|
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 |
|
10
|
|
|
|
|
11
|
|
|
|
|
12
|
|
|
class DataInputOutput: |
|
13
|
|
|
locale = None |
|
14
|
|
|
|
|
15
|
|
|
def __init__(self, in_language = 'en_US'): |
|
16
|
|
|
file_parts = os.path.normpath(os.path.abspath(__file__)).replace('\\', os.path.altsep) \ |
|
17
|
|
|
.split(os.path.altsep) |
|
18
|
|
|
locale_domain = file_parts[(len(file_parts) - 1)].replace('.py', '') |
|
19
|
|
|
locale_folder = os.path.normpath(os.path.join( |
|
20
|
|
|
os.path.join(os.path.altsep.join(file_parts[:-2]), 'project_locale'), |
|
21
|
|
|
locale_domain)) |
|
22
|
|
|
self.locale = gettext.translation(locale_domain, localedir = locale_folder, |
|
23
|
|
|
languages = [in_language], fallback = True) |
|
24
|
|
|
|
|
25
|
|
|
@staticmethod |
|
26
|
|
|
def fn_add_missing_defaults_to_dict_message(in_dict): |
|
27
|
|
|
if 'field delimiter' not in in_dict: |
|
28
|
|
|
in_dict['field delimiter'] = os.pathsep |
|
29
|
|
|
if 'compression' not in in_dict: |
|
30
|
|
|
in_dict['compression'] = 'infer' |
|
31
|
|
|
return in_dict |
|
32
|
|
|
|
|
33
|
|
|
def fn_build_feedback_for_logger(self, operation_details): |
|
34
|
|
|
messages = {} |
|
35
|
|
|
if operation_details['operation'] == 'load': |
|
36
|
|
|
files_counted = str(operation_details['files counted']) |
|
37
|
|
|
messages = { |
|
38
|
|
|
'failed' : self.locale.gettext( |
|
39
|
|
|
'Error encountered on loading Pandas Data Frame ' |
|
40
|
|
|
+ 'from {file_type} file type (see below)') |
|
41
|
|
|
.replace('{file_type}', operation_details['format'].upper()), |
|
42
|
|
|
'success': self.locale.gettext( |
|
43
|
|
|
'All {files_counted} files of type {file_type} ' |
|
44
|
|
|
+ 'successfully added to a Pandas Data Frame') |
|
45
|
|
|
.replace('{files_counted}', files_counted) |
|
46
|
|
|
.replace('{file_type}', operation_details['format'].upper()) |
|
47
|
|
|
} |
|
48
|
|
|
elif operation_details['operation'] == 'save': |
|
49
|
|
|
messages = { |
|
50
|
|
|
'failed' : self.locale.gettext( |
|
51
|
|
|
'Error encountered on saving Pandas Data Frame ' |
|
52
|
|
|
+ 'into a {file_type} file type (see below)') |
|
53
|
|
|
.replace('{file_type}', operation_details['format'].upper()), |
|
54
|
|
|
'success': self.locale.gettext( |
|
55
|
|
|
'Pandas Data Frame has just been saved to file "{file_name}", ' |
|
56
|
|
|
+ 'considering {file_type} as file type') |
|
57
|
|
|
.replace('{file_name}', operation_details['name']) |
|
58
|
|
|
.replace('{file_type}', operation_details['format'].upper()), |
|
59
|
|
|
} |
|
60
|
|
|
return messages |
|
61
|
|
|
|
|
62
|
|
|
def fn_file_operation_logger(self, local_logger, in_logger_dict): |
|
63
|
|
|
messages = self.fn_build_feedback_for_logger(in_logger_dict) |
|
64
|
|
|
if in_logger_dict['error details'] is None: |
|
65
|
|
|
local_logger.info(messages['success']) |
|
66
|
|
|
else: |
|
67
|
|
|
local_logger.error(messages['failed']) |
|
68
|
|
|
local_logger.error(in_logger_dict['error details']) |
|
69
|
|
|
|
|
70
|
|
|
def fn_load_file_into_data_frame(self, in_logger, timer, in_dict): |
