Tell us what’s happening:
Describe your issue in detail here.
Your code so far
import pandas as pd
# Load the dataset
data = pd.read_csv('demographic_data.csv') # Replace 'your_dataset.csv' with your dataset filename
# How many people of each race are represented in this dataset?
race_counts = data['race'].value_counts()
# What is the average age of men?
average_age_men = data[data['sex'] == 'Male']['age'].mean()
# What is the percentage of people who have a Bachelor's degree?
bachelors_percentage = (data['education'] == 'Bachelors').mean() * 100
# What percentage of people with advanced education make more than 50K?
advanced_education = data['education'].isin(['Bachelors', 'Masters', 'Doctorate'])
higher_education_rich = data[advanced_education & (data['salary'] == '>50K')].shape[0] / data[advanced_education].shape[0] * 100
# What percentage of people without advanced education make more than 50K?
lower_education_rich = data[~advanced_education & (data['salary'] == '>50K')].shape[0] / data[~advanced_education].shape[0] * 100
# What is the minimum number of hours a person works per week?
min_work_hours = data['hours-per-week'].min()
# What percentage of the people who work the minimum number of hours per week have a salary of more than 50K?
num_min_workers = data[data['hours-per-week'] == min_work_hours]
rich_percentage = (num_min_workers[num_min_workers['salary'] == '>50K'].shape[0] / num_min_workers.shape[0]) * 100
# What country has the highest percentage of people that earn >50K and what is that percentage?
highest_earning_country = (data[data['salary'] == '>50K']['native-country'].value_counts() / data['native-country'].value_counts()).idxmax()
highest_earning_country_percentage = (data[(data['native-country'] == highest_earning_country) & (data['salary'] == '>50K')].shape[0] / data[data['native-country'] == highest_earning_country].shape[0]) * 100
# Identify the most popular occupation for those who earn >50K in India.
top_IN_occupation = data[(data['native-country'] == 'India') & (data['salary'] == '>50K')]['occupation'].value_counts().idxmax()
# Displaying the results
print("Race counts:")
print(race_counts)
print("\nAverage age of men:", round(average_age_men, 1))
print("\nPercentage of people with Bachelor's degree:", round(bachelors_percentage, 1))
print("\nPercentage of people with advanced education earning >50K:", round(higher_education_rich, 1))
print("\nPercentage of people without advanced education earning >50K:", round(lower_education_rich, 1))
print("\nMinimum number of hours worked per week:", min_work_hours)
print("\nPercentage of people working min hours per week earning >50K:", round(rich_percentage, 1))
print("\nCountry with the highest percentage earning >50K:", highest_earning_country)
print("Percentage:", round(highest_earning_country_percentage, 1))
print("\nMost popular occupation for >50K earners in India:", top_IN_occupation)
Your browser information:
User Agent is: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36
Challenge Information:
Data Analysis with Python Projects - Demographic Data Analyzer
###Replit Link For Helping Out
https://replit.com/join/acrieunwgo-smrutiparida