From 57e7cdc85e3a4f908a64a8e0024616ccebc396eb Mon Sep 17 00:00:00 2001
From: Arnav Kohli <arnavkohli321@gmail.com>
Date: Sat, 7 Oct 2023 09:35:34 +0530
Subject: [PATCH 01/35] Created folder for losses in Machine_Learning

---
 .../losses/binary_cross_entropy.py            | 31 +++++++++++++++++++
 machine_learning/losses/mean_squared_error.py | 27 ++++++++++++++++
 2 files changed, 58 insertions(+)
 create mode 100644 machine_learning/losses/binary_cross_entropy.py
 create mode 100644 machine_learning/losses/mean_squared_error.py

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
new file mode 100644
index 000000000000..1c19974877ec
--- /dev/null
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -0,0 +1,31 @@
+import numpy as np
+
+
+def binary_cross_entropy(y_true, y_pred, epsilon=1e-15):
+    """
+    Calculate the BCE Loss between true labels and predicted probabilities.
+
+    Parameters:
+    - y_true: True binary labels (0 or 1).
+    - y_pred: Predicted probabilities for class 1.
+    - epsilon: Small constant to avoid numerical instability.
+
+    Returns:
+    - bce_loss: Binary Cross-Entropy Loss.
+
+    Example Usage:
+    true_labels = np.array([0, 1, 1, 0, 1])
+    predicted_probs = np.array([0.2, 0.7, 0.9, 0.3, 0.8])
+    bce_loss = binary_cross_entropy(true_labels, predicted_probs)
+    print(f"Binary Cross-Entropy Loss: {bce_loss}")
+    """
+    # Clip predicted probabilities to avoid log(0) and log(1)
+    y_pred = np.clip(y_pred, epsilon, 1 - epsilon)
+
+    # Calculate binary cross-entropy loss
+    bce_loss = -(y_true * np.log(y_pred) + (1 - y_true) * np.log(1 - y_pred))
+
+    # Take the mean over all samples
+    bce_loss = np.mean(bce_loss)
+
+    return bce_loss
diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
new file mode 100644
index 000000000000..580b1a123115
--- /dev/null
+++ b/machine_learning/losses/mean_squared_error.py
@@ -0,0 +1,27 @@
+import numpy as np
+
+
+def mean_squared_error(y_true, y_pred):
+    """
+    Calculate the Mean Squared Error (MSE) between two arrays.
+
+    Parameters:
+    - y_true: The true values (ground truth).
+    - y_pred: The predicted values.
+
+    Returns:
+    - mse: The Mean Squared Error between y_true and y_pred.
+
+    Example usage:
+    true_values = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
+    predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
+    mse = mean_squared_error(true_values, predicted_values)
+    print(f"Mean Squared Error: {mse}")
+    """
+    if len(y_true) != len(y_pred):
+        raise ValueError("Input arrays must have the same length.")
+
+    squared_errors = np.square(np.subtract(y_true, y_pred))
+    mse = np.mean(squared_errors)
+
+    return mse

From aedf0b953fc2ac8e1520b4a116a8dfc28081a3d1 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 09:51:52 +0530
Subject: [PATCH 02/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 1c19974877ec..a287a1e8ca92 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -1,7 +1,7 @@
 import numpy as np
 
 
-def binary_cross_entropy(y_true, y_pred, epsilon=1e-15):
+def binary_cross_entropy(y_true: list[int], y_pred: list[float], epsilon: int=1e-15) -> float:
     """
     Calculate the BCE Loss between true labels and predicted probabilities.
 

From 9b7468ccfb75c723ff90f9c3ac8a34570d1b9f01 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 7 Oct 2023 04:22:25 +0000
Subject: [PATCH 03/35] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/losses/binary_cross_entropy.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index a287a1e8ca92..b3758777e668 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -1,7 +1,9 @@
 import numpy as np
 
 
-def binary_cross_entropy(y_true: list[int], y_pred: list[float], epsilon: int=1e-15) -> float:
+def binary_cross_entropy(
+    y_true: list[int], y_pred: list[float], epsilon: int = 1e-15
+) -> float:
     """
     Calculate the BCE Loss between true labels and predicted probabilities.
 

