Large PMML Generator.py

import pandas
import numpy as np
from scipy.stats import randint
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
rng = np.random.RandomState(0)
X, y = make_classification(n_samples=100000000, n_features=500, random_state=rng)
with open('input', 'w') as f:
    f.write(str(X[0]))
    f.write("\n")
    f.write(str(y[0]))
print(X[0])
print(y[0])

from sklearn2pmml.pipeline import PMMLPipeline
pipeline = PMMLPipeline([
    ("classifier", RandomForestClassifier(n_jobs=40))
])
pipeline.fit(X, y)
from sklearn2pmml import sklearn2pmml
sklearn2pmml(pipeline, "rf-1b.pmml", with_repr = True)