chore: menambahkan fungsi gaussian (#49)

Signed-off-by: slowy07 <[email protected]>

OpenSeries/matematika.py

@@ -504,3 +504,21 @@ def distribusi_binomial(
     koefisien = float(math.factorial(percobaan))
     koefisien /= math.factorial(keberhasilan) * math.factorial(percobaan - keberhasilan)
     return probabilitas_kejadian * koefisien
+
+
+def gaussian(
+    x: int, mu: Union[float, int] = 0.0, sigma: Union[float, int] = 1.0
+) -> Union[float, error.ErrorTipeData]:
+    """
+    fungsi gaussian, yang biasa disebut fungsi kurva lonceng adalah fungsi
+    untuk mendeskripsikan probabilitas distribusi data yang normal
+    """
+    if not all(
+        isinstance(data, (float, int)) for data in [sigma, mu]
+    ) and not isinstance(x, int):
+        return error.ErrorTipeData(["float", "int"])
+    return (
+        1
+        / np.sqrt(2 * constant.PI * sigma**2)
+        * np.exp(-((x - mu) ** 2) / (2 * sigma**2))
+    )

example/matematika/fungsi_gaussian.py

@@ -0,0 +1,7 @@
+import OpenSeries.matematika as matematika
+import numpy as np
+
+print(matematika.gaussian(15))
+
+nilai_x = np.arange(15)
+print(matematika.gaussian(nilai_x))

testing/main_test.py

@@ -1,4 +1,5 @@
 import unittest
+
 from testing.matematika_test import (
     TestKonversi,
     TestKelilingLingkaran,
@@ -14,6 +15,7 @@
     TestFungsiEuler,
     TestSigmoid,
     TestDistribusiBinomial,
+    TestGaussian,
 )
 
 from testing.fisika_test import (
@@ -46,6 +48,7 @@
         TestFungsiEuler,
         TestSigmoid,
         TestDistribusiBinomial,
+        TestGaussian,
     ]
 
     testing_fisika: list = [

testing/matematika_test.py

@@ -242,3 +242,13 @@ def test_input_angka_tidak_integer(self):
         hasil = matematika.distribusi_binomial(2.4, 4.2, 0.5)
         with self.assertRaises(error.ErrorTipeData):
             raise hasil
+
+
+class TestGaussian(unittest.TestCase):
+    def test_data_valid_input(self):
+        x = 5
+        mu = 3
+        sigma = 2
+        ekspetasi_nilai = 0.12098536225957168
+        hasil = matematika.gaussian(x, mu, sigma)
+        self.assertAlmostEqual(hasil, ekspetasi_nilai, places=10)