更新 function.py

function.py

@@ -26,6 +26,7 @@ name = "邓龙树"
 
 # user_code.py
 
+import numpy as np
 from sklearn.preprocessing import StandardScaler
 
 def sigmoid(intX):
@@ -47,7 +48,7 @@ def train_logreg(X, y, numIter=150):
     return weights
 
 
-def predict(X, weights):
+def predict_logreg(X, weights):
     predictions = []
     for x in X:
         prob = sigmoid(np.dot(x, weights))
@@ -77,32 +78,13 @@ def load_data(filepath):
 
 
 def accuracy(X, y, weights):
-    predictions = predict(X, weights)
+    predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
 
-def colicTest():
-    X_train, y_train = load_data("./horse-colic.data")
-    X_test, y_test = load_data("./horse-colic.test")
-    trainWeights = train_logreg(X_train, y_train, 500)
-    errorCount = 0
-    numTestVec = 0.0
-    for x, true_label in zip(X_test, y_test):
-        if int(predict([x], trainWeights)[0])!= int(true_label):
-            errorCount += 1
-        numTestVec += 1.0
-    errorRate = (float(errorCount) / numTestVec) * 100
-    print("测试集错误率为: %.2f%%" % errorRate)
-
-
-def colicSklearn():
-    X_train, y_train = load_data("./horse-colic.data")
-    X_test, y_test = load_data("./horse-colic.test")
-    classifier = LogisticRegression(solver='liblinear', max_iter=20).fit(X_train, y_train)
-    test_accurcy = classifier.score(X_test, y_test) * 100
-    print('正确率:%f%%' % test_accurcy)
-
-
 if __name__ == '__main__':
-    # colicTest()
-    colicSklearn()
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
+    final_weights = train_logreg(X_train, y_train)
+    final_accuracy = accuracy(X_test, y_test, final_weights)
+    print(f"最终测试集的准确率: {final_accuracy:.4f}")