import urllib
import os.path
import sys
from sklearn import linear_model
from data_import import percolator_import, summary_stats
try:
import cPickle as pickle
kwargs = {}
except:
import _pickle as pickle
kwargs = {'encoding':'bytes'}
import gzip
data, true_hits, peptide_number = percolator_import(sys.argv[1])
data2, true_hits_2, peptide_number_2 = percolator_import(sys.argv[2])
means, sdevs = summary_stats(data)
pre_trans_data = data
pre_trans_data2 = data2
#save scans and labels
scan_nums = data[:,0]
labels = data[:,1]
scan_nums_2 = data2[:,0]
labels_2 = data2[:,1]
import string
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import time
import urllib
import os.path
import sys
import random
from datetime import datetime
from sklearn import linear_model
from data_import import percolator_import, summary_stats
data, true_hits, peptide_number = percolator_import(sys.argv[1])
pre_trans_data = data
scan_nums = data[:,0]
orig_labels = data[:,1]
labels = orig_labels
#strip scans and peps out
data = data [:, [i for i in range(2, 20)]]
#
# Creat First N Scan Subset
#
count = 0
N_scans = 50000
for scan in scan_nums:
if int(scan) > N_scans: