Add extractdata script
This commit is contained in:
parent
aa0f33fcc6
commit
381699f651
|
|
@ -0,0 +1,212 @@
|
|||
import os
|
||||
import csv
|
||||
import subprocess
|
||||
import argparse
|
||||
import matplotlib.pyplot as plt
|
||||
from collections import defaultdict
|
||||
|
||||
def extract_timestamp(filename):
|
||||
timestamp_str = filename[:10]
|
||||
try:
|
||||
timestamp = int(timestamp_str)
|
||||
return timestamp
|
||||
except ValueError:
|
||||
return 0
|
||||
|
||||
def extract_values_by_key(csv_file, key, exact_match):
|
||||
# Initialize a defaultdict for lists
|
||||
matched_values = defaultdict(list)
|
||||
with open(csv_file, 'r') as file:
|
||||
reader = csv.reader(file)
|
||||
for row in reader:
|
||||
if row:
|
||||
columns = row[0].split(';')
|
||||
if len(columns) > 1:
|
||||
first_column = columns[0].strip()
|
||||
path_key = first_column.split('/')[-1]
|
||||
for key_item in key:
|
||||
if exact_match:
|
||||
if key_item.lower() == row[0].split('/')[-1].split(';')[0].lower():
|
||||
matched_values[path_key].append(row[0])
|
||||
else:
|
||||
if key_item.lower() in first_column.lower():
|
||||
matched_values[path_key].append(row[0])
|
||||
#return matched_values
|
||||
# Concatenate all keys to create a single final_key
|
||||
final_key = ''.join(matched_values.keys())
|
||||
# Combine all lists of values into a single list
|
||||
combined_values = []
|
||||
for values in matched_values.values():
|
||||
combined_values.extend(values)
|
||||
# Create the final dictionary with final_key and all combined values
|
||||
final_dict = {final_key: combined_values}
|
||||
#return dict(matched_values)
|
||||
return final_dict
|
||||
|
||||
def list_files_in_range(start_timestamp, end_timestamp, sampling_stepsize):
|
||||
filenames_in_range = [f"{timestamp:10d}" for timestamp in range(start_timestamp, end_timestamp + 1, 2*sampling_stepsize)]
|
||||
return filenames_in_range
|
||||
|
||||
def check_s3_files_exist(bucket_number, filename):
|
||||
s3cmd_ls_command = f"s3cmd ls s3://{bucket_number}-3e5b3069-214a-43ee-8d85-57d72000c19d/{filename}*"
|
||||
try:
|
||||
result = subprocess.run(s3cmd_ls_command, shell=True, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
lines = result.stdout.decode().split('\n')[:-1]
|
||||
filenames = [line.split()[-1].split('/')[-1] for line in lines]
|
||||
return filenames
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f"Error checking S3 files: {e}")
|
||||
return []
|
||||
|
||||
def download_files(bucket_number, filenames_to_download):
|
||||
output_directory = f"S3cmdData_{bucket_number}"
|
||||
|
||||
|
||||
if not os.path.exists(output_directory):
|
||||
os.makedirs(output_directory)
|
||||
print(f"Directory '{output_directory}' created.")
|
||||
|
||||
for filename in filenames_to_download:
|
||||
stripfilename = filename.strip()
|
||||
local_path = os.path.join(output_directory, stripfilename + ".csv")
|
||||
if not os.path.exists(local_path):
|
||||
s3cmd_command = f"s3cmd get s3://{bucket_number}-3e5b3069-214a-43ee-8d85-57d72000c19d/{stripfilename}.csv {output_directory}/"
|
||||
try:
|
||||
subprocess.run(s3cmd_command, shell=True, check=True)
|
||||
downloaded_files = [file for file in os.listdir(output_directory) if file.startswith(filename)]
|
||||
if not downloaded_files:
|
||||
print(f"No matching files found for prefix '{filename}'.")
|
||||
else:
|
||||
print(f"Files with prefix '{filename}' downloaded successfully.")
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f"Error downloading files: {e}")
|
||||
continue
|
||||
else:
|
||||
print(f"File '{filename}.csv' already exists locally. Skipping download.")
|
||||
|
||||
|
||||
def visualize_data(data, output_directory):
|
||||
# Extract data for visualization (replace this with your actual data extraction)
|
||||
x_values = [int(entry[0]) for entry in data]
|
||||
y_values = [float(entry[1]) for entry in data]
|
||||
|
||||
# Plotting
|
||||
plt.plot(x_values, y_values, marker='o', linestyle='-', color='b')
|
||||
plt.xlabel('Timestamp')
|
||||
plt.ylabel('Your Y-axis Label')
|
||||
plt.title('Your Plot Title')
|
||||
plt.grid(True)
|
||||
plt.savefig(os.path.join(output_directory, f"{start_timestamp}_{key}_plot.png"))
|
||||
plt.close() # Close the plot window
|
||||
|
||||
|
||||
# Save data to CSV
|
||||
csv_file_path = os.path.join(output_directory, f"{start_timestamp}_{key}_extracted.csv")
|
||||
with open(csv_file_path, 'w', newline='') as csvfile:
|
||||
csv_writer = csv.writer(csvfile)
|
||||
csv_writer.writerow(['Timestamp', 'Value']) # Adjust column names as needed
|
||||
csv_writer.writerows(data)
|
||||
|
||||
def get_last_component(path):
|
||||
path_without_slashes = path.replace('/', '')
|
||||
return path_without_slashes
|
||||
|
||||
|
||||
def download_and_process_files(bucket_number, start_timestamp, end_timestamp, sampling_stepsize, key, booleans_as_numbers, exact_match):
|
||||
output_directory = f"S3cmdData_{bucket_number}"
|
||||
|
||||
if not os.path.exists(output_directory):
|
||||
os.makedirs(output_directory)
|
||||
print(f"Directory '{output_directory}' created.")
