analyze_predictions

source

analyze_predictions(result_or_model, newdata=None)

Return fitted values from a model (and residuals/actuals on the estimation sample).

Parameters

Name	Type	Description	Default
result_or_model	Any	A fitted model or a result object carrying `.models`.	required
newdata	pd.DataFrame \| None	Optional data frame to predict on. When omitted, predictions are for the estimation sample and the frame also includes the `actual` outcome and the `residual`.	`None`

Returns

Name	Type	Description
	PredictionResult	`df` with a `predicted` column (plus `actual` and `residual` in-sample).

Examples

Basic — in-sample fitted values, actuals, and residuals:

import expdpy as ex
from expdpy.data import load_kuznets, load_kuznets_data_def

df = ex.set_labels(load_kuznets(), load_kuznets_data_def(), set_panel=True)
model = ex.analyze_regression_table(
    df,
    dvs="gini_regional",
    idvs=["log_gdp_pc", "log_gdp_pc_sq", "log_gdp_pc_cu"],
    feffects=["country"],
)
ex.analyze_predictions(model).df.head()

	actual	predicted	residual
0	0.085611	0.095395	-0.009784
1	0.080064	0.124973	-0.044909
2	0.212049	0.197058	0.014991
3	0.221831	0.238076	-0.016245
4	0.261234	0.282897	-0.021663

Advanced — predict on new data (here a fresh slice of the panel):

import expdpy as ex
from expdpy.data import load_kuznets, load_kuznets_data_def

df = ex.set_labels(load_kuznets(), load_kuznets_data_def(), set_panel=True)
model = ex.analyze_regression_table(
    df,
    dvs="gini_regional",
    idvs=["log_gdp_pc", "log_gdp_pc_sq", "log_gdp_pc_cu"],
    feffects=["country"],
)
newdata = df[df["year"] == df["year"].max()]
ex.analyze_predictions(model, newdata=newdata).df.head()

/home/runner/work/expdpy/expdpy/.pixi/envs/docs/lib/python3.12/site-packages/pyfixest/estimation/post_estimation/prediction.py:125: UserWarning: Data types of fixed effects ['country'] do not match the model data. This leads to possible mismatched keys in the fixed effect dictionary -> NaN predictions for new levels.
  warnings.warn(

	predicted
0	0.385494
1	0.365067
2	0.298891
3	-0.028847
4	0.269609