From 38f405cbf247fa96598918240276a9071ba9ab8a Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 09:52:57 +0530
Subject: [PATCH 04/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 580b1a123115..e07201656330 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -1,7 +1,7 @@
 import numpy as np
 
 
-def mean_squared_error(y_true, y_pred):
+def mean_squared_error(y_true: list[float], y_pred: list[float]) -> float:
     """
     Calculate the Mean Squared Error (MSE) between two arrays.
 

From 448785c664cba3727fe5f6973966554378cc4819 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 09:56:40 +0530
Subject: [PATCH 05/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index b3758777e668..73717f095434 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -2,7 +2,7 @@
 
 
 def binary_cross_entropy(
-    y_true: list[int], y_pred: list[float], epsilon: int = 1e-15
+    y_true: np.array[int], y_pred: np.array[float], epsilon: float = 1e-15
 ) -> float:
     """
     Calculate the BCE Loss between true labels and predicted probabilities.

From 761fe3397451a8950b909690f1ee40fb3918ddf8 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 09:57:24 +0530
Subject: [PATCH 06/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index e07201656330..8777ec3b80e8 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -1,7 +1,7 @@
 import numpy as np
 
 
-def mean_squared_error(y_true: list[float], y_pred: list[float]) -> float:
+def mean_squared_error(y_true: np.array[float], y_pred: np.array[float]) -> float:
     """
     Calculate the Mean Squared Error (MSE) between two arrays.
 

From 7d59779a786a9674d1438531d689e5ff205ab569 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 10:03:05 +0530
Subject: [PATCH 07/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 73717f095434..2622c0b1b919 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -1,9 +1,7 @@
 import numpy as np
 
 
-def binary_cross_entropy(
-    y_true: np.array[int], y_pred: np.array[float], epsilon: float = 1e-15
-) -> float:
+def binary_cross_entropy(y_true: np.ndarray, y_pred: np.ndarray, epsilon: float = 1e-15) -> float:
     """
     Calculate the BCE Loss between true labels and predicted probabilities.
 

From e8e0aa2e5870adac5d0f665a4bbc8880a4e97284 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 7 Oct 2023 04:33:44 +0000
Subject: [PATCH 08/35] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/losses/binary_cross_entropy.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 2622c0b1b919..c29a6ac940c6 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -1,7 +1,9 @@
 import numpy as np
 
 
-def binary_cross_entropy(y_true: np.ndarray, y_pred: np.ndarray, epsilon: float = 1e-15) -> float:
+def binary_cross_entropy(
+    y_true: np.ndarray, y_pred: np.ndarray, epsilon: float = 1e-15
+) -> float:
     """
     Calculate the BCE Loss between true labels and predicted probabilities.
 

From 09cd35066a6b591caa2937fad3c8cccb54ca978e Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 10:03:54 +0530
Subject: [PATCH 09/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 8777ec3b80e8..fb62bb69ea15 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -1,7 +1,7 @@
 import numpy as np
 
 
-def mean_squared_error(y_true: np.array[float], y_pred: np.array[float]) -> float:
+def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     """
     Calculate the Mean Squared Error (MSE) between two arrays.
 

