gistfile1.txt

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

df = pd.read_csv("data.csv")
df.columns = [c.lower() for c in df.columns]
df = df[["period", "result", "starting_point_id", "online_hours", "undersupply_hours_pct", "oversupply_hours_pct",
         "is_late20min", "nd", "num_delivs"]]
df = df.rename(columns={
    "result": "group",
    "starting_point_id": "spid",
    "online_hours": "hours",
    "undersupply_hours_pct": "uh",
    "oversupply_hours_pct": "oh",
    "is_late20min": "late",
})

df["late_count"] = df["late"] * df["num_delivs"]
df["nd_count"] = df["nd"] * df["num_delivs"]

df_exp = df[df.period == "experiment"]


def plot_uh():
    g = sns.histplot(
        data=df_exp,
        x="uh",
        weights="hours",
        hue="group",
    )
    g.set_yscale("log")
    plt.show()


def plot_uh_normalized():
    g = sns.histplot(
        data=df_exp,
        x="uh",
        weights="hours",
        hue="group",
        stat="probability",
    )
    g.set_yscale("log")
    plt.show()


def plot_late():
    g = sns.histplot(
        data=df_exp,
        x="uh",
        weights="late_count",
    )
    g.set_yscale("log")
    plt.show()


def plot_nd():
    g = sns.histplot(
        data=df_exp,
        x="uh",
        weights="nd_count",
    )
    g.set_yscale("log")
    plt.show()