2025-03-13 12:01:54 +00:00
{
"cells": [
{
"cell_type": "code",
2025-03-27 04:14:28 +00:00
"execution_count": 47,
2025-03-13 12:01:54 +00:00
"metadata": {},
"outputs": [],
"source": [
2025-03-18 11:13:55 +00:00
"import openpyxl\n",
"from collections import defaultdict\n",
"import pandas as pd\n",
"import statistics\n",
"import os\n",
"import re\n",
"from utils.similarity import Similarity\n",
2025-03-13 12:01:54 +00:00
"\n",
"\n",
2025-03-27 04:14:28 +00:00
"imp_datapoints = [\"Management Fee and Costs\", \"Management Fee\", \"Performance fee and cost\", \"Interposed vehicle Performance fee and Costs\",\n",
" \"Administration Fee and costs\", \"Total Annual Dollar Based Charges\", \"Buy Spread\", \"Sell Spread\", \"Performance Fee\",\n",
" \"Minimum Initial Investment\", \"Benchmark\"]\n",
2025-03-13 12:01:54 +00:00
"\n",
"\n",
"imp_datapoints_mapping = {\n",
" \"Management Fee and Costs\": \"management_fee_and_costs\",\n",
" \"Management Fee\": \"management_fee\",\n",
" \"Performance fee and cost\": \"performance_fee_costs\",\n",
2025-03-27 04:14:28 +00:00
" \"Interposed vehicle Performance fee and Costs\": \"interposed_vehicle_performance_fee_cost\",\n",
2025-03-13 12:01:54 +00:00
" \"Administration Fee and costs\": \"administration_fees\",\n",
" \"Total Annual Dollar Based Charges\": \"total_annual_dollar_based_charges\",\n",
" \"Buy Spread\": \"buy_spread\",\n",
2025-03-27 04:14:28 +00:00
" \"Sell Spread\": \"sell_spread\",\n",
" \"Performance Fee\": \"PerformanceFeeCharged\",\n",
" \"Minimum Initial Investment\": \"minimum_initial_investment\",\n",
" \"Benchmark\": \"benchmark_name\"\n",
2025-03-18 11:13:55 +00:00
"}\n",
"\n",
2025-03-27 04:14:28 +00:00
"# imp_datapoints = [\"Management Fee and Costs\", \"Management Fee\", \"Performance fee and cost\",\n",
"# \"Administration Fee and costs\", \"Total Annual Dollar Based Charges\", \"Buy Spread\", \"Sell Spread\"]\n",
"\n",
"\n",
"# imp_datapoints_mapping = {\n",
"# \"Management Fee and Costs\": \"management_fee_and_costs\",\n",
"# \"Management Fee\": \"management_fee\",\n",
"# \"Performance fee and cost\": \"performance_fee_costs\",\n",
"# \"Administration Fee and costs\": \"administration_fees\",\n",
"# \"Total Annual Dollar Based Charges\": \"total_annual_dollar_based_charges\",\n",
"# \"Buy Spread\": \"buy_spread\",\n",
"# \"Sell Spread\": \"sell_spread\"\n",
"# }\n",
"\n",
"path_ground_truth = r\"/data/aus_prospectus/ground_truth/phase2_file/46_documents/46_documents_ground_truth_with_mapping.xlsx\"\n",
"# path_ground_truth = r\"/data/aus_prospectus/ground_truth/phase2_file/next_round/next_round_6_documents_ground_truth_with_mapping.xlsx\"\n",
2025-03-18 19:15:43 +00:00
"# path_generated_results = r\"/data/aus_prospectus/output/mapping_data/total/mapping_data_info_46_documents_by_text_20250317.xlsx\"\n",
2025-03-27 04:14:28 +00:00
"path_generated_results = r\"/data/aus_prospectus/output/mapping_data/total/mapping_data_info_46_documents_by_text_20250326224343.xlsx\"\n",
"# path_generated_results = r\"/data/aus_prospectus/output/mapping_data/total/mapping_data_info_6_documents_by_text_20250326203744.xlsx\"\n",
2025-03-18 11:13:55 +00:00
"provider_mapping_file_path = r\"/data/aus_prospectus/ground_truth/phase2_file/46_documents/TopProvidersBiz.xlsx\"\n",
"\n"
2025-03-13 12:01:54 +00:00
]
},
{
"cell_type": "code",
2025-03-27 04:14:28 +00:00
"execution_count": 48,
2025-03-13 12:01:54 +00:00
"metadata": {},
2025-03-18 11:13:55 +00:00
"outputs": [],
2025-03-13 12:01:54 +00:00
"source": [
"\n",
2025-03-18 11:13:55 +00:00
"message_list = []\n",
"total_fn = []\n",
2025-03-13 12:01:54 +00:00
"def load_excel(filepath, header_row_index):\n",
" \"\"\"Load an Excel file and use the specified row as the header.\"\"\"\n",