From ae4e3ee0404013f2979367398a571f9062494c3e Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 10:49:47 +0530
Subject: [PATCH 10/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index c29a6ac940c6..cbbb3b1d82e9 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -31,3 +31,8 @@ def binary_cross_entropy(
     bce_loss = np.mean(bce_loss)
 
     return bce_loss
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()

From 6f26bc36c5db356f3ed4c9ceb40426703b84188f Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 7 Oct 2023 05:20:20 +0000
Subject: [PATCH 11/35] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/losses/binary_cross_entropy.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index cbbb3b1d82e9..fdeed647734a 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -32,6 +32,7 @@ def binary_cross_entropy(
 
     return bce_loss
 
+
 if __name__ == "__main__":
     import doctest
 

From 66faa358a091700babc58797b0aaa85df68583ab Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 10:50:39 +0530
Subject: [PATCH 12/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index fb62bb69ea15..2e7314841ff3 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -25,3 +25,8 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     mse = np.mean(squared_errors)
 
     return mse
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()

From c5a58c372cc9428c65c11bc7c10d6cfb77de8676 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 7 Oct 2023 05:21:14 +0000
Subject: [PATCH 13/35] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/losses/mean_squared_error.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 2e7314841ff3..84a63e86c522 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -26,6 +26,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
 
     return mse
 
+
 if __name__ == "__main__":
     import doctest
 

From 0753db242d051e05a629666dcdb89a72e73af45e Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 11:00:22 +0530
Subject: [PATCH 14/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index fdeed647734a..4c4656ceca4c 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -16,10 +16,11 @@ def binary_cross_entropy(
     - bce_loss: Binary Cross-Entropy Loss.
 
     Example Usage:
-    true_labels = np.array([0, 1, 1, 0, 1])
-    predicted_probs = np.array([0.2, 0.7, 0.9, 0.3, 0.8])
-    bce_loss = binary_cross_entropy(true_labels, predicted_probs)
-    print(f"Binary Cross-Entropy Loss: {bce_loss}")
+    >>> true_labels = np.array([0, 1, 1, 0, 1])
+    >>> predicted_probs = np.array([0.2, 0.7, 0.9, 0.3, 0.8])
+    >>> bce_loss = binary_cross_entropy(true_labels, predicted_probs)
+    >>> bce_loss
+    0.6785203447911846
     """
     # Clip predicted probabilities to avoid log(0) and log(1)
     y_pred = np.clip(y_pred, epsilon, 1 - epsilon)

From 277a681ad63c7c284cb17daa67e5ba8187183e2f Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 11:00:51 +0530
Subject: [PATCH 15/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 84a63e86c522..8257bf981ea1 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -13,10 +13,11 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     - mse: The Mean Squared Error between y_true and y_pred.
 
     Example usage:
-    true_values = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
-    predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
-    mse = mean_squared_error(true_values, predicted_values)
-    print(f"Mean Squared Error: {mse}")
+    >>> true_values = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
+    >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
+    >>> mse = mean_squared_error(true_values, predicted_values)
+    >>> mse
+    0.10599999999999987
     """
     if len(y_true) != len(y_pred):
         raise ValueError("Input arrays must have the same length.")

From 1e3baed363c423095ffad760805e773720e08fd6 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 11:05:41 +0530
Subject: [PATCH 16/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 4c4656ceca4c..e1fef99aeff4 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -20,7 +20,7 @@ def binary_cross_entropy(
     >>> predicted_probs = np.array([0.2, 0.7, 0.9, 0.3, 0.8])
     >>> bce_loss = binary_cross_entropy(true_labels, predicted_probs)
     >>> bce_loss
-    0.6785203447911846
+    0.2529995012327421
     """
     # Clip predicted probabilities to avoid log(0) and log(1)
     y_pred = np.clip(y_pred, epsilon, 1 - epsilon)

From 25c550a388c2f3f01715402b8974597c487b8f88 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 11:06:41 +0530
Subject: [PATCH 17/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 8257bf981ea1..3f934cdd01a6 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -17,7 +17,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
     >>> mse = mean_squared_error(true_values, predicted_values)
     >>> mse
-    0.10599999999999987
+    0.028000000000000032
     """
     if len(y_true) != len(y_pred):
         raise ValueError("Input arrays must have the same length.")

