更新 function.py

function.py

@@ -27,54 +27,86 @@ name = "邓龙树"
 # user_code.py
 
 import numpy as np
-from sklearn.preprocessing import MinMaxScaler
+import matplotlib.pyplot as plt
+import random
+from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import StandardScaler
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    num_samples, num_features = X.shape
-    weights = np.zeros(num_features)
-    for _ in range(iterations):
-        z = np.dot(X, weights)
-        h = 1 / (1 + np.exp(-z))
-        gradient = np.dot(X.T, (h - y)) / num_samples
-        weights -= learning_rate * gradient
+def sigmoid(intX):
+    return 1.0 / (1 + np.exp(-intX))
+
+
+def stocGradAscent1(X, y, numIter=150):
+    m, n = X.shape
+    weights = np.ones(n)
+    for j in range(numIter):
+        dataIndex = list(range(m))
+        for i in range(m):
+            alpha = 4 / (1.0 + j + i) + 0.01
+            randIndex = int(random.uniform(0, len(dataIndex)))
+            h = sigmoid(np.dot(X[randIndex], weights))
+            error = y[randIndex] - h
+            weights = weights + np.dot(alpha * error, X[randIndex])
+            del(dataIndex[randIndex])
     return weights
 
-def predict_logreg(inX, weights):
-    z = np.dot(inX, weights)
-    return 1 if 1 / (1 + np.exp(-z)) > 0.5 else 0
+
+def predict(X, weights):
+    predictions = []
+    for x in X:
+        prob = sigmoid(np.dot(x, weights))
+        predictions.append(1 if prob > 0.5 else 0)
+    return predictions
+
 
 def load_data(filepath):
-    data = np.genfromtxt(filepath, delimiter=',', dtype=np.float64)
-    if len(data.shape) == 1:
-        data = data.reshape(1, -1)
-    # 处理缺失值
-    data[np.isnan(data)] = 0
-    X = data[:, :-1]
-    y = data[:, -1]
-    # 处理特征 23，合并取值 2 和 3 为 0
-    y[y == 2] = 0
-    y[y == 3] = 0
-    # 去掉特征 3、特征 24~28
-    X = np.delete(X, [2] + list(range(22, X.shape[1])), axis=1)
-    return X, y
+    data = []
+    labels = []
+    with open(filepath, 'r') as f:
+        lines = f.readlines()
+        for line in lines:
+            line = line.strip().split()
+            if len(line) >= 1 and line[-1].isdigit():
+                line_data = [1] + [0 if x == '?' else float(x) for x in line[:-1]]
+                data.append(line_data)
+                labels.append(int(line[-1]))
+    data = np.array(data)
+    labels = np.array(labels)
+    target_variable = labels
+    target_variable[(target_variable == 2) | (target_variable == 3)] = 0
+    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
+    scaler = StandardScaler()
+    data = scaler.fit_transform(data)
+    return data, target_variable
 
-if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
 
-    # 对训练集特征进行归一化
-    scaler = MinMaxScaler()
-    X_train = scaler.fit_transform(X_train)
+def accuracy(X, y, weights):
+    predictions = predict(X, weights)
+    return np.mean(predictions == y)
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 对测试集特征进行归一化
-    X_test = scaler.transform(X_test)
+def colicTest():
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
+    trainWeights = stocGradAscent1(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)
 
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
 
-    # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+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()