Refactor code structure for improved readability and maintainability

analysis.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "id": "b18c1027",
    "metadata": {},
    "outputs": [
@@ -10,7 +10,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'id': 'gen-1758708788-9UUhU8KfktBmyteT4BUC', 'provider': 'Google', 'model': 'google/gemini-2.5-flash-lite', 'object': 'chat.completion', 'created': 1758708788, 'choices': [{'logprobs': None, 'finish_reason': 'stop', 'native_finish_reason': 'STOP', 'index': 0, 'message': {'role': 'assistant', 'content': 'Parameters,Best,LLN,Pred.,%Pred.,ZScore,PRE#1,PRE#2,PRE#3\\nFVC,4.24,3.03,3.79,112.0,0.95,4.24,4.17,4.15\\nFEV1,3.26,2.53,3.16,103.3,0.28,3.26,3.21,3.14\\nFEV1/FVC%,76.89,72.47,83.78,91.8,-1.05,76.9,77.0,75.7\\nPEF,684,222,384,178.7,-,444,438,684\\nFEF2575,2.74,2.15,3.42,80.2,-0.84,2.74,2.68,2.48\\nFEF25,6.08,,,0.0,-,6.08,6.0,5.53\\nFEF50,3.06,,,0.0,-,3.06,3.1,2.77\\nFEF75,1.06,0.71,1.41,75.1,-0.72,1.06,1.12,0.94\\nPEFTime,79,,,49,-,79,40,39\\nEVol,78.0,,,77.0,-,78.0,77.0,197.0\\nFEV6,4.22,3.03,3.79,111.4,-,4.22,4.17,4.13', 'refusal': None, 'reasoning': None}}], 'usage': {'prompt_tokens': 1348, 'completion_tokens': 434, 'total_tokens': 1782, 'prompt_tokens_details': {'cached_tokens': 0}, 'completion_tokens_details': {'reasoning_tokens': 0, 'image_tokens': 0}}}\n",
+      "{'id': 'gen-1759135172-DIhs7TMuaaVY0h3T2ibV', 'provider': 'Google', 'model': 'google/gemini-2.5-flash-lite', 'object': 'chat.completion', 'created': 1759135172, 'choices': [{'logprobs': None, 'finish_reason': 'stop', 'native_finish_reason': 'STOP', 'index': 0, 'message': {'role': 'assistant', 'content': 'Parameters,Best,LLN,Pred.,%Pred.,ZScore,PRE#1,PRE#2,PRE#3\\nFVC,L,4.24,3.03,3.79,112.0,0.95,4.24,4.17,4.15\\nFEV1,L,3.26,2.53,3.16,103.3,0.28,3.26,3.21,3.14\\nFEV1/FVC%,76.89,72.47,83.78,91.8,-1.05,76.9,77.0,75.7\\nPEF,L/m,684,222,384,178.7,-,444,438,684\\nFEF2575,L/s,2.74,2.15,3.42,80.2,-0.84,2.74,2.68,2.48\\nFEF25,L/s,6.08,-,-,-,6.08,6.0,5.53\\nFEF50,L/s,3.06,-,-,-,3.06,3.1,2.77\\nFEF75,L/s,1.06,0.71,1.41,75.1,-0.72,1.06,1.12,0.94\\nPEFTime,ms,-,-,79,-,79,49,39\\nEvol,mL,-,-,78.0,-,78.0,77.0,197.0\\nFEV6,L,4.22,3.03,3.79,111.4,-,4.22,4.17,4.13', 'refusal': None, 'reasoning': None}}], 'usage': {'prompt_tokens': 1350, 'completion_tokens': 454, 'total_tokens': 1804, 'prompt_tokens_details': {'cached_tokens': 0}, 'completion_tokens_details': {'reasoning_tokens': 0, 'image_tokens': 0}}}\n",
       "Content saved to extracted_table.csv\n"
      ]
     }
@@ -44,7 +44,7 @@
     "        \"content\": [\n",
     "            {\n",
     "                \"type\": \"text\",\n",
-    "                \"text\": \"Please extract the table from the pdf and return the values in csv format, \"\n",
+    "                \"text\": \"Please extract the Spirometry table from the pdf and return the values in csv format, \"\n",
     "                \"note that it is the unit of parameter that is beside it and it should not be a column. \"\n",
     "                \"The '-' Should be treated as empty values.\"\n",
     "                \"do not add 'csv' at the start or end of the response\"\n",

context_generator.py

@@ -0,0 +1,5 @@
+import pandas as pd
+
+pnoe_df = pd.read_csv('data/pnoe_data.csv')
+patient_df = pd.read_csv('data/patient_data.csv')
+spirometry_df = pd.read_csv('data/spirometry_data.csv')

extracted_table.csv

@@ -0,0 +1,12 @@
+Parameters,Best,LLN,Pred.,%Pred.,ZScore,PRE#1,PRE#2,PRE#3
+FVC,L,4.24,3.03,3.79,112.0,0.95,4.24,4.17,4.15
+FEV1,L,3.26,2.53,3.16,103.3,0.28,3.26,3.21,3.14
+FEV1/FVC%,76.89,72.47,83.78,91.8,-1.05,76.9,77.0,75.7
+PEF,L/m,684,222,384,178.7,-,444,438,684
+FEF2575,L/s,2.74,2.15,3.42,80.2,-0.84,2.74,2.68,2.48
+FEF25,L/s,6.08,-,-,-,6.08,6.0,5.53
+FEF50,L/s,3.06,-,-,-,3.06,3.1,2.77
+FEF75,L/s,1.06,0.71,1.41,75.1,-0.72,1.06,1.12,0.94
+PEFTime,ms,-,-,79,-,79,49,39
+Evol,mL,-,-,78.0,-,78.0,77.0,197.0
+FEV6,L,4.22,3.03,3.79,111.4,-,4.22,4.17,4.13