2020C题数学建模国赛一等奖论文+完整代码和excel数据处理表格.zip

import xlrd import pandas as pd from numpy import mat from sklearn.model_selection import train_test_split from sklearn import tree def dataSet(filename): """ 读取问题1excel数据 :param filename: 文件名称 :return: 数据集 """ data = xlrd.open_workbook(filename) table = data.sheet_by_index(0) dataSet1 = [] dataSet2 = [] cols = [2, 5, 8, 9, 10, 13, 14, 15, 18] for i in range(1, 124): temp = [] for col in cols: temp.append(table.row(i)[col].value) dataSet2.append(temp[1:]) dataSet1.append(table.row(i)[2].value) return dataSet1, dataSet2 def dataSet2(filename): """ 读取问题2excel数据 :param filename:文件名 :return: 数据集 """ data = xlrd.open_workbook(filename) table = data.sheet_by_index(0) cols = [4, 7, 8, 9, 12, 13, 14, 17] dataSet = [] for i in range(1, 303): temp = [] for col in cols: temp.append(table.row(i)[col].value) dataSet.append(temp) return dataSet def dataSet3(filename): """ 读取问题1excel数据 :param filename: 文件名称 :return: 数据集 """ data = xlrd.open_workbook(filename) table = data.sheet_by_index(0) dataSet1 = [] dataSet2 = [] cols = [2, 5, 8, 9, 10, 13, 14, 15, 18, 19] for i in range(1, 124): temp = [] for col in cols: temp.append(table.row(i)[col].value) dataSet2.append(temp[0:-1]) dataSet1.append(table.row(i)[19].value) return dataSet1, dataSet2 target, data = dataSet('问题1数据处理.xlsx') # 预测信誉评级数据 test = dataSet2('问题2数据处理.xlsx') # 待预测数据 data = mat(data) target_final, data_final = dataSet3('问题1数据处理.xlsx') # 预测是否违约数据 data_final = mat(data_final) pd.concat([pd.DataFrame(data), pd.DataFrame(target)], axis=1) pd.concat([pd.DataFrame(data_final), pd.DataFrame(target_final)], axis=1) # 划分训练集和测试集 Xtrain, Xtest, Ytrain, Ytest = train_test_split(data, target, test_size=0.2) Xtrain_final, Xtest_final, Ytrain_final, Ytest_final = train_test_split(data_final, target_final, test_size=0.2) # 训练决策树模型 clf = tree.DecisionTreeClassifier() clf1 = clf.fit(Xtrain, Ytrain) # 先预测302家企业的信誉评级 predicts = clf1.predict(test) for i in range(302): test[i].append(predicts[i]) temp = test[i][0] test[i][0] = test[i][-1] test[i][-1] = temp # 训练决策树模型 clf2 = clf.fit(Xtrain_final, Ytrain_final) # 预测302家企业违约情况 result = clf2.predict(test) print(result)