From 6092840ac306e0dd2c080d4f088eabd5704960d2 Mon Sep 17 00:00:00 2001
From: kausthub-kannan <kausthubkannan961@gmail.com>
Date: Mon, 9 Oct 2023 01:32:28 +0530
Subject: [PATCH 1/3] Added Huber Loss Function

---
 machine_learning/loss_functions/huber_loss.py | 52 +++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 machine_learning/loss_functions/huber_loss.py

diff --git a/machine_learning/loss_functions/huber_loss.py b/machine_learning/loss_functions/huber_loss.py
new file mode 100644
index 000000000000..b3b7c0195d90
--- /dev/null
+++ b/machine_learning/loss_functions/huber_loss.py
@@ -0,0 +1,52 @@
+"""
+Huber Loss Function
+
+Description:
+Huber loss function describes the penalty incurred by an estimation procedure.
+It serves as a measure of the model's accuracy in regression tasks.
+
+Formula:
+Huber Loss = if |y_true - y_pred| <= delta then 0.5 * (y_true - y_pred)^2
+             else delta * |y_true - y_pred| - 0.5 * delta^2
+
+Source:
+[Wikipedia - Huber Loss](https://en.wikipedia.org/wiki/Huber_loss)
+"""
+
+import numpy as np
+
+
+def huber_loss(y_true: np.ndarray, y_pred: np.ndarray, delta: float) -> float:
+    """
+    Calculate the Huber Loss.
+
+    Parameters:
+    - y_true: The true values (ground truth).
+    - y_pred: The predicted values.
+
+    Returns:
+    - mse: The mean of Huber Loss between y_true and y_pred.
+
+    Example usage:
+    >>> true_values = np.array([0.9, 10.0, 2.0, 1.0, 5.2])
+    >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
+    >>> huber_loss(true_values, predicted_values, 1.0)
+    2.1020000000000003
+    >>> true_labels = np.array([11.0, 21.0, 3.32, 4.0, 5.0])
+    >>> predicted_probs = np.array([8.3, 20.8, 2.9, 11.2, 5.0])
+    >>> huber_loss(true_labels, predicted_probs, 1.0)
+    1.8016399999999997
+    """
+
+    if len(y_true) != len(y_pred):
+        raise ValueError("Input arrays must have the same length.")
+
+    huber_mse = 0.5 * (y_true - y_pred) ** 2
+    huber_mae = delta * (np.abs(y_true - y_pred) - 0.5 * delta)
+    return np.where(np.abs(y_true - y_pred) <= delta, huber_mse, huber_mae).mean()
+
+
+if __name__ == "__main__":
+    import doctest
+
+    doctest.testmod()

From fd67a73a5caaea6ba778efde03dbbb439c24cc4e Mon Sep 17 00:00:00 2001
From: kausthub-kannan <kausthubkannan961@gmail.com>
Date: Mon, 9 Oct 2023 01:34:44 +0530
Subject: [PATCH 2/3] Fixed Typos

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

diff --git a/machine_learning/loss_functions/huber_loss.py b/machine_learning/loss_functions/huber_loss.py
index b3b7c0195d90..4958e0190b9e 100644
--- a/machine_learning/loss_functions/huber_loss.py
+++ b/machine_learning/loss_functions/huber_loss.py
@@ -25,7 +25,7 @@ def huber_loss(y_true: np.ndarray, y_pred: np.ndarray, delta: float) -> float:
     - y_pred: The predicted values.
 
     Returns:
-    - mse: The mean of Huber Loss between y_true and y_pred.
+    - huber_loss: The mean of Huber Loss between y_true and y_pred.
 
     Example usage:
     >>> true_values = np.array([0.9, 10.0, 2.0, 1.0, 5.2])

From 6d64e5de294fe6d245ac78a98a2b2203e341f735 Mon Sep 17 00:00:00 2001
From: kausthub-kannan <kausthubkannan961@gmail.com>
Date: Mon, 9 Oct 2023 12:35:17 +0530
Subject: [PATCH 3/3] Added np.isclose() to doctests

---
 machine_learning/loss_functions/huber_loss.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/machine_learning/loss_functions/huber_loss.py b/machine_learning/loss_functions/huber_loss.py
index 4958e0190b9e..202e013f2928 100644
--- a/machine_learning/loss_functions/huber_loss.py
+++ b/machine_learning/loss_functions/huber_loss.py
@@ -18,7 +18,7 @@
 
 def huber_loss(y_true: np.ndarray, y_pred: np.ndarray, delta: float) -> float:
     """
-    Calculate the Huber Loss.
+    Calculate the mean of Huber Loss.
 
     Parameters:
     - y_true: The true values (ground truth).
@@ -30,12 +30,12 @@ def huber_loss(y_true: np.ndarray, y_pred: np.ndarray, delta: float) -> float:
     Example usage:
     >>> true_values = np.array([0.9, 10.0, 2.0, 1.0, 5.2])
     >>> predicted_values = np.array([0.8, 2.1, 2.9, 4.2, 5.2])
-    >>> huber_loss(true_values, predicted_values, 1.0)
-    2.1020000000000003
+    >>> np.isclose(huber_loss(true_values, predicted_values, 1.0), 2.102)
+    True
     >>> true_labels = np.array([11.0, 21.0, 3.32, 4.0, 5.0])
     >>> predicted_probs = np.array([8.3, 20.8, 2.9, 11.2, 5.0])
-    >>> huber_loss(true_labels, predicted_probs, 1.0)
-    1.8016399999999997
+    >>> np.isclose(huber_loss(true_labels, predicted_probs, 1.0), 1.80164)
+    True
     """
 
     if len(y_true) != len(y_pred):