" wb = openpyxl.load_workbook(filepath, data_only=True)\n",
" sheet = wb.active\n",
" headers = []\n",
" data = []\n",
"\n",
" for index, row in enumerate(sheet.iter_rows(values_only=True)):\n",
" if index == header_row_index:\n",
" headers = [cell if cell is not None else \"\" for cell in row]\n",
" elif index > header_row_index:\n",
" data.append([cell if cell is not None else \"\" for cell in row])\n",
"\n",
" return headers, data\n",
"\n",
2025-03-26 23:58:45 +00:00
"def index_data_by_key(data, header):\n",
2025-03-13 16:53:27 +00:00
" \"\"\"Index data by primary and secondary keys (doc_id and sec_name).\"\"\"\n",
2025-03-13 12:01:54 +00:00
" indexed_data = defaultdict(dict)\n",
" \n",
" for row in data:\n",
" row_data = {}\n",
" # Store the entire row, which will be useful for full row comparison\n",
" for i in range(len(row)):\n",
" if header[i] == \"doc_id\":\n",
" primary_key = int(row[i])\n",
2025-03-13 16:53:27 +00:00
" elif header[i] == \"sec_name\":\n",
" # share class should be the comparison level and key\n",
2025-03-13 12:01:54 +00:00
" secondary_key = str(row[i])\n",
" else:\n",
" row_data[header[i]] = convert_if_number(row[i])\n",
2025-03-13 22:52:06 +00:00
" if secondary_key is None or (isinstance(secondary_key, str) and len(secondary_key) == 0):\n",
" continue\n",
2025-03-13 12:01:54 +00:00
" indexed_data[primary_key][secondary_key] = row_data\n",
" return indexed_data\n",
"\n",
"def convert_if_number(value):\n",
" \"\"\"Attempt to convert value to a float or int, otherwise return as string.\"\"\"\n",
" try:\n",
" float_value = round(float(value), 2)\n",
" int_value = int(float_value)\n",
" return int_value if int_value == float_value else float_value\n",
" except (ValueError, TypeError):\n",
" return value\n",
"\n",
"def compare_values(value1, value2):\n",
" \"\"\"Convert values to numbers if possible and compare, otherwise compare as strings.\"\"\"\n",
" value1 = convert_if_number(value1)\n",
" value2 = convert_if_number(value2)\n",
" return value1 == value2\n",
2025-03-18 11:13:55 +00:00
"\n",
2025-03-26 23:58:45 +00:00
"def compare_data(ground_truth, generated_results, headers, intersection_list, document_list):\n",
2025-03-13 12:01:54 +00:00
" \"\"\"Compare data from two indexed sets, with the focus on matching generated results against ground truth.\"\"\"\n",
" results = {}\n",
2025-03-26 23:58:45 +00:00
" share_name_list = []\n",
" not_matched_share_name_list = []\n",
" share_matched, share_not_matched = 0, 0\n",
2025-03-13 12:01:54 +00:00
" # Initialize result dictionaries for each column except 'doc_id'\n",
" for keys in headers:\n",
" if keys != \"doc_id\":\n",
" results[keys] = {}\n",
" results[keys][\"TP\"] = 0\n",
" results[keys][\"TN\"] = 0\n",
" results[keys][\"FP\"] = 0\n",
" results[keys][\"FN\"] = 0\n",
" results[keys][\"SUPPORT\"] = 0\n",
" \n",
" # Iterate over the generated results instead of the ground truth\n",
" \n",
" total = 0\n",
2025-03-13 16:53:27 +00:00
" # print(document_list)\n",
" for doc_id, secs in ground_truth.items():\n",
" if document_list is not None and str(doc_id) not in document_list:\n",
" continue\n",
2025-03-13 12:01:54 +00:00
" if doc_id in generated_results:\n",
2025-03-13 16:53:27 +00:00
" for sec_name, truth_values in secs.items():\n",
" if sec_name in generated_results[doc_id]:\n",
" generated_values = generated_results[doc_id][sec_name]\n",
2025-03-13 12:01:54 +00:00
" # Compare all other columns\n",
" for i in intersection_list:\n",
" for keys in imp_datapoints:\n",
" if i == imp_datapoints_mapping[keys]:\n",
2025-03-14 06:04:51 +00:00
" truth = str(truth_values[i]).strip()\n",
" generated = str(generated_values[i]).strip()\n",
2025-03-13 12:01:54 +00:00