From 8513bdafe2db9cfee1f506fc8eaeb891ea839858 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 13:54:56 +0530
Subject: [PATCH 18/35] Update machine_learning/losses/binary_cross_entropy.py

Co-authored-by: Christian Clauss <cclauss@me.com>
---
 machine_learning/losses/binary_cross_entropy.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index e1fef99aeff4..7c52ce47302f 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -29,9 +29,7 @@ def binary_cross_entropy(
     bce_loss = -(y_true * np.log(y_pred) + (1 - y_true) * np.log(1 - y_pred))
 
     # Take the mean over all samples
-    bce_loss = np.mean(bce_loss)
-
-    return bce_loss
+    return np.mean(bce_loss)
 
 
 if __name__ == "__main__":

From cae669eb1038eac81f7d8e4c0b14c6fcb19092b7 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 13:55:08 +0530
Subject: [PATCH 19/35] Update machine_learning/losses/mean_squared_error.py

Co-authored-by: Christian Clauss <cclauss@me.com>
---
 machine_learning/losses/mean_squared_error.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 3f934cdd01a6..fc389608e44c 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -15,8 +15,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     Example usage:
     >>> true_values = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
     >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
-    >>> mse = mean_squared_error(true_values, predicted_values)
-    >>> mse
+    >>> mean_squared_error(true_values, predicted_values)
     0.028000000000000032
     """
     if len(y_true) != len(y_pred):

From 5624c229e720312cf11e0fa34916869041baf1e0 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 13:55:42 +0530
Subject: [PATCH 20/35] Update machine_learning/losses/binary_cross_entropy.py

Co-authored-by: Christian Clauss <cclauss@me.com>
---
 machine_learning/losses/binary_cross_entropy.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 7c52ce47302f..7e40f8bfd516 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -18,8 +18,7 @@ def binary_cross_entropy(
     Example Usage:
     >>> true_labels = np.array([0, 1, 1, 0, 1])
     >>> predicted_probs = np.array([0.2, 0.7, 0.9, 0.3, 0.8])
-    >>> bce_loss = binary_cross_entropy(true_labels, predicted_probs)
-    >>> bce_loss
+    >>> binary_cross_entropy(true_labels, predicted_probs)
     0.2529995012327421
     """
     # Clip predicted probabilities to avoid log(0) and log(1)

From 7cebd00b057ddba17d2114b9e9cda061d756a6a4 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 14:00:42 +0530
Subject: [PATCH 21/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index fc389608e44c..784f0b065dae 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -22,9 +22,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
         raise ValueError("Input arrays must have the same length.")
 
     squared_errors = np.square(np.subtract(y_true, y_pred))
-    mse = np.mean(squared_errors)
-
-    return mse
+    return np.mean(squared_errors)
 
 
 if __name__ == "__main__":

From f2000499f596feaca7815498648f02e2317b3f20 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:27:40 +0530
Subject: [PATCH 22/35] Update machine_learning/losses/mean_squared_error.py

Co-authored-by: Tianyi Zheng <tianyizheng02@gmail.com>
---
 machine_learning/losses/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 784f0b065dae..e8316fdbed3d 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -21,7 +21,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     if len(y_true) != len(y_pred):
         raise ValueError("Input arrays must have the same length.")
 
-    squared_errors = np.square(np.subtract(y_true, y_pred))
+    squared_errors = (y_true - y_pred) ** 2
     return np.mean(squared_errors)
 
 

From b302359d28a66e842446b66bb6d70a6a89100c9e Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:35:32 +0530
Subject: [PATCH 23/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 7e40f8bfd516..d733515e9152 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -1,3 +1,18 @@
+"""
+Binary Cross-Entropy (BCE) Loss Function
+
+This script defines the Binary Cross-Entropy (BCE) loss function, which is commonly used for binary classification problems.
+
+Description:
+Binary Cross-Entropy (BCE), also known as log loss or logistic loss, is a popular loss function for binary classification tasks. It quantifies the dissimilarity between the true binary labels (0 or 1) and the predicted probabilities produced by a model. Lower BCE values indicate better alignment between predicted probabilities and true labels.
+
+Formula:
+BCE = -Σ(y_true * log(y_pred) + (1 - y_true) * log(1 - y_pred))
+
+Source:
+- [Wikipedia - Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy)
+"""
+
 import numpy as np
 
