API tools faq
paste
Advertisement
shihab2196

REACTER_Module-lfp_reactionVStime_A0001_variable_Rmax

shihab2196
Dec 8th, 2024
55
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 11.91 KB | None | 0 0
raw download clone embed print report
  1. '''Created by Fakhrul Hasan Bhuiyan'''
  2.  
  3. ##### Edit history #######
  4.  
  5. # Fakhrul H Bhuiyan: 10.13.2020 | Finalized the first version of the module
  6. # Fakhrul H Bhuiyan: 10.28.2020 | Fixed issues: Same thermodynamic keyword as header
  7. #                               | Incomplete line in the data block
  8. #                               | Added a new flag: 'Per MPI rank memory allocation'
  9. # Shihab Ahmed: 04:06:2024      | Define thermo_panda function
  10.  
  11. from warnings import showwarning, warn
  12. import numpy as np
  13. from scipy.optimize import curve_fit
  14. import sys
  15. import pandas as pd
  16.  
  17. def thermo_dict(filename, serial):
  18.     with open(filename, 'r') as f:
  19.         start = 0
  20.         thermo_data = {}
  21.  
  22.         for step, line in enumerate(f):
  23.             #print (line)
  24.             if line.startswith('Memory usage per processor') or line.startswith('Per MPI rank memory allocation'):   # looks for this line in the file
  25.                 #print('start')
  26.                 start += 1      # seed for start taking in data
  27.                 data_row = 0    # this is equal to the line number of the data
  28.                 thermo_headers = []     # thermo information in log files
  29.                 continue
  30.             if start == serial:     # if the code reaches the desired portion of the log file
  31.                 data_row += 1
  32.                 data = line.split()
  33.                 if data_row == 1:   # in the first line you have the headers
  34.                     for i in (data):
  35.                         if i not in thermo_headers:
  36.                             thermo_headers.append(i)    # creating a list of str of headers
  37.                             thermo_data[i] = []         # Creating dictionary keys named after each thermodynamic property
  38.                         else:
  39.                             # There are identical thermodynamic keywords as header
  40.                             name = i + '_' + str(data.index(i) + 1)
  41.                             thermo_headers.append(name)
  42.                             thermo_data[name] = []
  43.                             showwarning('Log file has same Thermodynamic keyword ' + str(i),
  44.                                         UserWarning, 'log_parser_FHB.py', 31)
  45.  
  46.                     #print ('len', len(thermo_data), thermo_data)
  47.  
  48.                 elif data_row > 1:      # this is where the data information starts in the log file
  49.                     #print (start)
  50.                     for i in range(0, len(data)):
  51.                         try:
  52.                             data[i] = float(data[i])  # making the str to float
  53.  
  54.                             if len(data) != len(thermo_headers):    # checking if the data line is complete
  55.                                 showwarning('Line number: ' + str(step+1) + ' in the log file is incomplete.',
  56.                                             UserWarning, 'log_parser.py', 46)
  57.                                 #print (data)
  58.                                 break
  59.                             else:
  60.                                 thermo_data[thermo_headers[i]].append(
  61.                                     data[i])  # putting in the data info in respective header's dict
  62.                         except:
  63.                             start += 1
  64.                             #print ('breaking')
  65.                             break  # if data lines end, you get str again, this terminates taking any more data
  66.  
  67.  
  68.  
  69.  
  70.     #print (thermo_data['Step'])
  71.     ##print (thermo_data['KinEng'])
  72.     #for x in thermo_data: print (x)
  73.     f.close()
  74.    
  75.     from colorama import Fore, Style
  76.     print(Fore.CYAN + '#### From log_parser: Serial = {}, Total Steps = {} ####'.format(serial,len(thermo_data['Step'])),end='')
  77.     print(Style.RESET_ALL)
  78.  
  79.  
  80.     return thermo_data      # Returns the whole dictionary
  81.  
  82.  
  83. ##############
  84. #   Created by Shihab from here
  85. #   Date: 4/18/2023
  86. ##############
  87.  
