From a1c7fe1b6d95e2560e62c12453da287d36d4a714 Mon Sep 17 00:00:00 2001 From: Charles Cabergs Date: Sat, 29 Aug 2020 17:13:57 +0200 Subject: Removed bloat, Added logreg_train --- src/histogram.py | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100755 src/histogram.py (limited to 'src/histogram.py') diff --git a/src/histogram.py b/src/histogram.py new file mode 100755 index 0000000..1200233 --- /dev/null +++ b/src/histogram.py @@ -0,0 +1,28 @@ +#!/bin/python3 + +import sys + +import matplotlib.pyplot as plt + +from dataset import Dataset + + +def house_hist(ax, d, house_name): + h = d.df[d.df["house"] == house_name] + scores = h.loc[:, "arithmancy":"flying"] + x = (scores - scores.min()) / (scores.max() - scores.min()) + ax.hist(x.values.flatten(), bins=40, rwidth=0.8) + ax.set_title(house_name) + +if __name__ == "__main__": + if len(sys.argv) != 2: + raise "Usage: {} dataset_path".format(sys.argv[0]) + d = Dataset(sys.argv[1]) + + fig, axs = plt.subplots(2, 2, sharey=True, tight_layout=True) + house_hist(axs[0][0], d, "Gryffindor") + house_hist(axs[0][1], d, "Slytherin") + house_hist(axs[1][0], d, "Ravenclaw") + house_hist(axs[1][1], d, "Hufflepuff") + plt.show() + -- cgit