|
1
|
|
|
""" |
|
2
|
|
|
Data Input Output class |
|
3
|
|
|
""" |
|
4
|
|
|
# package to add support for multi-language (i18n) |
|
5
|
|
|
import gettext |
|
6
|
|
|
# package to handle files/folders and related metadata/operations |
|
7
|
|
|
import os |
|
8
|
|
|
# package facilitating Data Frames manipulation |
|
9
|
|
|
import pandas as pd |
|
10
|
|
|
|
|
11
|
|
|
|
|
12
|
|
|
class DataInputOutput: |
|
13
|
|
|
lcl = None |
|
14
|
|
|
|
|
15
|
|
|
def __init__(self, default_language='en_US'): |
|
16
|
|
|
current_script = os.path.basename(__file__).replace('.py', '') |
|
17
|
|
|
lang_folder = os.path.join(os.path.dirname(__file__), current_script + '_Locale') |
|
18
|
|
|
self.lcl = gettext.translation(current_script, lang_folder, languages=[default_language]) |
|
19
|
|
|
|
|
20
|
|
|
def fn_file_save_error_logger(self, local_logger, in_file_details, error_details): |
|
21
|
|
|
if error_details is None: |
|
22
|
|
|
local_logger.info(self.lcl.gettext( |
|
23
|
|
|
'Pandas Data Frame has just been saved to file "{file_name}", ' |
|
24
|
|
|
+ 'considering {file_type} as file type') |
|
25
|
|
|
.replace('{file_name}', in_file_details['name']) |
|
26
|
|
|
.replace('{file_type}', in_file_details['format'])) |
|
27
|
|
|
else: |
|
28
|
|
|
local_logger.error( |
|
29
|
|
|
self.lcl.gettext( |
|
30
|
|
|
'Error encountered on saving Pandas Data Frame ' |
|
31
|
|
|
+ 'into a {file_type} file type (see below)') |
|
32
|
|
|
.replace('{file_type}', in_file_details['format'].upper())) |
|
33
|
|
|
local_logger.error(error_details) |
|
34
|
|
|
|
|
35
|
|
|
def fn_load_file_list_to_data_frame(self, local_logger, timmer, file_list, csv_delimiter): |
|
36
|
|
|
timmer.start() |
|
37
|
|
|
out_data_frame = pd.concat([pd.read_csv(filepath_or_buffer=current_file, |
|
38
|
|
|
delimiter=csv_delimiter, |
|
39
|
|
|
cache_dates=True, |
|
40
|
|
|
index_col=None, |
|
41
|
|
|
memory_map=True, |
|
42
|
|
|
low_memory=False, |
|
43
|
|
|
encoding='utf-8', |
|
44
|
|
|
) for current_file in file_list]) |
|
45
|
|
|
local_logger.info(self.lcl.gettext( |
|
46
|
|
|
'All relevant files ({files_counted}) were merged into a Pandas Data Frame') |
|
47
|
|
|
.replace('{files_counted}', str(len(file_list)))) |
|
48
|
|
|
timmer.stop() |
|
49
|
|
|
return out_data_frame |
|
50
|
|
|
|
|
51
|
|
|
def fn_save_data_frame_to_csv(self, local_logger, in_data_frame, in_file_details): |
|
52
|
|
|
if in_file_details['format'].lower() == 'csv': |
|
53
|
|
|
if 'field-delimiter' not in in_file_details: |
|
54
|
|
|
in_file_details['field-delimiter'] = os.pathsep |
|
55
|
|
|
try: |
|
56
|
|
|
in_data_frame.to_csv(path_or_buf=in_file_details['name'], |
|
57
|
|
|
sep=in_file_details['field-delimiter'], |
|
58
|
|
|
header=True, |
|
59
|
|
|
index=False, |
|
60
|
|
|
encoding='utf-8') |
|
61
|
|
|
self.fn_file_save_error_logger(local_logger, in_file_details, None) |
|
62
|
|
|
except Exception as err: |
|
63
|
|
|
self.fn_file_save_error_logger(local_logger, in_file_details, err) |
