wwu-577/src/plots/links.py

import click
from data.main import connect, ticklabels, paths
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import silhouette_score
import pandas as pd


@click.command('links:elbow')
def elbow():
    from sklearn.cluster import KMeans

    save_to = paths('figures') / 'link_cluster_elbow.png'

    with connect() as db:
        df = db.query("""
            SELECT
                *
            FROM link_edges
        """).df()

    pivot = df.pivot(index='parent_id', columns='child_id', values='links').fillna(0)

    to_plot = []
    for k in range(2, 15):
        kmeans = KMeans(n_clusters=k, n_init="auto")
        kmeans.fit(pivot)
        label = kmeans.labels_
        coeff = silhouette_score(pivot, label, metric='euclidean')
        to_plot.append({'k': k, 'inertia' : kmeans.inertia_, 'coeff': coeff})
    to_plot = pd.DataFrame(to_plot)

    ax = sns.lineplot(x=to_plot.k, y=to_plot.inertia)
    ax.set(title="elbow criterion plot of clusters", xlabel="bin size (k)", ylabel="sum of squared distances between centroids/points")
    plt.savefig(save_to)
    plt.close()
    print(f"saved plot: {save_to}")

    # randomly pick 8

@click.command('links:pca-clusters')
@click.option('--source', type=click.Choice(['links', 'normalized', 'onehot']), default='links')
def link_pca_clusters(source):

    save_to = paths('figures') / f"link_pca_clusters_{source}.png"

    with connect() as db:
        df = db.query(f"""
            SELECT
                c.label as cluster
                ,p.tld
                --,b.label as bias
                ,pca.first
                ,pca.second
                ,s.cnt as stories
            FROM publisher_clusters_{source} c
            JOIN mbfc.publisher_stories ps
            ON ps.publisher_id = c.publisher_id
            JOIN mbfc.publishers p
            ON ps.publisher_id = p.id
            JOIN 
            (
                select
                    p.id as publisher_id
                    ,count(1) as cnt
                FROM mbfc.publishers p
                GROUP BY
                    p.id
            ) s
            ON s.publisher_id = p.id
            JOIN publisher_pca_{source} pca
            ON pca.publisher_id = p.id
        """).df()

    ax = sns.scatterplot(x=df['first'], y=df['second'], hue=df['cluster'])
    ax.set(title=f"pca components vs. clusters ({source})", xlabel="first pca component", ylabel="second pca component")
    plt.savefig(save_to)
    print(f"saved plot: {save_to}")


def test():

    with connect() as db:
        db.query("""
            SELECT
                p.id as publisher_id
                ,p.name
                ,p.tld
                ,cast(b.bias_id as int) as bias_id
                ,count(1) as stories
            FROM publishers p
            JOIN stories s
            ON s.publisher_id = p.id
            JOIN publisher_clusters c
            ON c.publisher_id = p.id
            LEFT JOIN publisher_bias b
            ON b.publisher_id = p.id
            where bias_id is null
            group by
                p.id
                ,p.name
                ,p.tld
                ,b.bias_id
            ORDER BY count(1) desc
        """)


@click.command('links:confusion')
def link_confusion():
    from sklearn.model_selection import train_test_split
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.metrics import ConfusionMatrixDisplay

    filename = "link_confusion.png"
    save_to = paths('figures') / filename

    with connect() as db:
        bias = db.query("""
            SELECT
                p.id as publisher_id
                ,b.ordinal
            FROM top.publishers p
            JOIN top.publisher_bias pb
            ON pb.publisher_id = p.id
            JOIN bias_ratings b
            ON b.id = pb.bias_id
        """).df()

        df = db.query("""
            SELECT
                *
            FROM top.link_edges
            WHERE parent_id in (
                select
                    publisher_id
                from bias
            )
            AND child_id in (
                select
                    publisher_id
                from bias
            )
        """).df()

    pivot = df.pivot(index='parent_id', columns='child_id', values='links').fillna(0)

    x = pivot.values
    y = bias.sort_values('publisher_id').ordinal


    x_train, x_test = train_test_split(x)
    y_train, y_test = train_test_split(y)

    model = KNeighborsClassifier(n_neighbors=5)
    model.fit(x_train, y_train)
    y_pred = model.predict(x_test)


    fig, ax = plt.subplots(figsize=(10, 5))
    ConfusionMatrixDisplay.from_predictions(y_test, y_pred, ax=ax)
    ticklabels = ['left', 'left-center', 'center', 'right-center', 'right']
    ax.set(title="confusion matrix for kNN classifier on test data.", xticklabels=ticklabels, yticklabels=ticklabels)
    plt.savefig(save_to)
    plt.close()
    print(f"saved plot: {save_to}")

@click.command('links:classifier')
def link_confusion():
    from sklearn.model_selection import train_test_split
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.metrics import ConfusionMatrixDisplay

    save_to = paths('figures') / "link_confusion.png"

    with connect() as db:
        bias = db.query("""
            SELECT
                p.id as publisher_id
                ,p.ordinal
            FROM mbfc.publishers p
            where ordinal != -1
        """).df()

    with connect() as db:
        df = db.query("""
            SELECT
                *
            FROM link_edges
            WHERE parent_id in (
                select
                    publisher_id
                from bias
            )
            AND child_id in (
                select
                    publisher_id
                from bias
            )
        """).df()

    pivot = df.pivot(index='parent_id', columns='child_id', values='links').fillna(0)
    publisher_matrix = pd.merge(pivot, bias, left_on='parent_id', right_on='publisher_id')
    x = publisher_matrix.loc[:, ~publisher_matrix.columns.isin(['publisher_id', 'ordinal'])].values
    y = publisher_matrix['ordinal']

    model = KNeighborsClassifier(n_neighbors=5)
    model.fit(x, y)
    y_pred = model.predict(x)
    publisher_matrix['pred'] = y_pred
    publisher_matrix


    fig, ax = plt.subplots(figsize=(5, 5))
    ConfusionMatrixDisplay.from_predictions(publisher_matrix['ordinal'], publisher_matrix['pred'], ax=ax)
    ax.set(xticklabels=ticklabels(), yticklabels=ticklabels())
    plt.xticks(rotation=45)
    plt.tight_layout()
    plt.savefig(save_to)
    plt.close()
    print(f"saved plot: {save_to}")

    # ax = sns.scatterplot(x=data['first'], y=data['second'], hue=data['pred'])
    # plt.savefig(out_dir / filename)
    # plt.close()
    # print(f"saved plot: {filename}")