import pandas as pd.docx
需积分: 5 164 浏览量
2024-05-23
10:22:34
上传
评论
收藏 3KB DOCX 举报
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import MinMaxScaler
# 构造模拟数据
data = {
'Version': ['Old', 'New'] * 10,
'Environment': ['Test', 'Prod'] * 10,
'ResponseTime_ms': [200, 180, 250, 230] * 5, # 假设数据
'Throughput': [500, 550, 1200, 1300] * 5, # 假设数据
'HardwareScore': [8, 9] * 10, # 测试和生产环境的硬件评分
}
df = pd.DataFrame(data)
# 添加环境差异调整因子，这里简化处理，实际中可能需要更复杂的计算
df['EnvAdjFactor'] = df['Environment'].map({'Test': 0.8, 'Prod': 1}) # 假设测试环境性能为生产环境的
80%
print(df.head())
# 分离测试和生产环境数据
test_data = df[df['Environment'] == 'Test']
prod_data_old = df[(df['Environment'] == 'Prod') & (df['Version'] == 'Old')]
# 归一化处理（简化处理，仅对部分列）
scaler = MinMaxScaler()
test_data[['ResponseTime_ms', 'Throughput']] = scaler.fit_transform(test_data[['ResponseTime_ms',
'Throughput']])
资源评论
