From 6922a8e6cb3370a13b08a3ade0acd54daf64193a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Batuhan=20Berk=20Ba=C5=9Fo=C4=9Flu?= <batuhan@basoglu.ca>
Date: Mon, 22 Sep 2025 18:01:29 -0400
Subject: [PATCH] Added weight report and more comments.

---
 linear-regression-parkinsons.py                | 4 ++++
 logistic-regression-wdbc.py                    | 8 ++++++--
 mini-batch-sgd-linear-regression-parkinsons.py | 8 ++++++--
 mini-batch-sgd-logistic-regression-wdbc.py     | 8 ++++++--
 4 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/linear-regression-parkinsons.py b/linear-regression-parkinsons.py
index 8759023..95aaf46 100644
--- a/linear-regression-parkinsons.py
+++ b/linear-regression-parkinsons.py
@@ -164,3 +164,7 @@ if __name__ == "__main__":
     preds = model.predict(x_test)
     print("\nFirst 10 predictions:")
     print(preds.head(10))
+
+    # weight report
+    print("\nWeights from the model:")
+    print(model.w)
\ No newline at end of file
diff --git a/logistic-regression-wdbc.py b/logistic-regression-wdbc.py
index 3e6b84f..75e9f6f 100644
--- a/logistic-regression-wdbc.py
+++ b/logistic-regression-wdbc.py
@@ -74,7 +74,7 @@ class LogisticRegression:
             z = self.x.dot(self.w) # linear prediction
             p = self.sigmoid(z) # probabilities of the model predictions
 
-            gradient = self.x.T.dot(p - self.y) / self.y.size # gradient calculation formula
+            gradient = self.x.T.dot(p - self.y) / self.y.size  # for logistic regression X^T*(p - y)
 
             self.w -= self.lr * gradient # gradient multiplied by learning rate is removed from weight
 
@@ -190,4 +190,8 @@ if __name__ == "__main__":
     # predict Y values using the trained data
     first_10 = X_test[:10]
     y_hat = model.predict(first_10)
-    print("\nFirst 10 predictions:", y_hat.ravel())
\ No newline at end of file
+    print("\nFirst 10 predictions:", y_hat.ravel())
+
+    # weight report
+    print("\nWeights from the model:")
+    print(model.w)
\ No newline at end of file
diff --git a/mini-batch-sgd-linear-regression-parkinsons.py b/mini-batch-sgd-linear-regression-parkinsons.py
index a7d3164..31370bc 100644
--- a/mini-batch-sgd-linear-regression-parkinsons.py
+++ b/mini-batch-sgd-linear-regression-parkinsons.py
@@ -74,7 +74,7 @@ class LinearRegression:
                 # makes Y prediction value for X batch value by multiplying X and weight vectors.
 
                 error = y_batch - y_pred  # error is difference between Y batch value and Y prediction value
-                grad = -2 * x_batch.T.dot(error) / batch_size
+                grad = -2 * x_batch.T.dot(error) / batch_size  # for linear regression -2*X^T*(error)
                 # gradient is calculated by multiplication of error, transposed X batch value and -2 divided by batch size
 
                 w_np -= self.lr * grad  # weight is decreased by multiplication of learning rate and gradient
@@ -169,4 +169,8 @@ if __name__ == "__main__":
     # predict Y values using the trained data
     preds = model.predict(x_test)
     print("\nFirst 10 predictions:")
-    print(preds.head(10))
\ No newline at end of file
+    print(preds.head(10))
+
+    # weight report
+    print("\nWeights from the model:")
+    print(model.w)
\ No newline at end of file
diff --git a/mini-batch-sgd-logistic-regression-wdbc.py b/mini-batch-sgd-logistic-regression-wdbc.py
index ef71567..e132b8e 100644
--- a/mini-batch-sgd-logistic-regression-wdbc.py
+++ b/mini-batch-sgd-logistic-regression-wdbc.py
@@ -30,7 +30,7 @@ class LogisticRegression:
         """Cross‑entropy loss is used for the cost calculation"""
         eps = 1e-15
         p = np.clip(p, eps, 1 - eps)
-        return -np.mean(y * np.log(p) + (1 - y) * np.log(1 - p))
+        return -np.mean(y * np.log(p) + (1 - y) * np.log(1 - p)) # mean of -[y*log(p) + (1 - y)*log(1-p)]
 
     def prepare(self, df: pd.DataFrame, target_col: str) -> None:
         """
@@ -90,7 +90,7 @@ class LogisticRegression:
                 z = x_batch.dot(self.w) # linear prediction
                 p = self.sigmoid(z) # probabilities of the model predictions
 
-                grad = x_batch.T.dot(p - y_batch) / y_batch.size # gradient calculation formula
+                grad = x_batch.T.dot(p - y_batch) / y_batch.size # for logistic regression X^T*(p - y)
                 self.w -= self.lr * grad # gradient multiplied by learning rate is removed from weight
 
             # cost is calculated through cross‑entropy and added for the current range
@@ -207,3 +207,7 @@ if __name__ == "__main__":
     first_10 = X_test[:10]
     y_hat = model.predict(first_10)
     print("\nFirst 10 predictions:", y_hat.ravel())
+
+    # weight report
+    print("\nWeights from the model:")
+    print(model.w)