working on setting up the neural_network functionality

.gitignore

@@ -127,3 +127,7 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+.idea
+
+.DS_Store

main.py

@@ -0,0 +1,31 @@
+import numpy as np
+
+
+def random_dataset():
+    """
+    initializes a training and
+    a testing dataset in the form
+    of numpy arrays
+    """
+    np.random.seed(8675309)
+    return (
+        np.random.randn(10000, 10),
+        np.random.randint(5, size=(10000, 1)),
+    )
+
+
+def main(method: str, X: np.array, y: np.array):
+    pass
+
+
+
+if __name__ == "__main__":
+    method = input("\nChoose a method to test: ").lower()
+
+    X, y = random_dataset()
+    main(
+        method=method, 
+        X=X, 
+        y=y,
+    )
+

neural_network/activation.py

@@ -0,0 +1,23 @@
+import numpy as np
+
+
+
+def sigmoid(x: float) -> float:
+    return 1.0 / (1.0 + np.exp(-x))
+
+def sigmoid_prime(x: float) -> float:
+    return sigmoid(x) / (1.0 - sigmoid())
+
+def relu(x: float) -> float:
+    """
+    returns the input if > 0
+    """
+    return max(0.0, x)
+
+def relu_prime(x: float) -> float:
+    """
+    returns 1 if input is +
+    returns 0 if input is -
+    """
+    return 1 if x > 0 else 0
+

neural_network/backprop.py

@@ -0,0 +1,11 @@
+import numpy as np
+
+
+
+
+# for testing only
+if __name__ == "__main__":
+    def test():
+        pass
+
+    test()

neural_network/forwardprop.py

@@ -0,0 +1,5 @@
+
+
+def forward_prop():
+    return
+

neural_network/main.py

@@ -0,0 +1,36 @@
+import numpy as np
+
+from neural_network.forwardprop import fp
+
+
+def init(X: np.array, y: np.array, hidden_size: int) -> dict:
+    """
+    returns a dictionary containing randomly initialized
+    weights and biases to start off the neural_network
+    """
+    return {
+        "W1": np.random.randn(X.shape[1], hidden_size),
+        "b1": np.zeros((1, hidden_size)),
+        "W2": np.random.randn(hidden_size, 1),
+        "b2": np.zeros((1, 1)),
+    }
+
+
+def main(
+    X: np.array, 
+    y: np.array, 
+    epochs: int, 
+    hidden_size: int, 
+    learning_rate: float,
+    activation_func: str,
+) -> None:
+    wb = init(X, y, hidden_size) 
+
+    for e in range(epochs):
+
+        fp()
+        bp()
+
+        # update weights and biases
+
+

requirements.txt

@@ -0,0 +1 @@
+numpy==1.24.2