# Errors with Demographic Data Analyzer

Tell us what’s happening:
I’m failing 3 of the tests:
1: highest earning country should be Iran, it’s coming up as the US for me, maybe I used incorrect parameters?
1b: the percentage is therefore incorrect, but somehow still low for me? (22% instead of almost 42%)
2: I’m getting that the most popular occupation, >50K or otherwise, in India is Private, and not Prof-specialty.

import pandas as pd

def calculate_demographic_data(print_data=True):

``````# How many of each race are represented in this dataset? This should be a Pandas series with race names as the index labels.
race_count = df.value_counts(subset=['race'])

# What is the average age of men?
age = df.loc[df['sex']=='Male', 'age'] #collect the ages of all males in df
average_age_men = round(age.mean(),1) #take the average of the ages

# What is the percentage of people who have a Bachelor's degree?
bachelors = len(df.loc[df['education']=='Bachelors']) #determine how many in df have a bachelor's degree
percentage_bachelors = round((bachelors/len(df) * 100),1) #calculate a percentage compared to the total population of df

# What percentage of people with advanced education (`Bachelors`, `Masters`, or `Doctorate`) make more than 50K?
# What percentage of people without advanced education make more than 50K?

# with and without `Bachelors`, `Masters`, or `Doctorate`
higher_education = df[(df['education']=='Bachelors')|(df['education']=='Masters')|(df['education']=='Doctorate')]
num_h_e_r = higher_education[higher_education['salary']=='>50K']
lower_education = df[(df['education']!='Bachelors')&(df['education']!='Masters')&(df['education']!='Doctorate')]
num_l_e_r = lower_education[lower_education['salary']=='>50K']
# percentage with salary >50K
higher_education_rich = round(len(num_h_e_r)/len(higher_education)*100,1)
lower_education_rich = round(len(num_l_e_r)/len(lower_education)*100,1)

# What is the minimum number of hours a person works per week (hours-per-week feature)?
work_hours=df['hours-per-week']
min_work_hours = work_hours.min()

# What percentage of the people who work the minimum number of hours per week have a salary of >50K?
num_min_workers = df[df['hours-per-week']==min_work_hours]
rich_min_workers = df[(df['hours-per-week']==min_work_hours) & (df['salary']=='>50K')]

rich_percentage = round(len(rich_min_workers)/len(num_min_workers) *100, 1)

# What country has the highest percentage of people that earn >50K?
rich = df.loc[df['salary']=='>50K','native-country']
ordered = rich.value_counts()

highest_earning_country = ordered.index[0]
highest_earning_country_percentage = round(ordered[0]/len(df) *100,1)

# Identify the most popular occupation for those who earn >50K in India.
IN = df.loc[df['native-country']=='India',['workclass','salary']]
occupations = IN.loc[IN['salary']=='>50K','workclass']
ordered_occupations = occupations.value_counts()
top_IN_occupation = ordered_occupations.index[0]

# DO NOT MODIFY BELOW THIS LINE

if print_data:
print("Number of each race:\n", race_count)
print("Average age of men:", average_age_men)
print(f"Percentage with Bachelors degrees: {percentage_bachelors}%")
print(f"Percentage with higher education that earn >50K: {higher_education_rich}%")
print(f"Percentage without higher education that earn >50K: {lower_education_rich}%")
print(f"Min work time: {min_work_hours} hours/week")
print(f"Percentage of rich among those who work fewest hours: {rich_percentage}%")
print("Country with highest percentage of rich:", highest_earning_country)
print(f"Highest percentage of rich people in country: {highest_earning_country_percentage}%")
print("Top occupation in India:", top_IN_occupation)

return {
'race_count': race_count,
'average_age_men': average_age_men,
'percentage_bachelors': percentage_bachelors,
'higher_education_rich': higher_education_rich,
'lower_education_rich': lower_education_rich,
'min_work_hours': min_work_hours,
'rich_percentage': rich_percentage,
'highest_earning_country': highest_earning_country,
'highest_earning_country_percentage':
highest_earning_country_percentage,
'top_IN_occupation': top_IN_occupation
}
``````

User Agent is: `Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36`

Challenge: Demographic Data Analyzer