def pipeline_override_d(data):
pipeline = Pipeline(steps=[("arima", AutoARIMA(out_of_sample_size=30))])
util = PmdarimaAnalyzer(df=data.df,
group_key_columns=data.key_columns,
y_col="y",
datetime_col="ds")
ndiffs = util.calculate_ndiffs(alpha=0.2, test="kpss", max_d=7)
nsdiffs = util.calculate_nsdiffs(m=7, test="ocsb", max_D=7)
return GroupedPmdarima(pipeline).fit(
df=data.df,
group_key_columns=data.key_columns,
y_col="y",
datetime_col="ds",
ndiffs=ndiffs,
nsdiffs=nsdiffs,
silence_warnings=True,
)
suppress_warnings=True,
error_action="ignore",
),
)
]
)
diff_analyzer = PmdarimaAnalyzer(
df=training_data,
group_key_columns=group_key_columns,
y_col="y",
datetime_col="ds",
)
ndiff = diff_analyzer.calculate_ndiffs(
alpha=0.05,
test="kpss",
max_d=4,
)
grouped_model = GroupedPmdarima(model_template=pipeline).fit(
df=training_data,
group_key_columns=group_key_columns,
y_col="y",
datetime_col="ds",
ndiffs=ndiff,
silence_warnings=True,
)
# Save to local directory
save_dir = "/tmp/group_pmdarima/pipeline_override.gpmd"
grouped_model.save(save_dir)
analyzer = PmdarimaAnalyzer(
df=training_data,
group_key_columns=group_key_columns,
y_col="y",
datetime_col="ds",
)
# Decompose the trends of each group
decomposed_trends = analyzer.decompose_groups(m=7, type_="additive")
print("Decomposed trend data for the groups")
print("-" * 100, "\n")
print(decomposed_trends[:50].to_string())
# Calculate optimal differencing for ARMA terms
ndiffs = analyzer.calculate_ndiffs(alpha=0.1, test="kpss", max_d=5)
_print_dict(ndiffs, "Differencing")
# Calculate seasonal differencing
nsdiffs = analyzer.calculate_nsdiffs(m=365, test="ocsb", max_D=5)
_print_dict(nsdiffs, "Seasonal Differencing")
# Get the autocorrelation function for each group
group_acf = analyzer.calculate_acf(unbiased=True,
nlags=120,
qstat=True,
fft=True,
alpha=0.05,
adjusted=True)