手写逻辑回归梯度下降

logistic/gradient_logistic.py

@@ -0,0 +1,127 @@
+# -*- encoding:utf-8 -*-
+from sklearn.linear_model import LogisticRegression
+from math import exp
+from math import log2
+import numpy as np
+import matplotlib.pyplot as plt
+
+def read_data(path):
+    with open(path) as f:
+        lines = f.readlines()
+    lines = [eval(line.strip()) for line in lines]
+    X, y = zip(*lines)
+    X = np.array(X)
+    y = np.array(y)
+    return X, y
+
+
+def curve(x_train, w, w0):
+    results = x_train.tolist()
+    for i in range(0, 100):
+        x1 = 1.0 * i / 10
+        x2 = -1 * (w[0] * x1 + w0) / w[1]
+        results.append([x1, x2])
+    results = ["{},{}".format(x1, x2) for [x1, x2] in results]
+    return results
+
+
+def drawScatterAndLine(p, q):
+    x1 = []
+    x2 = []
+    y1 = []
+    y2 = []
+
+    for idx,i in enumerate(q):
+        if i == 0:
+            x1.append(p[idx][0])
+            y1.append(p[idx][1])
+        else:
+            x2.append(p[idx][0])
+            y2.append(p[idx][1])
+
+    plt.scatter(x1, y1)
+    plt.scatter(x2, y2)
+    plt.xlabel('p')
+    plt.ylabel('q')
+    plt.title('line regesion')
+    plt.show()
+
+
+def sigmoid(x):
+    return 1 / (1 + exp(-x))
+
+
+def data_matrix(X):
+    data_mat = []
+    for d in X:
+        data_mat.append([1.0, *d])
+    return data_mat
+
+
+max_iter = 100
+last_weights = []
+
+
+def fit_1(X_train, y_train):
+    X_train = data_matrix(X_train)
+    weights = np.array([1,1,1])
+
+    x = np.array(X_train)
+    for iter_ in range(max_iter):
+        y = np.dot(x, np.transpose(weights))
+        sig_y = []
+        for i in range(len(y)):
+            sig_y.append(sigmoid(y[i]))
+
+        result = [0,0,0]
+        loss = 0
+        for i in range(len(X_train)):
+            delta_i = (y_train[i][0]*(1-sig_y[i]) - (1-y_train[i][0])*sig_y[i])
+            result = [result[0] + delta_i*X_train[i][0], result[1] + delta_i*X_train[i][1], result[2] + delta_i*X_train[i][2]]
+            loss = loss - y_train[i][0]*log2(sig_y[i]) - (1-y_train[i][0])*log2(1- sig_y[i])
+        result = -1 * np.array(result)/len(X_train)
+        print("loss: ", loss)
+
+        weights = weights - 0.8*result
+        print("weight:", weights)
+
+    return weights
+
+
+def score(X_test, y_test, last_weights):
+    X_test = data_matrix(X_test)
+    loss = 0
+
+    y = np.dot(X_test, np.transpose(last_weights))
+    sig_y = []
+    for i in range(len(y)):
+        sig_y.append(sigmoid(y[i]))
+
+    for i in range(len(X_test)):
+        loss = loss - y_test[i][0] * log2(sig_y[i]) - (1 - y_test[i][0]) * log2(1 - sig_y[i])
+    print("y_test loss ", loss)
+
+
+def main():
+    X_train, y_train = read_data("train_data")
+    drawScatterAndLine(X_train, y_train)
+    X_test, y_test = read_data("test_data")
+
+    weight = fit_1(X_train, y_train)
+
+    score(X_test, y_test, weight)
+    # y_pred = model.predict_proba(X_test)
+    # print y_pred
+    # loss=log_loss(y_test,y_pred)
+    # print "KL_loss:",loss
+    # loss=log_loss(y_pred,y_test)
+    # print "KL_loss:",loss
+    '''
+    curve_results=curve(X_train,model.coef_.tolist()[0],model.intercept_.tolist()[0])
+    with open("train_with_splitline","w") as f :
+        f.writelines("\n".join(curve_results))
+    '''
+
+
+if __name__ == '__main__':
+    main()