  88.  
  89.  
  90. def thermo_dict_v2(filename, serial):              
  91.     ## Local Function That can be called ##
  92.     def thermo_serial(filename,serial):
  93.         with open(filename, 'r') as f:
  94.             start = 0
  95.             thermo_data = {}
  96.    
  97.             for step, line in enumerate(f):
  98.                 #print (line)
  99.                 if line.startswith('Memory usage per processor') or line.startswith('Per MPI rank memory allocation'):   # looks for this line in the file
  100.                     #print('start')
  101.                     start += 1      # seed for start taking in data
  102.                     data_row = 0    # this is equal to the line number of the data
  103.                     thermo_headers = []     # thermo information in log files
  104.                     continue
  105.                 if start == serial:     # if the code reaches the desired portion of the log file
  106.                     data_row += 1
  107.                     data = line.split()
  108.                     if data_row == 1:   # in the first line you have the headers
  109.                         for i in (data):
  110.                             if i not in thermo_headers:
  111.                                 thermo_headers.append(i)    # creating a list of str of headers
  112.                                 thermo_data[i] = []         # Creating dictionary keys named after each thermodynamic property
  113.                             else:
  114.                                 # There are identical thermodynamic keywords as header
  115.                                 name = i + '_' + str(data.index(i) + 1)
  116.                                 thermo_headers.append(name)
  117.                                 thermo_data[name] = []
  118.                                 showwarning('Log file has same Thermodynamic keyword ' + str(i),
  119.                                             UserWarning, 'log_parser_FHB.py', 31)
  120.    
  121.                         #print ('len', len(thermo_data), thermo_data)
  122.    
  123.                     elif data_row > 1:      # this is where the data information starts in the log file
  124.                         #print (start)
  125.                         for i in range(0, len(data)):
  126.                             try:
  127.                                 data[i] = float(data[i])  # making the str to float
  128.    
  129.                                 if len(data) != len(thermo_headers):    # checking if the data line is complete
  130.                                     showwarning('Line number: ' + str(step+1) + ' in the log file is incomplete.',
  131.                                                 UserWarning, 'log_parser.py', 46)
  132.                                     #print (data)
  133.                                     break
  134.                                 else:
  135.                                     thermo_data[thermo_headers[i]].append(
  136.                                         data[i])  # putting in the data info in respective header's dict
  137.                             except:
  138.                                 start += 1
  139.                                 #print ('breaking')
  140.                                 break  # if data lines end, you get str again, this terminates taking any more data
  141.         return thermo_data
  142.  
  143.    
  144.     if type(serial) in [list,tuple]:
  145.         result = {}
  146.         for s in serial:
  147.             thermo = thermo_serial(filename,s)
  148.            
  149.             for key,value in thermo.items():
  150.                 if key in result.keys():
  151.                     result[key] +=thermo[key]
  152.                 else:
  153.                     result[key] = thermo[key]
  154.          
  155.     else:
  156.         result = thermo_serial(filename, serial)
  157.            
  158.            
  159.     from colorama import Fore, Style
  160.     print(Fore.CYAN + '#### From log_parser: Serial = {}, Total Steps = {} ####'.format(serial,len(result['Step'])),end='')
  161.     print(Style.RESET_ALL)
  162.  
  163.  
  164.     return result      # Returns the whole dictionary
  165.  
  166.  
  167. def thermo_panda(logfile, serial,
  168.                  start_string = 'Per MPI',
  169.                  end_string   = 'Loop time',
  170.                  zero_ref : str = None):
  171.     '''
  172.    zero_ref: str
  173.    Specifies which variables to apply zero-referencing to.
  174.    Options include:
  175.        - "energy": Apply zero-referencing to all energy (tot, pe, ke) columns.
  176.        - "time": Apply zero-referencing to time values.
  177.        - "energy+time" or "time+energy": Apply zero-referencing to both energy and time.
  178.    The values can be combined using an underscore (+) in any order.
  179.    '''
  180.    
