columns(network=network_name)
|
||||
node_table['stress_norm'] = node_table['Stress'] / node_table['Stress'].max()
|
||||
node_table[CYTO_SELECTION_PROPERTY] = (
|
||||
node_table[property_degree_weighted]
|
||||
* node_table['BetweennessCentrality']
|
||||
* node_table['stress_norm']
|
||||
)
|
||||
node_table = p4c.get_table_columns(table='node', network=network_name)
|
||||
node_table = node_table.sort_values(by=CYTO_SELECTION_PROPERTY, ascending=False)
|
||||
p4c.load_table_data(node_table, data_key_column='name', network=network_name)
|
||||
node_table_choice = node_table.iloc[:num_subgraphs, :]
|
||||
logger.debug('Selection of nodes for subgraph generation successful.')
|
||||
|
||||
@ -264,6 +320,7 @@ def make_subnetwork(
|
||||
index: int,
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
export_image: bool = True,
|
||||
target_folder: Path = SAVE_PATH_FOLDER,
|
||||
) -> None:
|
||||
"""Cytoscape: generate a new subnetwork based on the currently
|
||||
selected nodes and edges
|
||||
@ -289,7 +346,11 @@ def make_subnetwork(
|
||||
p4c.fit_content(selected_only=False, network=subnetwork_name)
|
||||
if export_image:
|
||||
time.sleep(1)
|
||||
export_network_to_image(filename=subnetwork_name, network_name=subnetwork_name)
|
||||
export_network_to_image(
|
||||
filename=subnetwork_name,
|
||||
target_folder=target_folder,
|
||||
network_name=subnetwork_name,
|
||||
)
|
||||
|
||||
logger.debug('Generation of subnetwork with index %d successful.', index)
|
||||
|
||||
@ -298,6 +359,7 @@ def build_subnetworks(
|
||||
nodes_to_analyse: Iterable[CytoNodeID],
|
||||
network_name: str = CYTO_BASE_NETWORK_NAME,
|
||||
export_image: bool = True,
|
||||
target_folder: Path = SAVE_PATH_FOLDER,
|
||||
) -> None:
|
||||
"""Cytoscape: iteratively build subnetworks from a collection of nodes
|
||||
and their respective neighbouring nodes
|
||||
@ -316,5 +378,10 @@ def build_subnetworks(
|
||||
logger.debug('Generating all subnetworks for node selection...')
|
||||
for idx, node in enumerate(nodes_to_analyse):
|
||||
select_neighbours_of_node(node=node, network_name=network_name)
|
||||
make_subnetwork(index=idx, network_name=network_name, export_image=export_image)
|
||||
make_subnetwork(
|
||||
index=idx,
|
||||
network_name=network_name,
|
||||
export_image=export_image,
|
||||
target_folder=target_folder,
|
||||
)
|
||||
logger.debug('Generation of all subnetworks for node selection successful.')
|
||||
|
||||
@ -33,6 +33,7 @@ ResultHandling: TypeAlias = list[tuple[bool, str | None]]
|
||||
class EntryPoints(enum.StrEnum):
|
||||
TIMELINE = 'TIMELINE'
|
||||
TIMELINE_POST = 'TIMELINE_POSTPROCESSING'
|
||||
TIMELINE_TK_GRAPH_RESCALED = 'TIMELINE_TK_GRAPH_RESCALED'
|
||||
TK_GRAPH_POST = 'TK-GRAPH_POSTPROCESSING'
|
||||
TK_GRAPH_ANALYSIS = 'TK-GRAPH_ANALYSIS'
|
||||
TK_GRAPH_ANALYSIS_RESCALED = 'TK-GRAPH_ANALYSIS_RESCALED'
|
||||
|
||||
@ -2,7 +2,7 @@
|
||||
|
||||
[paths]
|
||||
inputs = './inputs/'
|
||||
results = './results/test_20240619/'
|
||||
results = '../scripts/results/test_20240619/'
|
||||
dataset = '../data/02_202307/Export4.csv'
|
||||
#results = './results/Export7/'
|
||||
#dataset = './01_03_Rohdaten_202403/Export7_59499_Zeilen.csv'
|
||||
|
||||
File diff suppressed because one or more lines are too long
Loading…
x
Reference in New Issue
Block a user