import pmids

import classify

import os

import gzip

import queries

import shutil

import csv

import decimal

import time

import sys

import math

import operator

import collections

import Cosine_Sim

from nltk.stem.porter import *

from os import listdir

from os.path import isfile, join

from random import randrange

try:

import xml.etree.cElementTree as ET

except ImportError:

import xml.etree.ElementTree as ET

def get_already_downloaded_ids(q, models):

return already_downloaded_pmids

def get_already_downloaded_file_paths(q, models, num_articles):

return already_downloaded_file_path_list

# def run_tees_batch(q, id_list, models):

# current_dir = os.getcwd()

# already_downloaded_pmids = get_already_downloaded_ids(q, models)

# ignore_list_path = current_dir + '/text_files/id_ignore_list.txt'

# pmid_ignore_list = []

# with open (ignore_list_path, 'r') as f:

# reader = csv.reader(f,delimiter='\t')

# if reader:

# for pmid_list in reader:

# pmid_ignore_list = pmid_list

# else:

# pmid_ignore_list = []

#

# pmid_run_list = []

# for pmid in id_list:

# if pmid in pmid_ignore_list:

# continue

# elif pmid in already_downloaded_pmids:

# continue

# else:

# pmid_run_list.append(pmid)

#

#

#

# float_num = float(len(pmid_run_list))/25

# rounded_up_num = math.ceil(float_num)

# list_of_pmid_lists = []

# for x in range(int(rounded_up_num)):

# list_of_pmid_lists.append(pmid_run_list[25*x:(25*x)+24])

#

# file_path_list = []

# if not list_of_pmid_lists:

# return file_path_list

# else:

# for plist in list_of_pmid_lists:

# file_path = current_dir + 'output/batch/genes/{0}/{1}' .format(q , '-'.join(plist))

# addition = '-pred.xml.gz'

# file_path_check = file_path + addition

# file_path_list.append(file_path)

#

# if os.path.exists(file_path_check):

# print '--------------------------------SKIPPING ALREADY DOWNLOADED ABSTRACTS {0}-------------------------------------------' .format(plist)

# else:

# classify.classify('-'.join(plist),'GE11',file_path)

# try:

# classify.classify('-'.join(plist),'GE11',file_path)

# except (ValueError, UnicodeEncodeError, AssertionError, IndexError) as e:

# print 'error,', e

# file_path_list.remove(file_path)

# single_pmids_file_path_list = run_tees(q, plist)

# file_path_list += single_pmids_file_path_list

# return file_path_list

def run_tees(q, id_list, models, text_file):

return file_path_list

def get_info_from_interaction_xml(file_paths):

return final_dict

def get_all_words_dict(q1, q2, q1_dict, q2_dict):

return all_words_dict

def normalize_dict(dict_in, query, stemmed):

return normalized_dict

def combine_dictionaries(query_dicts):

return combined_dict

def output_pair_score_dict(angle_list, protein_dict, q1, q2, input_type, outputFileName):

f.write(str('\n'))

def main(q1, q2, articles, batch, input_type, outputFileName, dictType, outputType, evaluation_mode, stemmed, model, text_file):

return angle_list, return_dict_s, num_docs_processed

def write_output(list_of_queries, iteration_angle_dict, angle_score_query_dict, angle_protein_word_dicts, input_type, outputFileName,

raw_input('press enter to continue')

# print "iteration_angle_dict", iteration_angle_dict

# raw_input('press enter to continue')

# print 'angle_score_query_dict', angle_score_query_dict

# raw_input('press enter to continue')

# print 'angle_protein_word_dicts', angle_protein_word_dicts

# raw_input('press enter to continue')

# print 'list_of_queries', list_of_queries

def index(q1, q2, num_articles, batch, input_type , outputFileName, dictType, outputType, iterate, evaluation_mode, iteration_type, stemmed, model, text_file):

write_output(list_of_queries, iteration_angle_dict, angle_score_query_dict, angle_protein_word_dicts, input_type, outputFileName, outputType, processed_docs_all_proteins, final_protein_word_dict)

#known

# optparser.add_option("-q", "--q1", default='NEDD4', dest="q1", help="query1")

# optparser.add_option("-w", "--q2", default='GRIN2A', dest="q2", help="query2")

#uknown

# optparser.add_option("-q", "--q1", default='SSTR2', dest="q1", help="query1")

# optparser.add_option("-w", "--q2", default='FABP5', dest="q2", help="query2")

# default='/home/adam/workspace/TEESinput/example'

if __name__=="__main__":

from optparse import OptionParser

optparser = OptionParser(description="Get XML from PubMed")

optparser.add_option("-q", "--q1", default='MDM2', dest="q1", help="query1")

optparser.add_option("-w", "--q2", default='TERT', dest="q2", help="query2")

optparser.add_option("-n", "--n", default=60, dest="num_articles", help="Number of Pubmed Papers to download per gene/protein")

optparser.add_option("-o", "--outputFileName", default="", dest="outputFileName", help="output file name")

optparser.add_option("-i", "--input_type", default='known', dest="input_type", help="single or 50examples or known or unknown or random or FrequentlyViewed, madhavi_split, negatome")

optparser.add_option("-b", "--batch", default="no", dest="batch", help="yes or no")

optparser.add_option("-d", "--dict", default="all", dest="dictType", help="all or protein")

optparser.add_option("-t", "--outputType", default="tab", dest="outputType", help="'normal'= proteins/score/dict or 'tab'= csv #articles/angles")

optparser.add_option("-r", "--iterate", default="no", dest="iterate", help="yes or no --- to iterate is to output averages every 5 angles")

optparser.add_option("-a", "--iteration_type", default="docs", dest="iteration_type", help="docs or list_len")

optparser.add_option("-e", "--evaluation", default="no", dest="evaluation_mode", help="yes or no --- evaluation blocks downloading more papers")

optparser.add_option("-s", "--stemmed", default="no", dest="stemmed", help="yes or no for stemming")

optparser.add_option("-m", "--mod", default='REL11 EPI11 ID11', dest="model", help="GE11, REL11, EPI11, ID11")

optparser.add_option("-f", "--txt", default='no', dest="text_file", help="yes or no -- whether input is txt file or pmids")

(options, args) = optparser.parse_args()

index(options.q1, options.q2, options.num_articles, options.batch, options.input_type, options.outputFileName, options.dictType, options.outputType, options.iterate,

options.evaluation_mode, options.iteration_type, options.stemmed, options.model, options.text_file)