Presentation

app.py

@@ -9,7 +9,7 @@ import os
 
 # Define initial threshold values at the top of the script
 default_cause_threshold = 20
-default_indicator_threshold = 3
+default_indicator_threshold = 15
 
 # Load the trained model and tokenizer
 model_directory = "norygano/causalBERT"
@@ -31,7 +31,7 @@ st.markdown(
     unsafe_allow_html=True
 )
 st.markdown("[Model](https://huggingface.co/norygano/causalBERT) | [Data](https://huggingface.co/datasets/norygano/causenv) | [Project](https://www.uni-trier.de/universitaet/fachbereiche-faecher/fachbereich-ii/faecher/germanistik/professurenfachteile/germanistische-linguistik/professoren/prof-dr-martin-wengeler/kontroverse-diskurse/individium-gesellschaft)")
-st.write("Tags indicators and causes in explicit attributions of causality. GER only (atm)")
+st.write("Tags indicators and causes in explicit attributions of causality.")
 
 # Create tabs
 tab1, tab2, tab3, tab4, tab5 = st.tabs(["Prompt", "Indicators", "Causes", "Scatter", "Sankey"])
@@ -42,7 +42,7 @@ with tab1:
         "Autos stehen im Verdacht, Waldsterben zu verursachen.",
         "Fußball führt zu Waldschäden.",
         "Haustüren tragen zum Betonsterben bei.",
-    ]), placeholder="Your Sentences here.")
+    ]), placeholder="German only (currently)")
 
     sentences = [sentence.strip() for sentence in sentences_input.splitlines() if sentence.strip()]
 
@@ -84,8 +84,6 @@ with tab1:
 
 # Research Insights Tab
 with tab2:
-    st.write("## Indicators")
-
     # Overall
     st.subheader("Overall")
     fig_overall = indicator_chart(chart_type='overall')
@@ -97,29 +95,23 @@ with tab2:
     st.plotly_chart(fig_individual, use_container_width=True)
 
 with tab3:
-    st.write("## Causes")
     fig_causes = causes_chart()
     st.plotly_chart(fig_causes, use_container_width=True)
 
 with tab4:
-    st.write("## Scatter")
     fig_scatter = scatter()
     st.plotly_chart(fig_scatter, use_container_width=True)
 
 with tab5:
-    st.write("## Sankey")
-
     # Fixed height for the Sankey chart container
     with st.container():
         # Retrieve slider values and generate the diagram
         cause_threshold = st.session_state.get("cause_threshold", default_cause_threshold)
         indicator_threshold = st.session_state.get("indicator_threshold", default_indicator_threshold)
-
         fig_sankey = sankey(cause_threshold=cause_threshold, indicator_threshold=indicator_threshold)
         st.plotly_chart(fig_sankey, use_container_width=True)
 
     # Place sliders below the chart container
     with st.container():
-        st.write("Adjust thresholds for Sankey diagram:")
-        cause_threshold = st.slider("Cause Threshold", min_value=1, max_value=100, value=default_cause_threshold, key="cause_threshold")
-        indicator_threshold = st.slider("Indicator Threshold", min_value=1, max_value=100, value=default_indicator_threshold, key="indicator_threshold")
+        cause_threshold = st.slider("Cause >", min_value=1, max_value=100, value=default_cause_threshold, key="cause_threshold")
+        indicator_threshold = st.slider("Indicator >", min_value=1, max_value=100, value=default_indicator_threshold, key="indicator_threshold")

plot.py

@@ -61,6 +61,7 @@ def indicator_chart(chart_type='overall'):
             texttemplate='%{y}',
             textposition='inside',
             textfont=dict(color='rgb(255, 255, 255)'),
+            insidetextanchor='middle'
         )
 
     fig.update_layout(
@@ -150,32 +151,31 @@ def scatter(include_modality=False):
     df_reduced = pd.concat([df_reduced, metadata.reset_index(drop=True)], axis=1)
 
     # Plotting the scatter plot
-    hover_data = {'cause'}
+    hover_data = {'cause': True, 'Component 1': False, 'Component 2': False}
     if include_modality:
         hover_data['Modality'] = True
 
+    custom_labels = {
+    'subfolder': 'Effect',      # Renaming 'subfolder' to 'Category'
+    }
+
     fig = px.scatter(
         df_reduced,
         x='Component 1',
         y='Component 2',
         color='subfolder',  # Only subfolder colors will show in the legend
         symbol='indicator',  # Symbols for indicators, without showing in legend
+        labels=custom_labels,
         hover_data=hover_data,
-        labels={'Component 1': 'UMAP Dim 1', 'Component 2': 'UMAP Dim 2'},
         color_discrete_sequence=px.colors.qualitative.D3
     )
 
-    # Hide the legend for all symbol traces (indicator-based traces)
-    for trace in fig.data:
-        if trace.marker.symbol is not None:  # This targets symbol traces
-            trace.showlegend = False
-
     fig.update_layout(
-        xaxis=dict(showgrid=False),
-        yaxis=dict(showgrid=False),
+        xaxis=dict(showgrid=True),
+        yaxis=dict(showgrid=True),
         showlegend=True,  # Show only the subfolder legend
         legend=dict(
-            title="Term",  # Adjust title to indicate the subfolder legend
+            title="Effect, Indicator",  # Adjust title to indicate the subfolder legend
             yanchor="top",
             xanchor="left",
             borderwidth=1,

requirements.txt

@@ -3,4 +3,4 @@ transformers
 st-annotated-text
 plotly
 umap
-umap-learn
+umap-learn[cpu]