I Have a Script for data extraction from some CSV files and bifurcating the Data into different excel files. I using Ipython for the that and I m sure it using CPython as the Default interpreter.
But the script is taking too much time for the whole process to finish. Can someone please help to how use that script using the PyPy as i heard it is much faster than CPython. Script is something like this:
import pandas as pd
import xlsxwriter as xw
import csv
import pymsgbox as py
file1 = "vDashOpExel_Change_20150109.csv"
file2 = "vDashOpExel_T3Opened_20150109.csv"
path = "C:\Users\Abhishek\Desktop\Pandas Anlaysis"
def uniq(words):
seen = set()
for word in words:
l = word.lower()
if l in seen:
continue
seen.add(l)
yield word
def files(file_name):
df = pd.read_csv( path + '\\' + file_name, sep=',', encoding = 'utf-16')
final_frame = df.dropna(how='all')
file_list = list(uniq(list(final_frame['DOEClient'])))
return file_list, final_frame
def fill_data(f_list, frame1=None, frame2=None):
if f_list is not None:
for client in f_list:
writer = pd.ExcelWriter(path + '\\' + 'Accounts'+ '\\' + client + '.xlsx', engine='xlsxwriter')
if frame1 is not None:
data1 = frame1[frame1.DOEClient == client] # Filter the Data
data1.to_excel(writer,'Change',index=False, header=True) # Importing the Data to Excel File
if frame2 is not None:
data2 = frame2[frame2.DOEClient == client] # Filter the Data
data2.to_excel(writer,'Opened',index=False, header=True) # Importing the Data to Excel File
else:
py.alert('Please enter the First Parameter !!!', 'Error')
list1, frame1 = files(file1)
list2, frame2 = files(file2)
final_list = set(list1 + list2)