Last active
November 18, 2018 11:34
-
-
Save myrddian/d9ab8ddc5afa48a26b3cf5e76fe15d0a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
excel_file = 'excel.xlsx' | |
out_file = 'excel.csv' | |
#External Global variables | |
__col_size__ = 14 | |
__i_start__ = 6 | |
__c_size__ = 202 | |
"""Read the country file and parse its contents""" | |
def read_country_data(xls_file, country_size, index_start, output_file, col_size): | |
print('Conversion Starting') | |
#Open using XLRD | |
book = xlrd.open_workbook(xls_file) | |
first_sheet = book.sheet_by_index(0) | |
output_conversion = open(output_file, "w") | |
#Write the CSV header | |
write_header(output_conversion,col_size) | |
#Loop throught the countries, get index + offset, read row parse to write_line | |
for x in range(country_size): | |
row_items = first_sheet.row_values( x + index_start) | |
write_line(output_conversion,row_items,col_size) | |
#Flush and close file handles | |
output_conversion.flush() | |
output_conversion.close() | |
print('Conversion completed') | |
"""Writes a header for the CSV""" | |
def write_header(out_file, col_num): | |
header = "Country Name" | |
for x in range(col_num): | |
header = header +','+str(x) | |
header += '\n' | |
out_file.write(header) | |
"""Writes the line out given the items field, col_size specifies how many variables to | |
write before the function stops""" | |
def write_line(out_file, items, col_size): | |
line = "" | |
var_count = 0 | |
rsv_str = "–" | |
skip = "x" | |
#Start through the items in the row | |
for x in range(len(items)): | |
#Ignore less than 1, this is to keep the offsets sane | |
if(x < 1 ): | |
continue | |
else: | |
#Write the country | |
if(x == 1): | |
line += items[x] | |
else: | |
#Start processing the variables, if string process here | |
if(type(items[x]) == str): | |
if(items[x] == rsv_str): | |
line += "," | |
var_count+=1 | |
elif(items[x] == skip): | |
continue | |
#Integer here, remove any trailing zeros | |
elif(items[x].is_integer()): | |
line += ","+str(int(items[x])) | |
var_count+=1 | |
#Float use round to set the float as XLS output | |
else: | |
line += ","+str(round(items[x])) | |
var_count+=1 | |
if(var_count == col_size): | |
break | |
line+='\n' | |
out_file.write(line) | |
read_country_data(excel_file,__c_size__,__i_start__,out_file,__col_size__) | |
df = pd.read_csv(out_file) | |
print(df.head()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment