OsmanMutlu

import sys
import csv

input_csv_file = sys.argv[1]

user_prefs = {}
first_paper_prefs = {}
with open(input_csv_file, "r", encoding="utf-8") as csv_file:
    lines = list(csv.reader(csv_file, delimiter=','))
    paper_names = lines[0][2:]

OsmanMutlu

Reference

Remove sensitive files from Git/Github

In Terminal

git filter-branch --index-filter 'git rm --cached --ignore-unmatch [file path/name]' --prune-empty --tag-name-filter cat -- --all

Example:

OsmanMutlu

import lxml.html
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
import re
import codecs
import json

with codecs.open("urls.jl","r","utf-8") as f:

OsmanMutlu

import pandas as pd

# y1 and y2 are series
def calculate_kalpha(y1,y2):
    df = pd.concat([y1,y2], axis=1)
    df.columns = ['y1', 'y2']
    agg = 0
    diss = 0
    for label in df.y1.unique().tolist():
        agg += 2*len(df[(df.y1 == label) & (df.y2 == label)])

OsmanMutlu

def url_to_filename(row): #Takes a pandas row
    url = row.url
    url = re.sub(r"://", r"__", url)
    url = re.sub(r"/", r"_", url)
    row.url = re.sub(r"\.?(cms|html|ece|ece1)?$", r".folia.xml", url)
    return row

def getwordtext(entity): #Takes a folia entity
    annot = ""
    for word in entity.wrefs():

OsmanMutlu

import pandas as pd

def calculate_Kalpha2(y1,y2):
    df = pd.concat([y1,y2], axis=1)
    df.columns = ['y1', 'y2']
    n = 2*len(df)
    agg = 0
    all = 0
    for label in df.y1.unique().tolist():
        agg += 2*len(df[(df.y1 == label) & (df.y2 == label)])

OsmanMutlu

import pandas as pd
import re
import codecs
from glob import glob
from pynlpl.formats import folia

files = glob("alladjudicated/http*")

all_df = pd.DataFrame(files, columns=["filename"])