fr24splitMerge.py

# Developed for taking a number of .csv files with flight data from flightradar24 and prepare them for use in kepler.gl to 
# visualize flight paths over time.
#
# This script uses the Pandas library to manipulate CSV files. It starts by using the glob library to find all CSV files in 
# the current directory, and stores them in a list called "csv_files".
# 
# It then creates an empty list called "df_list" which will be used to store the modified DataFrames.
# 
# A for loop then iterates over each file in the "csv_files" list, using the Pandas function "pd.read_csv()" to read the file 
# and store it as a DataFrame. It then uses the Pandas function "df["Position"].str.replace('"','')" to remove any double 
# quotes from the "Position" column.
# 
# It then uses the Pandas function "df[["Latitude", "Longitude"]] = df["Position"].str.split(",", expand=True)" to split the 
# "Position" column into two separate columns: "Latitude" and "Longitude" by using the "," as a separator.
#
# The modified DataFrame is then appended to the "df_list" list.
# 
# After all files have been processed, the script uses the Pandas function "pd.concat(df_list, ignore_index=True)" to 
# concatenate all the DataFrames in the "df_list" list into a single DataFrame called "result".
#
# Finally, the script uses the Pandas function "result.to_csv("cleaned_merged_file.csv", index=False)" to save the "result" 
# DataFrame as a new CSV file called "cleaned_merged_file.csv" with the index set to false.

import pandas as pd
import glob

# Find all CSV files in the current directory
csv_files = glob.glob("*.csv")

df_list = []

# Iterate over each file and split the "Position" column into separate "Latitude" and "Longitude" columns
for file in csv_files:
    df = pd.read_csv(file)
    df["Position"] = df["Position"].str.replace('"','')
    df[["Latitude", "Longitude"]] = df["Position"].str.split(",", expand=True)
    df_list.append(df)

# Concatenate all the DataFrames into a single DataFrame
result = pd.concat(df_list, ignore_index=True)

# Create a new file with the "cleaned_merged_file.csv"
result.to_csv("cleaned_merged_file.csv", index=False)