锦中融合门户系统

# 导入必要的库

import pandas as pd

from sklearn.ensemble import RandomForestClassifier

from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score

# 加载数据（模拟）

data = {

'University': ['A', 'B', 'C', 'D'],

'Research_Papers': [100, 200, 150, 80],

'Faculty_Publications': [50, 70, 60, 30],

'Employment_Rate': [90, 85, 95, 80],

'Rank': [1, 2, 3, 4]

}

df = pd.DataFrame(data)

# 特征和标签

X = df[['Research_Papers', 'Faculty_Publications', 'Employment_Rate']]

y = df['Rank']

# 划分训练集和测试集

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

# 训练模型

model = RandomForestClassifier(n_estimators=100)

model.fit(X_train, y_train)

# 预测

predictions = model.predict(X_test)

# 评估

print("预测排名:", predictions)

print("准确率:", accuracy_score(y_test, predictions))

def adjust_weights(user_preferences):

weights = {

'research': 0.4,

'employment': 0.3,

'faculty': 0.3

}

for key in user_preferences:

if key in weights:

weights[key] = user_preferences[key]

return weights

def calculate_rank_with_weights(df, weights):

df['Weighted_Score'] = (

df['Research_Papers'] * weights['research'] +

df['Faculty_Publications'] * weights['faculty'] +

df['Employment_Rate'] * weights['employment']

)

df = df.sort_values(by='Weighted_Score', ascending=False)

df['Rank'] = range(1, len(df) + 1)

return df

# 示例用户偏好

user_prefs = {'research': 0.5, 'employment': 0.3, 'faculty': 0.2}

adjusted_weights = adjust_weights(user_prefs)

ranked_universities = calculate_rank_with_weights(df, adjusted_weights)

print(ranked_universities)