" total = total +1\n",
2025-03-14 06:04:51 +00:00
" if truth == \"\":\n",
" if truth == generated:\n",
2025-03-13 12:01:54 +00:00
" results[i][\"TN\"] = results[i][\"TN\"] + 1\n",
" else:\n",
" results[i][\"FP\"] = results[i][\"FP\"] + 1\n",
2025-03-13 16:53:27 +00:00
" # if \"Performance fee and cost\" in keys:\n",
" debug = 0\n",
" # print(keys, \" - \" , doc_id, \" truth is null and generated - \", generated_values[i], sec_name) \n",
2025-03-14 06:04:51 +00:00
" message = {\"data_point\": i, \"doc_id\": doc_id, \"sec_name\": sec_name, \n",
" \"truth\": truth, \"generated\": generated, \"error\": \"Truth is null and generated is not null\"}\n",
2025-03-13 16:53:27 +00:00
" message_list.append(message) \n",
2025-03-13 12:01:54 +00:00
" else:\n",
2025-03-14 06:04:51 +00:00
" if truth == generated:\n",
2025-03-13 12:01:54 +00:00
" results[i][\"TP\"] = results[i][\"TP\"] + 1\n",
2025-03-14 06:04:51 +00:00
" elif generated != \"\":\n",
" if i == \"benchmark_name\" and compare_text(truth, generated):\n",
2025-03-13 16:53:27 +00:00
" results[i][\"TP\"] = results[i][\"TP\"] + 1\n",
" else:\n",
" results[i][\"FP\"] = results[i][\"FP\"] + 1\n",
" # if \"Performance fee and cost\" in keys:\n",
2025-03-13 12:01:54 +00:00
" debug = 0\n",
2025-03-13 16:53:27 +00:00
" # print(keys, \" - \" , doc_id, \" truth - \", truth_values[i], \" and generated - \", generated_values[i], \" \", sec_name)\n",
2025-03-14 06:04:51 +00:00
" message = {\"data_point\": i, \"doc_id\": doc_id, \"sec_name\": sec_name, \n",
" \"truth\": truth, \"generated\": generated, \"error\": \"Truth is not equal with generated\"}\n",
2025-03-13 16:53:27 +00:00
" message_list.append(message)\n",
2025-03-13 12:01:54 +00:00
" else:\n",
" results[i][\"FN\"] = results[i][\"FN\"] + 1\n",
2025-03-13 16:53:27 +00:00
" # if \"Performance fee and cost\" in keys:\n",
" debug = 0\n",
" # print(keys, \" - \" , doc_id, \" generated is null and truth is - \", truth_values[i], sec_name)\n",
2025-03-14 06:04:51 +00:00
" message = {\"data_point\": i, \"doc_id\": doc_id, \"sec_name\": sec_name, \n",
" \"truth\": truth, \"generated\": generated, \"error\": \"Generated is null and truth is not null\"}\n",
2025-03-13 16:53:27 +00:00
" message_list.append(message)\n",
2025-03-13 12:01:54 +00:00
" results[i][\"SUPPORT\"] = results[i][\"SUPPORT\"] + 1\n",
2025-03-26 23:58:45 +00:00
" if sec_name not in share_name_list:\n",
" share_name_list.append(sec_name)\n",
" share_matched += 1\n",
2025-03-13 12:01:54 +00:00
" else:\n",
2025-03-26 23:58:45 +00:00
" if sec_name not in share_name_list:\n",
" share_name_list.append(sec_name)\n",
" if sec_name not in not_matched_share_name_list:\n",
" # If the share class is not found in the generated results, count it as not matched\n",
" # print(\"Share class not matched - \", sec_name, doc_id)\n",
" message = {\"data_point\": \"Share Class\", \"doc_id\": doc_id, \"sec_name\": sec_name, \n",
" \"truth\": \"\", \"generated\": \"\", \"error\": \"Share class not found in generated results\"}\n",
" message_list.append(message)\n",
" share_not_matched += 1\n",
" not_matched_share_name_list.append(sec_name)\n",
2025-03-13 12:01:54 +00:00
" else:\n",
" # If the entire document is not found, count all funds as not matched\n",
2025-03-26 23:58:45 +00:00
" message = {\"data_point\": \"Document\", \"doc_id\": doc_id, \"sec_name\": \"\",\n",
" \"truth\": \"\", \"generated\": \"\", \"error\": \"Document not found in generated results\"}\n",
" message_list.append(message)\n",
" \n",
" # share_not_matched += len(secs)\n",
" return results, message_list, share_matched, share_not_matched, not_matched_share_name_list\n",
2025-03-13 16:53:27 +00:00
"\n",
"def clean_text(text: str):\n",