|
71
|
|
|
timer.start() |
|
72
|
|
|
if self.fn_store_data_frame_to_file_validation(in_logger, in_dict): |
|
73
|
|
|
in_dict = self.fn_add_missing_defaults_to_dict_message(in_dict) |
|
74
|
|
|
in_dict.update({'operation': 'load'}) |
|
75
|
|
|
in_dict = self.fn_pack_dict_message(in_dict, in_dict['file list']) |
|
76
|
|
|
in_dict = self.fn_internal_load_csv_file_into_data_frame(in_dict) |
|
77
|
|
|
in_dict = self.fn_internal_load_excel_file_into_data_frame(in_dict) |
|
78
|
|
|
in_dict = self.fn_internal_load_json_file_into_data_frame(in_dict) |
|
79
|
|
|
in_dict = self.fn_internal_load_parquet_file_into_data_frame(in_dict) |
|
80
|
|
|
in_dict = self.fn_internal_load_pickle_file_into_data_frame(in_dict) |
|
81
|
|
|
self.fn_file_operation_logger(in_logger, in_dict) |
|
82
|
|
|
timer.stop() |
|
83
|
|
|
return in_dict['out data frame'] |
|
84
|
|
|
|
|
85
|
|
|
@staticmethod |
|
86
|
|
|
def fn_internal_load_csv_file_into_data_frame(in_dict): |
|
87
|
|
|
if in_dict['format'].lower() == 'csv': |
|
88
|
|
|
try: |
|
89
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
90
|
|
|
[pandas.read_csv(filepath_or_buffer = crt_file, |
|
91
|
|
|
delimiter = in_dict['field delimiter'], |
|
92
|
|
|
cache_dates = True, |
|
93
|
|
|
index_col = None, |
|
94
|
|
|
memory_map = True, |
|
95
|
|
|
low_memory = False, |
|
96
|
|
|
encoding = 'utf-8', |
|
97
|
|
|
) for crt_file in in_dict['files list']], |
|
98
|
|
|
sort = False) |
|
99
|
|
|
except Exception as err: |
|
100
|
|
|
in_dict['error details'] = err |
|
101
|
|
|
return in_dict |
|
102
|
|
|
|
|
103
|
|
|
@staticmethod |
|
104
|
|
|
def fn_internal_load_excel_file_into_data_frame(in_dict): |
|
105
|
|
|
if in_dict['format'].lower() == 'excel': |
|
106
|
|
|
try: |
|
107
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
108
|
|
|
[pandas.read_excel(io = crt_file, |
|
109
|
|
|
verbose = True, |
|
110
|
|
|
) for crt_file in in_dict['files list']], |
|
111
|
|
|
sort = False) |
|
112
|
|
|
except Exception as err: |
|
113
|
|
|
in_dict['error details'] = err |
|
114
|
|
|
return in_dict |
|
115
|
|
|
|
|
116
|
|
|
@staticmethod |
|
117
|
|
|
def fn_internal_load_json_file_into_data_frame(in_dict): |
|
118
|
|
|
if in_dict['format'].lower() == 'json': |
|
119
|
|
|
try: |
|
120
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
121
|
|
|
[pandas.read_json(path_or_buf = crt_file, |
|
122
|
|
|
compression = in_dict['compression'], |
|
123
|
|
|
) for crt_file in in_dict['files list']], |
|
124
|
|
|
sort = False) |
|
125
|
|
|
except Exception as err: |
|
126
|
|
|
in_dict['error details'] = err |
|
127
|
|
|
return in_dict |
|
128
|
|
|
|
|
129
|
|
|
@staticmethod |
|
130
|
|
|
def fn_internal_load_parquet_file_into_data_frame(in_dict): |
|
131
|
|
|
if in_dict['format'].lower() == 'parquet': |
|
132
|
|
|
try: |
|
133
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
134
|
|
|
[pandas.read_parquet(path = crt_file, |
|
135
|
|
|
) for crt_file in in_dict['files list']], |
|
136
|
|
|
sort = False) |
|
137
|
|
|
