更新 function.py

function.py

@@ -83,7 +83,18 @@ def load_data(filepath):
         for line in f:
             line = line.strip().split()
             if len(line) >= 1 and line[-1].isdigit():
-                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
+                line_data = []
+                for x in line[:-1]:
+                    if x == '?':
+                        # 用均值填充缺失值
+                        data_array = np.array(data)
+                        if len(data_array) > 0:
+                            column_mean = np.nanmean(data_array[:, len(line_data)], axis=0)
+                            line_data.append(column_mean)
+                        else:
+                            line_data.append(0)
+                    else:
+                        line_data.append(float(x))
                 data.append(line_data)
                 labels.append(int(line[-1]))
 
@@ -105,16 +116,6 @@ def accuracy(X, y, weights):
     predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
-def loadDataSet(filename='dataSet.txt'):
-    dataList = []
-    labelList = []
-    fr = open(filename)
-    for line in fr.readlines():
-        lineList = line.strip().split()
-        # 修改后
-        dataList.append ([float (lineList [0]), float (lineList [1])])
-        labelList.append(int(lineList[2]))
-    return dataList, labelList
 
 
 if __name__ == "__main__":