Codes 4 W06

Author: canbula

Week06/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Bora Canbula
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Week06/README.md

@@ -0,0 +1,3 @@
+# boracanbula
+This is a test package 
+for the PyPi tutorial.

Week06/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "boracanbula"
+version = "0.0.1"
+authors = [
+    { name = "Bora Canbula", email = "bora.canbula@cbu.edu.tr" },
+]
+description = "A simple package for calculating statistics."
+readme = "README.md"
+keywords = ["canbula", "statistics"]
+requires-python = ">=3.6.0"
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+
+[project.urls]
+Homepage = "https://github.com/canbula/boracanbula"

Week06/src/boracanbula/__init__.py

@@ -0,0 +1,82 @@
+import random
+
+
+def simple_random_sampling(data, n, replacement=False):
+    """Simple Random Sampling with or without replacement."""
+    if replacement:
+        return [random.choice(data) for _ in range(n)]
+    return random.sample(data, min(n, len(data)))
+
+
+def stratified_sampling(data, n, strata):
+    """Strafied Sampling with proportional representation of strata."""
+    sample = []
+    for key in strata:
+        sample += random.sample(data[key], min(n // len(strata), len(data[key])))
+    return sample
+
+
+def cluster_sampling(data, n, clusters):
+    """Cluster Sampling with random selection of clusters."""
+    picked_clusters = random.sample(clusters, min(n, len(clusters)))
+    sample = []
+    for cluster in picked_clusters:
+        sample += data[cluster]
+    sample = list(set(sample))
+    return sample
+
+
+def systematic_sampling(data, n):
+    """Systematic Sampling."""
+    sample = []
+    for i in range(0, len(data), n):
+        sample.append(data[i])
+    return sample
+
+
+def mean(x: list) -> float:
+    """Calculate the mean of a list of numbers."""
+    return sum(x) / len(x)
+
+
+def median(data):
+    """Find the median of a list of numbers."""
+    data = sorted(data)
+    n = len(data)
+    if n % 2 == 1:
+        return data[int((n + 1) / 2) - 1]
+    return (data[(n // 2) - 1] + data[((n // 2) + 1) - 1]) / 2
+
+
+def mode(data):
+    """Find the mode(s) of a list of numbers."""
+    counts = {}
+    for value in data:
+        if value in counts:
+            counts[value] += 1
+        else:
+            counts[value] = 1
+    max_count = max(counts.values())
+    mode = [value for value, count in counts.items() if count == max_count]
+    return mode
+
+
+def range(x):
+    """Calculate the range of x."""
+    return max(x) - min(x)
+
+
+def variance(x):
+    """Calculate the variance of x."""
+    mean_ = mean(x)
+    return sum((xi - mean_) ** 2 for xi in x) / (len(x) - 1)
+
+
+def standard_deviation(x):
+    """Calculate the standard deviation of x."""
+    return variance(x) ** 0.5
+
+
+def coefficient_of_variation(x):
+    """Calculate the coefficient of variation of x."""
+    return standard_deviation(x) / mean(x)

Week06/src/boracanbula/statistics.py

@@ -0,0 +1,26 @@
+import sys
+
+sys.path.append(".")
+
+import pytest
+from src.boracanbula import statistics
+
+
+@pytest.mark.parametrize(
+    "input, expected",
+    [
+        ([1, 2, 3, 4, 5], 3),
+        ([1, 2, 3, 4, 5, 6], 3.5),
+        ([1, 2, 3, 4], 2.5),
+        ([1, 2, 3], 2),
+        ([1, 2], 1.5),
+        ([1], 1),
+        ([1, 2, 3, 4, 5, 6, 7], 4),
+        ([1, 2, 3, 4, 5, 6, 7, 8], 4.5),
+        ([1, 2, 3, 4, 5, 6, 7, 8, 9], 5),
+    ],
+)
+def test_mean(input, expected):
+    assert (
+        statistics.mean(input) == expected
+    ), f"failed on test_mean with input {input} and expected {expected}"