prepare usage of cytoscape API

scripts/analyse_dataset.py

@@ -1,13 +1,14 @@
 import typing
 from typing import cast
 
-from pandas import DataFrame, Series
+from pandas import DataFrame
 
-from lang_main.analysis.graphs import TokenGraph
+from lang_main.analysis.graphs import Graph, TokenGraph, save_to_GraphML
 from lang_main.constants import (
     PATH_TO_DATASET,
     SAVE_PATH_FOLDER,
     SKIP_GRAPH_POSTPROCESSING,
+    SKIP_GRAPH_RESCALING,
     SKIP_PREPROCESSING,
     SKIP_TIME_ANALYSIS,
     SKIP_TOKEN_ANALYSIS,
@@ -20,6 +21,7 @@ from lang_main.pipelines.predefined import (
     build_timeline_pipe,
     build_tk_graph_pipe,
     build_tk_graph_post_pipe,
+    build_tk_graph_rescaling,
 )
 from lang_main.types import (
     EntryPoints,
@@ -34,6 +36,7 @@ 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_timeline = build_timeline_pipe()
 
 
@@ -81,6 +84,24 @@ def run_graph_postprocessing() -> None:
     )
 
 
+def run_graph_edge_rescaling() -> None:
+    entry_point_path = get_entry_point(SAVE_PATH_FOLDER, EntryPoints.TK_GRAPH_ANALYSIS)
+    loaded_results = cast(
+        tuple[TokenGraph],
+        load_pickle(entry_point_path),
+    )
+    tk_graph = loaded_results[0]
+    ret = cast(
+        tuple[TokenGraph, Graph], pipe_graph_rescaling.run(starting_values=(tk_graph,))
+    )
+    undirected_rescaled_graph = ret[1]
+    save_to_GraphML(
+        undirected_rescaled_graph,
+        saving_path=SAVE_PATH_FOLDER,
+        filename='TokenGraph-undirected-rescaled',
+    )
+
+
 # ** time analysis
 def run_time_analysis() -> None:
     # load entry point
@@ -101,6 +122,7 @@ def build_pipeline_container() -> PipelineContainer:
     container.add(run_preprocessing, skip=SKIP_PREPROCESSING)
     container.add(run_token_analysis, skip=SKIP_TOKEN_ANALYSIS)
     container.add(run_graph_postprocessing, skip=SKIP_GRAPH_POSTPROCESSING)
+    container.add(run_graph_edge_rescaling, skip=SKIP_GRAPH_RESCALING)
     container.add(run_time_analysis, skip=SKIP_TIME_ANALYSIS)
 
     return container

scripts/lang_main_config.toml

@@ -13,9 +13,10 @@ dataset = '../data/02_202307/Export4.csv'
 # be fully executed
 [control]
 preprocessing_skip = true
-token_analysis_skip = true
-graph_postprocessing_skip = true
-time_analysis_skip = false
+token_analysis_skip = false
+graph_postprocessing_skip = false
+graph_rescaling_skip = false
+time_analysis_skip = true
 
 #[export_filenames]
 #filename_cossim_filter_candidates = 'CosSim-FilterCandidates'

scripts/test.py

@@ -1,12 +1 @@
-from lang_main.analysis.preprocessing import clean_string_slim
-from lang_main.constants import SAVE_PATH_FOLDER
-
-print(SAVE_PATH_FOLDER)
-txt = """
-Wir feiern den Jahrestag am 23.11.2023, olé!
-tel:::: !!!!???? +++49 123 456 789
-
-Doch leben wir länger.
-"""
-print(txt)
-print(clean_string_slim(txt))
+import py4cytoscape