accessing feature decorated dataframe from pipe?

Hi,

When I fit a pipe using automatminer to a dataset like below, how do I extract the data (i.e the original data frame that has been augmented with additional features) from the newly learned pipe? Thank you!!

Sincerely,

tom

from matminer.datasets.convenience_loaders import load_castelli_perovskites

user inputs

target = ‘gap gllbsc’

RS = 29

timelimitmins = 120

print('timelimitmins = ', timelimitmins)

model_type = ‘regression’

scoring = ‘r2’

df_init = load_castelli_perovskites()

from automatminer.pipeline import MatPipe

Fit a pipeline to training data to predict band gap

pipe = MatPipe()

pipe.fit(df_init.head(100), target)

pipe.digest()

Hey Tom,

You can actually use the output of pipe.digest to check out all the available attribute names.

To get the df with features used for fitting, you can use pipe.post_fit_df, it should contain all the features

···

On Friday, December 14, 2018 at 8:29:00 AM UTC-8, thomas heiman wrote:

Hi,

When I fit a pipe using automatminer to a dataset like below, how do I extract the data (i.e the original data frame that has been augmented with additional features) from the newly learned pipe? Thank you!!

Sincerely,

tom

from matminer.datasets.convenience_loaders import load_castelli_perovskites

user inputs

target = ‘gap gllbsc’

RS = 29

timelimitmins = 120

print('timelimitmins = ', timelimitmins)

model_type = ‘regression’

scoring = ‘r2’

df_init = load_castelli_perovskites()

from automatminer.pipeline import MatPipe

Fit a pipeline to training data to predict band gap

pipe = MatPipe()

pipe.fit(df_init.head(100), target)

pipe.digest()