54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
|
import csv
|
||
|
|
|
||
|
|
def convert_dataset(input_file, output_file):
|
||
|
|
attributes = {
|
||
|
|
1: ["empty", "low", "medium", "high"],
|
||
|
|
2: ["empty", "full"],
|
||
|
|
3: ["none", "available"],
|
||
|
|
4: ["none", "available"],
|
||
|
|
5: ["unavailable", "available"],
|
||
|
|
6: ["low", "medium", "high"],
|
||
|
|
7: ["no", "yes"],
|
||
|
|
8: ["no", "yes"]
|
||
|
|
}
|
||
|
|
|
||
|
|
# Create a mapping dictionary for attribute values
|
||
|
|
mapping = {}
|
||
|
|
for attr, values in attributes.items():
|
||
|
|
mapping[attr] = {value: index for index, value in enumerate(values)}
|
||
|
|
|
||
|
|
converted_dataset = []
|
||
|
|
|
||
|
|
# Read the input CSV file
|
||
|
|
with open(input_file, "r") as csvfile:
|
||
|
|
reader = csv.reader(csvfile)
|
||
|
|
|
||
|
|
header = next(reader) # Skip the header row
|
||
|
|
|
||
|
|
# Convert the data rows
|
||
|
|
for row in reader:
|
||
|
|
converted_row = []
|
||
|
|
for i, value in enumerate(row):
|
||
|
|
# Convert the attribute values
|
||
|
|
if i + 1 in mapping:
|
||
|
|
converted_value = mapping[i + 1][value]
|
||
|
|
else:
|
||
|
|
converted_value = value
|
||
|
|
|
||
|
|
converted_row.append(converted_value)
|
||
|
|
|
||
|
|
converted_dataset.append(converted_row)
|
||
|
|
|
||
|
|
# Write the converted dataset to a new CSV file
|
||
|
|
with open(output_file, "w", newline="") as csvfile:
|
||
|
|
writer = csv.writer(csvfile)
|
||
|
|
|
||
|
|
# Write the header row
|
||
|
|
#writer.writerow(header)
|
||
|
|
|
||
|
|
# Write the converted data rows
|
||
|
|
for row in converted_dataset:
|
||
|
|
writer.writerow(row)
|
||
|
|
|
||
|
|
# Example usage:
|
||
|
|
convert_dataset("dataset/Dataset.csv", "dataset/converted_dataset.csv")
|