1
|
import inspect
|
2
|
from shared_types import StringSetType
|
3
|
from Utilities.CSV import csv_data_line
|
4
|
|
5
|
# Path to processed data
|
6
|
PROCESSED_DATA_PATH = "ProcessedData/"
|
7
|
|
8
|
|
9
|
def get_unique_names_from_file(filename: str,
|
10
|
column_number: int) -> StringSetType:
|
11
|
"""
|
12
|
Extract set of unique names from file
|
13
|
Args:
|
14
|
filename: path to processed file
|
15
|
column_number: unique names are expected in csv file on column_number
|
16
|
|
17
|
Returns:
|
18
|
set of unique names
|
19
|
"""
|
20
|
# create set of unique names
|
21
|
name_set = set()
|
22
|
|
23
|
with open(filename, "r") as file:
|
24
|
# go through every line of line
|
25
|
for x in file:
|
26
|
# split by csv splitter ;
|
27
|
array = x.split(";")
|
28
|
# add string from chosen column to set
|
29
|
name_set.add(array[column_number])
|
30
|
|
31
|
return name_set
|
32
|
|
33
|
|
34
|
def export_data_to_csv(filename: str, data_dict) -> None:
|
35
|
"""
|
36
|
Takes data_dict and export it into a csv file
|
37
|
Args:
|
38
|
filename: name of exported file
|
39
|
data_dict: dictionary containing data from DatasetProcessor
|
40
|
"""
|
41
|
with open(PROCESSED_DATA_PATH + filename[12:], "w+") as file:
|
42
|
|
43
|
for date in data_dict:
|
44
|
if len(date) != 13:
|
45
|
raise ValueError(
|
46
|
"Invalid date format for key value --> YYYY-mm-dd-hh expected!"
|
47
|
)
|
48
|
for data in data_dict[date]:
|
49
|
csv_line = data_dict[date][data]
|
50
|
if not isinstance(csv_line, csv_data_line.CSVDataLine):
|
51
|
raise ValueError(
|
52
|
"data_dict is expected to have CSVDataLine as values")
|
53
|
file.write(csv_line.to_csv() + '\n')
|