res = mod.fit(maxiter=1000, disp=False)
print(res.summary())
res.forecast(steps=1)
fcast_res1 = res.get_forecast(steps=1)
# Most results are collected in the `summary_frame` attribute.
print(fcast_res1.summary_frame(4))
import statsmodels.api as sm
X=df.iloc[:, 1:38]
y=df.iloc[:, 38]
model=sm.OLS(y,X).fit()
predictions=model.predict(X)
model.summary()
predictions
pd.concat([y,predictions], axis=1)
#Ordinal Brier score for 5 bin questions
#forecast
f=[0.2, 0.2, 0.2, 0.2, 0.2]
#actual
a=[1,0,0,0,0]
def ord_brier(forecast, actual):
#find squared error of each cumulative group of bins
bin1cumulativeerror=(sum(forecast[:1])-sum(actual[:1]))**2
model.fit(X_train, y_train)
# get coefficients
print('Intercept:', model.intercept_)
print('Slope:', model.coef_)
print(
pd.DataFrame({
'Variable': ['intercept'] + list(X.columns),
'Coefficient': [
"{0:.5f}".format(v) for v in np.append(
model.intercept_, model.coef_.flatten()).round(6)
]
}))
# get fitted value on training set
y_train_predicted = model.predict(X_train)
# compare predictions
print(
pd.DataFrame({
'True': y_train.ravel(),
'Predicted': y_train_predicted.ravel()
}))
# deleting outliers
Q1 = df_linreg.quantile(0.2)
Q3 = df_linreg.quantile(0.8)
IQR = Q3 - Q1
dataset_outlier = df_linreg[~((df_linreg <
(Q1 - IQR)) | (df_linreg >