|
64
|
|
|
|
|
65
|
|
View Code Duplication |
def fn_save_data_frame_to_excel(self, local_logger, in_data_frame, in_file_details): |
|
|
|
|
|
|
66
|
|
|
if in_file_details['format'].lower() == 'excel': |
|
67
|
|
|
if 'compression' not in in_file_details: |
|
68
|
|
|
in_file_details['compression'] = 'gzip' |
|
69
|
|
|
try: |
|
70
|
|
|
in_data_frame.to_pickle(path=in_file_details['name'], |
|
71
|
|
|
compression=in_file_details['compression']) |
|
72
|
|
|
self.fn_file_save_error_logger(local_logger, in_file_details, None) |
|
73
|
|
|
except Exception as err: |
|
74
|
|
|
self.fn_file_save_error_logger(local_logger, in_file_details, err) |
|
75
|
|
|
|
|
76
|
|
View Code Duplication |
def fn_save_data_frame_to_pickle(self, local_logger, in_data_frame, in_file_details): |
|
|
|
|
|
|
77
|
|
|
if in_file_details['format'].lower() == 'pickle': |
|
78
|
|
|
if 'compression' not in in_file_details: |
|
79
|
|
|
in_file_details['compression'] = 'gzip' |
|
80
|
|
|
try: |
|
81
|
|
|
in_data_frame.to_pickle(path=in_file_details['name'], |
|
82
|
|
|
compression=in_file_details['compression']) |
|
83
|
|
|
self.fn_file_save_error_logger(local_logger, in_file_details, None) |
|
84
|
|
|
except Exception as err: |
|
85
|
|
|
self.fn_file_save_error_logger(local_logger, in_file_details, err) |
|
86
|
|
|
|
|
87
|
|
|
def fn_store_data_frame_to_file(self, local_logger, timmer, in_data_frame, in_file_details): |
|
88
|
|
|
timmer.start() |
|
89
|
|
|
self.fn_store_data_frame_to_file_validation(local_logger, in_file_details) |
|
90
|
|
|
if 'format' in in_file_details: |
|
91
|
|
|
self.fn_save_data_frame_to_csv(local_logger, in_data_frame, in_file_details) |
|
92
|
|
|
self.fn_save_data_frame_to_excel(local_logger, in_data_frame, in_file_details) |
|
93
|
|
|
self.fn_save_data_frame_to_pickle(local_logger, in_data_frame, in_file_details) |
|
94
|
|
|
timmer.stop() |
|
95
|
|
|
|
|
96
|
|
|
def fn_store_data_frame_to_file_validation(self, local_logger, in_file_details): |
|
97
|
|
|
if 'format' in in_file_details: |
|
98
|
|
|
implemented_file_formats = ['csv', 'excel', 'pickle'] |
|
99
|
|
|
given_format = in_file_details['format'].lower() |
|
100
|
|
|
if given_format not in implemented_file_formats: |
|
101
|
|
|
local_logger.error(self.lcl.gettext( |
|
102
|
|
|
'File "format" attribute has a value of "{format_value}" ' |
|
103
|
|
|
+ 'which is not among currently implemented values: ' |
|
104
|
|
|
+ '"{implemented_file_formats}", therefore file saving is not possible') |
|
105
|
|
|
.replace('{format_value}', given_format) |
|
106
|
|
|
.replace('{implemented_file_formats}', |
|
107
|
|
|
'", "'.join(implemented_file_formats))) |
|
108
|
|
|
else: |
|
109
|
|
|
local_logger.error(self.lcl.gettext('File "format" attribute is mandatory ' |
|
110
|
|
|
+ 'in the file setting, but missing, ' |
|
111
|
|
|
+ 'therefore file saving is not possible')) |
|
112
|
|
|
|
danielgp /
db-extractor
Loading history...