add preprocessing function

app.py

@@ -13,6 +13,11 @@ with gr.Blocks() as ui:
         with gr.Column():
             output = gr.Text()
     
+    # Second row for additional outputs
+    #with gr.Row():
+     #   statistics_output = gr.Dataframe(label="Statistics Summary")
+    
+    # Submit button action
     submit_btn.click(get_statistics, 
     file_input, output)
 

requirements.txt

@@ -1,3 +1,4 @@
 gradio==4.44.1
 pydantic==2.10.6
-returns>=0.26.0
+returns>=0.26.0
+openpyxl

utils/main_processor.py

@@ -1,11 +1,11 @@
 import json
 import os
 from utils.whisp_api_client import whisp_request
+from utils.whisp_preprocessing import preprocess_whisp_data
 
 # Import secrets
 whisp_api_key = os.environ.get("WHISP_API_KEY")
 
-
 # Define main function to fetch geojson, do API call and get statistics
 
 def get_statistics(file): 
@@ -23,8 +23,11 @@ def get_statistics(file):
     # Do the API call
     whisp_response = whisp_request(geojson_file, api_key=whisp_api_key)
 
+    # Preprocess
+    preprocessed_response = preprocess_whisp_data(whisp_response)
+
     # Do preprocessing
-    return whisp_response
+    return preprocessed_response
 
 
 

utils/whisp_preprocessing.py

@@ -0,0 +1,16 @@
+import pandas as pd
+import openpyxl 
+
+def preprocess_whisp_data(response): 
+
+    # Get whisp metadata
+    # whisp_metadata_url = "https://github.com/forestdatapartnership/whisp/blob/main/whisp_columns.xlsx"
+    # df_metadata = pd.read_excel(whisp_metadata_url, engine="openpyxl")
+
+    # Drop irrelevant entries
+    preprocessed_response = response['properties']
+
+    return preprocessed_response
+
+
+