|
||||
|
||||
filenames_to_check = list_files_in_range(start_timestamp, end_timestamp, sampling_stepsize)
|
||||
#filenames_on_s3 = check_s3_files_exist(bucket_number, filenames_to_check, key)
|
||||
|
||||
existing_files = [filename for filename in filenames_to_check if os.path.exists(os.path.join(output_directory, f"{filename}.csv"))]
|
||||
files_to_download = set(filenames_to_check) - set(existing_files)
|
||||
|
||||
if os.listdir(output_directory):
|
||||
print("Files already exist in the local folder. Skipping download.")
|
||||
else:
|
||||
if files_to_download:
|
||||
download_files(bucket_number, files_to_download)
|
||||
|
||||
|
||||
# Process CSV files
|
||||
csv_files = [file for file in os.listdir(output_directory) if file.endswith('.csv')]
|
||||
csv_files.sort(key=extract_timestamp)
|
||||
keypath = ''
|
||||
for key_item in key:
|
||||
keypath+= get_last_component(key_item)
|
||||
output_csv_filename = f"{keypath}_{start_timestamp}_{bucket_number}.csv"
|
||||
with open(output_csv_filename, 'w', newline='') as csvfile:
|
||||
csv_writer = csv.writer(csvfile)
|
||||
header = ['time']
|
||||
add_header = True
|
||||
|
||||
for csv_file in csv_files:
|
||||
file_path = os.path.join(output_directory, csv_file)
|
||||
extracted_values = extract_values_by_key(file_path, key, exact_match)
|
||||
if add_header:
|
||||
add_header = False
|
||||
for values in extracted_values.values():
|
||||
first_value = values
|
||||
for first_val in first_value:
|
||||
header.append(first_val.split(';')[0].strip())
|
||||
break
|
||||
csv_writer.writerow(header)
|
||||
if extracted_values:
|
||||
for first_column, values in extracted_values.items():
|
||||
if booleans_as_numbers:
|
||||
values = [1 if value.split(';')[1].strip() == "True" else 0 if value.split(';')[1].strip() == "False" else value.split(';')[1].strip() for value in values]
|
||||
values_list = []
|
||||
values_list.append(csv_file.replace(".csv", ""))
|
||||
for i, value in enumerate(values):
|
||||
if value is None:
|
||||
value = "No value provided"
|
||||
else:
|
||||
values_list.append(value.split(';')[1].strip())
|
||||
csv_writer.writerow(values_list)
|
||||
|
||||
print(f"Extracted data saved in '{output_csv_filename}'.")
|
||||
|
||||
def parse_keys(input_string):
|
||||
# Split the input string by commas and strip whitespace
|
||||
keys = [key.strip() for key in input_string.split(',')]
|
||||
# Return keys as a list if more than one, else return the single key
|
||||
#return keys if len(keys) > 1 else keys[0]
|
||||
return keys
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description='Download files from S3 using s3cmd and extract specific values from CSV files.')
|
||||
parser.add_argument('start_timestamp', type=int, help='The start timestamp for the range (even number)')
|
||||
parser.add_argument('end_timestamp', type=int, help='The end timestamp for the range (even number)')
|
||||
#parser.add_argument('--key', type=str, required=True, help='The part to match from each CSV file')
|
||||
parser.add_argument('--keys', type=parse_keys, required=True, help='The part to match from each CSV file, can be a single key or a comma-separated list of keys')
|
||||
parser.add_argument('--bucket-number', type=int, required=True, help='The number of the bucket to download from')
|
||||
parser.add_argument('--sampling_stepsize', type=int, required=False, default=1, help='The number of 2sec intervals, which define the length of the sampling interval in S3 file retrieval')
|
||||
parser.add_argument('--booleans_as_numbers', action="store_true", required=False, help='If key used, then booleans are converted to numbers [0/1], if key not used, then booleans maintained as text [False/True]')
|
||||
parser.add_argument('--exact_match', action="store_true", required=False, help='If key used, then key has to match exactly "=", else it is enough that key is found "in" text')
|
||||
|
||||
|
||||
args = parser.parse_args();
|
||||
start_timestamp = args.start_timestamp
|
||||
end_timestamp = args.end_timestamp
|
||||
keys = args.keys
|
||||
bucket_number = args.bucket_number
|
||||
sampling_stepsize = args.sampling_stepsize
|
||||
booleans_as_numbers = args.booleans_as_numbers
|
||||
exact_match = args.exact_match
|
||||
|
||||
|
||||
|
||||
# Check if start_timestamp is smaller than end_timestamp
|
||||
if start_timestamp >= end_timestamp:
|
||||
print("Error: start_timestamp must be smaller than end_timestamp.")
|
||||
return
|
||||
download_and_process_files(bucket_number, start_timestamp, end_timestamp, sampling_stepsize, keys, booleans_as_numbers, exact_match)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Loading…
Reference in New Issue