except Exception as err: |
|
138
|
|
|
in_dict['error details'] = err |
|
139
|
|
|
return in_dict |
|
140
|
|
|
|
|
141
|
|
|
@staticmethod |
|
142
|
|
|
def fn_internal_load_pickle_file_into_data_frame(in_dict): |
|
143
|
|
|
if in_dict['format'].lower() == 'pickle': |
|
144
|
|
|
try: |
|
145
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
146
|
|
|
[pandas.read_pickle(path = crt_file, |
|
147
|
|
|
compression = in_dict['compression'], |
|
148
|
|
|
) for crt_file in in_dict['files list']], |
|
149
|
|
|
sort = False) |
|
150
|
|
|
except Exception as err: |
|
151
|
|
|
in_dict['error details'] = err |
|
152
|
|
|
return in_dict |
|
153
|
|
|
|
|
154
|
|
|
@staticmethod |
|
155
|
|
|
def fn_internal_store_data_frame_to_csv_file(in_dict): |
|
156
|
|
|
if in_dict['format'].lower() == 'csv': |
|
157
|
|
|
try: |
|
158
|
|
|
in_dict['in data frame'].to_csv(path_or_buf = in_dict['name'], |
|
159
|
|
|
sep = in_dict['field delimiter'], |
|
160
|
|
|
header = True, |
|
161
|
|
|
index = False, |
|
162
|
|
|
encoding = 'utf-8') |
|
163
|
|
|
except Exception as err: |
|
164
|
|
|
in_dict['error details'] = err |
|
165
|
|
|
return in_dict |
|
166
|
|
|
|
|
167
|
|
|
@staticmethod |
|
168
|
|
|
def fn_internal_store_data_frame_to_excel_file(in_dict): |
|
169
|
|
|
if in_dict['format'].lower() == 'excel': |
|
170
|
|
|
try: |
|
171
|
|
|
in_dict['in data frame'].to_excel(excel_writer = in_dict['name'], |
|
172
|
|
|
engine = 'xlsxwriter', |
|
173
|
|
|
freeze_panes = (1, 1), |
|
174
|
|
|
encoding = 'utf-8', |
|
175
|
|
|
index = False, |
|
176
|
|
|
verbose = True) |
|
177
|
|
|
except Exception as err: |
|
178
|
|
|
in_dict['error details'] = err |
|
179
|
|
|
return in_dict |
|
180
|
|
|
|
|
181
|
|
|
@staticmethod |
|
182
|
|
|
def fn_internal_store_data_frame_to_json_file(in_dict): |
|
183
|
|
|
if in_dict['format'].lower() == 'json': |
|
184
|
|
|
try: |
|
185
|
|
|
in_dict['in data frame'].to_json(path_or_buf = in_dict['name'], |
|
186
|
|
|
compression = in_dict['compression']) |
|
187
|
|
|
except Exception as err: |
|
188
|
|
|
in_dict['error details'] = err |
|
189
|
|
|
return in_dict |
|
190
|
|
|
|
|
191
|
|
|
@staticmethod |
|
192
|
|
|
def fn_internal_store_data_frame_to_parquet_file(in_dict): |
|
193
|
|
|
if in_dict['format'].lower() == 'parquet': |
|
194
|
|
|
try: |
|
195
|
|
|
in_dict['in data frame'].to_parquet(path = in_dict['name'], |
|
196
|
|
|
compression = in_dict['compression'], |
|
197
|
|
|
use_deprecated_int96_timestamps = True) |
|
198
|
|
|
except Exception as err: |
|
199
|
|
|
in_dict['error details'] = err |
|
200
|
|
|
return in_dict |
|
201
|
|
|
|
|
202
|
|
|
@staticmethod |
|
203
|
|
|
def fn_internal_store_data_frame_to_pickle_file(in_dict): |
|
204
|
|
|
if in_dict['format'].lower() == 'pickle': |
|
205
|
|
|
try: |
|
206
|
|
|
in_dict['in data frame'].to_pickle(path = in_dict['name'], |
|
207
|
|
|
compression = in_dict['compression']) |
|
208
|
|
|
except Exception as err: |
|
209
|
|
|
in_dict['error details'] = err |
|
210
|
|
|
return in_dict |
|
211
|
|
|
|
|
212
|
|
|
