2023-03-01 20:38:03 +03:00

74 lines
2.1 KiB
Python

import pandas as pd
from matplotlib import pyplot as plt, colors
from matplotlib.font_manager import FontProperties
import numpy as np
subjects = ["Maths", "Reading", "Science"]
data = pd.read_csv("./practice1.csv", names=["country", *subjects])
country_codes = pd.read_csv("./country_codes.csv", names=["country", "code"])
data = data.merge(country_codes, how="outer", on="country")
data = data.dropna(subset=subjects)
data["Average"] = data.loc[:, subjects].mean(axis=1)
data = data.sort_values(by="Average", ascending=False)
data.to_csv("res.csv", index=False, header=False)
if data[data["code"].isna()].size != 0:
raise ValueError("NaN country code")
fig, ax = plt.subplots(nrows=4)
fig.set_size_inches(16, 11.69)
positions = np.array(list(map(str,range(1, len(data.index)+1))))
x = data["code"] + "\n" + positions
# colors=("#ef476f", "#ffd166", "#06d6a0", "#118ab2", "#073B4C")
colors=("tab:blue", "tab:orange", "tab:green", "tab:red", "tab:grey")
subjects_labels = ("🔢", "📚", "🔬", "")
for i, subj in enumerate((*subjects, "Average")):
bar = ax[i].bar(x, data[subj], color=colors[i])
bar_labels = list(map(lambda j: str(int(data[subj][data.index[j]])) if data["code"][data.index[j]] == "UK" else "", range(len(data.index))))
ax[i].bar_label(bar, labels=bar_labels, weight="bold")
ax[i].set_title(subjects_labels[i])
ax[i].autoscale(tight=True)
ax[i].set_ylim(350)
mean = int(data[subj].mean())
ax[i].set_yticks(list(set((*ax[i].get_yticks(), mean, 650))))
for label in ax[i].get_xticklabels():
if "UK" in label.get_text():
label.set(fontweight="bold")
for label in ax[i].get_yticklabels():
if label.get_text() == str(mean):
label.set(fontweight="bold")
ax[i].hlines([mean], 0, 1, transform=ax[i].get_yaxis_transform(), color=colors[-1])
ax[i].spines['top'].set_visible(False)
ax[i].spines['right'].set_visible(False)
ax[i].spines['bottom'].set_visible(False)
ax[i].spines['left'].set_visible(False)
# ax[i].grid()
fig.tight_layout()
fig.savefig("test.png")