 

From ba41942528a76242eda00fc4f0f6677098e0a2cf Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:36:00 +0530
Subject: [PATCH 24/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index e8316fdbed3d..9a6bdbf5b243 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -1,3 +1,18 @@
+"""
+Mean Squared Error (MSE) Loss Function
+
+This script defines the Mean Squared Error (MSE) loss function, which is commonly used for regression problems.
+
+Description:
+The Mean Squared Error (MSE) measures the average squared difference between the true values (ground truth) and the predicted values produced by a model. It is widely used in regression tasks and serves as a measure of the model's accuracy.
+
+Formula:
+MSE = (1/n) * Σ(y_true - y_pred)^2
+
+Source:
+- [Wikipedia - Mean squared error](https://en.wikipedia.org/wiki/Mean_squared_error)
+"""
+
 import numpy as np
 
 

From 26beff697602058d64d8dc110bcb7e86affa6dfc Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:36:38 +0530
Subject: [PATCH 25/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index d733515e9152..8ac02802ec87 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -4,7 +4,9 @@
 This script defines the Binary Cross-Entropy (BCE) loss function, which is commonly used for binary classification problems.
 
 Description:
-Binary Cross-Entropy (BCE), also known as log loss or logistic loss, is a popular loss function for binary classification tasks. It quantifies the dissimilarity between the true binary labels (0 or 1) and the predicted probabilities produced by a model. Lower BCE values indicate better alignment between predicted probabilities and true labels.
+Binary Cross-Entropy (BCE), also known as log loss or logistic loss, is a popular loss function for binary classification tasks.
+It quantifies the dissimilarity between the true binary labels (0 or 1) and the predicted probabilities produced by a model.
+Lower BCE values indicate better alignment between predicted probabilities and true labels.
 
 Formula:
 BCE = -Σ(y_true * log(y_pred) + (1 - y_true) * log(1 - y_pred))

From e60dd140e11b96c813d81d6eef33816ae00fd34b Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:37:28 +0530
Subject: [PATCH 26/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 9a6bdbf5b243..181268e614fb 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -4,7 +4,8 @@
 This script defines the Mean Squared Error (MSE) loss function, which is commonly used for regression problems.
 
 Description:
-The Mean Squared Error (MSE) measures the average squared difference between the true values (ground truth) and the predicted values produced by a model. It is widely used in regression tasks and serves as a measure of the model's accuracy.
+The Mean Squared Error (MSE) measures the average squared difference between the true values (ground truth) and the predicted values produced by a model.
+It is widely used in regression tasks and serves as a measure of the model's accuracy.
 
 Formula:
 MSE = (1/n) * Σ(y_true - y_pred)^2

From 747e8cc9e94a3b178ad69c326450ac2369ab5528 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:43:50 +0530
Subject: [PATCH 27/35] Update mean_squared_error.py

---
 machine_learning/losses/mean_squared_error.py | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/losses/mean_squared_error.py
index 181268e614fb..8f32e4111377 100644
--- a/machine_learning/losses/mean_squared_error.py
+++ b/machine_learning/losses/mean_squared_error.py
@@ -1,17 +1,16 @@
 """
 Mean Squared Error (MSE) Loss Function
 
-This script defines the Mean Squared Error (MSE) loss function, which is commonly used for regression problems.
+This script defines the Mean Squared Error (MSE) loss function, commonly used for regression problems.
 
 Description:
-The Mean Squared Error (MSE) measures the average squared difference between the true values (ground truth) and the predicted values produced by a model.
-It is widely used in regression tasks and serves as a measure of the model's accuracy.
+MSE measures the average squared difference between true values (ground truth) and predicted values.
+It serves as a measure of the model's accuracy in regression tasks.
 
