sachaMorin
commented
1 year ago I can reproduce. Seems to be an issue with the bootstrap function taking dataframes as inputs.
I'll fix this soon, but in the meantime you can replace the last line with
model, bootstrapped_params = bootstrap(model, mm_data.to_numpy(), sm_data.to_numpy(), n_repetitions=20)
Hi,
I am new to Python and I am trying to produce a model with a categorical distal outcome that has missing values. However, I am having to use bootstrapping, because I get this error message while using the bootstrap() function:
KeyError: "None of [Index([109, 126, 66, 98, 17, 83, 106, 123, 57, 96,\n ...\n 50, 101, 130, 146, 46, 45, 18, 73, 62, 139],\n dtype='int64', length=150)] are in the [columns]"
Here is a simple example with the Iris database:
import pandas as pd from sklearn.datasets import load_iris from sklearn.metrics import rand_score from stepmix.stepmix import StepMix from stepmix.utils import get_mixed_descriptor from stepmix.bootstrap import bootstrap
data, target = load_iris(return_X_y=True, as_frame=True)
for c in data: c_categorical = c.replace("cm", "cat") data[c_categorical] = pd.qcut(data[c], q=3).cat.codes c_binary = c.replace("cm", "binary") data[c_binary] = pd.qcut(data[c], q=2).cat.codes
for i, c in enumerate(data.columns): data[c] = data[c].sample(frac=.5, random_state=42*i)
mm_data, mm_descriptor = get_mixed_descriptor( dataframe=data, continuous_nan=['sepal length (cm)', 'sepal width (cm)'], binary_nan=['sepal length (binary)', 'sepal width (binary)'], categorical_nan=['sepal length (cat)', 'sepal width (cat)'], )
sm_data, sm_descriptor = get_mixed_descriptor( dataframe=data, categorical_nan=['petal length (cat)', 'petal width (cat)'], )
model = StepMix(n_components=3, measurement=mm_descriptor, structural=sm_descriptor, verbose=1, random_state=123) model.fit(mm_data, sm_data)
here is the error model, bootstrapped_params = bootstrap(model, mm_data, sm_data, n_repetitions=1000)