本文共 3744 字，大约阅读时间需要 12 分钟。

赛题介绍：数据集的内容包括实验志愿者的性别、年龄、人种、专业、地区、收入等特征，以及志愿者对配偶是否来自同一地区、同一信仰等观点的预期。

具体介绍请移步：

具体思路：

简单的二分类问题用极端回归树一般都是100%准确率

代码如下：

import osimport matplotlib.pyplot as pltimport numpy as npimport pandas as pdfrom sklearn import metricsfrom sklearn.ensemble import ExtraTreesClassifierfrom sklearn.model_selection import train_test_splitos.chdir(r'E:\项目文件\测测你的一见钟情指数')df = pd.read_csv('speed_dating_train.csv', encoding='gbk')dating_test = pd.read_csv('speed_dating_test.csv', encoding='gbk')percent_missing = df.isnull().sum() * 100 / len(df)missing_value_df = pd.DataFrame({
       'column_name': df.columns,    'percent_missing': percent_missing})missing_value_df.sort_values(by='percent_missing')# 多少人通过Speed Dating找到了对象plt.subplots(figsize=(3, 3), dpi=110, )# 构造数据size_of_groups = df.match.value_counts().valuessingle_percentage = round(size_of_groups[0] / sum(size_of_groups) * 100, 2)matched_percentage = round(size_of_groups[1] / sum(size_of_groups) * 100, 2)names = [    'Single:' + str(single_percentage) + '%',    'Matched' + str(matched_percentage) + '%']# 多少女生通过Speed Dating找到了对象plt.subplots(figsize=(3, 3), dpi=110, )# 构造数据size_of_groups = df[df.gender == 0].match.value_counts().values  # 男生只需要吧0替换成1即可single_percentage = round(size_of_groups[0] / sum(size_of_groups) * 100, 2)matched_percentage = round(size_of_groups[1] / sum(size_of_groups) * 100, 2)# 年龄分布age = df[np.isfinite(df['age'])]['age']date_df = df[[    'iid', 'gender', 'pid', 'match', 'int_corr', 'samerace', 'age_o',    'race_o', 'pf_o_att', 'pf_o_sin', 'pf_o_int', 'pf_o_fun', 'pf_o_amb',    'pf_o_sha', 'dec_o', 'attr_o', 'sinc_o', 'intel_o', 'fun_o', 'like_o',    'prob_o', 'met_o', 'age', 'race', 'imprace', 'imprelig', 'goal', 'date',    'go_out', 'career_c', 'sports', 'tvsports', 'exercise', 'dining',    'museums', 'art', 'hiking', 'gaming', 'clubbing', 'reading', 'tv',    'theater', 'movies', 'concerts', 'music', 'shopping', 'yoga', 'attr1_1',    'sinc1_1', 'intel1_1', 'fun1_1', 'amb1_1', 'attr3_1', 'sinc3_1',    'fun3_1', 'intel3_1', 'dec', 'attr', 'sinc', 'intel', 'fun', 'like',    'prob', 'met']]dating_test = dating_test[[    'iid', 'gender', 'pid', 'int_corr', 'samerace', 'age_o',    'race_o', 'pf_o_att', 'pf_o_sin', 'pf_o_int', 'pf_o_fun', 'pf_o_amb',    'pf_o_sha', 'dec_o', 'attr_o', 'sinc_o', 'intel_o', 'fun_o', 'like_o',    'prob_o', 'met_o', 'age', 'race', 'imprace', 'imprelig', 'goal', 'date',    'go_out', 'career_c', 'sports', 'tvsports', 'exercise', 'dining',    'museums', 'art', 'hiking', 'gaming', 'clubbing', 'reading', 'tv',    'theater', 'movies', 'concerts', 'music', 'shopping', 'yoga', 'attr1_1',    'sinc1_1', 'intel1_1', 'fun1_1', 'amb1_1', 'attr3_1', 'sinc3_1',    'fun3_1', 'intel3_1', 'dec', 'attr', 'sinc', 'intel', 'fun', 'like',    'prob', 'met']]# clean_df = date_df[['attr_o', 'sinc_o', 'intel_o', 'fun_o', 'amb_o', 'shar_o', 'match']]date_df.dropna(inplace=True)dating_test = dating_test.fillna(0)x = date_df.drop(columns=['match'])y = date_df['match']# oversample = imblearn.over_sampling.SVMSMOTE()# x, y = oversample.fit_resample(X, y)# 做训练集和测试集分割X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0, stratify=y)# logistic regression classification modelmodel = ExtraTreesClassifier()model.fit(X_train, y_train)predict_train_lrc = model.predict(X_train)predict_test_lrc = model.predict(X_test)print('Training Accuracy:', metrics.accuracy_score(y_train, predict_train_lrc))print('Validation Accuracy:', metrics.accuracy_score(y_test, predict_test_lrc))predict_test = model.predict(dating_test)print(predict_test)np.savetxt('predict_test.csv', predict_test)

转载地址：https://data-mining.blog.csdn.net/article/details/109556606 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！