Simplify example files

Author: LiamPattinson

learners/files/06-floating-point-data/statistics/stats.py

@@ -1,6 +1,3 @@
-import numpy as np
-import pandas as pd
-
 import random
 
 
@@ -35,104 +32,3 @@ def randomly_sample_and_filter_participants(
     age_filtered_participants = filter_participants_by_age(sampled_participants, min_age, max_age)
     height_filtered_participants = filter_participants_by_height(age_filtered_participants, min_height, max_height)
     return height_filtered_participants
-
-
-def remove_anomalies(data: list, maximum_value: float, minimum_value: float) -> list:
-    """Remove anomalies from a list of numbers"""
-
-    result = []
-
-    for value in data:
-        if minimum_value <= value <= maximum_value:
-            result.append(value)
-
-    return result
-
-
-def calculate_frequency(data: list) -> dict:
-    """Calculate the frequency of each element in a list"""
-
-    frequencies = {}
-
-    # Iterate over each value in the list
-    for value in data:
-        # If the value is already in the dictionary, increment the count
-        if value in frequencies:
-            frequencies[value] += 1
-        # Otherwise, add the value to the dictionary with a count of 1
-        else:
-            frequencies[value] = 1
-
-    return frequencies
-
-
-def calculate_cumulative_sum(array: np.ndarray) -> np.ndarray:
-    """Calculate the cumulative sum of a numpy array"""
-
-    # don't use the built-in numpy function
-    result = np.zeros(array.shape)
-    result[0] = array[0]
-    for i in range(1, len(array)):
-        result[i] = result[i - 1] + array[i]
-
-    return result
-
-
-def calculate_player_total_scores(participants: dict):
-    """Calculate the total score of each player in a dictionary.
-
-    Example input:
-    {
-        "Alice": {
-            "scores": np.array([1, 2, 3])
-        },
-        "Bob": {
-            "scores": np.array([4, 5, 6])
-        },
-        "Charlie": {
-            "scores": np.array([7, 8, 9])
-        },
-    }
-
-    Example output:
-    {
-        "Alice": {
-            "scores": np.array([1, 2, 3]),
-            "total_score": 6
-        },
-        "Bob": {
-            "scores": np.array([4, 5, 6]),
-            "total_score": 15
-        },
-        "Charlie": {
-            "scores": np.array([7, 8, 9]),
-            "total_score": 24
-        },
-    }
-    """
-
-    for player in participants:
-        participants[player]["total_score"] = np.sum(participants[player]["scores"])
-
-    return participants
-
-
-def calculate_player_average_scores(df: pd.DataFrame) -> pd.DataFrame:
-    """Calculate the average score of each player in a pandas DataFrame.
-
-    Example input:
-    |   | player  | score_1 | score_2 |
-    |---|---------|---------|---------|
-    | 0 | Alice   | 1       | 2       |
-    | 1 | Bob     | 3       | 4       |
-
-    Example output:
-    |   | player  | score_1 | score_2 | average_score |
-    |---|---------|---------|---------|---------------|
-    | 0 | Alice   | 1       | 2       | 1.5           |
-    | 1 | Bob     | 3       | 4       | 3.5           |
-    """
-
-    df["average_score"] = df[["score_1", "score_2"]].mean(axis=1)
-
-    return df

learners/files/06-floating-point-data/statistics/test_stats.py

@@ -1,16 +1,8 @@
-import numpy as np
-import pandas as pd
-
 from stats import (
     sample_participants,
     filter_participants_by_age,
     filter_participants_by_height,
     randomly_sample_and_filter_participants,
-    remove_anomalies,
-    calculate_frequency,
-    calculate_cumulative_sum,
-    calculate_player_total_scores,
-    calculate_player_average_scores,
 )
 
