pyarrow for faster Parquet operations

Dataset_prep/parquet_conversion.py

@@ -0,0 +1,18 @@
+import pandas as pd
+
+# Use 'pyarrow' or 'fastparquet' for faster Parquet operations
+parquet_engine = 'pyarrow'  # or 'fastparquet'
+
+# Specify data types for columns if known
+dtype = {
+    'column1': 'int64',
+    'column2': 'float64',
+    'column3': 'object',
+    # Add other columns as needed
+}
+
+# Load CSV data with specified data types
+df = pd.read_csv('airport.csv', dtype=dtype)
+
+# Save as Parquet using the specified engine
+df.to_parquet('airport.parquet', engine=parquet_engine)

app.py

@@ -4,9 +4,8 @@ from map_generator import *
 from flight_distance import *
 from optimize import *
 from weather import *
-
-# Load airport data and aircraft data from CSV files
-airport_df = pd.read_csv(r'airport.csv')  # Adjust the path to your CSV file
+# Load airport data and aircraft data from Parquet and CSV files
+airport_df = pd.read_parquet(r'airport.parquet')  # Adjust the path to your Parquet file
 aircraft_df = pd.read_csv(r'aircraft.csv')  # Adjust the path to your CSV file
 
 airport_options = [f"{row['IATA']} - {row['Airport_Name']}" for _, row in airport_df.iterrows()]
@@ -117,7 +116,7 @@ def check_route(airport_selections, aircraft_type):
     return result, map_html
 
 # Gradio Interface
-with gr.Blocks(theme='dark') as demo:
+with gr.Blocks(theme=gr.themes.Default()) as demo:
     gr.Markdown("## Airport Route Feasibility Checker")
 
     # Place components in two columns for results and map

flight_distance.py

@@ -24,7 +24,15 @@ def get_airport_lat_long(identifiers):
     Get latitude and longitude for a list of airport identifiers (IATA codes).
     """
     csv_file = 'airport.csv'
-    df = pd.read_csv(csv_file)
+    parquet_file = 'airport.parquet'
+    
+    # Try reading the parquet file first
+    try:
+        df = pd.read_parquet(parquet_file)
+    except FileNotFoundError:
+        # If parquet file is not found, fall back to reading the CSV file
+        df = pd.read_csv(csv_file)
+    
     df_filtered = df[df['Airport_Name'].isin(identifiers) | df['IATA'].isin(identifiers)]
     lat_long_dict = {row['IATA']: (row['Lat'], row['Long']) for _, row in df_filtered.iterrows()}
     return lat_long_dict