p2 files added

Author: mayankyadav23

Diff for: Demographic Data Analyzer/demographic_data_analyzer.py

@@ -0,0 +1,77 @@
+import pandas as pd
+
+
+def calculate_demographic_data(print_data=True):
+    # Read data from file
+    df = pd.read_csv('adult.data.csv')
+
+    # 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['race'].value_counts()
+
+    # What is the average age of men?
+    men = df[df['sex'] == 'Male']
+    average_age_men = round(men['age'].mean(), 1)
+
+    # What is the percentage of people who have a Bachelor's degree?
+    bachelor = df[df['education'] == 'Bachelors']
+    percentage_bachelors = round(bachelor.shape[0] / df.shape[0] * 100, 1)
+
+    # 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'].isin(['Bachelors', 'Masters', 'Doctorate'])]
+    lower_education = df[~df['education'].isin(['Bachelors', 'Masters', 'Doctorate'])]
+
+    # percentage with salary >50K
+    higher_education_rich = round(higher_education[higher_education['salary'] == '>50K'].shape[0] / higher_education.shape[0] * 100, 1)
+    lower_education_rich = round(lower_education[lower_education['salary'] == '>50K'].shape[0] / lower_education.shape[0] * 100, 1)
+
+    # What is the minimum number of hours a person works per week (hours-per-week feature)?
+    min_work_hours = df['hours-per-week'].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_percentage = round(num_min_workers[num_min_workers['salary'] == '>50K'].shape[0] / num_min_workers.shape[0] * 100, 1)
+
+    # What country has the highest percentage of people that earn >50K?
+    num_high_salary_per_country = df[df['salary'] == ">50K"]['native-country'].value_counts()
+    num_country = df['native-country'].value_counts()
+    percentage = num_high_salary_per_country / num_country  * 100
+
+    highest_earning_country = percentage.idxmax()
+    highest_earning_country_percentage = round(percentage.max(), 1)
+
+    # Identify the most popular occupation for those who earn >50K in India.
+    high_salary_india_occ = df[(df['salary'] == ">50K") & (df['native-country'] == "India")]['occupation'].value_counts()
+
+    top_IN_occupation = high_salary_india_occ.idxmax()
+
+    # 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 occupations 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
+    }

Diff for: Demographic Data Analyzer/main.py

@@ -0,0 +1,9 @@
+# This entrypoint file to be used in development. Start by reading README.md
+import demographic_data_analyzer
+from unittest import main
+
+# Test your function by calling it here
+demographic_data_analyzer.calculate_demographic_data()
+
+# Run unit tests automatically
+main(module='test_module', exit=False)

Diff for: Demographic Data Analyzer/test_module.py

@@ -0,0 +1,59 @@
+import unittest
+import demographic_data_analyzer
+
+class DemographicAnalyzerTestCase(unittest.TestCase):
+    def setUp(self):
+        self.data = demographic_data_analyzer.calculate_demographic_data(print_data = False)
+
+    def test_race_count(self):
+        actual = self.data['race_count'].tolist()
+        expected = [27816, 3124, 1039, 311, 271]
+        self.assertAlmostEqual(actual, expected, msg="Expected race count values to be [27816, 3124, 1039, 311, 271]")
+    
+    def test_average_age_men(self):
+        actual = self.data['average_age_men']
+        expected = 39.4
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for average age of men.")
+
+    def test_percentage_bachelors(self):
+        actual = self.data['percentage_bachelors']
+        expected = 16.4 
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for percentage with Bachelors degrees.")
+
+    def test_higher_education_rich(self):
+        actual = self.data['higher_education_rich']
+        expected = 46.5
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for percentage with higher education that earn >50K.")
+  
+    def test_lower_education_rich(self):
+        actual = self.data['lower_education_rich']
+        expected = 17.4
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for percentage without higher education that earn >50K.")
+
+    def test_min_work_hours(self):
+        actual = self.data['min_work_hours']
+        expected = 1
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for minimum work hours.")     
+
+    def test_rich_percentage(self):
+        actual = self.data['rich_percentage']
+        expected = 10
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for percentage of rich among those who work fewest hours.")   
+
+    def test_highest_earning_country(self):
+        actual = self.data['highest_earning_country']
+        expected = 'Iran'
+        self.assertEqual(actual, expected, "Expected different value for highest earning country.")   
+
+    def test_highest_earning_country_percentage(self):
+        actual = self.data['highest_earning_country_percentage']
+        expected = 41.9
+        self.assertAlmostEqual(actual, expected, msg="Expected different value for highest earning country percentage.")   
+
+    def test_top_IN_occupation(self):
+        actual = self.data['top_IN_occupation']
+        expected = 'Prof-specialty'
+        self.assertEqual(actual, expected, "Expected different value for top occupations in India.")      
+
+if __name__ == "__main__":
+    unittest.main()