from datetime import datetime
import matplotlib.pyplot as plt
import pandas as pd


# pd.set_option('display.max_columns', None)
# pd.set_option('display.max_rows', None)

df = pd.read_csv(filepath_or_buffer='call_history_bash.csv', sep=";")
df["elapsed"] = df["finished"].apply(lambda x: datetime.strptime(x, "%Y-%m-%d %H:%M:%S.%f")) - df["started"].apply(lambda x: datetime.strptime(x, "%Y-%m-%d %H:%M:%S.%f"))
df["elapsed"] = df["elapsed"].apply(lambda x: x.total_seconds())
df.to_csv("output.csv", index=False, sep=";")

student_numbers = df['active_students'].unique()

plt.figure(figsize=(16, 10))
rows = len(student_numbers)

for index, student_number in enumerate(student_numbers, 1):
    data = df[df["active_students"] == student_number]
    plt.subplot(rows, 2, 2 * index - 1)
    plt.title("y=seconds, x=active students", x=0.75, y=0.75)
    plt.boxplot(x=data["elapsed"], labels=[student_number])
    plt.subplot(rows, 2, 2 * index)
    plt.title("y=count of seconds, x=seconds", x=0.75, y=0.75)
    plt.hist(x=data["elapsed"], bins=25, edgecolor='white')


plt.show()