Upload app.py

app.py

@@ -222,6 +222,166 @@ def fs(data, method, num_fea_int, clf):
     # 添加你们的代码在这里,我们先全部写成函数，然后再封装成类，主要是先把样子做出来
     # 然后目前最终结果是返回一个图片，包含了含有特征的索引及其对应的分数的图，还有一张是增量式特征选择的准确率图
     # 我上面的代码很多地方还可以优化，比如画图，选择分类器这些，但是你们都先不用管，把下面的几个elif写完先，然后我们再讨论优化代码的事情。
+    elif method == 'CFS':
+        X = data.iloc[:, :-1].values
+        y = data['Label'].values
+
+        def loadDataSet(fileName):
+            df = pd.read_csv(fileName)
+            return df
+
+        def writesortedlist(filename, thelist):
+            with open(filename, "w") as fw:
+                for item in thelist:
+                    fw.write(item[0] + "\t" + str(item[1]) + "\n")
+
+        def writethelist(filename, thelist):
+            with open(filename, "w") as fw:
+                for item in thelist:
+                    fw.write(item + "\n")
+
+        def getdatadf(datafile):
+            datadf = loadDataSet(datafile)
+            labellist = datadf["Label"].tolist()
+            del datadf["Label"]
+            return datadf, labellist
+
+        def CFSmethod(datafile):
+
+            datadf, labellist = getdatadf(datafile)
+            print(datadf)
+            selectdf = datadf.copy()
+            allflist = datadf.columns.tolist()
+            namelist = list(datadf.index)
+            print(namelist)
+            namelist = [int(var) for var in namelist]
+            selectdf["class"] = namelist
+
+            bestfset, sortlist = calBFset(selectdf, allflist)
+            # writethelist("bestfeature.txt", bestfset)  # 保存最佳特征子集
+
+            return dict(sortlist)
+
+        def calmulmerit(selectdf, sublist):
+            retvalue = 0
+            label = "class"
+            k = len(sublist)
+            namelist = list(selectdf["class"])
+            classset = set(namelist)
+            caldf = selectdf[sublist]
+            allvalue = 0.0
+            for feature in sublist:
+                caldf = selectdf[sublist]
+                middlevalue = 0.0
+                for ind in classset:
+                    caldf[label] = np.where(selectdf[label] == ind, 1, 0)
+                    coeff = pointbiserialr(caldf[feature], caldf[label])
+                    middlevalue = abs(coeff.correlation) + middlevalue
+                allvalue = middlevalue / float(len(classset)) + allvalue
+            allvalue = allvalue / float(k)
+
+            corr = selectdf[sublist].corr()
+            corr.values[np.tril_indices_from(corr.values)] = np.nan
+            corr = abs(corr)
+            rff = corr.unstack().mean()
+            retvalue = (k * allvalue) / sqrt(k + k * (k - 1) * rff)
+            print(retvalue)
+            return retvalue
+
+        def calBFset(selectdf, allflist):
+            allfdict = getallfscoredict(selectdf, allflist)
+            sortedflist = sorted(allfdict.items(), key=lambda item: item[1], reverse=True)
+            # writesortedlist("sorteddict.txt", sortedflist)  # 保存特征得分的降序
+            feaS = []
+            feaS.append(sortedflist[0][0])
+            maxvalue = sortedflist[0][1]
+            for i in range(1, len(sortedflist)):
+                print(str(i) + "/" + str(len(sortedflist)))
+                itemf = sortedflist[i][0]
+                feaS.append(itemf)
+                newvalue = calmulmerit(selectdf, feaS)
+                if newvalue > maxvalue:
+                    maxvalue = newvalue
+                else:
+                    feaS.pop()
+            print(feaS)
+            return feaS, sortedflist
+
+        def getallfscoredict(selectdf, allflist):
+            retdict = {}
+            k = 1
+            for f in allflist:
+                print(k)
+                k = k + 1
+                score = calonemerit(selectdf, f)
+                if math.isnan(score):
+                    continue
+                retdict[f] = score
+            return retdict
+
+        def calonemerit(selectdf, subname):
+            retvalue = 0
+            label = "class"
+            namelist = list(selectdf["class"])
+            classset = set(namelist)
+            caldf = selectdf[subname].to_frame()
+            allvalue = 0.0
+            for ind in classset:
+                caldf[label] = np.where(selectdf[label] == ind, 1, 0)
+                coeff = pointbiserialr(caldf[subname], caldf[label])
+                allvalue = abs(coeff.correlation) + allvalue
+            allvalue = allvalue / float(len(classset))
+            return allvalue
+
+        # 获取特征分数
+        sortdict = CFSmethod(data.name)
+        # 画图
+        fig = plt.figure(figsize=(24, 12))
+        ax1 = fig.add_subplot(211)
+        ax1.set_title(str(method))
+        indexlist = list(range(1, len(sortdict.keys() + 1)))
+        ax1.plot(indexlist, sortdict.values())  # 特征分数图
+        # 设置x轴和y轴的标签
+        ax1.set_xlabel('Feature Index')
+        ax1.set_ylabel('Feature Score')
+
+        # 分类器
+        if clf == 'RF':
+            clf = RandomForestClassifier(n_jobs=-1)
+        elif clf == 'KNN':
+            clf = KNeighborsClassifier()
+        elif clf == 'DT':
+            clf = DecisionTreeClassifier()
+        elif clf == 'SVM':
+            clf = SVC()
+        elif clf == 'Naive Bayes':
+            clf = GaussianNB()
+        # 画交叉验证图
+        acc = []
+        # 对于index列表中的每个特征索引
+        for i in range(len(indexlist)):
+            # 使用前i个特征进行交叉验证
+            selected_features = X[:, 0:i]
+            scores = cross_val_score(clf, selected_features, y, cv=5)
+            # 计算平均准确率并添加到acc列表中
+            acc.append(scores.mean())
+        max_acc = max(acc)
+        max_index = acc.index(max_acc)  # 应该不用加1吧
+
+        ax2 = fig.add_subplot(212)
+        ax2.set_title("IFS_mRMR_FCD_Accuracy")
+        ax2.plot(max_index, max_acc, 'ro')
+        ax2.plot(acc)
+        ax2.annotate(f'({max_index}, {max_acc})', (max_index, max_acc), textcoords="offset points", xytext=(-5, -5),
+                     ha='center')
+        # 设置x轴和y轴的标签
+        ax2.set_xlabel('Top n features')
+        ax2.set_ylabel('Accuracy')
+        plt.grid(True)
+        plt.savefig('output.png')
+        return 'output.png'
+
+        pass
     elif method == 'Lasso':
         data = pd.read_csv(data.name)
         X = data.iloc[:, :-1]
@@ -357,8 +517,8 @@ iface = gr.Interface(
         ["example_data.csv", 'MRMR_FCQ', 20, 'RF'],
         ["example_data.csv", 'MRMR_FCD', 10, 'SVM'],
         ["example_data.csv", 'MRMR_FCD', 30, 'KNN'],
-        ["example_data.csv", 'Lasso', 50, 'DT'],
-        ["example_data.csv", 'Lasso', 40, 'Naive Bayes'],
+        ["example_data.csv", 'CFS', 50, 'DT'],
+        ["example_data.csv", 'CFS', 40, 'Naive Bayes'],
     ],
     allow_flagging="never"
 )