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