Python支持向量回归和核岭回归

Question

我正在尝试创建SVR和KRR模型，它们可以根据测试结果中大约32个特征来预测利率。我要用于培训的数据在一个非常大的CVS文件中。 以下是我当前需要输入的列车数据：

import pandas as pd
import numpy as np
from numpy import nan
from datetime import datetime as dt
import statsmodels.api as sm

def strip2float(x):
    try:
        return float(x.strip('%'))/100 # convert percent strings to 
float
    except:
        return nan

def strip2int(x):
    try:
        return int(x.strip('$').replace(',','')) # convert monetary 
strings to int
    except:
        return nan

def verify2bool(x):
    if("not verified" in x.lower()): return False
    elif("verified" in x.lower()): return True
    else: return nan

def subgrade2int(x):
    try: return((ord(x[0].upper())-65)*5+int(x[1]))
    except: return nan

def payments2bool(x):
    try:
        if (int(x.replace(' months',''))==36): return False
        elif (int(x.replace(' months',''))==60): return True
        else: return nan
    except: return nan

def year2int(x):
    try:
        if("<" in x): return 0
        elif("+" in x): return 15
        else: return int(x.replace(' years',''))
    except:
        return nan

def date2int(x):
    try: return dt.strptime(x, '%b-%d')
    except:
        try: return dt.strptime(x, '%d-%b')
        except: return nan

def month2int(x):
    try: return dt.strptime(x, '%b-%y')
    except:
        try: return dt.strptime(x, '%y-%b')
        except: return nan

def status2bool(x):
    if(x.lower()=="f"): return True
    elif(x.lower()=="w"): return False
    else: return nan

filepath='Data for Cleaning & Modeling.csv'
dtype={'X2':float, 'X3':float, 'X8':str, 'X16':str}
converters={'X1':strip2float, 'X4':strip2int, 'X5':strip2int, 
'X6':strip2int, 'X7':payments2bool, 'X14':verify2bool, 
'X9':subgrade2int, 'X11':year2int, 'X15':date2int, 'X23':month2int, 
'X32':status2bool}
l=list(range(32))
data=pd.read_csv(filepath, index_col=False, dtype=dtype, 
converters=converters)
data.drop(['X2','X3','X8','X10','X16','X18','X19'], axis=1)

我在这方面很新，但我需要知道如何使用我目前拥有的，并创建一个SVR和KRR模型