promotion/literaturanalyse
Archived
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Verbesserungen: Balken und Sankey implementiert

Browse Source
This commit is contained in:
Jochen Hanisch-Johannsen
2025-05-18 15:30:07 +02:00
parent a5c4875e7f
commit 6c96b10cda
1 changed files with 122 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files

295
analyse_netzwerk.py
View File

@ -4,6 +4,9 @@ import os
# Clear the terminal # Clear the terminal
os.system('cls' if os.name == 'nt' else 'clear') os.system('cls' if os.name == 'nt' else 'clear')
import sys
sys.path.append('/Users/jochenhanisch-johannsen/Documents/scripte/ci_template')
import bibtexparser import bibtexparser
import pandas as pd import pandas as pd
import numpy as np import numpy as np
@ -21,8 +24,16 @@ import math
import re import re
import subprocess import subprocess
export_fig_visual = False # Expot der Visualsierungen gesamt
theme = "dark" # Optionen: "dark" oder "light"
# Template
from ci_template import plotly_template
plotly_template.set_theme(theme)
pd.set_option('display.max_columns', None)
pd.set_option('future.no_silent_downcasting', True)
bib_filename = "Suchergebnisse.bib" bib_filename = "Suchergebnisse.bib"
export_fig_visual = False
# Optional: slugify-Funktion # Optional: slugify-Funktion
def slugify(value): def slugify(value):
@ -68,19 +79,11 @@ def export_figure(fig, name, flag, bib_filename=None):
print("❌ Fehler beim Übertragen:") print("❌ Fehler beim Übertragen:")
print(e.stderr) print(e.stderr)
# Farben definieren from ci_template.plotly_template import get_colors, get_plot_styles, get_standard_layout
colors = {
"background": "#003366", # Hintergrundfarbe # Farben und Plot-Styles zentral aus Template laden
"text": "#333333", # Textfarbe colors = get_colors()
"accent": "#663300", # Akzentfarbe plot_styles = get_plot_styles()
"primaryLine": "#660066", # Bildungswirkfaktor
"secondaryLine": "#cc6600", # Bildungswirkindikator
"depthArea": "#006666", # Kompetenzmessunsicherheit
"brightArea": "#66CCCC", # Kompetenzentwicklungsunsicherheit
"positiveHighlight": "#336600", # Positive Hervorhebung
"negativeHighlight": "#990000", # Negative Hervorhebung
"white": "#ffffff" # Weiß
}
# Liste der Farben, die für die Wörter verwendet werden sollen # Liste der Farben, die für die Wörter verwendet werden sollen
word_colors = [ word_colors = [
@ -267,7 +270,7 @@ def visualize_network(bib_database):
edge_trace = go.Scatter( edge_trace = go.Scatter(
x=edge_x, y=edge_y, x=edge_x, y=edge_y,
line=dict(width=0.5, color=colors['white']), line=plot_styles['linie_secondaryLine'],
hoverinfo='none', hoverinfo='none',
mode='lines') mode='lines')
@ -290,6 +293,16 @@ def visualize_network(bib_database):
tertiary_nodes.append(node_data) tertiary_nodes.append(node_data)
def create_node_trace(nodes, name, color): def create_node_trace(nodes, name, color):
# Wähle Punktstil je nach color
if color == colors['primaryLine']:
marker_style = plot_styles['punkt_primaryLine'].copy()
elif color == colors['secondaryLine']:
marker_style = plot_styles['punkt_secondaryLine'].copy()
elif color == colors['brightArea']:
marker_style = plot_styles['punkt_brightArea'].copy()
else:
marker_style = dict(color=color)
marker_style['size'] = [n['size'] for n in nodes]
return go.Scatter( return go.Scatter(
x=[n['x'] for n in nodes], x=[n['x'] for n in nodes],
y=[n['y'] for n in nodes], y=[n['y'] for n in nodes],
@ -297,13 +310,9 @@ def visualize_network(bib_database):
text=[n['text'] for n in nodes], text=[n['text'] for n in nodes],
hovertext=[n['hovertext'] for n in nodes], hovertext=[n['hovertext'] for n in nodes],
hoverinfo='text', hoverinfo='text',
marker=dict( marker=marker_style,
size=[n['size'] for n in nodes],
color=color,
line_width=2
),
textposition="top center", textposition="top center",
textfont=dict(size=12), textfont=dict(size=10, color=colors['white']),
name=name name=name
) )
@ -311,42 +320,15 @@ def visualize_network(bib_database):
