adding accuracy score metric

example/main.py

@@ -1,17 +1,29 @@
 import requests
 
-with open("iris.csv", "rb") as csv:
-    iris_data = csv.read()
+with open("mushrooms.csv", "rb") as csv:
+    data = csv.read()
+
+# class,cap-shape,cap-surface,cap-color,bruises,odor,gill-attachment,gill-spacing,gill-size,gill-color,stalk-shape,stalk-root,stalk-surface-above-ring,stalk-surface-below-ring,stalk-color-above-ring,stalk-color-below-ring,veil-type,veil-color,ring-number,ring-type,spore-print-color,population,habitat
 
 ARGS = {
-    "epochs": 10000,
+    "epochs": 1_000,
     "hidden_size": 8,
     "learning_rate": 0.0001,
     "test_size": 0.1,
     "activation": "relu",
-    "features": ["sepal width", "sepal length", "petal width", "petal length"],
-    "target": "species",
-    "data": iris_data.decode("utf-8"),
+    "features": [
+        "cap-shape",
+        "cap-surface",
+        "cap-color",
+        "bruises",
+        "odor",
+        "gill-attachment",
+        "gill-spacing",
+        "gill-size",
+        "gill-color",
+    ],
+    "target": "class",
+    "data": data.decode("utf-8"),
 }
 
 if __name__ == "__main__":

nn/nn.py

@@ -26,7 +26,6 @@ class NN:
         self.loss_hist: list[float] = None
         self.func_prime: Callable = None
         self.func: Callable = None
-        self.df: pd.DataFrame = None
         self.X: pd.DataFrame = None
         self.y: pd.DataFrame = None
         self.y_dummy: pd.DataFrame = None
@@ -34,16 +33,11 @@ class NN:
         self.output_size: int = None
 
     def set_df(self, df: pd.DataFrame) -> None:
-
-        # issue right now here because we need a way to convert
-        # back and forth from dummies and non dummy vars
-
         assert isinstance(df, pd.DataFrame)
-        self.df = df
-        self.y = df[self.target]
         x = df[self.features]
-        self.y_dummy = pd.get_dummies(self.y, columns=self.target)
+        y = df[self.target]
         self.X = pd.get_dummies(x, columns=self.features)
+        self.y_dummy = pd.get_dummies(y, columns=self.target)
         self.input_size = len(self.X.columns)
         self.output_size = len(self.y_dummy.columns)
 

nn/train.py

@@ -1,5 +1,5 @@
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import log_loss, accuracy_score, f1_score
+from sklearn.metrics import log_loss
 from typing import Callable
 from nn.nn import NN
 import numpy as np
@@ -81,7 +81,8 @@ def train(nn: NN) -> dict:
     )
 
     return {
-        "log loss": log_loss(y_true=y_test, y_pred=y_hat)
+        "log loss": log_loss(y_true=y_test, y_pred=y_hat),
+        "accuracy": accuracy_score(y_true=y_test, y_pred=y_hat)
     }
 
 
@@ -107,3 +108,15 @@ def hidden_weight_prime(data, error):
 
 def output_weight_prime(hidden_output, error):
     return np.dot(hidden_output.T, error)
+
+
+def accuracy_score(y_true, y_pred):
+    # Ensure y_true and y_pred have the same shape
+    if y_true.shape != y_pred.shape:
+        raise ValueError("Input shapes do not match.")
+
+    # Calculate the accuracy
+    num_samples = len(y_true)
+    num_correct = np.sum(y_true == y_pred)
+
+    return num_correct / num_samples