Summary
This chapter covers using built-in methods to extract the set of unique values from a data column and to count how many distinct entries it contains.

General domain of usage
Data analysis

Data often gets **duplicated** in DataFrames. For instance, in the `countries` DataFrame, the `'continent'` column has repeated entries. There's a method that retrieves an **array of distinct values** from a specific DataFrame column.

import pandas as pd 

country_data = {'country' : ['Thailand', 'Philippines', 'Monaco', 'Malta', 'Sweden', 'Paraguay', 'Latvia'],
          'continent' : ['Asia', 'Asia', 'Europe', 'Europe', 'Europe', 'South America', 'Europe'],
          'capital':['Bangkok', 'Manila', 'Monaco', 'Valletta', 'Stockholm', 'Asuncion', 'Riga']}
countries = pd.DataFrame(country_data)
print(countries)

Next, apply the `unique()` method to the `'continent'` and `'country'` columns:


import pandas as pd

country_data = {'country' : ['Thailand', 'Philippines', 'Monaco', 'Malta', 'Sweden', 'Paraguay', 'Latvia'],
          'continent' : ['Asia', 'Asia', 'Europe', 'Europe', 'Europe', 'South America', 'Europe'],
          'capital':['Bangkok', 'Manila', 'Monaco', 'Valletta', 'Stockholm', 'Asuncion', 'Riga']}
countries = pd.DataFrame(country_data)
unique_countries = countries['country'].unique()
unique_continents = countries['continent'].unique()
print(unique_countries)
print(unique_continents)

Sometimes, instead of retrieving all unique values, you might just want to know **how many distinct values** exist in a column. In such cases, you can use the **`nunique()`** method. It returns the **count** of unique entries in a column — not the values themselves.

import pandas as pd

country_data = {'country' : ['Thailand', 'Philippines', 'Monaco', 'Malta', 'Sweden', 'Paraguay', 'Latvia'],
          'continent' : ['Asia', 'Asia', 'Europe', 'Europe', 'Europe', 'South America', 'Europe'],
          'capital':['Bangkok', 'Manila', 'Monaco', 'Valletta', 'Stockholm', 'Asuncion', 'Riga']}
countries = pd.DataFrame(country_data)
print(countries['continent'].nunique())

import unittest
import importlib
import numpy as np


# Helper function for dynamic test names and assertions
def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)


class TestUserCode(unittest.TestCase):

    def test_unique_years_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'unique_years'),
            "The `unique_years` variable is declared.",
            "Expected `unique_years` to be declared."
        )

    def test_unique_years_contains_correct_values(self):
        import user_code
        expected_value = sorted([2017, 2016, 2019])
        try:
            if isinstance(user_code.unique_years, np.ndarray):
                actual_value = sorted(user_code.unique_years)
                condition = actual_value == expected_value
                failure_message = f"Expected `unique_years` to contain `{expected_value}`, but got `{actual_value}`."
            else:
                condition = False
                failure_message = f"`unique_years` is not a `numpy.ndarray`."

        except AttributeError:
            condition = False
            failure_message = "The `unique_years` variable is not declared."

        _dynamic_test(
            self,
            condition,
            f"`unique_years` contains correct values.",
            failure_message
        )

    def test_unique_fueltype_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'unique_fueltype'),
            "The `unique_fueltype` variable is declared.",
            "Expected `unique_fueltype` to be declared."
        )

    def test_unique_fueltype_contains_correct_values(self):
        import user_code
        expected_value = sorted(["petrol", "diesel"])
        try:
            if isinstance(user_code.unique_fueltype, np.ndarray):
                actual_value = sorted(user_code.unique_fueltype)
                condition = actual_value == expected_value
                failure_message = f"Expected `unique_fueltype` to contain `{expected_value}`, but got `{actual_value}`."
            else:
                condition = False
                failure_message = f"`unique_fueltype` is not a `numpy.ndarray`."
        except AttributeError:
            condition = False
            failure_message = "The `unique_fueltype` variable is not declared."

        _dynamic_test(
            self,
            condition,
            f"`unique_fueltype` contains correct values.",
            failure_message
        )

    def test_count_unique_fueltypes_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'count_unique_fueltypes'),
            "The `count_unique_fueltypes` variable is declared.",
            "Expected `count_unique_fueltypes` to be declared."
        )

    def test_count_unique_fueltypes_is_correct(self):
        import user_code
        expected_value = 2
        try:
            actual_value = user_code.count_unique_fueltypes
            condition = actual_value == expected_value
            failure_message = f"Expected `count_unique_fueltypes` to be `{expected_value}`, but got `{actual_value}`."
        except AttributeError:
            condition = False
            failure_message = "The `count_unique_fueltypes` variable is not declared."

        _dynamic_test(
            self,
            condition,
            f"`count_unique_fueltypes` is correct.",
            failure_message
        )


if __name__ == '__main__':
    unittest.main()

test_main.py

Build practical data manipulation skills using pandas. Learn to work with Series and DataFrames, read and explore datasets, select and filter data, perform aggregations, reshape tables, combine multiple DataFrames, and prepare data for analysis.

Unique Values

Solution