TidyTuesday Week 23: US Judges

This week we’re exploring U. S. judge data from the {historydata} R package! This dataset contains information about the appointments and careers of all federal judges in United States history since 1789.

1. Python code

# ! pip install polars
# ! pip install pandas
# ! pip install numpy
# ! pip install folium
# ! pip install geopy
import polars as pl
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.io as pio
import matplotlib.pyplot as plt

pio.templates.default = 'plotly_white'


judges_appointments = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-06-10/judges_appointments.csv')
judges_people = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-06-10/judges_people.csv')

merged_df = pd.merge(judges_appointments, judges_people, on = 'judge_id', how = 'left')
merged_df["commission_date"] = pd.to_datetime(merged_df["commission_date"], format="%m/%d/%Y")
merged_df = merged_df.assign(Non_white = np.where(merged_df["race"] != "White", "Non-White", "White"))

# Top 100  judges per apppointment

top10 = pd.DataFrame(merged_df.groupby(['president_name']).president_name.value_counts().nlargest(10)).reset_index()
top10.columns = ['president_name', 'count']
pio.templates.default = 'plotly_white'

# NUmber of judges per party
parties = ["Democratic", "Republican"]

party = merged_df[merged_df["president_party"].isin(parties)]
parties = pd.DataFrame(party.groupby("president_party").size()).reset_index()
parties.columns = ['president_party', 'count']

fig, ax = plt.subplots(figsize=(10, 6)); 
bars = ax.bar(x=top10['president_name'], height=top10['count'], color='skyblue')
ax.set_xlabel('President Name')
ax.set_ylabel('Number of Appointments per President')
ax.set_title('Top 10 Presidents by Number of Appointments')
ax.tick_params(axis='x', rotation=45)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
for bar in bars:
    height = bar.get_height()
    ax.annotate(
        f'{int(height)}',
        xy=(bar.get_x() + bar.get_width() / 2, height),
        xytext=(0, 3),  # Offset above bar
        textcoords='offset points',
        ha='center',
        va='bottom',
        fontsize=9,
        color='black'
    )
    
    
plt.tight_layout()

# By Politcial PArty
party_colors = {
    "Democratic": "blue",
    "Republican": "red"
}

colors = parties['president_party'].map(party_colors)

# Create plot
fig1, ax = plt.subplots(figsize=(10, 6));
bars = ax.bar(x=parties['president_party'], height=parties['count'], color=colors)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.set_xlabel('Political Party')
ax.set_ylabel('Number of Appointments per Party')
ax.set_title('Number of Appointments by Political Party')
ax.tick_params(axis='x', rotation=0)

# Add count labels on top of bars
for bar in bars:
    height = bar.get_height()
    ax.annotate(
        f'{int(height)}',
        xy=(bar.get_x() + bar.get_width() / 2, height),
        xytext=(0, 3),
        textcoords='offset points',
        ha='center',
        va='bottom',
        fontsize=9,
        color='black'
    )
    
plt.tight_layout()


female_judge_percent = merged_df.groupby("gender").size()
percent_df = female_judge_percent.div(female_judge_percent.sum()).mul(100)

dict(
  value = f"{round(percent_df.get('F', 0), 1)}%"
)



cut_off = pd.to_datetime("1969-01-01")

pre_1968 = merged_df[merged_df["commission_date"] <= cut_off]


non_white_number = pre_1968.groupby("Non_white").size()
non_White_percent = non_white_number.div(non_white_number.sum()).mul(100)

dict(
  value = f"{round(non_White_percent.get('Non-White', 0), 1)}%"
);




repub = merged_df[merged_df["president_party"].isin(["Republican", "Democratic"])]
repub_number = repub.groupby("president_party").size()
repub_percent = repub_number.div(repub_number.sum()).mul(100)

dict(
  value = f"{round(repub_percent.get('Republican', 0), 1)}%"
);