hw4/hw4_10.py

@@ -33,57 +33,32 @@ def error(gt, pred):
         err = (err+1) if gt[index]!=pred[index] else err
     return err/len(gt)
 
-def transform(features):
+if __name__ == '__main__':
-    output_features = []
+    x, y = read_data(FILENAME)
-    for index, feature in enumerate(features):
+    x = form(x)
-        output_features.append([ 0 for _ in range(84) ])
+    prob = problem(y, x)
-        output_features[index][0] = 1
+    lambda_powers = [-6, -4, -2, 0, 2]
-        
-        d_index = 1   
-        # 1-order
-        for i in feature:
-            output_features[index][d_index] = i
-            d_index += 1
-    
-        # 2-orde
-        for i in range(len(feature)):
-            for j in range(i, len(feature)):
-                output_features[index][d_index] = feature[i]*feature[j]
-                d_index += 1
-        # 3-order
-        for i in range(len(feature)):
-            for j in range(i, len(feature)):
-                for k in range(j, len(feature)):
-                    output_features[index][d_index] = i*j*k
-                    d_index += 1
-    return output_features
 
-x, y = read_data(FILENAME)
+    results = []
-x = transform(x)
+    for lambda_power in lambda_powers:
-x = form(x)
+        lambda_value = 10 ** lambda_power
-prob = problem(y, x)
+        param_C = 1/(2*lambda_value) 
-lambda_powers = [-6, -4, -2, 0, 2]
+        param = parameter('-s 0 -c {} -e 0.000001 -q'.format(param_C))
+        model = train(prob, param)
+        p_label, p_acc, p_val = predict(y, x, model)
+        err = error(y, p_label)
+        print("0/1 error: ", err)
+        print()
+        results.append({'lambda': lambda_power, 'error': err})
 
-results = []
+    ans, min_err = None, 1
-for lambda_power in lambda_powers:
+    for i in results:
-    lambda_value = 10 ** lambda_power
+        print(i['error'])
-    param_C = 1/(2*lambda_value) 
+        if i['error'] <= min_err:
-    param = parameter('-s 0 -c {} -e 0.000001 -q'.format(param_C))
+            min_err = i['error']
-    model = train(prob, param)
+            ans = i
-    p_label, p_acc, p_val = predict(y, x, model)
-    err = error(y, p_label)
-    print("0/1 error: ", err)
-    print()
-    results.append({'lambda': lambda_power, 'error': err})
 
-ans, min_err = None, 1
+    print("the largest lambda: {}, log_10(lambda*): {}".format(10**ans['lambda'], ans['lambda']))
-for i in results:
-    print(i['error'])
-    if i['error'] <= min_err:
-        min_err = i['error']
-        ans = i
-
-print("the largest lambda: {}, log_10(lambda*): {}".format(10**ans['lambda'], ans['lambda']))
 
         
 

hw4/hw4_11.py

@@ -36,6 +36,7 @@ def error(gt, pred):
     return err/len(gt)
 
 def new_split(x, y):
+    random.seed(datetime.datetime.now().timestamp())
     data = list(zip(x, y))
     random.shuffle(data)
     x, y = zip(*data)
@@ -43,37 +44,10 @@ def new_split(x, y):
     train_y, val_y = y[:120], y[120:]
     return (train_x, train_y), (val_x, val_y)
 
-def transform(features):
-    output_features = []
-    for index, feature in enumerate(features):
-        output_features.append([ 0 for _ in range(84) ])
-        output_features[index][0] = 1
-        
-        d_index = 1   
-        # 1-order
-        for i in feature:
-            output_features[index][d_index] = i
-            d_index += 1
-    
-        # 2-orde
-        for i in range(len(feature)):
-            for j in range(i, len(feature)):
-                output_features[index][d_index] = feature[i]*feature[j]
-                d_index += 1
-        # 3-order
-        for i in range(len(feature)):
-            for j in range(i, len(feature)):
-                for k in range(j, len(feature)):
-                    output_features[index][d_index] = i*j*k
-                    d_index += 1
-    return output_features
-
 x, y = read_data(FILENAME)
-x = transform(x)
 x = format(x)
 log_lambda = []
-for index in range(128):
+for _ in range(128):
-    random.seed(datetime.datetime.now().timestamp()+index)
     (train_x, train_y), (val_x, val_y) = new_split(x, y)
     prob = problem(train_y, train_x)
 

hw4/hw4_12.py

@@ -52,33 +52,7 @@ def new_split(x, y):
 
     return folds
 
-def transform(features):
-    output_features = []
-    for index, feature in enumerate(features):
-        output_features.append([ 0 for _ in range(84) ])
-        output_features[index][0] = 1
-        
-        d_index = 1   
-        # 1-order
-        for i in feature:
-            output_features[index][d_index] = i
-            d_index += 1
-    
-        # 2-orde
-        for i in range(len(feature)):
-            for j in range(i, len(feature)):
-                output_features[index][d_index] = feature[i]*feature[j]
-                d_index += 1
-        # 3-order
-        for i in range(len(feature)):
-            for j in range(i, len(feature)):
-                for k in range(j, len(feature)):
-                    output_features[index][d_index] = i*j*k
-                    d_index += 1
-    return output_features
-
 x, y = read_data(FILENAME)
-x = transform(x)
 x = format(x)
 log_lambda = []
 lambda_powers = [-6, -4, -2, 0, 2]