secondary_trace = create_node_trace(secondary_nodes, "Sekundäre Begriffe", colors['secondaryLine']) secondary_trace = create_node_trace(secondary_nodes, "Sekundäre Begriffe", colors['secondaryLine'])
tertiary_trace = create_node_trace(tertiary_nodes, "Tertiäre Begriffe", colors['brightArea']) tertiary_trace = create_node_trace(tertiary_nodes, "Tertiäre Begriffe", colors['brightArea'])
fig = go.Figure(data=[edge_trace, primary_trace, secondary_trace, tertiary_trace], fig = go.Figure(data=[edge_trace, primary_trace, secondary_trace, tertiary_trace])
layout=go.Layout( layout = get_standard_layout(
title=f'Suchbegriff-Netzwerk nach Relevanz und Semantik (n={sum(fundzahlen.values())}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', title=f"Suchbegriff-Netzwerk nach Relevanz und Semantik (n={sum(fundzahlen.values())}, Stand: {current_date})",
titlefont_size=16, x_title="Technologische Dimension",
showlegend=True, y_title="Pädagogische Dimension"
legend=dict( )
bgcolor=colors['background'], layout["margin"] = dict(b=20, l=5, r=5, t=40)
bordercolor=colors['white'], layout["hovermode"] = "closest"
borderwidth=1, fig.update_layout(**layout)
font=dict(color=colors['white']),
itemsizing='constant'
),
hovermode='closest',
margin=dict(b=20, l=5, r=5, t=40),
xaxis=dict(
range=[x_scale_min, x_scale_max + 1],
showgrid=True,
zeroline=True,
tickmode='linear',
tick0=x_scale_min,
dtick=(x_scale_max - x_scale_min) / 4,
title='Technologische Dimension'
),
yaxis=dict(
range=[y_scale_min, y_scale_max + 1],
showgrid=True,
zeroline=True,
tickmode='linear',
tick0=y_scale_min,
dtick=(y_scale_max - y_scale_min) / 4,
title='Pädagogische Dimension'
),
plot_bgcolor=colors['background'],
paper_bgcolor=colors['background'],
font=dict(color=colors['white'])
))
fig.show() fig.show()
export_figure(fig, "visualize_network", export_fig_visualize_network, bib_filename) export_figure(fig, "visualize_network", export_fig_visualize_network, bib_filename)
@ -434,26 +416,18 @@ def visualize_tags(bib_database):
data, data,
x='Tag', x='Tag',
y='Count', y='Count',
title=f'Häufigkeit der Suchbegriffe in der Literaturanalyse (n={total_count}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', title=f'Häufigkeit der Suchbegriffe in der Literaturanalyse (n={total_count}, Stand: {current_date})',
labels={'Tag': 'Tag', 'Count': 'Anzahl der Vorkommen'}, labels={'Tag': 'Tag', 'Count': 'Anzahl der Vorkommen'},
color='Type', color='Type',
color_discrete_map=color_map, color_discrete_map=color_map,
text_auto=True text_auto=True
) )
# Layout anpassen fig.update_layout(**get_standard_layout(
fig.update_layout( title=fig.layout.title.text,
plot_bgcolor=colors['background'], x_title='Tag',
paper_bgcolor=colors['background'], y_title='Anzahl der Vorkommen'
font=dict(color=colors['white']), ))
margin=dict(l=0, r=0, t=40, b=40),
autosize=True
)
fig.update_traces(
marker_line_color=colors['white'],
marker_line_width=1.5
)
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_tags", export_fig_visualize_tags, bib_filename) export_figure(fig, "visualize_tags", export_fig_visualize_tags, bib_filename)
@ -488,18 +462,13 @@ def visualize_index(bib_database):
print(f"Häufigkeit Indizes (Gesamtanzahl: {total_count}):") print(f"Häufigkeit Indizes (Gesamtanzahl: {total_count}):")
print(tabulate(index_data, headers="keys", tablefmt="grid")) print(tabulate(index_data, headers="keys", tablefmt="grid"))
fig = px.bar(index_data, x='Index', y='Count', title=f'Relevanzschlüssel nach Indexkategorien (n={total_count}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', labels={'Index': 'Index', 'Count': 'Anzahl der Vorkommen'}, text_auto=True) fig = px.bar(index_data, x='Index', y='Count', title=f'Relevanzschlüssel nach Indexkategorien (n={total_count}, Stand: {current_date})', labels={'Index': 'Index', 'Count': 'Anzahl der Vorkommen'}, text_auto=True)
fig.update_layout(**get_standard_layout(
fig.update_layout( title=fig.layout.title.text,
plot_bgcolor=colors['background'], x_title='Index',