" if text is None or len(text) == 0:\n",
" return text\n",
" text = re.sub(r\"\\W\", \" \", text)\n",
" text = re.sub(r\"\\s+\", \" \", text)\n",
" return text\n",
"\n",
"def compare_text(source_text, target_text):\n",
" source_text = clean_text(source_text)\n",
" target_text = clean_text(target_text)\n",
" if source_text == target_text or source_text in target_text or target_text in source_text:\n",
" return True\n",
" similarity = Similarity()\n",
" jacard_score = similarity.jaccard_similarity(source_text.lower().split(), target_text.lower().split())\n",
" if jacard_score > 0.8:\n",
" return True\n",
2025-03-18 11:13:55 +00:00
" \n",
" \n",
2025-03-13 12:01:54 +00:00
"def calculate_metrics(tp, tn, fp, fn):\n",
" \"\"\"Calculate precision, recall, accuracy, and F1-score.\"\"\"\n",
" precision = tp / (tp + fp) if (tp + fp) != 0 else 0\n",
" recall = tp / (tp + fn) if (tp + fn) != 0 else 0\n",
" accuracy = (tp + tn) / (tp + tn + fp + fn) if (tp + tn + fp + fn) != 0 else 0\n",
" f1_score = 2 * (precision * recall) / (precision + recall) if (precision + recall) != 0 else 0\n",
" return precision, recall, accuracy, f1_score\n",
"\n",
"def print_metrics_table(data):\n",
" # Print table headers\n",
2025-03-13 22:52:06 +00:00
" print(\"{:<50}\\t{:<10}\\t{:<10}\\t{:<10}\\t{:<10}\\t{:<10}\\t{:<10}\\t{:<10}\\t{:<10}\\t{:<10}\".format(\"Metric\", \"F1-Score\", \"Precision\", \"Recall\", \"Accuracy\", \"SUPPORT\", \"TP\", \"TN\", \"FP\", \"FN\"))\n",
2025-03-13 12:01:54 +00:00
" total_precision, total_recall, total_accuracy, total_f1_score, total_support= [],[],[],[],[]\n",
" \n",
" total_tp = []\n",
" total_tn = []\n",
" total_fp = []\n",
" #total_fn = []\n",
" # Calculate and print metrics for each item\n",
2025-03-13 16:53:27 +00:00
" metrics_list = []\n",
2025-03-13 12:01:54 +00:00
" for keys in imp_datapoints:\n",
" try:\n",
" key = imp_datapoints_mapping[keys]\n",
" values = data[key]\n",
2025-03-13 22:52:06 +00:00
" if values[\"SUPPORT\"] == 0:\n",
" continue\n",
2025-03-13 12:01:54 +00:00
" tp, tn, fp, fn = values['TP'], values['TN'], values['FP'], values['FN']\n",
" precision, recall, accuracy, f1_score = calculate_metrics(tp, tn, fp, fn)\n",
2025-03-13 22:52:06 +00:00
" metrics = {\"Datapoint\": key, \"F1-Score\": f1_score, \"Precision\": precision, \"Recall\": recall, \"Accuracy\": accuracy, \"SUPPORT\": values[\"SUPPORT\"], \"TP\": tp, \"TN\": tn, \"FP\": fp, \"FN\": fn}\n",
2025-03-13 16:53:27 +00:00
" metrics_list.append(metrics)\n",
2025-03-13 12:01:54 +00:00
" total_precision.append(precision)\n",
" total_recall.append(recall)\n",
" total_accuracy.append(accuracy)\n",
" total_f1_score.append(f1_score)\n",
" total_support.append(values[\"SUPPORT\"])\n",
" total_tp.append(tp)\n",
" total_tn.append(tn)\n",
" total_fp.append(fp)\n",
" total_fn.append(fn)\n",
"\n",
" if values[\"SUPPORT\"] > 0 and key > \"\":\n",
2025-03-13 22:52:06 +00:00
" print(\"{:<50}\\t{:<10.4f}\\t{:<10.4f}\\t{:<10.4f}\\t{:<10.4f}\\t{:<10.0f}\\t{:<10.0f}\\t{:<10.0f}\\t{:<10.0f}\\t{:<10.0f}\".format(key, f1_score, precision, recall, accuracy, values[\"SUPPORT\"], tp, tn, fp, fn))\n",
2025-03-13 12:01:54 +00:00
" except:\n",
" pass\n",
2025-03-13 16:53:27 +00:00
" total_mean_precision = statistics.mean(total_precision)\n",
" total_mean_recall = statistics.mean(total_recall)\n",
" total_mean_accuracy = statistics.mean(total_accuracy)\n",
" total_mean_f1_score = statistics.mean(total_f1_score)\n",
" total_sum_support = sum(total_support)\n",
" total_sum_tp = sum(total_tp)\n",
" total_sum_tn = sum(total_tn)\n",
" total_sum_fp = sum(total_fp)\n",
" total_sum_fn = sum(total_fn)\n",