@staticmethod |
|
213
|
|
|
def fn_pack_dict_message(in_dict, in_file_list): |
|
214
|
|
|
if in_dict['format'].lower() in ('parquet', 'pickle') \ |
|
215
|
|
|
and in_dict['compression'].lower() == 'none': |
|
216
|
|
|
in_dict['compression'] = None |
|
217
|
|
|
return { |
|
218
|
|
|
'compression' : in_dict['compression'], |
|
219
|
|
|
'field delimiter': in_dict['field delimiter'], |
|
220
|
|
|
'files list' : in_file_list, |
|
221
|
|
|
'files counted' : len(in_file_list), |
|
222
|
|
|
'error details' : None, |
|
223
|
|
|
'format' : in_dict['format'], |
|
224
|
|
|
'name' : in_dict['name'], |
|
225
|
|
|
'in data frame' : None, |
|
226
|
|
|
'operation' : in_dict['operation'], |
|
227
|
|
|
'out data frame' : None, |
|
228
|
|
|
} |
|
229
|
|
|
|
|
230
|
|
|
def fn_store_data_frame_to_file(self, in_logger, timer, in_data_frame, in_dict): |
|
231
|
|
|
timer.start() |
|
232
|
|
|
if self.fn_store_data_frame_to_file_validation(in_logger, in_dict): |
|
233
|
|
|
in_dict = self.fn_add_missing_defaults_to_dict_message(in_dict) |
|
234
|
|
|
in_dict.update({'operation': 'save'}) |
|
235
|
|
|
in_dict = self.fn_pack_dict_message(in_dict, []) |
|
236
|
|
|
in_dict.update({'in data frame': in_data_frame}) |
|
237
|
|
|
# special case treatment |
|
238
|
|
|
in_dict = self.fn_internal_store_data_frame_to_csv_file(in_dict) |
|
239
|
|
|
in_dict = self.fn_internal_store_data_frame_to_excel_file(in_dict) |
|
240
|
|
|
in_dict = self.fn_internal_store_data_frame_to_json_file(in_dict) |
|
241
|
|
|
in_dict = self.fn_internal_store_data_frame_to_parquet_file(in_dict) |
|
242
|
|
|
in_dict = self.fn_internal_store_data_frame_to_pickle_file(in_dict) |
|
243
|
|
|
self.fn_file_operation_logger(in_logger, in_dict) |
|
244
|
|
|
timer.stop() |
|
245
|
|
|
|
|
246
|
|
|
def fn_store_data_frame_to_file_validation(self, local_logger, in_file_details): |
|
247
|
|
|
given_format_is_implemented = False |
|
248
|
|
|
if 'format' in in_file_details: |
|
249
|
|
|
implemented_file_formats = ['csv', 'excel', 'json', 'parquet', 'pickle'] |
|
250
|
|
|
given_format = in_file_details['format'].lower() |
|
251
|
|
|
given_format_is_implemented = True |
|
252
|
|
|
if given_format not in implemented_file_formats: |
|
253
|
|
|
given_format_is_implemented = False |
|
254
|
|
|
local_logger.error(self.locale.gettext( |
|
255
|
|
|
'File "format" attribute has a value of "{format_value}" ' |
|
256
|
|
|
+ 'which is not among currently implemented values: ' |
|
257
|
|
|
+ '"{implemented_file_formats}", ' |
|
258
|
|
|
+ 'therefore desired file operation is not possible') |
|
259
|
|
|
.replace('{format_value}', given_format) |
|
260
|
|
|
.replace('{implemented_file_formats}', |
|
261
|
|
|
'", "'.join(implemented_file_formats))) |
|
262
|
|
|
else: |
|
263
|
|
|
local_logger.error(self.locale.gettext( |
|
264
|
|
|
'File "format" attribute is mandatory in the file setting, but missing, ' |
|
265
|
|
|
+ 'therefore desired file operation is not possible')) |
|
266
|
|
|
return given_format_is_implemented |
|
267
|
|
|
|
danielgp /
db-extractor
