From b19d823dbe1218b39feba8687717a956146ad3c7 Mon Sep 17 00:00:00 2001 From: Luca Lombardo Date: Sat, 12 Mar 2022 18:48:53 +0100 Subject: [PATCH] analysis for the movie graph --- .../movie_bench/closeness_results/analysis.py | 28 +++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 scripts/movie_bench/closeness_results/analysis.py diff --git a/scripts/movie_bench/closeness_results/analysis.py b/scripts/movie_bench/closeness_results/analysis.py new file mode 100644 index 0000000..aea97b9 --- /dev/null +++ b/scripts/movie_bench/closeness_results/analysis.py @@ -0,0 +1,28 @@ +import os +import matplotlib.pyplot as plt +import numpy as np +import pandas as pd + +dfs = { + i: pd.read_csv(f"top_movies_{i:02d}_c.txt", sep='\t', usecols=[1], names=["actor"]) + for i in [5] + list(range(10, 71, 10))} +sets = {i: set(df["movie"]) for i, df in dfs.items()} + +diff = [] +for i in sets.keys(): + diff.append([len(sets[i]) - len(sets[i] & sets[j]) for j in sets.keys()]) +diff = np.array(diff, dtype=float) +diff /= len(next(iter(sets.values()))) + +plt.matshow(diff) +for (i, j), z in np.ndenumerate(diff): + plt.gca().text(j, i, f'{z:0.2f}', ha='center', va='center') +plt.gca().set_xticks(np.linspace(0.0, len(sets) - 1, len(sets))) +plt.gca().set_yticks(np.linspace(0.0, len(sets) - 1, len(sets))) +plt.gca().set_xticklabels([f"{i:d}" for i in sets.keys()]) +plt.gca().set_yticklabels([f"{i:d}" for i in sets.keys()]) +plt.ylabel("\nNumber of Votes") +plt.xlabel("\nNumber of Votes") +cb = plt.colorbar() +cb.set_label("\npercentace of difference in results varing the number of votes") +plt.show()