 import random
@@ -88,50 +80,3 @@ def test_randomly_sample_and_filter_participants():
     )
     expected = [{"age": 38, "height": 165}, {"age": 30, "height": 170}, {"age": 35, "height": 160}]
     assert filtered_participants == expected
-
-
-def test_remove_anomalies():
-    """Test remove_anomalies function"""
-    data = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
-    maximum_value = 5
-    minimum_value = 2
-    expected_result = [2, 3, 4, 5]
-    assert remove_anomalies(data, maximum_value, minimum_value) == expected_result
-
-
-def test_calculate_frequency():
-    """Test calculate_frequency function"""
-    data = [1, 2, 3, 1, 2, 1, 1, 3, 3, 3]
-    expected_result = {1: 4, 2: 2, 3: 4}
-    assert calculate_frequency(data) == expected_result
-
-
-def test_calculate_cumulative_sum():
-    """Test calculate_cumulative_sum function"""
-    array = np.array([1, 2, 3, 4, 5])
-    expected_result = np.array([1, 3, 6, 10, 15])
-    np.testing.assert_array_equal(calculate_cumulative_sum(array), expected_result)
-
-
-def test_calculate_player_total_scores():
-    """Test calculate_player_total_scores function"""
-    participants = {
-        "Alice": {"scores": np.array([1, 2, 3])},
-        "Bob": {"scores": np.array([4, 5, 6])},
-        "Charlie": {"scores": np.array([7, 8, 9])},
-    }
-    expected_result = {
-        "Alice": {"scores": np.array([1, 2, 3]), "total_score": 6},
-        "Bob": {"scores": np.array([4, 5, 6]), "total_score": 15},
-        "Charlie": {"scores": np.array([7, 8, 9]), "total_score": 24},
-    }
-    np.testing.assert_equal(calculate_player_total_scores(participants), expected_result)
-
-
-def test_calculate_player_average_scores():
-    """Test calculate_player_average_scores function"""
-    df = pd.DataFrame({"player": ["Alice", "Bob"], "score_1": [1, 3], "score_2": [2, 4]})
-    expected_result = pd.DataFrame(
-        {"player": ["Alice", "Bob"], "score_1": [1, 3], "score_2": [2, 4], "average_score": [1.5, 3.5]}
-    )
-    pd.testing.assert_frame_equal(calculate_player_average_scores(df), expected_result)

learners/files/07-fixtures/statistics/stats.py

@@ -1,6 +1,3 @@
-import numpy as np
-import pandas as pd
-
 import random
 
 
@@ -35,104 +32,3 @@ def randomly_sample_and_filter_participants(
     age_filtered_participants = filter_participants_by_age(sampled_participants, min_age, max_age)
     height_filtered_participants = filter_participants_by_height(age_filtered_participants, min_height, max_height)
     return height_filtered_participants
-
-
-def remove_anomalies(data: list, maximum_value: float, minimum_value: float) -> list:
-    """Remove anomalies from a list of numbers"""
-
-    result = []
-
-    for value in data:
-        if minimum_value <= value <= maximum_value:
-            result.append(value)
-
-    return result
-
-
-def calculate_frequency(data: list) -> dict:
-    """Calculate the frequency of each element in a list"""
-
-    frequencies = {}
-
-    # Iterate over each value in the list
-    for value in data:
-        # If the value is already in the dictionary, increment the count
-        if value in frequencies:
-            frequencies[value] += 1
-        # Otherwise, add the value to the dictionary with a count of 1
-        else:
-            frequencies[value] = 1
-
-    return frequencies
-
-
-def calculate_cumulative_sum(array: np.ndarray) -> np.ndarray:
-    """Calculate the cumulative sum of a numpy array"""
-
-    # don't use the built-in numpy function
-    result = np.zeros(array.shape)
-    result[0] = array[0]
-    for i in range(1, len(array)):
-        result[i] = result[i - 1] + array[i]
-
-    return result
-
-
-def calculate_player_total_scores(participants: dict):
-    """Calculate the total score of each player in a dictionary.
-
-    Example input:
-    {
-        "Alice": {
-            "scores": np.array([1, 2, 3])
-        },
-        "Bob": {
-            "scores": np.array([4, 5, 6])
-        },
-        "Charlie": {
-            "scores": np.array([7, 8, 9])
-        },
-    }
-
-    Example output:
-    {
-        "Alice": {
-            "scores": np.array([1, 2, 3]),
-            "total_score": 6
-        },
-        "Bob": {
-            "scores": np.array([4, 5, 6]),
-            "total_score": 15
-        },
-        "Charlie": {
-            "scores": np.array([7, 8, 9]),
-            "total_score": 24
-        },
-    }
-    """
-
-    for player in participants:
-        participants[player]["total_score"] = np.sum(participants[player]["scores"])
-
-    return participants
-
-
-def calculate_player_average_scores(df: pd.DataFrame) -> pd.DataFrame:
-    """Calculate the average score of each player in a pandas DataFrame.
-
-    Example input:
-    |   | player  | score_1 | score_2 |
-    |---|---------|---------|---------|
-    | 0 | Alice   | 1       | 2       |
-    | 1 | Bob     | 3       | 4       |
-
-    Example output:
-    |   | player  | score_1 | score_2 | average_score |
-    |---|---------|---------|---------|---------------|
-    | 0 | Alice   | 1       | 2       | 1.5           |
-    | 1 | Bob     | 3       | 4       | 3.5           |
-    """
-
-    df["average_score"] = df[["score_1", "score_2"]].mean(axis=1)
-
-    return df

