46 lines
1.1 KiB
Python
Executable file
46 lines
1.1 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Wed Aug 19 14:33:51 2020
|
|
|
|
@author: tanu
|
|
"""
|
|
|
|
|
|
#%% load packages
|
|
import os,sys
|
|
import subprocess
|
|
import argparse
|
|
import requests
|
|
import re
|
|
import time
|
|
from bs4 import BeautifulSoup
|
|
import pandas as pd
|
|
from pandas.api.types import is_string_dtype
|
|
from pandas.api.types import is_numeric_dtype
|
|
#%%============================================================================
|
|
|
|
#1) define muts batch
|
|
#take mcsm file
|
|
#split into 'n' batches
|
|
#write output file with suffix of batch number
|
|
|
|
|
|
#********** done this par ****************
|
|
#2) get results for a batch url
|
|
# read file
|
|
# store batch url
|
|
#extract number
|
|
#build single url
|
|
#build single results urls
|
|
#get results and store them in df
|
|
#update df
|
|
#dim of df = no. of muts in batch
|
|
|
|
#3) format results
|
|
# store unit measurements separtely
|
|
# omit unit measurements from cols
|
|
# create extra columns '_outcome' suffix by splitting numerical output
|
|
# create separate col for mcsm as it doesn't have output text
|
|
|
|
#%%============================================================================
|