aialenti

order_id	product_id	seller_id	date	num_pieces_sold	bill_raw_text
1	0	0	2020-07-07	12	bdgwqyboczbitqzsxwmtjhehnxyvdfsddlftaiPmDbzqntavetfrxxdyparkxinoqVcgqycdkaeowfwmingazormirqlwgcvztqdrdtnhjmkhgpxifzzadlecpycygfpdmedzecbddjujesrypwgrrlcbnorfjpyknmaccpmnagcaijgkegnpikisizjmjooicizlqneuqscjvktzbsvwpvjfdthmvmgqasstsxkcvfwdutoedebkpxagljrcspxblsfucsktxplyphxbytpozaomcbovjzymqwjzhmcrfqlnpqtlcxcjlqgivhsipmudmpgnmzozmzdfbyvnuszezasszdofwzbnyfcvqtlhohofagfdsgpcbgjsaspbnkghlqmmoekikkzfzasuzfevqpyyvzqluukxsqufviyejrgjneyocosghxqkefrplpomldzgcyrbmbckaqowwzxoeasfjndgszeeijciUficjumhajvpvau
2	0	0	2020-07-01	71	wmewueqbyoqivcpjfsmadtgxsvxjaretdoitcymxqnfWfbycedbbvhexudyhjapqyidfuxwvnilaifpylpfxlsryrtexnfckgkmcdmmkxjrcgpultohyuqbwkrqrlkoezzehlaiahlhontcsvibbtbvclevfhiqkinklxfprejfdldzgcofhqwgyyuvxsdggpadsemwiqtcujsjcrukrildfelwagyvoduzevilIzuimflinuecfattldmgggxjyujhwhjnlqucrebqpdnoczlnouftexamxicbbfdchtZmycpjpgylmzxqcehpqspgftjfcwhzxiblqeqbcnvrjvlwsiwpwutppzgclhizcmexwhsynxacayaaulbGkoosviaxrpjpgaiisbcmkzfxnvxhoqodjmozxbp

	# Imports
	import numpy as np
	import pandas as pd
	import xgboost as xgb
	from interruptingcow import timeout
	from sklearn.model_selection import KFold # import KFold
	from sklearn.metrics import r2_score
	import json
	from preprocessing import preprocessing, xgb_r2_score
	from generate_random_configuration import generate_random_configuration

	from interruptingcow import timeout
	from sklearn.model_selection import KFold
	import pymongo
	from joblibspark import register_spark
	from joblib import Parallel, delayed
	from pprint import pprint
	import random

	def random_search_spark(timeout_seconds, cv_splits, boosting_rounds):
	# Read and preprocess input data

	import numpy as np
	import xgboost as xgb
	from sklearn.metrics import r2_score
	import pymongo
	from joblib import Parallel, delayed

	import random

	# "evaluate" is the function that is executed on the single Spark executor
	def evaluate(X, y, kf, boosting_rounds):

	# Imports
	import random
	import math

	def generate_random_configuration():
	params = {'learning_rate': random.uniform(0.01, 0.25),
	'colsample_bytree': random.uniform(0.8, 1.0),
	'subsample': random.uniform(0.5, 1.0),
	'n_estimators': math.floor(random.uniform(100, 3000)),
	'reg_alpha': random.uniform(0.01, 0.5),