 Formula:
 MSE = (1/n) * Σ(y_true - y_pred)^2
 
-Source:
-- [Wikipedia - Mean squared error](https://en.wikipedia.org/wiki/Mean_squared_error)
+Source: [Wikipedia - Mean squared error](https://en.wikipedia.org/wiki/Mean_squared_error)
 """
 
 import numpy as np

From e618611d5c1d8e2e44df512e75fb585b6a9e03f3 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sat, 7 Oct 2023 15:44:43 +0530
Subject: [PATCH 28/35] Update binary_cross_entropy.py

---
 machine_learning/losses/binary_cross_entropy.py | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/losses/binary_cross_entropy.py
index 8ac02802ec87..1cfd8b96a12a 100644
--- a/machine_learning/losses/binary_cross_entropy.py
+++ b/machine_learning/losses/binary_cross_entropy.py
@@ -1,18 +1,16 @@
 """
 Binary Cross-Entropy (BCE) Loss Function
 
-This script defines the Binary Cross-Entropy (BCE) loss function, which is commonly used for binary classification problems.
+This script defines the Binary Cross-Entropy (BCE) loss function, commonly used for binary classification.
 
 Description:
-Binary Cross-Entropy (BCE), also known as log loss or logistic loss, is a popular loss function for binary classification tasks.
-It quantifies the dissimilarity between the true binary labels (0 or 1) and the predicted probabilities produced by a model.
-Lower BCE values indicate better alignment between predicted probabilities and true labels.
+BCE quantifies dissimilarity between true binary labels (0 or 1) and predicted probabilities.
+It's widely used in binary classification tasks.
 
 Formula:
 BCE = -Σ(y_true * log(y_pred) + (1 - y_true) * log(1 - y_pred))
 
-Source:
-- [Wikipedia - Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy)
+Source: [Wikipedia - Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy)
 """
 
 import numpy as np

From fc15fb85f3faa3f34cd7c0ebe7280be81a4fd81b Mon Sep 17 00:00:00 2001
From: Arnav Kohli <arnavkohli321@gmail.com>
Date: Sat, 7 Oct 2023 15:47:12 +0530
Subject: [PATCH 29/35] renamed: losses -> loss_functions

---
 .../{losses => loss_functions}/binary_cross_entropy.py            | 0
 machine_learning/{losses => loss_functions}/mean_squared_error.py | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 rename machine_learning/{losses => loss_functions}/binary_cross_entropy.py (100%)
 rename machine_learning/{losses => loss_functions}/mean_squared_error.py (100%)

diff --git a/machine_learning/losses/binary_cross_entropy.py b/machine_learning/loss_functions/binary_cross_entropy.py
similarity index 100%
rename from machine_learning/losses/binary_cross_entropy.py
rename to machine_learning/loss_functions/binary_cross_entropy.py
diff --git a/machine_learning/losses/mean_squared_error.py b/machine_learning/loss_functions/mean_squared_error.py
similarity index 100%
rename from machine_learning/losses/mean_squared_error.py
rename to machine_learning/loss_functions/mean_squared_error.py

From 7ff794822363ebe6e83f54853e086bffd98b7a8a Mon Sep 17 00:00:00 2001
From: Arnav Kohli <arnavkohli321@gmail.com>
Date: Sat, 7 Oct 2023 15:53:08 +0530
Subject: [PATCH 30/35] updated 2 files

---
 machine_learning/loss_functions/binary_cross_entropy.py | 7 +++----
 machine_learning/loss_functions/mean_squared_error.py   | 7 +++----
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/machine_learning/loss_functions/binary_cross_entropy.py b/machine_learning/loss_functions/binary_cross_entropy.py
index 1cfd8b96a12a..49e792bd23ad 100644
--- a/machine_learning/loss_functions/binary_cross_entropy.py
+++ b/machine_learning/loss_functions/binary_cross_entropy.py
@@ -1,16 +1,15 @@
 """
 Binary Cross-Entropy (BCE) Loss Function
 
-This script defines the Binary Cross-Entropy (BCE) loss function, commonly used for binary classification.
-
 Description:
-BCE quantifies dissimilarity between true binary labels (0 or 1) and predicted probabilities.
+Quantifies dissimilarity between true labels (0 or 1) and predicted probabilities.
 It's widely used in binary classification tasks.
 
