在python上滚动回归

Question

我正在尝试使用以下代码对几个x_variable运行滚动回归：

# Get data for specified date range
pred = pred[beg_date:end_date]
# Lag and standardize pred
pred[var_list_all] = pred[var_list_all].shift(1)
pred[var_list_all] = preprocessing.StandardScaler().fit_transform(pred[var_list_all])
# Initialize dictionary of lists
d = {}
for i in ['coeff', 't-stat', 'r2']:
d[i] = []
# Run bi-variate regression for each pred variable
y_var = 'EP'
for x_var in var_list_all:
formula = y_var + ' ~ ' + x_var
results = RollingOLS.from_formula(formula, window=60, data=pred)
d['coeff'].append(results.params[x_var])
d['t-stat'].append(results.params[x_var] / results.bse[x_var])
d['r2'].append(results.rsquared * 100)

目的是收集每个变量的系数、t-stat和r2，并将每个变量的r2绘制在单独的图上。

每当我运行回归时，我都会不断收到以下消息：

属性错误："NoneType"对象没有属性"f_locates"

我也在上尝试过这个例子https://www.statsmodels.org/stable/examples/notebooks/generated/rolling_ls.html看看我是否理解发生了什么，但我收到了同样的错误消息。

我不太确定我做错了什么。

如有任何帮助，我们将不胜感激。

提前谢谢。

Answer 1

下面是一个从statsmodels使用RollingOLS的工作示例。灵感来自于对这个问题的回答——滚动OLS回归和预测(按组(。

from statsmodels.regression.rolling import RollingOLS
from statsmodels.tools.tools import add_constant
import statsmodels.api as sm
import pandas as pd
import numpy as np
data = sm.datasets.grunfeld.load()
df_grunfeld = pd.DataFrame(data.data)
df_grunfeld.set_index(['firm'], append=True, inplace=True)
# Simple Model
# $$invest = beta_0 + beta_1 value$$
def invest_params(df_gf, intercept=False):
"""
Function to operate on the data of a single firm.
Assumes df_gf has the columns 'invest' and 'value' available.
Returns a dataframe containing model parameters
"""
# we should have at least k + 1 observations
min_obs = 3 if intercept else 2
wndw = 8 
# if there are less than min_obs rows in df_gf, RollingOLS will throw an error
# Instead, handle this case separately
if df_gf.shape[0] < min_obs:
cols = ['coef_intercept', 'coef_value'] if intercept else ['coef_value']
return pd.DataFrame(index=df_gf.index, columns=cols)
y = df_gf['invest']
x = add_constant(df_gf['value']) if intercept else df_gf['value']
model = RollingOLS(y, x, expanding=True, min_nobs=min_obs, window=wndw).fit()
parameters = model.params
params_shifted = model.params.shift(1)
mse = model.mse_resid
parameters['invest_hat'] = (parameters.mul(add_constant(df_gf['value']), axis=0)
.sum(axis=1, min_count=1)).to_frame('invest_hat')
parameters['invest_hat_shift'] = (params_shifted.mul(add_constant(df_gf['value']), axis=0)
.sum(axis=1, min_count=1)).to_frame('invest_hat_shift')
parameters['mse'] = mse
parameters['rmse'] = np.sqrt(mse)
parameters['nobs'] = model.nobs
parameters['ssr'] = model.ssr
parameters['t_const'] = model.tvalues['const']
parameters['t_value'] = model.tvalues['value']
parameters.rename(columns = {'const' : 'b0', 'value' : 'b1'}, inplace = True)
parameters['r2_adj'] = model.rsquared_adj

return parameters
grouped = df_grunfeld.groupby('firm')
df_params = grouped.apply(lambda x: invest_params(x, True))
df_grunfeld_output = df_grunfeld.join(df_params, rsuffix='_coef')