|
1
|
|
|
""" |
|
2
|
|
|
DataOutput - class to handle disk file storage |
|
3
|
|
|
""" |
|
4
|
|
|
# package facilitating Data Frames manipulation |
|
5
|
|
|
import pandas |
|
6
|
|
|
|
|
7
|
|
|
|
|
8
|
|
|
class DataDiskRead: |
|
9
|
|
|
|
|
10
|
|
|
@staticmethod |
|
11
|
|
|
def fn_internal_load_csv_file_into_data_frame(in_dict): |
|
12
|
|
|
if in_dict['format'].lower() == 'csv': |
|
13
|
|
|
try: |
|
14
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
15
|
|
|
[pandas.read_csv(filepath_or_buffer = crt_file, |
|
16
|
|
|
delimiter = in_dict['field delimiter'], |
|
17
|
|
|
cache_dates = True, |
|
18
|
|
|
index_col = None, |
|
19
|
|
|
memory_map = True, |
|
20
|
|
|
low_memory = False, |
|
21
|
|
|
encoding = 'utf-8', |
|
22
|
|
|
) for crt_file in in_dict['files list']], |
|
23
|
|
|
sort = False) |
|
24
|
|
|
except Exception as err: |
|
25
|
|
|
in_dict['error details'] = err |
|
26
|
|
|
return in_dict |
|
27
|
|
|
|
|
28
|
|
|
@staticmethod |
|
29
|
|
|
def fn_internal_load_excel_file_into_data_frame(in_dict): |
|
30
|
|
|
if in_dict['format'].lower() == 'excel': |
|
31
|
|
|
try: |
|
32
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
33
|
|
|
[pandas.read_excel(io = crt_file, |
|
34
|
|
|
verbose = True, |
|
35
|
|
|
) for crt_file in in_dict['files list']], |
|
36
|
|
|
sort = False) |
|
37
|
|
|
except Exception as err: |
|
38
|
|
|
in_dict['error details'] = err |
|
39
|
|
|
return in_dict |
|
40
|
|
|
|
|
41
|
|
|
@staticmethod |
|
42
|
|
|
def fn_internal_load_json_file_into_data_frame(in_dict): |
|
43
|
|
|
if in_dict['format'].lower() == 'json': |
|
44
|
|
|
try: |
|
45
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
46
|
|
|
[pandas.read_json(path_or_buf = crt_file, |
|
47
|
|
|
compression = in_dict['compression'], |
|
48
|
|
|
) for crt_file in in_dict['files list']], |
|
49
|
|
|
sort = False) |
|
50
|
|
|
except Exception as err: |
|
51
|
|
|
in_dict['error details'] = err |
|
52
|
|
|
return in_dict |
|
53
|
|
|
|
|
54
|
|
|
@staticmethod |
|
55
|
|
|
def fn_internal_load_parquet_file_into_data_frame(in_dict): |
|
56
|
|
|
if in_dict['format'].lower() == 'parquet': |
|
57
|
|
|
try: |
|
58
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
59
|
|
|
[pandas.read_parquet(path = crt_file, |
|
60
|
|
|
) for crt_file in in_dict['files list']], |
|
61
|
|
|
sort = False) |
|
62
|
|
|
except Exception as err: |
|
63
|
|
|
in_dict['error details'] = err |
|
64
|
|
|
return in_dict |
|
65
|
|
|
|
|
66
|
|
|
@staticmethod |
|
67
|
|
|
def fn_internal_load_pickle_file_into_data_frame(in_dict): |
|
68
|
|
|
if in_dict['format'].lower() == 'pickle': |
|
69
|
|
|
try: |
|
70
|
|
|
in_dict['out data frame'] = pandas.concat( |
|
71
|
|
|
[pandas.read_pickle(filepath_or_buffer = crt_file, |
|
72
|
|
|
compression = in_dict['compression'], |
|
73
|
|
|
) for crt_file in in_dict['files list']], |
|
74
|
|
|
sort = False) |
|
75
|
|
|
except Exception as err: |
|
76
|
|
|
in_dict['error details'] = err |
|
77
|
|
|
return in_dict |
|
78
|
|
|
|
danielgp /
db-extractor