" total_metrics = {\"Datapoint\": \"TOTAL\", \"F1-Score\": total_mean_f1_score, \"Precision\": total_mean_precision, \"Recall\": total_mean_recall, \"Accuracy\": total_mean_accuracy, \"SUPPORT\": total_sum_support, \"TP\": total_sum_tp, \"TN\": total_sum_tn, \"FP\": total_sum_fp, \"FN\": total_sum_fn}\n",
" metrics_list.append(total_metrics)\n",
2025-03-13 22:52:06 +00:00
" print(\"{:<50}\\t{:<10.4f}\\t{:<10.4f}\\t{:<10.4f}\\t{:<10.4f}\\t{:<10.0f}\\t{:<10.0f}\\t{:<10.0f}\\t{:<10.0f}\\t{:<10.0f}\".format(\"TOTAL\", total_mean_f1_score, total_mean_precision, total_mean_recall, total_mean_accuracy, total_sum_support, total_sum_tp, total_sum_tn, total_sum_fp, total_sum_fn))\n",
2025-03-13 16:53:27 +00:00
" return metrics_list\n",
2025-03-13 12:01:54 +00:00
" \n",
"def create_metrics_df(data):\n",
" # Define a list to hold data for DataFrame\n",
" rows = []\n",
" \n",
" # Iterate through each metric item\n",
" for key in imp_datapoints:\n",
" try:\n",
" mapped_key = imp_datapoints_mapping[key]\n",
" values = data[mapped_key]\n",
" tp, tn, fp, fn = values['TP'], values['TN'], values['FP'], values['FN']\n",
" precision, recall, accuracy, f1_score = calculate_metrics(tp, tn, fp, fn)\n",
" \n",
" # Only add rows where SUPPORT > 0\n",
" if values[\"SUPPORT\"] > 0:\n",
" row = {\n",
" \"Metric\": key,\n",
" \"Precision\": precision,\n",
" \"Recall\": recall,\n",
" \"Accuracy\": accuracy,\n",
" \"F1-Score\": f1_score,\n",
" \"SUPPORT\": values[\"SUPPORT\"]\n",
" }\n",
" rows.append(row)\n",
" except KeyError as e:\n",
" continue\n",
"\n",
" # Create a DataFrame from the list of rows\n",
" df_metrics = pd.DataFrame(rows)\n",
" df_metrics.reset_index(inplace=True)\n",
" df_metrics.drop(columns=[\"index\"], inplace=True)\n",
" print(df_metrics)\n",
" return df_metrics\n",
"\n",
"\n",
"\n",
"def get_provider_mapping(file_path):\n",
" df = pd.read_excel(file_path)\n",
" df = (df.groupby([\"Docid\", \"ProviderName\"]).first())\n",
" df.reset_index(inplace = True)\n",
" return df[[\"Docid\", \"ProviderName\"]]\n",
"\n",
"\n",
"def get_provider_names(generated_results_indexed, df_provider_mapping):\n",
" providers_dict = {}\n",
" for doc_id in generated_results_indexed:\n",
" try:\n",
" provider_name = (df_provider_mapping[df_provider_mapping[\"Docid\"] == doc_id][\"ProviderName\"].values)[0]\n",
" if provider_name in providers_dict:\n",
" providers_dict[provider_name].append(doc_id)\n",
" else:\n",
" providers_dict[provider_name] = []\n",
" providers_dict[provider_name].append(doc_id)\n",
"\n",
" except:\n",
" pass\n",
" return providers_dict\n",
"\n",
"def get_specified_doc_data(results, doc_list):\n",
" provider_res = {}\n",
" for doc_id in doc_list:\n",
" if doc_id in results:\n",
" provider_res[doc_id] = results[doc_id]\n",
2025-03-18 11:13:55 +00:00
" return provider_res\n"
]
},
{
"cell_type": "code",
2025-03-27 04:14:28 +00:00
"execution_count": 49,
2025-03-18 11:13:55 +00:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\n",
"\n",
"All Providers Results: \n",
"Document List File - None\n",
"Metric \tF1-Score \tPrecision \tRecall \tAccuracy \tSUPPORT \tTP \tTN \tFP \tFN \n",
2025-03-27 04:14:28 +00:00
"management_fee_and_costs \t0.9375 \t0.8993 \t0.9791 \t0.8829 \t424 \t375 \t2 \t42 \t8 \n",
"management_fee \t0.9571 \t0.9353 \t0.9799 \t0.9180 \t424 \t390 \t2 \t27 \t8 \n",
"performance_fee_costs \t0.8801 \t0.8601 \t0.9011 \t0.8431 \t291 \t246 \t114 \t40 \t27 \n",
"interposed_vehicle_performance_fee_cost \t0.9172 \t0.8471 \t1.0000 \t0.9696 \t73 \t72 \t342 \t13 \t0 \n",
"administration_fees \t0.9081 \t0.8317 \t1.0000 \t0.9602 \t84 \t84 \t326 \t17 \t0 \n",
"total_annual_dollar_based_charges \t0.9930 \t0.9861 \t1.0000 \t0.9977 \t71 \t71 \t355 \t1 \t0 \n",
"buy_spread \t0.9291 \t0.8930 \t0.9681 \t0.8806 \t376 \t334 \t42 \t40 \t11 \n",
