from data.main import connect
import pandas as pd
import numpy as np

DB = connect()
edges = DB.query("""
    select
    *
    from link_edges
""").df()
DB.close()

edges

adj = edges.pivot(index='parent_id', columns='child_id', values='links').fillna(0)
select_publishers = pd.DataFrame(adj.index.tolist(), columns=['publisher_id'])

DB = connect()
DB.query("create schema top")

DB.query("""
    CREATE OR REPLACE TABLE top.publishers AS
    SELECT
        p.*
    FROM publishers p
    JOIN select_publishers s
    ON s.publisher_id = p.id
""")

DB.query("""
    CREATE OR REPLACE TABLE top.stories AS
    SELECT
        s.*
    FROM stories s
    JOIN top.publishers p
    ON s.publisher_id = p.id
    WHERE year(s.published_at) >= 2006
    AND year(s.published_at) < 2023
""")

DB.query("""
    CREATE OR REPLACE TABLE top.related_stories AS
    SELECT
        r.*
    FROM top.stories s
    JOIN related_stories r
    ON s.id = r.parent_id
""")