src/app.py

import numpy as np
import pandas as pd

import streamlit as st

from process import (
    process_comparisons,
    process_model_sentences
)

from components import (
    render_heading,
    render_loading,
    render_parameters,
    render_tab_info,
    render_tab_tables,
    render_tab_counts,
    render_tab_models,
    render_tab_inspect,
    render_tab_project,
)


comparison_file = 'data/visualize/model-segments_vs_bill-texts.json.zst'
billtext_file = 'data/visualize/texts.json.zst'
modelseg_file = 'data/visualize/segments.json.zst'

# Heading
render_heading.render()

# Load data
df, text_df, seg_df = render_loading.render(
    comparison_file,
    billtext_file,
    modelseg_file
)


# Set parameters
(
    min_nwords, 
    thres_ratio,
    min_high_sim_num_sents,
    min_high_sim_pct_sim,
    version_to_count
) = render_parameters.render()

# Process data
(
    sim_df,
    proj_df,
    disp_sim_df, 
    multi_model_bills,
    sim_bill_counts, 
    sim_state_counts, 
    sec_counts
) = process_comparisons(
    df,
    seg_df,
    min_nwords,
    thres_ratio,
    min_high_sim_num_sents,
    min_high_sim_pct_sim,
    version_to_count
)

model_sent_df = process_model_sentences(
    df,
    seg_df,
    min_nwords, 
    thres_ratio,
)

model_bills = model_sent_df['model'].unique()

# Construct tabs
(
    tab_info,
    tab_tables, 
    tab_counts, 
    tab_models, 
    tab_inspect,
    tab_project,
) = st.tabs([
    "Information",
    "Tables", 
    "Counts",
    "Models",
    "Inspect",
    "Projection"
])

# Render information
render_tab_info.render(tab_info)

# Render data tables of similar bills
render_tab_tables.render(
    tab_tables, 
    disp_sim_df, multi_model_bills
)

# Render bar charts for counts
render_tab_counts.render(
    tab_counts,
    sim_bill_counts, sim_state_counts, 
    model_bills, sec_counts
)

# Render model sentences' prevalence
render_tab_models.render(
    tab_models,
    model_bills, model_sent_df
)

# Render tab to inspect model sentence and corresponding bill's sentences across versions
render_tab_inspect.render(
    tab_inspect,
    df, seg_df, 
    text_df, disp_sim_df,
    min_nwords, thres_ratio,
)

# Projection of bills
render_tab_project.render(
    tab_project,
    proj_df,
)