Bill Pipeline Timing and Scope

# --- COLLAPSIBLE SETUP BLOCK ---
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, congress_range

# --- COLLAPSIBLE PARAMETER BLOCK ---
# Change SELECTED_CONGRESS to any congress the API serves (8-20). Leave it as the
# default to analyze the most recent congress. We clamp to the valid range so a
# typo cannot break the build.
available = congress_range()
SELECTED_CONGRESS = available[-1]          # <-- edit this (e.g. 13, 17, 19)
SELECTED_CONGRESS = min(max(SELECTED_CONGRESS, available[0]), available[-1])
print(f"Available congresses: {available}")
print(f"Analyzing the {SELECTED_CONGRESS}th Congress")

# --- COLLAPSIBLE CONTEXT BLOCK ---
# Show where the selected congress sits in the overall archive.
stats, _ = api_get("stats")
bills_by_congress = pd.DataFrame(stats["bills_by_congress"]).sort_values("congress")
bills_by_congress.tail()

# --- COLLAPSIBLE INGESTION BLOCK ---
# Pull the full selected congress, sorted by filing date so the monthly timeline
# reads chronologically. Deriving a month bucket lets us group filings by month.
documents = pd.DataFrame(
    fetch_all("documents", congress=SELECTED_CONGRESS, sort="date_filed", dir="asc")
)
documents["date_filed"] = pd.to_datetime(documents["date_filed"], errors="coerce")
documents["month"] = documents["date_filed"].dt.to_period("M").dt.to_timestamp()
documents[["name", "subtype", "scope", "date_filed", "title"]].head()

# --- COLLAPSIBLE MONTHLY-PACE BLOCK ---
# Count bills per (month, subtype). Dropping rows without a parsed month keeps
# undated bills from collapsing into a bogus bucket.
monthly = (
    documents.dropna(subset=["month"])
    .groupby(["month", "subtype"], as_index=False)
    .size()
    .rename(columns={"size": "bills"})
)

px.line(
    monthly,
    x="month",
    y="bills",
    color="subtype",
    markers=True,
    title=f"Monthly Filing Pace in the {SELECTED_CONGRESS}th Congress",
    labels={"month": "Month filed", "bills": "Bills filed", "subtype": "Bill type"},
)

# --- COLLAPSIBLE CUMULATIVE BLOCK ---
# Build a cumulative count over time per bill type using a running sum.
cumulative = (
    documents.dropna(subset=["month"])
    .groupby(["month", "subtype"], as_index=False)
    .size()
    .rename(columns={"size": "bills"})
    .sort_values("month")
)
cumulative["cumulative_bills"] = cumulative.groupby("subtype")["bills"].cumsum()

px.area(
    cumulative,
    x="month",
    y="cumulative_bills",
    color="subtype",
    title=f"Cumulative Bills Filed in the {SELECTED_CONGRESS}th Congress",
    labels={"month": "Month filed", "cumulative_bills": "Cumulative bills", "subtype": "Bill type"},
)

# --- COLLAPSIBLE SCOPE BLOCK ---
# Normalize the scope label (fill blanks, title-case) and count by (subtype, scope).
scope_mix = (
    documents.assign(scope=documents["scope"].fillna("Unknown").str.title())
    .groupby(["subtype", "scope"], as_index=False)
    .size()
    .rename(columns={"size": "bills"})
)

px.bar(
    scope_mix,
    x="scope",
    y="bills",
    color="subtype",
    barmode="group",
    title=f"National and Local Scope in the {SELECTED_CONGRESS}th Congress",
    labels={"scope": "Scope", "bills": "Bills", "subtype": "Bill type"},
)