"sell_spread \t0.9291 \t0.8930 \t0.9681 \t0.8806 \t376 \t334 \t42 \t40 \t11 \n",
"minimum_initial_investment \t0.9507 \t0.9633 \t0.9383 \t0.9297 \t308 \t289 \t108 \t11 \t19 \n",
"benchmark_name \t0.9139 \t0.8846 \t0.9452 \t0.9391 \t156 \t138 \t263 \t18 \t8 \n",
"TOTAL \t0.9316 \t0.8994 \t0.9680 \t0.9201 \t2583 \t2333 \t1596 \t249 \t92 \n",
"Total Shares Matched - 379\n",
"Total Shares Not Matched - 128\n",
"Percentage of Shares Matched - 74.7534516765286\n",
"Not Matched Shares Name List - ['SPDR® S&P World ex Australia Carbon Control Fund', 'Mercer Multi-manager Growth Fund – –
"All Providers Results: \n",
"Document List File - ./sample_documents/aus_prospectus_29_documents_sample.txt\n",
"Metric \tF1-Score \tPrecision \tRecall \tAccuracy \tSUPPORT \tTP \tTN \tFP \tFN \n",
"management_fee_and_costs \t0.9621 \t0.9270 \t1.0000 \t0.9270 \t177 \t165 \t0 \t13 \t0 \n",
"management_fee \t0.9886 \t0.9775 \t1.0000 \t0.9775 \t177 \t174 \t0 \t4 \t0 \n",
"performance_fee_costs \t0.8557 \t0.8037 \t0.9149 \t0.8371 \t100 \t86 \t63 \t21 \t8 \n",
"interposed_vehicle_performance_fee_cost \t0.8966 \t0.8125 \t1.0000 \t0.9326 \t53 \t52 \t114 \t12 \t0 \n",
"administration_fees \t0.9655 \t0.9333 \t1.0000 \t0.9944 \t14 \t14 \t163 \t1 \t0 \n",
"buy_spread \t0.9496 \t0.9091 \t0.9938 \t0.9045 \t175 \t160 \t1 \t16 \t1 \n",
"sell_spread \t0.9464 \t0.9034 \t0.9938 \t0.8989 \t175 \t159 \t1 \t17 \t1 \n",
"minimum_initial_investment \t0.9064 \t0.9528 \t0.8643 \t0.8596 \t140 \t121 \t32 \t6 \t19 \n",
"benchmark_name \t0.9186 \t0.8587 \t0.9875 \t0.9213 \t89 \t79 \t85 \t13 \t1 \n",
"TOTAL \t0.9322 \t0.8976 \t0.9727 \t0.9170 \t1100 \t1010 \t459 \t103 \t122 \n",
"Total Shares Matched - 173\n",
2025-03-26 23:58:45 +00:00
"Total Shares Not Matched - 18\n",
2025-03-27 04:14:28 +00:00
"Percentage of Shares Matched - 90.57591623036649\n",
"Not Matched Shares Name List - ['Dimensional Australian Core Equity Trust', 'FC W Pen-CFS TTR Global Infrastructure Securities', 'CFS MIF-High Growth', 'CFS MIF-Property Securities', 'CFS MIF-Geared Share NEF', 'CFS MIF-Australian Share', 'CFS MIF-Geared Global Share', 'CFS MIF-Global Tech & Comm', 'CFS MIF-Stewart Inv Worldwide Leaders Sustainability', 'CFS MIF-Geared Share', 'CFS MIF-Diversified', 'CFS MIF-Janus Henderson Global Natural Resources Fund', 'CFS MIF-Macquarie Australian Emerging Companies', 'CFS MIF-Balanced', 'CFS MIF-Conservative', 'CFS MIF-Imputation', 'CFS MIF-Global Health & Biotech', 'Dimensional Australia Core Equity Trust - Active ETF']\n",
"All Providers Results: \n",
"Document List File - ./sample_documents/aus_prospectus_17_documents_sample.txt\n",
"Metric \tF1-Score \tPrecision \tRecall \tAccuracy \tSUPPORT \tTP \tTN \tFP \tFN \n",
"management_fee_and_costs \t0.9190 \t0.8787 \t0.9633 \t0.8514 \t247 \t210 \t2 \t29 \t8 \n",
"management_fee \t0.9330 \t0.9038 \t0.9643 \t0.8755 \t247 \t216 \t2 \t23 \t8 \n",
"performance_fee_costs \t0.8939 \t0.8939 \t0.8939 \t0.8474 \t191 \t160 \t51 \t19 \t19 \n",
"interposed_vehicle_performance_fee_cost \t0.9756 \t0.9524 \t1.0000 \t0.9960 \t20 \t20 \t228 \t1 \t0 \n",
"administration_fees \t0.8974 \t0.8140 \t1.0000 \t0.9357 \t70 \t70 \t163 \t16 \t0 \n",
"total_annual_dollar_based_charges \t1.0000 \t1.0000 \t1.0000 \t1.0000 \t71 \t71 \t178 \t0 \t0 \n",
"buy_spread \t0.9110 \t0.8788 \t0.9457 \t0.8635 \t201 \t174 \t41 \t24 \t10 \n",
"sell_spread \t0.9138 \t0.8838 \t0.9459 \t0.8675 \t201 \t175 \t41 \t23 \t10 \n",
"minimum_initial_investment \t0.9853 \t0.9711 \t1.0000 \t0.9799 \t168 \t168 \t76 \t5 \t0 \n",
"benchmark_name \t0.9077 \t0.9219 \t0.8939 \t0.9518 \t67 \t59 \t178 \t5 \t7 \n",
"TOTAL \t0.9337 \t0.9098 \t0.9607 \t0.9169 \t1483 \t1323 \t960 \t145 \t184 \n",
"Total Shares Matched - 249\n",
"Total Shares Not Matched - 110\n",
