'''
Binary Classification.
'''
import numpy
import pandas
from microsoftml import rx_fast_linear, rx_predict
from revoscalepy.etl.RxDataStep import rx_data_step
from microsoftml.datasets.datasets import get_dataset
claims = get_dataset("claims")
import sklearn
if sklearn.__version__ < "0.18":
from sklearn.cross_validation import train_test_split
else:
from sklearn.model_selection import train_test_split
claimsdf = claims.as_df()
claimsdf["isCase"] = claimsdf.case == 1
data_train, data_test, y_train, y_test = train_test_split(claimsdf, claimsdf.isCase)
forest_model = rx_fast_linear(
formula=" isCase ~ age + parity + education + spontaneous + induced ",
data=data_train)
# RuntimeError: The type (RxTextData) for file is not supported.
score_ds = rx_predict(forest_model, data=data_test,
extra_vars_to_write=["isCase", "Score"])
# Print the first five rows
print(rx_data_step(score_ds, number_rows_read=5))
No comments:
Post a Comment