import matplotlib.pyplot as plt import pandas as pd import seaborn as sns from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import accuracy_score from sklearn.model_selection import train_test_split # 读取训练集和测试集数据 train_data = pd.read_csv(r'C:\ADULT\Titanic\train.csv') test_data = pd.read_csv(r'C:\ADULT\Titanic\test.csv') # 统计训练集和测试集缺失值数目 print(train_data.isnull().sum()) print(test_data.isnull().sum()) # 处理 Age, Fare 和 Embarked 缺失值 most_lists = ['Age', 'Fare', 'Embarked'] for col in most_lists: train_data[col] = train_data[col].fillna(train_data[col].mode()[0]) test_data[col] = test_data[col].fillna(test_data[col].mode()[0]) # 拆分 X, Y 数据并将分类变量 one-hot 编码 y_train_data = train_data['Survived'] features = ['Pclass', 'Age', 'SibSp', 'Parch', 'Fare', 'Sex', 'Embarked'] X_train_data = pd.get_dummies(train_data[features]) X_test_data = pd.get_dummies(test_data[features]) # 合并训练集 Y 和 X 数据，并创建乘客信息分类变量 train_data_selected = pd.concat([y_train_data, X_train_data], axis=1) print(train_data_selected) cate_features = ['Pclass', 'SibSp', 'Parch', 'Sex', 'Embarked', 'Age_category', 'Fare_category'] train_data['Age_category'] = pd.cut(train_data.Fare, bins=range(0, 100, 10)).astype(str) train_data['Fare_category'] = pd.cut(train_data.Fare, bins=list(range(-20, 110, 20)) + [800]).astype(str) print(train_data) # 统计各分类变量的分布并作出可视化呈现 plt.figure(figsize=(18, 16)) plt.subplots_adjust(hspace=0.3, wspace=0.3) for i, cate_feature in enumerate(cate_features): plt.subplot(7, 2, 2 * i + 1) sns.histplot(x=cate_feature, data=train_data, stat="density") plt.xlabel(cate_feature) plt.ylabel('Density') plt.subplot(7, 2, 2 * i + 2) sns.lineplot(x=cate_feature, y='Survived', data=train_data) plt.xlabel(cate_feature) plt.ylabel('Survived') plt.show() # 绘制点状的相关系数热图 plt.figure(figsize=(12, 8)) sns.heatmap(train_data_selected.corr(), vmin=-1, vmax=1, annot=True) plt.show() sourceRow = 891 output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions}) output.head() # 保存结果 output.to_csv('gender_submission.csv', index=False) print(output) train_X, test_X, train_y, test_y = train_test_split(X_train_data, y_train_data, train_size=0.8, random_state=42) print("随机森林分类结果") y_pred_train1 = train_data.predict(train_X) y_pred_test1 = train_data.predict(test_X) accuracy_train1 = accuracy_score(train_y, y_pred_train1) accuracy_test1 = accuracy_score(test_y, y_pred_test1) print("训练集——随机森林分类器准确率为：", accuracy_train1) print("测试集——随机森林分类器准确率为：", accuracy_train1)

在你的代码中，你正在尝试从 `train_data` 对象上调用一个名为 "predict" 的方法，而 `train_data` 实际上是一个 DataFrame 对象，该对象并没有 "predict" 方法。你应该使用你之前定义的随机森林分类器对象 `RandomForestClassifier` 来进行预测。请将以下代码：

y_pred_train1 = train_data.predict(train_X)
y_pred_test1 = train_data.predict(test_X)

更改为：

# 定义随机森林分类器对象
rfc = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=42)

# 在训练数据上拟合分类器
rfc.fit(train_X, train_y)

# 在训练集和测试集上进行预测
y_pred_train1 = rfc.predict(train_X)
y_pred_test1 = rfc.predict(test_X)

这将使用你之前定义的随机森林分类器对象 `rfc` 来进行预测。同时，你需要使用 `rfc.fit(train_X, train_y)` 在训练数据上拟合分类器，然后使用 `rfc.predict(train_X)` 和 `rfc.predict(test_X)` 在训练集和测试集上进行预测。