  181.     timestep=None # starting None value
  182.    
  183.     start_lines  = []
  184.     end_lines    = []
  185.     with open(logfile, 'r') as file:
  186.         for i, line in enumerate(file):
  187.             if start_string in line:
  188.                 start_lines.append(i)
  189.             if end_string in line:
  190.                 end_lines.append(i)
  191.            
  192.             # getting timestep
  193.             if line.strip().startswith('timestep'):
  194.                 try:
  195.                     timestep=float(line.split('#')[0].split()[1])
  196.                 except:
  197.                     pass
  198.                 else:
  199.                     print(f'timestep found from the log file: {timestep}')
  200.    
  201.     if timestep is None:
  202.         raise ValueError("No 'timestep' value is found")
  203.                
  204.     if len(start_lines)!=len(end_lines):
  205.         print('Warning: Log file is incomplete')
  206.         end_lines.append(i)
  207.        
  208.     feed = list(zip(start_lines,end_lines))  
  209.    
  210.     if serial=='all':
  211.         thermo_list = []  # Create an empty list to store dataframes
  212.         for f in feed:
  213.             start, end = f
  214.             # Read each serial and append it to the list of thermos
  215.             thermo_part = pd.read_csv(logfile, sep=r'\s+', skiprows=start+1,
  216.                                       nrows=end-start-2)
  217.             thermo_list.append(thermo_part)  # Append the read data to the list
  218.        
  219.         # Combine all the individual thermos into one dataframe
  220.         thermo = pd.concat(thermo_list, ignore_index=True)
  221.        
  222.     elif isinstance(serial,int):
  223.         if serial>len(feed):
  224.             raise ValueError(f'Only {len(feed)} serial exists but found {serial}')
  225.            
  226.         start, end = feed[serial-1]
  227.         thermo = pd.read_csv(logfile,sep=r'\s+',skiprows=start+1,
  228.                            nrows=end-start-2)
  229.        
  230.     elif isinstance(serial,list):
  231.         if any(s > len(feed) for s in serial):
  232.             raise ValueError('Found a serial number greater than '
  233.                              f'the total number of serials ({len(feed)}).')
  234.        
  235.         # check what if serials are not consecutive
  236.         # under construction
  237.        
  238.         thermo_list = []  # Create an empty list to store dataframes
  239.  
  240.         for s in serial:
  241.             start, end = feed[s-1]
  242.             # Read each serial and append it to the list of thermos
  243.             thermo_part = pd.read_csv(logfile, sep=r'\s+', skiprows=start+1,
  244.                                       nrows=end-start-2)
  245.             thermo_list.append(thermo_part)  # Append the read data to the list
  246.        
  247.         # Combine all the individual thermos into one dataframe
  248.         thermo = pd.concat(thermo_list, ignore_index=True)
  249.            
  250.         print('Code is under construction..')
  251.     else:
  252.         raise TypeError("Serial must be a single int or an array of int or 'all'")
  253.    
  254.     # Time column
  255.     ps = thermo['Step']*timestep/1000
  256.     thermo['Time'] = ps
  257.        
  258.     if zero_ref:
  259.         zrefs = zero_ref.split('+')
  260.         for z in zrefs:
  261.             if z.lower()=='energy':
  262.                 energy_columns = ['PotEng', 'TotEng', 'KinEng']
  263.                 for col in energy_columns:
  264.                     if col in thermo.columns:
  265.                         thermo[col] = thermo[col] - thermo[col].min()
  266.                        
  267.             elif z.lower()=='time':
  268.                 if 'Time' in thermo.columns:
  269.                     thermo['Time'] = thermo['Time'] - thermo['Time'].min()
  270.            
  271.             else:
  272.  
  273.                 warn(f"The 'zero_ref' parameter '{z}' is not recognized. "
  274.                     "Please use 'energy', 'time', or a combination of them.",
  275.                     UserWarning
  276.                 )
  277.                 print()
  278.  
  279.     return thermo
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!