simple-data-science-notebook/src/utils.py

import numpy as np
import pandas as pd
from sklearn.metrics import adjusted_mutual_info_score
import yaml

def read_config(
    config_path: str
):
    with open(config_path) as file:
        config_file = yaml.safe_load(file)

    return config_file

def show_mutial_info(
    df: pd.DataFrame
) -> None:
    
    scores = uniform_labelings_scores(score_func, n_samples, n_clusters_range)
    print("done in %0.3fs" % (time() - t0))
    plots.append(
        plt.errorbar(n_clusters_range, np.median(scores, axis=1), scores.std(axis=1))[0]
    )
    names.append(score_func.__name__)
    
    
def uniform_labelings_scores(
    score_func, n_samples, n_clusters_range, fixed_n_classes=None, n_runs=5, seed=42
):
    """Compute score for 2 random uniform cluster labelings.

    Both random labelings have the same number of clusters for each value
    possible value in ``n_clusters_range``.

    When fixed_n_classes is not None the first labeling is considered a ground
    truth class assignment with fixed number of classes.
    """
    random_labels = np.random.RandomState(seed).randint
    scores = np.zeros((len(n_clusters_range), n_runs))

    if fixed_n_classes is not None:
        labels_a = random_labels(low=0, high=fixed_n_classes, size=n_samples)

    for i, k in enumerate(n_clusters_range):
        for j in range(n_runs):
            if fixed_n_classes is None:
                labels_a = random_labels(low=0, high=k, size=n_samples)
            labels_b = random_labels(low=0, high=k, size=n_samples)
            scores[i, j] = score_func(labels_a, labels_b)
    return scores


def ami_score(U, V):
    return adjusted_mutual_info_score(U, V)