File size: 5,276 Bytes
df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 df2b5a3 8b4e4f2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | import streamlit as st
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
# Streamlit page setup
st.set_page_config(page_title="Legislative Bill Analysis", layout="wide")
st.title("Legislative Bill Analysis Dashboard")
# File uploader
uploaded_file = st.file_uploader("Upload Illinois_Entire_Data_Insights_Final_v2.csv", type=["csv", "xlsx"])
if uploaded_file:
# Read file
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!")
# Preprocessing date and year
df['status_date'] = pd.to_datetime(df['status_date'], errors='coerce')
df['year'] = df['status_date'].dt.year
# ------------------------
# 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')
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)
# ------------------------
# 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')
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)
else:
st.info(" Please upload a dataset file to view the visualizations.")
|