learners/files/07-fixtures/statistics/test_stats.py

@@ -1,17 +1,10 @@
-import numpy as np
-import pandas as pd
 import pytest
 
 from stats import (
     sample_participants,
     filter_participants_by_age,
     filter_participants_by_height,
     randomly_sample_and_filter_participants,
-    remove_anomalies,
-    calculate_frequency,
-    calculate_cumulative_sum,
-    calculate_player_total_scores,
-    calculate_player_average_scores,
 )
 
 import random
@@ -69,50 +62,3 @@ def test_randomly_sample_and_filter_participants(participants):
     )
     expected = [{"age": 38, "height": 165}, {"age": 30, "height": 170}, {"age": 35, "height": 160}]
     assert filtered_participants == expected
-
-
-def test_remove_anomalies():
-    """Test remove_anomalies function"""
-    data = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
-    maximum_value = 5
-    minimum_value = 2
-    expected_result = [2, 3, 4, 5]
-    assert remove_anomalies(data, maximum_value, minimum_value) == expected_result
-
-
-def test_calculate_frequency():
-    """Test calculate_frequency function"""
-    data = [1, 2, 3, 1, 2, 1, 1, 3, 3, 3]
-    expected_result = {1: 4, 2: 2, 3: 4}
-    assert calculate_frequency(data) == expected_result
-
-
-def test_calculate_cumulative_sum():
-    """Test calculate_cumulative_sum function"""
-    array = np.array([1, 2, 3, 4, 5])
-    expected_result = np.array([1, 3, 6, 10, 15])
-    np.testing.assert_array_equal(calculate_cumulative_sum(array), expected_result)
-
-
-def test_calculate_player_total_scores():
-    """Test calculate_player_total_scores function"""
-    participants = {
-        "Alice": {"scores": np.array([1, 2, 3])},
-        "Bob": {"scores": np.array([4, 5, 6])},
-        "Charlie": {"scores": np.array([7, 8, 9])},
-    }
-    expected_result = {
-        "Alice": {"scores": np.array([1, 2, 3]), "total_score": 6},
-        "Bob": {"scores": np.array([4, 5, 6]), "total_score": 15},
-        "Charlie": {"scores": np.array([7, 8, 9]), "total_score": 24},
-    }
-    np.testing.assert_equal(calculate_player_total_scores(participants), expected_result)
-
-
-def test_calculate_player_average_scores():
-    """Test calculate_player_average_scores function"""
-    df = pd.DataFrame({"player": ["Alice", "Bob"], "score_1": [1, 3], "score_2": [2, 4]})
-    expected_result = pd.DataFrame(
-        {"player": ["Alice", "Bob"], "score_1": [1, 3], "score_2": [2, 4], "average_score": [1.5, 3.5]}
-    )
-    pd.testing.assert_frame_equal(calculate_player_average_scores(df), expected_result)