Skip to content

implemented code to transform data #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
HR-Supaero wants to merge 2 commits into
base: main
Choose a base branch
from
Open

implemented code to transform data #3

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
700cbb8
implemented code to transform data
HR-Supaero Sep 16, 2025
ddb48ca
Merge branch 'main' into devHugo
HR-Supaero Sep 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 41 additions & 9 deletions src/transform_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,21 +30,36 @@ def clean_airports(airports_df):
# Make a copy to avoid modifying the original
df = airports_df.copy()

# TODO: Remove rows with missing latitude or longitude
# df = df.dropna(subset=['latitude', 'longitude'])
# TODO: Remove rows with missing latitude or longitud
# Hint: Use .dropna(subset=['latitude', 'longitude'])
df = df.dropna(subset=['latitude', 'longitude'])

# TODO: Remove airports with invalid coordinates
# Latitude should be between -90 and 90
# Longitude should be between -180 and 180
# Hint: df = df[(df['latitude'] >= -90) & (df['latitude'] <= 90)]
# Hint: df = df[(df['longitude'] >= -180) & (df['longitude'] <= 180)]
df = df[(df['latitude'] >= -90) & (df['latitude'] <= 90)]
df = df[(df['longitude'] >= -180) & (df['longitude'] <= 180)]

# TODO: Handle missing IATA codes (replace empty strings or 'N' with None)
# Hint: df['iata_code'] = df['iata_code'].replace(['', 'N', '\\N'], None)
df['iata_code'] = df['iata_code'].replace(['', 'N', '\\N'], None)

# TODO: Convert altitude to numeric (handle non-numeric values)
# Hint: df['altitude'] = pd.to_numeric(df['altitude'], errors='coerce')
df['altitude'] = pd.to_numeric(df['altitude'], errors='coerce')

=======

# TODO: Handle missing IATA codes (replace empty strings or 'N' with None)

# TODO: Convert altitude to numeric (handle non-numeric values)

# TODO: Print how many airports remain after cleaning
# print(f"After cleaning: {len(df)} airports remain")
print(f"After cleaning: {len(df)} airports remain")

print("⚠️ Airport cleaning not yet implemented")
# print("⚠️ Airport cleaning not yet implemented")
return df

def clean_flights(flights_df):
Expand Down Expand Up @@ -85,6 +100,23 @@ def clean_flights(flights_df):
df = flights_df.copy()

# TODO: Assign column names to the DataFrame
df.columns = expected_columns

# TODO: Remove flights with missing coordinates
df = df.dropna(subset=['longitude', 'latitude'])

# TODO: Convert altitude from meters to feet (multiply by 3.28084)
# This makes it easier to understand for aviation
df['altitude'] = df['altitude'] * 3.28084

# TODO: Remove flights with invalid coordinates
# Same coordinate bounds as airports
df = df[(df['latitude'] >= -90) & (df['latitude'] <= 90)]
df = df[(df['longitude'] >= -180) & (df['longitude'] <= 180)]

# TODO: Clean callsign (remove extra whitespace)
df['callsign'] = df['callsign'].str.strip()


# TODO: Remove flights with missing coordinates

Expand All @@ -97,9 +129,9 @@ def clean_flights(flights_df):
# TODO: Clean callsign (remove extra whitespace)

# TODO: Print how many flights remain after cleaning
# print(f"After cleaning: {len(df)} flights remain")
print(f"After cleaning: {len(df)} flights remain")

print("⚠️ Flight cleaning not yet implemented")
# print("⚠️ Flight cleaning not yet implemented")
return df

def combine_data(airports_df, flights_df):
Expand Down Expand Up @@ -128,9 +160,9 @@ def combine_data(airports_df, flights_df):
# TODO (Optional): If you want to try something more advanced,
# you could find the nearest airport for each flight:
#
# def find_nearest_airport(flight_lat, flight_lon, airports_df):
# # Calculate distances and return nearest airport
# pass
def find_nearest_airport(flight_lat, flight_lon, airports_df):

pass

return airports_df, flights_df

Expand Down