|
1
|
|
|
""" |
|
2
|
|
|
Data Manipulation class |
|
3
|
|
|
""" |
|
4
|
|
|
# package to facilitate operating system operations |
|
5
|
|
|
import os |
|
6
|
|
|
# package |
|
7
|
|
|
import pathlib |
|
8
|
|
|
# package facilitating Data Frames manipulation |
|
9
|
|
|
import pandas as pd |
|
10
|
|
|
|
|
11
|
|
|
|
|
12
|
|
|
class DataManipulator: |
|
13
|
|
|
|
|
14
|
|
|
def fn_apply_query_to_data_frame(self, local_logger, timmer, data_frame, extract_params): |
|
15
|
|
|
timmer.start() |
|
16
|
|
|
query_expression = '' |
|
17
|
|
|
if extract_params['filter_to_apply'] == 'equal': |
|
18
|
|
|
local_logger.debug('Will retain only values equal with "' |
|
19
|
|
|
+ extract_params['filter_values'] + '" within the field "' |
|
20
|
|
|
+ extract_params['column_to_filter'] + '"') |
|
21
|
|
|
query_expression = '`' + extract_params['column_to_filter'] + '` == "' \ |
|
22
|
|
|
+ extract_params['filter_values'] + '"' |
|
23
|
|
|
elif extract_params['filter_to_apply'] == 'different': |
|
24
|
|
|
local_logger.debug('Will retain only values different than "' |
|
25
|
|
|
+ extract_params['filter_values'] + '" within the field "' |
|
26
|
|
|
+ extract_params['column_to_filter'] + '"') |
|
27
|
|
|
query_expression = '`' + extract_params['column_to_filter'] + '` != "' \ |
|
28
|
|
|
+ extract_params['filter_values'] + '"' |
|
29
|
|
|
elif extract_params['filter_to_apply'] == 'multiple_match': |
|
30
|
|
|
local_logger.debug('Will retain only values equal with "' |
|
31
|
|
|
+ extract_params['filter_values'] + '" within the field "' |
|
32
|
|
|
+ extract_params['column_to_filter'] + '"') |
|
33
|
|
|
query_expression = '`' + extract_params['column_to_filter'] + '` in ["' \ |
|
34
|
|
|
+ '", "'.join(extract_params['filter_values'].values()) \ |
|
35
|
|
|
+ '"]' |
|
36
|
|
|
local_logger.debug('Query expression to apply is: ' + query_expression) |
|
37
|
|
|
data_frame.query(query_expression, inplace = True) |
|
38
|
|
|
timmer.stop() |
|
39
|
|
|
return data_frame |
|
40
|
|
|
|
|
41
|
|
|
def fn_build_relevant_file_list(self, local_logger, timmer, in_folder, matching_pattern): |
|
42
|
|
|
timmer.start() |
|
43
|
|
|
local_logger.info('Will list all files within ' + in_folder |
|
44
|
|
|
+ ' folder looking for ' + matching_pattern + ' as matching pattern') |
|
45
|
|
|
list_files = [] |
|
46
|
|
|
file_counter = 0 |
|
47
|
|
|
if os.path.isdir(in_folder): |
|
48
|
|
|
working_path = pathlib.Path(in_folder) |
|
49
|
|
|
for current_file in working_path.iterdir(): |
|
50
|
|
|
if current_file.is_file() and current_file.match(matching_pattern): |
|
51
|
|
|
list_files.append(file_counter) |
|
52
|
|
|
list_files[file_counter] = str(current_file.absolute()) |
|
53
|
|
|
file_counter = file_counter + 1 |
|
54
|
|
|
local_logger.info('Relevant CSV files from ' + in_folder + ' folder were identified!') |
|
55
|
|
|
local_logger.info(list_files) |
|
56
|
|
|
timmer.stop() |
|
57
|
|
|
return list_files |
|
58
|
|
|
|
|
59
|
|
|
def fn_load_file_list_to_data_frame(self, local_logger, timmer, file_list, csv_delimiter): |
|
60
|
|
|
timmer.start() |
|
61
|
|
|
combined_csv = pd.concat([pd.read_csv(filepath_or_buffer = current_file, |
|
62
|
|
|
delimiter = csv_delimiter, |
|
63
|
|
|
cache_dates = True, |
|
64
|
|
|
index_col = None, |
|
65
|
|
|
memory_map = True, |
|
66
|
|
|
low_memory = False, |
|
67
|
|
|
encoding = 'utf-8', |
|
68
|
|
|
) for current_file in file_list]) |
|
69
|
|
|
local_logger.info('All relevant files were merged into a Pandas Data Frame') |
|
70
|
|
|
timmer.stop() |
|
71
|
|
|
return combined_csv |
|
72
|
|
|
|
|
73
|
|
|
def fn_move_files(self, local_logger, timmer, source_folder, match_pattern, destination_folder): |
|
74
|
|
|
csv_file_names = self.fn_build_relevant_file_list(local_logger, timmer, |
|
75
|
|
|
source_folder, match_pattern) |
|
76
|
|
|
timmer.start() |
|
77
|
|
|
for current_file in csv_file_names: |
|
78
|
|
|
new_file_name = current_file.replace(source_folder, destination_folder) |
|
79
|
|
|
os.rename(current_file, new_file_name) |
|
80
|
|
|
local_logger.info('File ' + current_file + ' has just been renamed as ' + new_file_name) |
|
81
|
|
|
timmer.stop() |
|
82
|
|
|
|
|
83
|
|
|
def fn_store_data_frame_to_file(self, local_logger, timmer, input_data_frame, |
|
84
|
|
|
destination_file_name, csv_delimiter): |
|
85
|
|
|
timmer.start() |
|
86
|
|
|
input_data_frame.to_csv(path_or_buf = destination_file_name, |
|
87
|
|
|
sep = csv_delimiter, |
|
88
|
|
|
header = True, |
|
89
|
|
|
index = False, |
|
90
|
|
|
encoding = 'utf-8') |
|
91
|
|
|
local_logger.info('Data frame has just been saved to file "' + destination_file_name + '"') |
|
92
|
|
|
timmer.stop() |
|
93
|
|
|
|
danielgp /
db-extractor
