数据挖掘课程设计-基于Python-通过已有数据集（学生成绩预测.csv），预处理，分析预测，数据和结果的可视化，来预测学生成绩

import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import classification_report, confusion_matrix import matplotlib.pyplot as plt import seaborn as sns # 加载数据 df = pd.read_csv("C:\\Users\吴鑫\Desktop\数据挖掘\数据挖掘课程设计\学生成绩预测.csv") # 需将学生成绩预测.csv这个文件放在该路径下 # 查看数据 print(df.head()) # 对'Class'列进行编码（L, M, H -> 0, 1, 2） le_class = LabelEncoder() df['Class'] = le_class.fit_transform(df['Class']) # 对'StudentAbsenceDays'列进行编码（Under-7, Above-7 -> 0, 1） df['StudentAbsenceDays'] = df['StudentAbsenceDays'].map({'Under-7': 0, 'Above-7': 1}) # 选择特征列和目标列 X = df[['raisedhands', 'VisITedResources', 'AnnouncementsView', 'Discussion', 'StudentAbsenceDays']] y = df['Class'] # 划分数据集为训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 创建并训练随机森林分类器 clf = RandomForestClassifier(n_estimators=100, random_state=42) clf.fit(X_train, y_train) # 预测测试集 y_pred = clf.predict(X_test) # 评估模型 print(classification_report(y_test, y_pred)) print(confusion_matrix(y_test, y_pred)) # 数据可视化：特征与成绩等级的关系 plt.figure(figsize=(12, 8)) sns.pairplot(df[['raisedhands', 'VisITedResources', 'AnnouncementsView', 'Discussion', 'StudentAbsenceDays', 'Class']], hue='Class', palette='coolwarm') plt.show() # 结果可视化：混淆矩阵 cm = confusion_matrix(y_test, y_pred) plt.figure(figsize=(10, 7)) sns.heatmap(cm, annot=True, fmt='d', cmap='Blues') plt.xlabel('Predicted') plt.ylabel('True') plt.show() # 将混淆矩阵的数值转换回成绩等级（L, M, H） class_labels = le_class.inverse_transform([0, 1, 2]) cm_df = pd.DataFrame(cm, index=class_labels, columns=class_labels) print(cm_df)