For FSEC data analysis(UCSF_MInorLab). Reads CSV files kept in a directory and give maximum intensity vs time/vol in csv format.

SEC_Data_Analyzer(SDA)_v.1.0.py

#! /usr/bin/env python
######################################################################################################################
##################     SEC Data Analyzer (SDA)   #####################################################################
########################### v.1.0     (11/18/2019)          ##########################################################
###########################  Author: Abhisek Mondal, UCSF ############################################################
######################################################################################################################
"""
Program Description and input:
> Takes a directory path containing all csv files
> Walks along the directory to search and analyze CSV files
>Takes a CSV file as input with .txt extension.
>Creates specific data structue and performs user defined mining 
>Outputs:
    * maximum intensity with corresponding volume or time within the user defined range
    * volume and intensity in a user defined area (optional).
...

"""

import os
import sys
import itertools
from os.path import basename
from itertools import islice
import glob
import csv
import time

print "*********************************************************************************************************"
print "                  Hi there! You are executing SEC_peakAnalyzer algorithm on "+ time.asctime()+" PST "
print "                                     PROGRAM NAME: SEC Data Analyzer (SDA) v.1.0 "
print "                                             designed by => Abhisek Mondal"
print "                                 abhisek.mondal@ucsf.edu[github:https://github.com/diffracteD]"
print "                                                 UCSF, California, USA"
print "**********************************************************************************************************"


path=raw_input("Please enter the directory path containing all the csv files(Do Not enter / at the end of the path). . . \n ")
volMin=raw_input(" Enter the lower boundary of volumetric search... \n")
volMax=raw_input(" Enter the upper boundary of vulumetric search... \n")

#Starting to walk across directories of given path to open files
for root, dirs, files in os.walk(path):
    listOfFile = glob.iglob(os.path.join(root, '*.txt'))  #Supplied csv is in txt extension. Do not change the txt to csv else the file gets scrambled...
    print "          Enterring Directory: " + root
    
    maxOutList = [] #List for storing maximum vol/min vs intensity values including filename for csv output...   
    
    for csvFileName in listOfFile:
        #Checking if target file is empty...
        if os.stat(csvFileName)[6] != 0: 
            #Trimming the path and keeping only the filename for cool output...
            filename = basename(csvFileName)
            
             
            
            #Generating header for the csv output..
            #maxOutHeader = str('File Name'), str('Max Peak'),str('volume/time'), str('intensity')
            #maxOutList.append(maxOutHeader)            
            
            #Opening and preparing .csv as per python array syatem...
            print " > Processing File: " + filename #shows current file being read...
            
            csvList = [] #storing all csv data as python list  
            modifiedCsvList = [] #storing all csv data after filtering only volume vs intensity section...
            inp = open(csvFileName, 'r').read().strip().split('\n')
            
        
            
            #Mapping the csv file...
            for line in map(str.split, inp):
                #print line
                csvList.append(line)
                
            #Determining from which Line program starts to enlist data {V V IMP.}, as different FSEC peak arats from different line in CSV file
            #Indexing all the lines in CSV > then filtering based on value 'R.Time...' as the data starts after that.
            #Converting value from enumerate to string to count len(as lowest among all the index xorresponds to the actual data)
            for index, value in enumerate(csvList):              ###Weired things going on
                if value == ['R.Time', '(min)', 'Intensity']:
                    if len(str(index))<5:
                        #Now adding +1 to the index as the value starts after this line.
                        skipLine = int(index) +1 #this value will be used for slicing the csvList and discard other junk information...
                        #print index, value
                        #print skipLine
                
            #Filetering the csvList to get the desired range of data...
            volume = []
            intensity = []
            
            
            
            #value iterator
            for item in csvList[skipLine:]:
                print item
                #Creating exception for empty list entry based termination...
                try:
                    #print float (item[0]), float(item[1])
                    modifiedCsvList.append(item)
                    volume.append(float(item[0]))
                    intensity.append(int(item[1]))  #volumes comes as int as per the csv
                    
                except IndexError:
                    break             #Breaks the iteration upon first encounter of empty list...
                
            
                
                       
            #Peak search by volumetri area...
            #variable handler takes user input and sear and output intensities in that region
            #z = max(intensity)  #filtering out maximum intensity value
            
            #Opening list for storing all the values in user defined range, will be used in maximum intensity calculation...
            requiredVolume = []
            requiredIntensity = []
            
            for vol, uv in zip(volume, intensity):
                
                #detemining volume vs peak list based on user defined ranges...
                if len(volMin) > 0 and volMax > 0:
                    
                    if vol >= float(volMin) and vol <= float(volMax):    #printing zones of peak based on user provided bounderies...
                        #print vol, uv
                        requiredVolume.append(vol)
                        requiredIntensity.append(uv)
                        #Active below lines if all the intensities within user deined boundary is required...
                        #boundaryValues = str(vol), str(uv) #Taking in all the value within desired range before filtering out max intensity data...
                        #maxOutList.append(boundaryValues)                        
                        
            z = max(requiredIntensity)   #filtering out maximum intensity value within the user defined range
            for reqVol, reqInt in zip(requiredVolume, requiredIntensity):
                if reqInt == z:
                    print " >> Location of maximum UV intensity (time/volume, intensity):"+ str(' ')+ str(reqVol)+'  '+str(reqInt)
                    m = 'Max Peak Info(time/volume, intensity):'  #Just to make sure each alphabet does not occupy each column...
                    maxOut = str(filename), str(m),str(reqVol), str(reqInt)
                    #print maxOut
                    maxOutList.append(maxOut)
                            
                                        
            #print maxOutList               
            #______________________________________________________________________________________________________________________________________
            #for items in maxOutList:
            #    print items
            #Writing csv output...
            #List architecture: Filename
            #                   Max Peak Info: vol intensity
            #                   vol intensities (for user defined bounderies)
            #_______________________________________________________________________________________________________________________________________
    outFile= path +'/'+'peakAnalyzerOut.csv'  #name of the output file
    with open(outFile, 'wb') as outputFile:
        for items in maxOutList:            #this loop is necessary else whole list will be dumped into one massive row in csv file...
            #print items
            wr = csv.writer(outputFile, quoting=csv.QUOTE_ALL) #writer operator writes the list to a csv file...
            wr.writerow(items)  #writing the maxOutList into CSV format in the same user provided path...
            
    print " __________________________________________________________ "
    print "| >>> CSV file generated under the given path...           |"
    print "| >>>    *** adios amigo ! ***                             |"
    print "| >>> Word of Advice: Life is short for manual processing !|"
    print "|__________________________________________________________|"