计算b

linear/gradient_linear.py

@@ -26,20 +26,54 @@ def cal_step_pow(data, w, b=3):
     sum_p = sum(p)
     return sum_p/len(data)
 
-def cal_mse(data, w, b=3):
+
+def cal_step_pow_b(data, w, b=1):
+    p = [(w*item[0][0] + b - item[1][0])*2  for item in data]
+    sum_p = sum(p)
+    return sum_p/len(data)
+
+
+def cal_mse(data, w, b=1):
     sum_p = sum([(w * item[0][0] + b - item[1][0]) * (w * item[0][0] + b - item[1][0]) for item in data])
     return sum_p / len(data)
 
+
 def train():
     train_data = read_data('train_data')
     w = random.uniform(-50, 50)
-    for i in range(10):
+    for i in range(50):
         step = cal_step_pow(train_data, w)*0.01
         mse = cal_mse(train_data, w)
         print w, step, mse
 
         w = w - step
+    return w
+
+
+def train_b(w):
+    train_data = read_data('train_data')
+    b = random.uniform(-50, 50)
+    for i in range(1000):
+        step = cal_step_pow_b(train_data, w, b)*0.01
+        mse = cal_mse(train_data, w, b)
+        print b, step, mse
+
+        b = b - step
+    return b
 
 
 if __name__ == '__main__':
-    train()
+    w = train()
+    print "__________"
+    b = train_b(w)
+    print "__________"
+    print w,b
+
+    train_data = read_data('train_data')
+    X, y = zip(*train_data)
+    X = np.array(X)
+    y = np.array(y)
+    model = LinearRegression()
+    # 一调用这个函数，就会不停地找合适的w和b 直到误差最小
+    model.fit(X, y)
+    print model.coef_, model.intercept_