paper_bgcolor=colors['background'], y_title='Anzahl der Vorkommen'
font=dict(color=colors['white']), ))
margin=dict(l=0, r=0, t=40, b=40), fig.update_traces(marker=plot_styles['balken_primaryLine'])
autosize=True
)
fig.update_traces(marker_color=colors['primaryLine'], marker_line_color=colors['white'], marker_line_width=1.5)
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_index", export_fig_visualize_index, bib_filename) export_figure(fig, "visualize_index", export_fig_visualize_index, bib_filename)
@ -534,18 +503,13 @@ def visualize_research_questions(bib_database):
print(f"Häufigkeit Forschungsunterfragen (Gesamtanzahl: {total_count}):") print(f"Häufigkeit Forschungsunterfragen (Gesamtanzahl: {total_count}):")
print(tabulate(rq_data, headers="keys", tablefmt="grid")) print(tabulate(rq_data, headers="keys", tablefmt="grid"))
fig = px.bar(rq_data_df, x='Research_Question', y='Count', title=f'Zuordnung der Literatur zu Forschungsunterfragen (n={total_count}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', labels={'Research_Question': 'Forschungsunterfrage', 'Count': 'Anzahl der Vorkommen'}, text_auto=True) fig = px.bar(rq_data_df, x='Research_Question', y='Count', title=f'Zuordnung der Literatur zu Forschungsunterfragen (n={total_count}, Stand: {current_date})', labels={'Research_Question': 'Forschungsunterfrage', 'Count': 'Anzahl der Vorkommen'}, text_auto=True)
fig.update_layout(**get_standard_layout(
fig.update_layout( title=fig.layout.title.text,
plot_bgcolor=colors['background'], x_title='Forschungsunterfrage',
paper_bgcolor=colors['background'], y_title='Anzahl der Vorkommen'
font=dict(color=colors['white']), ))
margin=dict(l=0, r=0, t=40, b=40), fig.update_traces(marker=plot_styles['balken_primaryLine'])
autosize=True
)
fig.update_traces(marker_color=colors['primaryLine'], marker_line_color=colors['white'], marker_line_width=1.5)
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_research_questions", export_fig_visualize_research_questions, bib_filename) export_figure(fig, "visualize_research_questions", export_fig_visualize_research_questions, bib_filename)
@ -575,18 +539,13 @@ def visualize_categories(bib_database):
print(f"Häufigkeit Kategorien (Gesamtanzahl: {total_count}):") print(f"Häufigkeit Kategorien (Gesamtanzahl: {total_count}):")
print(tabulate(cat_data, headers="keys", tablefmt="grid")) print(tabulate(cat_data, headers="keys", tablefmt="grid"))
fig = px.bar(cat_data_df, x='Category', y='Count', title=f'Textsortenzuordnung der analysierten Quellen (n={total_count}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', labels={'Category': 'Kategorie', 'Count': 'Anzahl der Vorkommen'}, text_auto=True) fig = px.bar(cat_data_df, x='Category', y='Count', title=f'Textsortenzuordnung der analysierten Quellen (n={total_count}, Stand: {current_date})', labels={'Category': 'Kategorie', 'Count': 'Anzahl der Vorkommen'}, text_auto=True)
fig.update_layout(**get_standard_layout(
fig.update_layout( title=fig.layout.title.text,
plot_bgcolor=colors['background'], x_title='Kategorie',
paper_bgcolor=colors['background'], y_title='Anzahl der Vorkommen'
font=dict(color=colors['white']), ))
margin=dict(l=0, r=0, t=40, b=40), fig.update_traces(marker=plot_styles['balken_primaryLine'])
autosize=True
)
fig.update_traces(marker_color=colors['primaryLine'], marker_line_color=colors['white'], marker_line_width=1.5)
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_categories", export_fig_visualize_categories, bib_filename) export_figure(fig, "visualize_categories", export_fig_visualize_categories, bib_filename)
@ -616,24 +575,21 @@ def visualize_time_series(bib_database):
df, df,
x='Year', x='Year',
y='Count', y='Count',
title=f'Jährliche Veröffentlichungen in der Literaturanalyse (n={sum(year_counts.values())}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', title=f'Jährliche Veröffentlichungen in der Literaturanalyse (n={sum(year_counts.values())}, Stand: {current_date})',