"Percentage of Shares Matched - 69.35933147632312\n",
"Not Matched Shares Name List - ['SPDR® S&P World ex Australia Carbon Control Fund', 'Mercer Multi-manager Growth Fund – –
2025-03-18 11:13:55 +00:00
]
}
],
"source": [
2025-03-13 12:01:54 +00:00
"\n",
2025-03-18 11:13:55 +00:00
"\"\"\"\n",
"Blade's updates\n",
"1. Set the secondary key to be the share class name, instead of the fund name\n",
"2. Remove the data point which support is 0 to calculate the metrics\n",
"3. Add the message list to store the error message\n",
"4. Support save metrics/ error message to excel file\n",
"5. Support statistics for different document list\n",
"6. Set F1-Score to the first column in the metrics table\n",
"\"\"\"\n",
"\n",
"# Load the files\n",
"headers_gt, ground_truth_data = load_excel(path_ground_truth, 0)\n",
"headers_gen, generated_results_data = load_excel(path_generated_results, 0)\n",
"\n",
"# Assuming doc_id is the first column and fund_name is the second column\n",
2025-03-26 23:58:45 +00:00
"# doc_id_index = 0\n",
"# fund_name_index = 1\n",
2025-03-18 11:13:55 +00:00
"\n",
"# Index the data\n",
2025-03-26 23:58:45 +00:00
"ground_truth_indexed = index_data_by_key(ground_truth_data, headers_gt)\n",
"generated_results_indexed = index_data_by_key(generated_results_data, headers_gen)\n",
2025-03-18 11:13:55 +00:00
"\n",
"intersection = set(headers_gen).intersection(headers_gt)\n",
2025-03-13 12:01:54 +00:00
"\n",
2025-03-18 11:13:55 +00:00
"# Convert the result back to a list (if you need it as a list)\n",
"intersection_list = list(intersection)\n",
2025-03-13 12:01:54 +00:00
"\n",
2025-03-18 11:13:55 +00:00
"total_fn = []\n",
"\n",
"# df_provider_mapping = get_provider_mapping(provider_mapping_file_path)\n",
"\n",
"# all_provider_dict = get_provider_names(generated_results_indexed, df_provider_mapping)\n",
2025-03-13 12:01:54 +00:00
"\n",
"\n",
"# for provider_name in all_provider_dict:\n",
"# provider_vise_generated_results = get_specified_doc_data(generated_results_indexed, all_provider_dict[provider_name])\n",
"# comparison_results, funds_matched, funds_not_matched = compare_data(ground_truth_indexed, provider_vise_generated_results, headers_gt, doc_id_index, fund_name_index, intersection_list,funds_matched, funds_not_matched)\n",
"# print(\"\\n\")\n",
"# print(\"\\n\")\n",
"# print(\"Provider Name - \" + provider_name + \"\\t Number of Docs - \" + str(len(all_provider_dict[provider_name])))\n",
"# #create_metrics_df(comparison_results)\n",
"# print_metrics_table(comparison_results)\n",
"# print(\"Total Funds Matched - \" + str(funds_matched) + \"\\nTotal Funds Not Matched - \" + str(funds_not_matched))\n",
"# print(\"Percentage of Funds Matched - \" + str((funds_matched/(funds_matched + funds_not_matched))*100))\n",
"\n",
"\n",
"\n",
"print(\"\\n\")\n",
"print(\"\\n\")\n",
2025-03-27 04:14:28 +00:00
"document_list_file_list = [None, \n",
" \"./sample_documents/aus_prospectus_29_documents_sample.txt\", \n",
" \"./sample_documents/aus_prospectus_17_documents_sample.txt\"]\n",
"# document_list_file_list = [None]\n",
2025-03-13 16:53:27 +00:00
"for document_list_file in document_list_file_list:\n",
" document_list = None\n",
" if document_list_file is not None:\n",
" with open(document_list_file, \"r\", encoding=\"utf-8\") as f:\n",
" document_list = f.readlines()\n",
" document_list = [doc_id.strip() for doc_id in document_list]\n",
" \n",
" print(\"All Providers Results: \")\n",
" print(\"Document List File - \", document_list_file)\n",
2025-03-26 23:58:45 +00:00
" comparison_results, message_list, share_matched, \\\n",
" share_not_matched, not_matched_share_name_list = compare_data(ground_truth_indexed, \n",
" generated_results_indexed,\n",
