Legislator Bill Authorship

# --- COLLAPSIBLE SETUP BLOCK ---
from collections import Counter

import pandas as pd
import plotly.express as px
import sys
from pathlib import Path

cwd = Path.cwd().resolve()
sys.path[:0] = [str(cwd), str(cwd.parent)]

from book_utils import api_get, fetch_all, full_name, wrap_label, searchable_table

# --- COLLAPSIBLE PARAMETER BLOCK ---
# Pick the congress to analyze (8-20). Author linkage improves sharply from the
# 13th Congress onward, so the most recent congress is the default.
stats, _ = api_get("stats")
available = sorted(int(row["congress"]) for row in stats["bills_by_congress"])
SELECTED_CONGRESS = available[-1]          # <-- edit this (e.g. 17, 18, 19)
SELECTED_CONGRESS = min(max(SELECTED_CONGRESS, available[0]), available[-1])
print(f"Analyzing the {SELECTED_CONGRESS}th Congress")

# --- COLLAPSIBLE INGESTION BLOCK ---
documents = pd.DataFrame(fetch_all("documents", congress=SELECTED_CONGRESS))
documents[["name", "subtype", "date_filed", "authors"]].head()

# --- COLLAPSIBLE AUTHOR-TALLY BLOCK ---
# Walk every bill's author list. Each author gets credit for the bill (co-authors
# included). We keep two counters: overall bills per author, and bills per author
# split by chamber (subtype), keyed by a stable (id, name) tuple.
author_counts = Counter()
author_chamber_counts = Counter()

for _, row in documents.iterrows():
    for author in row.get("authors") or []:
        author_id = author.get("id")
        name = full_name(author)
        if author_id and name:
            key = (author_id, name)
            author_counts[key] += 1
            author_chamber_counts[(author_id, name, row.get("subtype"))] += 1

top_authors = pd.DataFrame(
    [{"author_id": key[0], "author": key[1], "authored_bills": value} for key, value in author_counts.items()]
).sort_values("authored_bills", ascending=False)

print(f"Distinct authors with at least one linked bill: {len(top_authors)}")
top_authors.head(20)

# Client-side searchable roster of every author and their bill count.
roster = top_authors.rename(
    columns={"author": "Legislator", "authored_bills": "Authored bills", "author_id": "ID"}
)[["Legislator", "Authored bills", "ID"]]
searchable_table(roster, caption=f"All bill authors in the {SELECTED_CONGRESS}th Congress (searchable)")

# --- COLLAPSIBLE TOP-AUTHOR CHART BLOCK ---
# wrap_label breaks long names across lines so they do not overflow the y-axis;
# we keep the untruncated name available for the hover tooltip.
top25 = top_authors.head(25).sort_values("authored_bills").copy()
top25["label"] = top25["author"].map(lambda n: wrap_label(n, width=24))

fig = px.bar(
    top25,
    x="authored_bills",
    y="label",
    orientation="h",
    custom_data=["author"],
    title=f"Top Bill Authors in the {SELECTED_CONGRESS}th Congress",
    labels={"authored_bills": "Authored bills", "label": "Legislator"},
)
# Show the full, unwrapped name in the tooltip.
fig.update_traces(hovertemplate="%{customdata[0]}<br>Authored bills: %{x}<extra></extra>")
# Extra left margin gives the wrapped names room to breathe.
fig.update_layout(margin={"l": 160}, yaxis_title="")
fig

# --- COLLAPSIBLE CHAMBER-SPLIT CHART BLOCK ---
# Expand the (author, chamber) counter into a tidy frame, keep only the top 15
# authors, and wrap their names for the axis.
by_type = pd.DataFrame(
    [
        {"author_id": author_id, "author": author, "bill_type": subtype, "bills": count}
        for (author_id, author, subtype), count in author_chamber_counts.items()
    ]
)
top_author_ids = top_authors.head(15)["author_id"]
by_type = by_type[by_type["author_id"].isin(top_author_ids)].copy()
by_type["label"] = by_type["author"].map(lambda n: wrap_label(n, width=24))

fig = px.bar(
    by_type,
    x="bills",
    y="label",
    color="bill_type",
    orientation="h",
    custom_data=["author"],
    title=f"Top Authors by Bill Type ({SELECTED_CONGRESS}th Congress)",
    labels={"bills": "Authored bills", "label": "Legislator", "bill_type": "Bill type"},
)
fig.update_traces(hovertemplate="%{customdata[0]}<br>Bills: %{x}<extra></extra>")
fig.update_layout(margin={"l": 160}, yaxis_title="")
fig