labels={'Year': 'Jahr', 'Count': 'Anzahl der Veröffentlichungen'} labels={'Year': 'Jahr', 'Count': 'Anzahl der Veröffentlichungen'}
) )
layout = get_standard_layout(
fig.update_layout( title=fig.layout.title.text,
plot_bgcolor=colors['background'], x_title='Jahr',
paper_bgcolor=colors['background'], y_title='Anzahl der Veröffentlichungen'
font=dict(color=colors['white']), )
xaxis=dict( layout["xaxis"] = dict(
tickmode='linear', tickmode='linear',
dtick=2, dtick=2,
tick0=min(publication_years) tick0=min(publication_years)
),
margin=dict(l=0, r=0, t=40, b=40),
autosize=True
) )
fig.update_layout(**layout)
fig.update_traces(line=dict(color=colors['secondaryLine'], width=3)) fig.update_traces(line=plot_styles['linie_secondaryLine'])
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_time_series", export_fig_visualize_time_series, bib_filename) export_figure(fig, "visualize_time_series", export_fig_visualize_time_series, bib_filename)
else: else:
@ -653,16 +609,13 @@ def visualize_top_authors(bib_database):
if top_authors: if top_authors:
df = pd.DataFrame(top_authors, columns=['Author', 'Count']) df = pd.DataFrame(top_authors, columns=['Author', 'Count'])
fig = px.bar(df, x='Author', y='Count', title=f'Meistgenannte Autor:innen in der Literaturanalyse (Top {top_n}, n={sum(author_counts.values())}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', labels={'Author': 'Autor', 'Count': 'Anzahl der Werke'}, text_auto=True) fig = px.bar(df, x='Author', y='Count', title=f'Meistgenannte Autor:innen in der Literaturanalyse (Top {top_n}, n={sum(author_counts.values())}, Stand: {current_date})', labels={'Author': 'Autor', 'Count': 'Anzahl der Werke'}, text_auto=True)
fig.update_layout( fig.update_layout(**get_standard_layout(
plot_bgcolor=colors['background'], title=fig.layout.title.text,
paper_bgcolor=colors['background'], x_title='Autor',
font=dict(color=colors['white']), y_title='Anzahl der Werke'
margin=dict(l=0, r=0, t=40, b=40), ))
autosize=True fig.update_traces(marker=plot_styles['balken_primaryLine'])
)
fig.update_traces(marker_color=colors['primaryLine'], marker_line_color=colors['white'], marker_line_width=1.5)
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_top_authors", export_fig_visualize_top_authors, bib_filename) export_figure(fig, "visualize_top_authors", export_fig_visualize_top_authors, bib_filename)
else: else:
@ -695,19 +648,16 @@ def visualize_top_publications(bib_database):
df = pd.DataFrame(publication_data) df = pd.DataFrame(publication_data)
fig = px.bar(df, x='Title', y='Count', title=f'Häufig zitierte Publikationen in der Analyse (Top {top_n}, n={sum(publication_counts.values())}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', labels={'Title': 'Titel', 'Count': 'Anzahl der Nennungen'}) fig = px.bar(df, x='Title', y='Count', title=f'Häufig zitierte Publikationen in der Analyse (Top {top_n}, n={sum(publication_counts.values())}, Stand: {current_date})', labels={'Title': 'Titel', 'Count': 'Anzahl der Nennungen'})
layout = get_standard_layout(
fig.update_layout( title=fig.layout.title.text,
plot_bgcolor=colors['background'], x_title='Titel',
paper_bgcolor=colors['background'], y_title='Anzahl der Nennungen'
font=dict(color=colors['white']),
xaxis_tickangle=-45,
margin=dict(l=0, r=0, t=40, b=40),
autosize=True
) )
layout["xaxis"] = layout.get("xaxis", {})
fig.update_traces(marker_color=colors['primaryLine'], marker_line_color=colors['white'], marker_line_width=1.5) layout["xaxis"]["tickangle"] = -45
fig.update_layout(**layout)
fig.update_traces(marker=plot_styles['balken_primaryLine'])
fig.show(config={"responsive": True}) fig.show(config={"responsive": True})
export_figure(fig, "visualize_top_publications", export_fig_visualize_top_publications, bib_filename) export_figure(fig, "visualize_top_publications", export_fig_visualize_top_publications, bib_filename)
@ -823,7 +773,7 @@ def create_path_diagram(data):
node=dict( node=dict(
pad=15, pad=15,
thickness=20, thickness=20,
