Update app.py

app.py

@@ -1,19 +1,17 @@
 import streamlit as st
 import pandas as pd
+import plotly.express as px
 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")
 
+# Streamlit page setup
+st.set_page_config(page_title="Legislative Bill Analysis", 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"])
+# File uploader
+uploaded_file = st.file_uploader("Upload Illinois_Entire_Data_Insights_Final_v2.csv", type=["csv", "xlsx"])
 
 if uploaded_file:
-    # Load dataset
+    # Read file
     if uploaded_file.name.endswith('.csv'):
         df = pd.read_csv(uploaded_file)
     else:
@@ -21,52 +19,126 @@ if 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()
+    # Preprocessing date and year
+    df['status_date'] = pd.to_datetime(df['status_date'], errors='coerce')
+    df['year'] = df['status_date'].dt.year
 
-    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)}
+    # ------------------------
+    #  Visualization 1: Yearly Bills by Intent
+    # ------------------------
+    st.header(" Bills Over Time by Intent")
+    yearly_intent_counts = df.groupby(['year', 'intent_standardized']).size().reset_index(name='bill_count')
 
-        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')
+    fig1 = px.bar(
+        yearly_intent_counts,
+        x='year',
+        y='bill_count',
+        color='intent_standardized',
+        title='Bills Over Time by Intent',
+        labels={'year': 'Year', 'bill_count': 'Number of Bills', 'intent_standardized': 'Intent'},
+        barmode='group',
+        height=500,
+        color_discrete_sequence=px.colors.qualitative.Set2
+    )
+    fig1.update_layout(
+        xaxis=dict(tickangle=0),
+        legend_title_text='Intent',
+        plot_bgcolor='white',
+        paper_bgcolor='white',
+        font=dict(color='black'),
+        title_font=dict(size=20)
+    )
+    st.plotly_chart(fig1, use_container_width=True)
 
-        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()
+    # ------------------------
+    #  Visualization 2: Animated Stance Distribution by Policy Area
+    # ------------------------
+    st.header("Stance Distribution Across Policy Areas (Animated by Year)")
+    grouped = df.groupby(['year', 'policy_impact_areas_standardized', 'stance_standardized']).size().reset_index(name='count')
 
-        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)
+    fig2 = px.bar(
+        grouped,
+        x='count',
+        y='policy_impact_areas_standardized',
+        color='stance_standardized',
+        orientation='h',
+        animation_frame='year',
+        title='Stance Distribution Across Policy Areas (Animated by Year)',
+        labels={
+            'count': 'Number of Bills',
+            'policy_impact_areas_standardized': 'Policy Area',
+            'stance_standardized': 'Stance'
+        },
+        height=600,
+        color_discrete_sequence=px.colors.qualitative.Set2
+    )
+    fig2.update_layout(
+        legend_title='Stance',
+        xaxis_title='Number of Bills',
+        yaxis_title='Policy Area',
+        plot_bgcolor='white',
+        paper_bgcolor='white',
+        font=dict(color='black'),
+        title_font=dict(size=20),
+        margin=dict(t=60, l=150)
+    )
+    st.plotly_chart(fig2, use_container_width=True)
+
+    # ------------------------
+    #  Visualization 3: Sankey Diagram - Intent → Beneficiaries → Increasing Aspects
+    # ------------------------
+    st.header("🔗 Top Intent → Beneficiaries → Increasing Aspect Flows (Sankey)")
+
+    def shorten(text, max_len=35):
+        return text if len(text) <= max_len else text[:max_len] + "..."
+
+    sankey_data = df[['intent_standardized', 'intended_beneficiaries_standardized', 'increasing_aspects_standardized']].dropna()
+    path_counts = (
+        sankey_data.groupby(['intent_standardized', 'intended_beneficiaries_standardized', 'increasing_aspects_standardized'])
+        .size()
+        .reset_index(name='count')
+        .sort_values(by='count', ascending=False)
+    )
+
+    TOP_N = 15
+    filtered_paths = path_counts.head(TOP_N)
+    unique_labels = pd.unique(filtered_paths[['intent_standardized', 'intended_beneficiaries_standardized', 'increasing_aspects_standardized']].values.ravel())
+    short_labels = [shorten(label) for label in unique_labels]
+    label_to_index = {label: i for i, label in enumerate(unique_labels)}
+    label_to_short = dict(zip(unique_labels, short_labels))
+
+    sources = list(filtered_paths['intent_standardized'].map(label_to_index))
+    targets = list(filtered_paths['intended_beneficiaries_standardized'].map(label_to_index))
+    values = list(filtered_paths['count'])
+
+    sources += list(filtered_paths['intended_beneficiaries_standardized'].map(label_to_index))
+    targets += list(filtered_paths['increasing_aspects_standardized'].map(label_to_index))
+    values += list(filtered_paths['count'])
+
+    fig3 = go.Figure(data=[go.Sankey(
+        arrangement="snap",
+        node=dict(
+            pad=25,
+            thickness=20,
+            line=dict(color="black", width=0.3),
+            label=[label_to_short[label] for label in unique_labels],
+            color="lightsteelblue"
+        ),
+        link=dict(
+            source=sources,
+            target=targets,
+            value=values,
+            color="rgba(150,150,150,0.4)"
+        )
+    )])
+
+    fig3.update_layout(
+        title_text="Top Intent → Beneficiaries → Increasing Aspect Flows",
+        font_size=12,
+        height=600,
+        margin=dict(l=50, r=50, t=80, b=30)
+    )
+    st.plotly_chart(fig3, use_container_width=True)
 
-        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.")
+    st.info(" Please upload a dataset file to view the visualizations.")