 Formula:
 BCE = -Σ(y_true * log(y_pred) + (1 - y_true) * log(1 - y_pred))
 
-Source: [Wikipedia - Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy)
+Source: 
+[Wikipedia - Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy)
 """
 
 import numpy as np
diff --git a/machine_learning/loss_functions/mean_squared_error.py b/machine_learning/loss_functions/mean_squared_error.py
index 8f32e4111377..674c8be02e77 100644
--- a/machine_learning/loss_functions/mean_squared_error.py
+++ b/machine_learning/loss_functions/mean_squared_error.py
@@ -1,16 +1,15 @@
 """
 Mean Squared Error (MSE) Loss Function
 
-This script defines the Mean Squared Error (MSE) loss function, commonly used for regression problems.
-
 Description:
-MSE measures the average squared difference between true values (ground truth) and predicted values.
+MSE measures the mean squared difference between true values and predicted values.
 It serves as a measure of the model's accuracy in regression tasks.
 
 Formula:
 MSE = (1/n) * Σ(y_true - y_pred)^2
 
-Source: [Wikipedia - Mean squared error](https://en.wikipedia.org/wiki/Mean_squared_error)
+Source: 
+[Wikipedia - Mean squared error](https://en.wikipedia.org/wiki/Mean_squared_error)
 """
 
 import numpy as np

From 9502a0cbefc7f0deb94f9d35a7409c6885fdc545 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Sat, 7 Oct 2023 10:24:03 +0000
Subject: [PATCH 31/35] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 machine_learning/loss_functions/binary_cross_entropy.py | 2 +-
 machine_learning/loss_functions/mean_squared_error.py   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/machine_learning/loss_functions/binary_cross_entropy.py b/machine_learning/loss_functions/binary_cross_entropy.py
index 49e792bd23ad..0f2542c3ff85 100644
--- a/machine_learning/loss_functions/binary_cross_entropy.py
+++ b/machine_learning/loss_functions/binary_cross_entropy.py
@@ -8,7 +8,7 @@
 Formula:
 BCE = -Σ(y_true * log(y_pred) + (1 - y_true) * log(1 - y_pred))
 
-Source: 
+Source:
 [Wikipedia - Cross entropy](https://en.wikipedia.org/wiki/Cross_entropy)
 """
 
diff --git a/machine_learning/loss_functions/mean_squared_error.py b/machine_learning/loss_functions/mean_squared_error.py
index 674c8be02e77..6f697f8360dd 100644
--- a/machine_learning/loss_functions/mean_squared_error.py
+++ b/machine_learning/loss_functions/mean_squared_error.py
@@ -8,7 +8,7 @@
 Formula:
 MSE = (1/n) * Σ(y_true - y_pred)^2
 
-Source: 
+Source:
 [Wikipedia - Mean squared error](https://en.wikipedia.org/wiki/Mean_squared_error)
 """
 

From 2a4989dc6c4fc8845220cb2b07e28ece8f7caf03 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sun, 8 Oct 2023 13:00:47 +0530
Subject: [PATCH 32/35] Update mean_squared_error.py

---
 machine_learning/loss_functions/mean_squared_error.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/machine_learning/loss_functions/mean_squared_error.py b/machine_learning/loss_functions/mean_squared_error.py
index 6f697f8360dd..5d540e93a07e 100644
--- a/machine_learning/loss_functions/mean_squared_error.py
+++ b/machine_learning/loss_functions/mean_squared_error.py
@@ -31,6 +31,12 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
     >>> mean_squared_error(true_values, predicted_values)
     0.028000000000000032
+    >>> true_labels = np.array([0, 1, 1, 0, 1])
+    >>> predicted_probs = np.array([0.3, 0.8, 0.9, 0.2])
+    >>> binary_cross_entropy(true_labels, predicted_probs)
+    Traceback (most recent call last):
+        ...
+    ValueError: Input arrays must have the same length.
     """
     if len(y_true) != len(y_pred):
         raise ValueError("Input arrays must have the same length.")

