just focusing on neural_network first

README.md

@@ -1,2 +1,4 @@
 # Data-Mining-Study
 Building out things I have learned in CIS-335 in order to prepare for final exam
+
+Trying my best to build most of this stuff purely off of my notes and lecture powerpoints

main.py

@@ -1,5 +1,7 @@
 import numpy as np
 
+import neural_network.main as nn
+
 
 def random_dataset():
     """
@@ -14,18 +16,18 @@ def random_dataset():
     )
 
 
-def main(method: str, X: np.array, y: np.array):
-    pass
-
-
-
 if __name__ == "__main__":
     method = input("\nChoose a method to test: ").lower()
+    if method != "nn":
+        raise ValueError(f"Invalid method '{method}'. Choose 'nn' instead.")
 
     X, y = random_dataset()
-    main(
-        method=method, 
-        X=X, 
+    args = nn.get_args()
+    nn.main(
+        X=X,
         y=y,
+        epochs=args["epochs"],
+        hidden_size=args["hidden_size"],
+        learning_rate=args["learning_rate"],
+        activation_func=args["activation_func"],
     )
-

neural_network/backprop.py

@@ -1,11 +1,7 @@
 import numpy as np
 
 
+def bp():
+    return
 
 
-# for testing only
-if __name__ == "__main__":
-    def test():
-        pass
-
-    test()

neural_network/forwardprop.py

@@ -1,5 +1,6 @@
+import numpy as np
 
 
-def forward_prop():
+def fp():
     return
 

neural_network/main.py

@@ -1,6 +1,21 @@
 import numpy as np
 
 from neural_network.forwardprop import fp
+from neural_network.backprop import bp
+
+
+def get_args():
+    """
+    returns a dictionary containing
+    the arguments to be passed to
+    the main function
+    """
+    return {
+        "epochs": int(input("Enter the number of epochs: ")),
+        "hidden_size": int(input("Enter the number of hidden nodes: ")),
+        "learning_rate": float(input("Enter the learning rate: ")),
+        "activation_func": input("Enter the activation function: "),
+    }
 
 
 def init(X: np.array, y: np.array, hidden_size: int) -> dict:
@@ -17,14 +32,14 @@ def init(X: np.array, y: np.array, hidden_size: int) -> dict:
 
 
 def main(
-    X: np.array, 
-    y: np.array, 
-    epochs: int, 
-    hidden_size: int, 
+    X: np.array,
+    y: np.array,
+    epochs: int,
+    hidden_size: int,
     learning_rate: float,
     activation_func: str,
 ) -> None:
-    wb = init(X, y, hidden_size) 
+    wb = init(X, y, hidden_size)
 
     for e in range(epochs):
 
@@ -32,5 +47,3 @@ def main(
         bp()
 
         # update weights and biases
-
-

neural_network/opts.py

@@ -0,0 +1,14 @@
+from neural_network.activation import *
+
+
+activation = {
+    "relu": {
+        "main": relu,
+        "prime": relu_prime,
+    },
+
+    "sigmoid": {
+        "main": sigmoid,
+        "prime": sigmoid_prime,
+    },
+}