mvsrc

fieldExtraction/src/categorization.py

@@ -0,0 +1,34 @@
+
+import os
+
+import utils
+import preprocess
+import table_funcs
+
+
+def contains_reimbursement(text_dict, page):
+    return ('%' in text_dict[page] or '$' in text_dict[page] or 'percent' in text_dict[page].lower())
+
+directory_path = "C:\\Users\\kminhas\\Documents\\Doczy\\doczy.ai\\data\\centene_healthnet"
+#input_dict = utils.read_input(path=folder_path)
+all_files = {}
+reimbursement_count = 0
+total_count = 0
+# Walk through all directories and files in the directory
+for root, dirs, files in os.walk(directory_path):
+    for file in files:
+        if file.endswith('.txt'):
+            # Construct full file path
+            file_path = os.path.join(root, file)
+            print(file_path)
+            try:
+                with open(file_path, 'r', encoding='utf-8') as file:
+                    contract_text = file.read()
+                    if ('%' in contract_text or '$' in contract_text or 'percent' in contract_text.lower()):
+                        reimbursement_count += 1
+                    total_count += 1
+            except:
+                continue
+
+print(f"For Centene HealthNet, {reimbursement_count}/{total_count} files contain potential reimbursement terms.")
+