From 5a23be75f906e8998a609ae6143508d7a1f91aa9 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sun, 8 Oct 2023 13:01:14 +0530
Subject: [PATCH 33/35] Update mean_squared_error.py

---
 machine_learning/loss_functions/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/loss_functions/mean_squared_error.py b/machine_learning/loss_functions/mean_squared_error.py
index 5d540e93a07e..c231499e1992 100644
--- a/machine_learning/loss_functions/mean_squared_error.py
+++ b/machine_learning/loss_functions/mean_squared_error.py
@@ -33,7 +33,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     0.028000000000000032
     >>> true_labels = np.array([0, 1, 1, 0, 1])
     >>> predicted_probs = np.array([0.3, 0.8, 0.9, 0.2])
-    >>> binary_cross_entropy(true_labels, predicted_probs)
+    >>> mean_squared_error(true_labels, predicted_probs)
     Traceback (most recent call last):
         ...
     ValueError: Input arrays must have the same length.

From 9e1b7d3f7813d1501d3fbd96d0c1d723b98963ea Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sun, 8 Oct 2023 13:03:00 +0530
Subject: [PATCH 34/35] Update binary_cross_entropy.py

---
 machine_learning/loss_functions/binary_cross_entropy.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/machine_learning/loss_functions/binary_cross_entropy.py b/machine_learning/loss_functions/binary_cross_entropy.py
index 0f2542c3ff85..4ebca7f21757 100644
--- a/machine_learning/loss_functions/binary_cross_entropy.py
+++ b/machine_learning/loss_functions/binary_cross_entropy.py
@@ -34,7 +34,15 @@ def binary_cross_entropy(
     >>> predicted_probs = np.array([0.2, 0.7, 0.9, 0.3, 0.8])
     >>> binary_cross_entropy(true_labels, predicted_probs)
     0.2529995012327421
+    >>> true_labels = np.array([0, 1, 1, 0, 1])
+    >>> predicted_probs = np.array([0.3, 0.8, 0.9, 0.2])
+    >>> binary_cross_entropy(true_labels, predicted_probs)
+    Traceback (most recent call last):
+        ...
+    ValueError: Input arrays must have the same length.
     """
+    if len(y_true) != len(y_pred):
+        raise ValueError("Input arrays must have the same length.")
     # Clip predicted probabilities to avoid log(0) and log(1)
     y_pred = np.clip(y_pred, epsilon, 1 - epsilon)
 

From f47d2c368029335015699712915678473502e9f6 Mon Sep 17 00:00:00 2001
From: Arnav Kohli <95236897+THEGAMECHANGER416@users.noreply.github.com>
Date: Sun, 8 Oct 2023 13:03:33 +0530
Subject: [PATCH 35/35] Update mean_squared_error.py

---
 machine_learning/loss_functions/mean_squared_error.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/machine_learning/loss_functions/mean_squared_error.py b/machine_learning/loss_functions/mean_squared_error.py
index c231499e1992..d2b0e1e158ba 100644
--- a/machine_learning/loss_functions/mean_squared_error.py
+++ b/machine_learning/loss_functions/mean_squared_error.py
@@ -31,7 +31,7 @@ def mean_squared_error(y_true: np.ndarray, y_pred: np.ndarray) -> float:
     >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
     >>> mean_squared_error(true_values, predicted_values)
     0.028000000000000032
-    >>> true_labels = np.array([0, 1, 1, 0, 1])
+    >>> true_labels = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
     >>> predicted_probs = np.array([0.3, 0.8, 0.9, 0.2])
     >>> mean_squared_error(true_labels, predicted_probs)
     Traceback (most recent call last):