Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Illinois_Entire_Data_Insights_Final_v2.csv filter=lfs diff=lfs merge=lfs -text

Illinois_Entire_Data_Insights_Final_v2.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0575adb9b5378333ea6165aed84a71464f64837d7e5e5ecdb3b67d411ab6eed8
+size 85904918

app.py

@@ -0,0 +1,72 @@
+import streamlit as st
+import pandas as pd
+import plotly.graph_objects as go
+import matplotlib.pyplot as plt
+import seaborn as sns
+#trial
+# Set Streamlit page config
+st.set_page_config(page_title="Legislative Visualizations", layout="wide")
+
+st.title("Legislative Bill Analysis Dashboard")
+
+# Upload dataset
+uploaded_file = st.file_uploader("Illinois_Entire_Data_Insights_Final_v2.csv", type=["csv", "xlsx"])
+
+if uploaded_file:
+    # Load dataset
+    if uploaded_file.name.endswith('.csv'):
+        df = pd.read_csv(uploaded_file)
+    else:
+        df = pd.read_excel(uploaded_file)
+
+    st.success("File uploaded and read successfully!")
+
+    # Sankey Diagram
+    st.header("🔗 Sankey Diagram: Intent → Stance → Beneficiaries")
+    sankey_df = df[['intent_standardized', 'stance_standardized', 'intended_beneficiaries_standardized']].dropna()
+
+    if not sankey_df.empty:
+        labels = list(pd.unique(sankey_df['intent_standardized'].tolist() +
+                                sankey_df['stance_standardized'].tolist() +
+                                sankey_df['intended_beneficiaries_standardized'].tolist()))
+        label_map = {label: i for i, label in enumerate(labels)}
+
+        intent_stance = sankey_df.groupby(['intent_standardized', 'stance_standardized']).size().reset_index(name='count')
+        stance_beneficiary = sankey_df.groupby(['stance_standardized', 'intended_beneficiaries_standardized']).size().reset_index(name='count')
+
+        source = intent_stance['intent_standardized'].map(label_map).tolist() + stance_beneficiary['stance_standardized'].map(label_map).tolist()
+        target = intent_stance['stance_standardized'].map(label_map).tolist() + stance_beneficiary['intended_beneficiaries_standardized'].map(label_map).tolist()
+        value  = intent_stance['count'].tolist() + stance_beneficiary['count'].tolist()
+
+        fig_sankey = go.Figure(data=[go.Sankey(
+            node=dict(pad=15, thickness=20, line=dict(color="black", width=0.5), label=labels),
+            link=dict(source=source, target=target, value=value)
+        )])
+        fig_sankey.update_layout(title_text="Sankey: Intent → Stance → Beneficiary", font_size=12)
+
+        st.plotly_chart(fig_sankey, use_container_width=True)
+    else:
+        st.warning("Sankey input columns contain only null values or are missing.")
+
+    # Heatmap
+    st.header("🧯 Heatmap: Category vs Policy Impact Area")
+    heat_df = df[['category_&_subcategory_standardized', 'policy_impact_areas_standardized']].dropna()
+
+    if not heat_df.empty:
+        heat = heat_df.pivot_table(index='category_&_subcategory_standardized',
+                                   columns='policy_impact_areas_standardized',
+                                   aggfunc=len,
+                                   fill_value=0)
+
+        plt.figure(figsize=(14, 8))
+        sns.heatmap(heat, cmap='coolwarm', annot=False)
+        plt.title("Heatmap: Category vs Policy Impact Area")
+        plt.xlabel("Policy Impact Area")
+        plt.ylabel("Category")
+        plt.tight_layout()
+
+        st.pyplot(plt)
+    else:
+        st.warning("Heatmap input columns contain only null values or are missing.")
+else:
+    st.info("Please upload a dataset file to view the visualizations.")

requirements.txt

@@ -1,3 +1,76 @@
-altair
-pandas
-streamlit
+altair==5.5.0
+asttokens==3.0.0
+attrs==24.2.0
+blinker==1.9.0
+branca==0.8.0
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+comm==0.2.2
+contourpy==1.3.1
+cycler==0.12.1
+debugpy==1.8.9
+decorator==5.1.1
+executing==2.1.0
+folium==0.18.0
+fonttools==4.55.1
+gitdb==4.0.11
+GitPython==3.1.43
+idna==3.10
+ipykernel==6.29.5
+ipython==8.30.0
+jedi==0.19.2
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.9.3
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+narwhals==1.15.2
+nest-asyncio==1.6.0
+numpy==2.1.3
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.0.0
+platformdirs==4.3.6
+plotly==5.24.1
+prompt_toolkit==3.0.48
+protobuf==5.29.1
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==18.1.0
+pydeck==0.9.1
+Pygments==2.18.0
+pyparsing==3.2.0
+python-dateutil==2.9.0.post0
+pytz==2024.2
+pyzmq==26.2.0
+referencing==0.35.1
+requests==2.32.3
+rich==13.9.4
+rpds-py==0.22.3
+seaborn==0.13.2
+six==1.17.0
+smmap==5.0.1
+stack-data==0.6.3
+streamlit==1.40.2
+streamlit_folium==0.23.2
+tenacity==9.0.0
+toml==0.10.2
+tornado==6.4.2
+traitlets==5.14.3
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+watchdog==6.0.0
+wcwidth==0.2.13
+xyzservices==2024.9.0