Use Python to find specific files from one location to another location

import os
import shutil
from fnmatch import fnmatch


root = r'H:'
dst_dir = r'G:'
pattern = "*.tif"
i = 1
for path, subdirs, files in os.walk(root):
  for name in files:
    if fnmatch(name, pattern):
      current_file = os.path.join(path, name)
      shutil.copy(current_file, dst_dir)
      dst_file = os.path.join(dst_dir, name)
      dst_new_file_name = os.path.join(dst_dir, "["+ str(i) +"] " + name)
      os.rename(dst_file, dst_new_file_name)
      print(os.path.join(path, name))
      i += 1

Python Split a large file into multiple files....

def file_split(filehandler, delimiter='\t', 
               row_limit=25, 
               output_name_template='output_%s.txt', 
               output_path='F:\\Novus\\Decision Tree\\Data\\', keep_headers=True):
    import csv
    reader = csv.reader(filehandler, delimiter=delimiter)   #reading the source file using csv module
    current_piece = 1                                       #identifier of the out data int number
    current_out_path = ''.join([output_path, output_name_template % current_piece]) #create the full path of the out data
    
    of = open(current_out_path, 'w')                            #open the source data
    current_out_writer = csv.writer(of, delimiter=delimiter)    #put the source data into a variable
    current_limit = row_limit                                   #set the max row limit
    
    if keep_headers:                            #check if the header option is True or False
        headers = next(reader)
        current_out_writer.writerow(headers)    #if header is True write the header into the out file
        
    for i, row in enumerate(reader):
        if i + 1 > current_limit:
            of.close()
            current_piece += 1
            current_limit = row_limit * current_piece
            current_out_path = ''.join([output_path, output_name_template % current_piece])
            of = open(current_out_path, 'w')
            current_out_writer = csv.writer(of, delimiter=delimiter)  #if the row limit is achieved then create a new out file
            
            if keep_headers:
                current_out_writer.writerow(headers)
        current_out_writer.writerow(row)
    of.close()
        
               
file_split(open(r'F:\Novus\Decision Tree\Data\iris_data.txt', 'r'), row_limit=100,
           output_name_template='iris_split_%s.txt',
           output_path='F:\\Novus\\Decision Tree\\Data\\')

Python dask dataframe for large data

The data that I am using here fits in memory, but dask will work even when the data is larger than memory.

import dask.dataframe as dd

df = dd.read_csv(r'F:\Novus\Decision Tree\Data\iris_data_copy.txt', 
                sep='\t', header=0, encoding='latin-1', blocksize=100**4)
df.npartitions

df_summary = df.groupby(['Species']).mean()
print(df_summary.compute())