一站式网上办事大厅

import pandas as pd

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

# 模拟数据

data = {

'student_id': [101, 102, 103, 104, 105],

'attendance_rate': [90, 85, 75, 95, 80],

'assignment_score': [85, 78, 65, 92, 70],

'final_grade': [88, 80, 68, 93, 72]

}

df = pd.DataFrame(data)

# 特征和目标变量

X = df[['attendance_rate', 'assignment_score']]

y = df['final_grade']

# 分割数据集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 训练模型

model = LinearRegression()

model.fit(X_train, y_train)

# 预测

predictions = model.predict(X_test)

print("预测结果：", predictions)

def approve_application(student_data):

if student_data['gpa'] >= 3.0 and student_data['credit_hours'] >= 12:

return "Approved"

else:

return "Rejected"

# 示例数据

application = {

'student_id': 101,

'gpa': 3.2,

'credit_hours': 15

}

result = approve_application(application)

print("申请结果：", result)

from sklearn.ensemble import RandomForestClassifier

from sklearn.preprocessing import StandardScaler

# 假设我们有更多特征

data = {

'student_id': [101, 102, 103, 104, 105],

'gpa': [3.2, 2.9, 3.5, 2.8, 3.1],

'credit_hours': [15, 10, 18, 12, 14],

'approval_status': ['Approved', 'Rejected', 'Approved', 'Rejected', 'Approved']

}

df = pd.DataFrame(data)

# 特征和标签

X = df[['gpa', 'credit_hours']]

y = df['approval_status']

# 转换标签为数字

y = pd.factorize(y)[0]

# 标准化特征

scaler = StandardScaler()

X_scaled = scaler.fit_transform(X)

# 训练模型

model = RandomForestClassifier(n_estimators=100)

model.fit(X_scaled, y)

# 新数据预测

new_student = [[3.0, 14]]

prediction = model.predict(scaler.transform(new_student))

print("预测结果：", "Approved" if prediction[0] == 1 else "Rejected")

from sklearn.cluster import KMeans

# 模拟学生数据

student_data = {

'student_id': [101, 102, 103, 104, 105],

'attendance_rate': [90, 85, 75, 95, 80],

'assignment_score': [85, 78, 65, 92, 70],

'exam_score': [88, 80, 68, 93, 72]

}

df = pd.DataFrame(student_data)

# 特征

X = df[['attendance_rate', 'assignment_score', 'exam_score']]

# 聚类

kmeans = KMeans(n_clusters=2)

clusters = kmeans.fit_predict(X)

# 添加聚类结果到数据框

df['cluster'] = clusters

print(df)