a wrapper function for linear regression analysis using statsmodels

my_regmodel.py

import pandas as pd
import statsmodels.formula.api as smf
from statsmodels.stats.outliers_influence import variance_inflation_factor

def get_vif(data):
    d = {data.columns.values[i]: variance_inflation_factor(data.values, i)\
         for i in range(data.shape[1])}
    vif_series = pd.Series(d)
    return vif_series

def my_fitmodel(formula, data, target_col=-1):
    model = smf.ols(formula, data=data).fit()
    if target_col == -1:
        target_col = data.columns.size-1
    feature_col = [item.strip() for item in formula.split('~')[-1].split('+')]
    result = {'vif': get_vif(data[feature_col])}
    for item in ['params', 'pvalues', 'tvalues', 'HC0_se']:
        result[item] = eval('model.{}.copy()'.format(item))
    result['conf_int_lo'] = model.conf_int()[0]
    result['conf_int_hi'] = model.conf_int()[1]
    return {'result': pd.DataFrame(result),
            'rsquared_adj': model.rsquared_adj,
            'rsquared': model.rsquared,
           }