plot functionality'

neural_network/backprop.py

@@ -13,14 +13,14 @@ def bp(X_train: np.array, y_train: np.array, wb: dict, args: dict) -> (dict, np.
     lr = args["learning_rate"]
 
     r = {}
-    loss_history = np.array([])
+    loss_history = []
     for e in tqdm(range(epochs)):
         # forward prop
         node1 = compute_node(arr=X_train, w=w1, b=b1, func=func)
         y_hat = compute_node(arr=node1, w=w2, b=b2, func=func)
         error = y_hat - y_train
         mean_squared_error = mse(y_train, y_hat)
-        loss_history = np.append(loss_history, mean_squared_error)
+        loss_history.append(mean_squared_error)
 
         # backprop
         dw1 = np.dot(

neural_network/main.py

@@ -4,6 +4,7 @@ import numpy as np
 from neural_network.opts import activation
 from neural_network.backprop import bp
 from neural_network.model import Model
+from neural_network.plot import loss_history_plt
 
 
 def get_args() -> dict:
@@ -60,3 +61,4 @@ def main(
 
     # plot predicted versus actual
     # also plot the training loss over epochs
+    loss_history_plt(loss_history)

neural_network/plot.py

@@ -0,0 +1,15 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import seaborn as sns
+
+sns.set()
+
+
+def loss_history_plt(loss_history: np.array) -> None:
+    sns.lineplot(
+        x=np.arange(len(loss_history)),
+        y=loss_history,
+    )
+    plt.xlabel("Epoch")
+    plt.ylabel("Training Loss")
+    plt.show()

requirements.txt

@@ -1,3 +1,5 @@
+matplotlib==3.7.1
 numpy==1.24.2
 scikit_learn==1.2.2
+seaborn==0.12.2
 tqdm==4.65.0