line=dict(color=colors['white'], width=0.5), line=dict(color="black", width=0.5),
label=labels, label=labels,
color=node_colors color=node_colors
), ),
@ -833,14 +783,13 @@ def create_path_diagram(data):
value=values value=values
) )
)]) )])
layout = get_standard_layout(
fig.update_layout( title=f'Kategorischer Analysepfad der Literatur (n={len(data)}, Stand: {current_date})',
title_text=f'Kategorischer Analysepfad der Literatur (n={len(data)}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', x_title='',
font=dict(size=10, color=colors['white']), y_title=''
plot_bgcolor=colors['background'],
paper_bgcolor=colors['background']
) )
layout["font"] = dict(size=10, color=colors['white'])
fig.update_layout(**layout)
fig.show() fig.show()
export_figure(fig, "create_path_diagram", export_fig_create_path_diagram, bib_filename) export_figure(fig, "create_path_diagram", export_fig_create_path_diagram, bib_filename)
@ -950,30 +899,26 @@ def create_sankey_diagram(bib_database):
# Sankey-Diagramm erstellen # Sankey-Diagramm erstellen
fig = go.Figure(go.Sankey( fig = go.Figure(go.Sankey(
node=dict( node=dict(
pad=15, **plot_styles["sankey_node"],
thickness=20,
line=dict(color="black", width=0.5),
label=node_labels, label=node_labels,
color=node_colors color=node_colors
), ),
link=dict( link=dict(
**plot_styles["sankey_link"],
source=sources, source=sources,
target=targets, target=targets,
value=values, value=values
hoverinfo='all', # Zeigt detaillierte Infos bei Mouseover an
color=colors['accent']
) )
)) ))
# Layout anpassen # Layout anpassen
fig.update_layout( layout = get_standard_layout(
title_text=f"Flussdiagramm der Literaturselektion (Stichprobe: n={sample_size}, Stand: {current_date}) | Quelle: {bib_filename.replace('.bib', '')}", title=f"Flussdiagramm der Literaturselektion (Stichprobe: n={sample_size}, Stand: {current_date})",
font_size=12, # Größere Schriftgröße für bessere Lesbarkeit x_title='',
plot_bgcolor=colors['background'], y_title=''
paper_bgcolor=colors['background'],
font=dict(color=colors['white'])
) )
layout["font"] = layout.get("font", {})
layout["font"]["size"] = 12
fig.update_layout(**layout)
fig.show() fig.show()
export_figure(fig, "create_sankey_diagram", export_fig_create_sankey_diagram, bib_filename) export_figure(fig, "create_sankey_diagram", export_fig_create_sankey_diagram, bib_filename)
@ -1073,35 +1018,29 @@ def visualize_sources_status(bib_database):
)) ))
fig = go.Figure() fig = go.Figure()
fig.add_trace(go.Bar( fig.add_trace(go.Bar(
x=tags, x=tags,
y=analysiert_values, y=analysiert_values,
name='Analysiert', name='Analysiert',
marker=dict(color=analysiert_colors) marker=dict(color=analysiert_colors)
)) ))
fig.add_trace(go.Bar( fig.add_trace(go.Bar(
x=tags, x=tags,
y=nicht_analysiert_values, y=nicht_analysiert_values,
name='Nicht-Analysiert', name='Nicht-Analysiert',
marker=dict(color=colors['primaryLine']) marker=plot_styles['balken_primaryLine']
)) ))
layout = get_standard_layout(
fig.update_layout( title=f'Analyse- und Stichprobenstatus je Suchordner (n={sum(counts["Identifiziert"] for counts in source_data.values())}, Stand: {current_date})',
barmode='stack', x_title='Suchbegriffsordner',
title=f'Analyse- und Stichprobenstatus je Suchordner (n={sum(counts["Identifiziert"] for counts in source_data.values())}, Stand: {current_date}) | Quelle: {bib_filename.replace(".bib", "")}', y_title='Anzahl der Quellen'
xaxis_title='Suchbegriffsordner', )
yaxis_title='Anzahl der Quellen', layout["barmode"] = "stack"
plot_bgcolor=colors['background'], layout["xaxis"] = dict(
paper_bgcolor=colors['background'],
font=dict(color=colors['white']),
xaxis=dict(
categoryorder='array', categoryorder='array',
categoryarray=search_folder_tags categoryarray=search_folder_tags
) )
) fig.update_layout(**layout)
fig.show() fig.show()
export_figure(fig, "visualize_sources_status", export_fig_visualize_sources_status, bib_filename) export_figure(fig, "visualize_sources_status", export_fig_visualize_sources_status, bib_filename)