Online Robotics and Coding Classes in Daan District, Taipei

1. Shape, Spread, Skew

Distribution plots summarize continuous variables as bins, smooth densities, or cumulative curves—without needing a scatter of every row.

• sns.histplot — discrete bins and counts (stack / layer / dodge)
• sns.kdeplot — smooth kernel density (no bins)
• sns.ecdfplot — cumulative proportion from 0 to 1

2. Useful Arguments

• multiple: stack, layer, or dodge groups
• stat: count, density, or probability
• bins: number of intervals for histograms
• fill: shade under KDE curves

3. Treatment Cost Histogram

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

df = pd.read_csv("healthcare_patient_analytics_seaborn.csv")

plt.figure(figsize=(9, 5))
sns.histplot(data=df, x="Treatment Cost", bins=30)
plt.title("Treatment Cost Distribution (30 Bins)")
plt.xlabel("Treatment Cost ($)")
plt.ylabel("Count")
plt.show()

Mid-range costs dominate; extremes are rarer.

4. Stacked Readmission Risk

plt.figure(figsize=(9, 5))
sns.histplot(
    data=df,
    x="Readmission Risk",
    hue="Visit Type",
    multiple="stack",
    bins=30
)
plt.title("Readmission Risk Distribution by Visit Type (Stacked)")
plt.show()

5. KDE of Recovery Score

plt.figure(figsize=(9, 5))
sns.kdeplot(
    data=df,
    x="Recovery Score",
    hue="Visit Type",
    fill=True
)
plt.title("Recovery Score Density Distribution by Visit Type")
plt.show()

Routine visits often show a sharper, higher density peak than Emergency.

6. ECDF of Length of Stay

plt.figure(figsize=(9, 5))
sns.ecdfplot(
    data=df,
    x="Length of Stay (Days)",
    hue="Visit Type"
)
plt.title("Cumulative Length of Stay (Days) by Visit Type")
plt.ylabel("Proportion")
plt.show()

In the example, about 80% of stays fall at or below 6 days.

7. Quick Comparison

Plot	Function	Use
Histogram	sns.histplot	Binned frequencies
KDE	sns.kdeplot	Smooth density
ECDF	sns.ecdfplot	Percentile thresholds