statsmodels における予測¶

endog = macrodata['infl']
endog.plot(figsize=(15, 5))

# Construct the model
mod = sm.tsa.SARIMAX(endog, order=(1, 0, 0), trend='c')
# Estimate the parameters
res = mod.fit()

print(res.summary())

# The default is to get a one-step-ahead forecast:
print(res.forecast())

# Here we construct a more complete results object.
fcast_res1 = res.get_forecast()

# Most results are collected in the `summary_frame` attribute.
# Here we specify that we want a confidence level of 90%
print(fcast_res1.summary_frame(alpha=0.10))

print(res.forecast(steps=2))

fcast_res2 = res.get_forecast(steps=2)
# Note: since we did not specify the alpha parameter, the
# confidence level is at the default, 95%
print(fcast_res2.summary_frame())

print(res.forecast('2010Q2'))

fcast_res3 = res.get_forecast('2010Q2')
print(fcast_res3.summary_frame())

fig, ax = plt.subplots(figsize=(15, 5))

# Plot the data (here we are subsetting it to get a better look at the forecasts)
endog.loc['1999':].plot(ax=ax)

# Construct the forecasts
fcast = res.get_forecast('2011Q4').summary_frame()
fcast['mean'].plot(ax=ax, style='k--')
ax.fill_between(fcast.index, fcast['mean_ci_lower'], fcast['mean_ci_upper'], color='k', alpha=0.1);

# Step 1: fit model parameters w/ training sample
training_obs = int(len(endog) * 0.8)

training_endog = endog[:training_obs]
training_mod = sm.tsa.SARIMAX(
    training_endog, order=(1, 0, 0), trend='c')
training_res = training_mod.fit()

# Print the estimated parameters
print(training_res.params)

# Step 2: produce one-step-ahead forecasts
fcast = training_res.forecast()

# Step 3: compute root mean square forecasting error
true = endog.reindex(fcast.index)
error = true - fcast

# Print out the results
print(pd.concat([true.rename('true'),
                 fcast.rename('forecast'),
                 error.rename('error')], axis=1))

# Step 1: append a new observation to the sample and refit the parameters
append_res = training_res.append(endog[training_obs:training_obs + 1], refit=True)

# Print the re-estimated parameters
print(append_res.params)

# Step 2: produce one-step-ahead forecasts
fcast = append_res.forecast()

# Step 3: compute root mean square forecasting error
true = endog.reindex(fcast.index)
error = true - fcast

# Print out the results
print(pd.concat([true.rename('true'),
                 fcast.rename('forecast'),
                 error.rename('error')], axis=1))

# Setup forecasts
nforecasts = 3
forecasts = {}

# Get the number of initial training observations
nobs = len(endog)
n_init_training = int(nobs * 0.8)

# Create model for initial training sample, fit parameters
init_training_endog = endog.iloc[:n_init_training]
mod = sm.tsa.SARIMAX(training_endog, order=(1, 0, 0), trend='c')
res = mod.fit()

# Save initial forecast
forecasts[training_endog.index[-1]] = res.forecast(steps=nforecasts)

# Step through the rest of the sample
for t in range(n_init_training, nobs):
    # Update the results by appending the next observation
    updated_endog = endog.iloc[t:t+1]
    res = res.append(updated_endog, refit=False)

    # Save the new set of forecasts
    forecasts[updated_endog.index[0]] = res.forecast(steps=nforecasts)

# Combine all forecasts into a dataframe
forecasts = pd.concat(forecasts, axis=1)

print(forecasts.iloc[:5, :5])

# Construct the forecast errors
forecast_errors = forecasts.apply(lambda column: endog - column).reindex(forecasts.index)

print(forecast_errors.iloc[:5, :5])

# Reindex the forecasts by horizon rather than by date
def flatten(column):
    return column.dropna().reset_index(drop=True)

flattened = forecast_errors.apply(flatten)
flattened.index = (flattened.index + 1).rename('horizon')

print(flattened.iloc[:3, :5])

# Compute the root mean square error
rmse = (flattened**2).mean(axis=1)**0.5

print(rmse)

# Setup forecasts
nforecasts = 3
forecasts = {}

# Get the number of initial training observations
nobs = len(endog)
n_init_training = int(nobs * 0.8)

# Create model for initial training sample, fit parameters
init_training_endog = endog.iloc[:n_init_training]
mod = sm.tsa.SARIMAX(training_endog, order=(1, 0, 0), trend='c')
res = mod.fit()

# Save initial forecast
forecasts[training_endog.index[-1]] = res.forecast(steps=nforecasts)

# Step through the rest of the sample
for t in range(n_init_training, nobs):
    # Update the results by appending the next observation
    updated_endog = endog.iloc[t:t+1]
    res = res.extend(updated_endog)

    # Save the new set of forecasts
    forecasts[updated_endog.index[0]] = res.forecast(steps=nforecasts)

# Combine all forecasts into a dataframe
forecasts = pd.concat(forecasts, axis=1)

print(forecasts.iloc[:5, :5])

# Construct the forecast errors
forecast_errors = forecasts.apply(lambda column: endog - column).reindex(forecasts.index)

print(forecast_errors.iloc[:5, :5])

# Reindex the forecasts by horizon rather than by date
def flatten(column):
    return column.dropna().reset_index(drop=True)

flattened = forecast_errors.apply(flatten)
flattened.index = (flattened.index + 1).rename('horizon')

print(flattened.iloc[:3, :5])

# Compute the root mean square error
rmse = (flattened**2).mean(axis=1)**0.5

print(rmse)

print(endog.index)

# Annual frequency, using a PeriodIndex
index = pd.period_range(start='2000', periods=4, freq='A')
endog1 = pd.Series([1, 2, 3, 4], index=index)
print(endog1.index)

# Quarterly frequency, using a DatetimeIndex
index = pd.date_range(start='2000', periods=4, freq='QS')
endog2 = pd.Series([1, 2, 3, 4], index=index)
print(endog2.index)

# Monthly frequency, using a DatetimeIndex
index = pd.date_range(start='2000', periods=4, freq='M')
endog3 = pd.Series([1, 2, 3, 4], index=index)
print(endog3.index)

index = pd.DatetimeIndex([
    '2000-01-01 10:08am', '2000-01-01 11:32am',
    '2000-01-01 5:32pm', '2000-01-02 6:15am'])
endog4 = pd.Series([0.2, 0.5, -0.1, 0.1], index=index)
print(endog4.index)

mod = sm.tsa.SARIMAX(endog4)
res = mod.fit()

res.forecast(1)

# Here we'll catch the exception to prevent printing too much of
# the exception trace output in this notebook
try:
    res.forecast('2000-01-03')
except KeyError as e:
    print(e)