" headers_gt,\n",
" intersection_list,\n",
" document_list)\n",
2025-03-13 16:53:27 +00:00
" metrics_list = print_metrics_table(comparison_results)\n",
2025-03-26 23:58:45 +00:00
" print(\"Total Shares Matched - \" + str(share_matched) + \"\\nTotal Shares Not Matched - \" + str(share_not_matched))\n",
" print(\"Percentage of Shares Matched - \" + str((share_matched/(share_matched + share_not_matched))*100))\n",
" print(\"Not Matched Shares Name List - \", not_matched_share_name_list)\n",
2025-03-13 16:53:27 +00:00
"\n",
" metrics_df = pd.DataFrame(metrics_list)\n",
" message_df = pd.DataFrame(message_list)\n",
2025-03-26 23:58:45 +00:00
" share_matched_data = {\"share_matched\": share_matched, \"share_not_matched\": share_not_matched, \"not_matched_share_name_list\": not_matched_share_name_list}\n",
" share_matched_df = pd.DataFrame([share_matched_data])\n",
2025-03-13 16:53:27 +00:00
"\n",
" output_metrics_folder = r\"/data/aus_prospectus/output/metrics_data/\"\n",
2025-03-13 22:52:06 +00:00
" os.makedirs(output_metrics_folder, exist_ok=True)\n",
2025-03-13 16:53:27 +00:00
" if os.path.exists(output_metrics_folder):\n",
" generated_file_base_name = os.path.basename(path_generated_results).replace(\".xlsx\", \"\")\n",
" metrics_file_name = f\"metrics_{generated_file_base_name}\"\n",
" if document_list_file is not None:\n",
" metrics_file_name = f\"{metrics_file_name}_{len(document_list)}_documents.xlsx\"\n",
" else:\n",
" metrics_file_name = f\"{metrics_file_name}_all_documents.xlsx\"\n",
" metrics_file_path = os.path.join(output_metrics_folder, metrics_file_name)\n",
" with pd.ExcelWriter(metrics_file_path) as writer:\n",
" metrics_df.to_excel(writer, sheet_name=\"metrics_data\", index=False)\n",
2025-03-26 23:58:45 +00:00
" message_df.to_excel(writer, sheet_name=\"message_data\", index=False)\n",
" share_matched_df.to_excel(writer, sheet_name=\"share_matched_data\", index=False)\n"
2025-03-13 12:01:54 +00:00
]
},
{
"cell_type": "code",
2025-03-26 23:58:45 +00:00
"execution_count": 6,
2025-03-13 12:01:54 +00:00
"metadata": {},
2025-03-26 23:58:45 +00:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'data_point': 'performance_fee_costs', 'doc_id': 539791362, 'sec_name': 'REST High Growth Pension', 'truth': '0.6', 'generated': '0.08', 'error': 'Truth is not equal with generated'}\n"
]
}
],
2025-03-18 11:13:55 +00:00
"source": [
"for message_list_element in message_list:\n",
" if message_list_element[\"data_point\"] == \"performance_fee_costs\":\n",
" print(message_list_element)"
]
2025-03-13 12:01:54 +00:00
},
{
"cell_type": "code",
2025-03-24 23:00:53 +00:00
"execution_count": null,
2025-03-13 12:01:54 +00:00
"metadata": {},
2025-03-24 23:00:53 +00:00
"outputs": [],
2025-03-18 12:24:33 +00:00
"source": [
"import pandas as pd\n",
"\n",
"\n",
"# Convert data to DataFrame\n",
"df = pd.DataFrame(message_list)\n",
"\n",
"# Sort DataFrame by 'doc_id'\n",
"df_sorted = df.sort_values(by=['doc_id'])\n",
"\n",
"# Save DataFrame to Excel file\n",
2025-03-18 19:15:43 +00:00
"os.makedirs(\"/data/aus_prospectus/output/error_analysis/\", exist_ok=True)\n",
"output_filename = r\"/data/aus_prospectus/output/error_analysis/anomalies_found.xlsx\"\n",
2025-03-18 12:24:33 +00:00
"df_sorted.to_excel(output_filename, index=False)\n",
"\n",
"print(f\"Excel file '{output_filename}' has been created successfully.\")\n"
]
2025-03-13 12:01:54 +00:00
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
2025-03-24 22:10:16 +00:00
"display_name": "emea_ar_test",
2025-03-13 12:01:54 +00:00
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
2025-03-18 19:15:43 +00:00
"version": "3.12.6"
2025-03-13 12:01:54 +00:00
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
