diff --git a/instructions/aus_prospectus/data_extraction_prompts_config.json b/instructions/aus_prospectus/data_extraction_prompts_config.json index 8417eea..642dbd6 100644 --- a/instructions/aus_prospectus/data_extraction_prompts_config.json +++ b/instructions/aus_prospectus/data_extraction_prompts_config.json @@ -17,8 +17,8 @@ "data_business_features": { "common": [ "## General rules", - "- 1. The data is in the context, perhaps in table(s), semi-table(s) or paragraphs.", - "- 2. Fund name: ", + "1. The data is in the context, perhaps in table(s), semi-table(s) or paragraphs.", + "2. Fund name: ", "a. The full fund name should be main fund name + sub-fund name, e,g, main fund name is Black Rock European, sub-fund name is Growth, the full fund name is: Black Rock European Growth.", "b. The sub-fund name may be as the first column or first row values in the table.", "b.1 fund name example:", @@ -67,12 +67,12 @@ "---Example 3 End---", "Although exist \"Retirement account\" and \"Transition to Retirement account\", but the investment option is not exist, so fund name and share name should be: \"Rest Pension\".", "\n", - "- 3. Only extract the latest data from context:", + "3. Only extract the latest data from context:", "If with multiple data values in same row, please extract the latest.", "\n", - "- 4. Reported names:", + "4. Reported names:", "Only output the values which with significant reported names.", - "- Multiple data columns with same reported name but different post-fix:", + "Multiple data columns with same reported name but different post-fix:", "If there are multiple reported names with different post-fix text, here is the priority rule:", "The pos-fix text is in the brackets: (gross), (net), pick up the values from (net).", "---Example Start---", @@ -80,14 +80,14 @@ "---Example End---", "The output should be:", "{\"data\": [{\"fund name\": \"Allan Gray Australian Equity Fund\", \"share name\": \"Class A\", \"management_fee_and_costs\": 1.19, \"management_fee\": 0.77, \"administration_fees\": 0.42}]}", - "- 5. Please ignore these words as fund names, it means never extract these words as fund names. They are:", + "5. Please ignore these words as fund names, it means never extract these words as fund names. They are:", "\"Ready-made portfolios\", \"Simple choice\", \"Build-your-own portfolio\".", - "- 6. Identify the value of data point and if it is written 0% or 0.00% or 0 or 0.00 then extract the same as 0 do not assume null for the same and return its values as 0", + "6. Identify the value of data point and if it is written 0% or 0.00% or 0 or 0.00 then extract the same as 0 do not assume null for the same and return its values as 0", "---Example Start---", "Retirement account \n\nInvestment option \n(A) Investment fees \nand costs (including \n(B) performance \nfees) (pa)* \n(B) Performance \nfees (pa) \n# \n(C) Transaction \ncosts (pa)*^ \n(A) + (C) Total \ninvestment cost \n(pa) \nBalanced – Indexed 0.00% 0.00% 0.00% 0.00%\n", "---Example End---", "For this example, as \"Investment fees and costs (including (B) performance fees)\" and \"Performance fees (pa)\" mentioned as 0.00% so return 0 as datapoint values.", - "- 7. If for data point value specifically Nil is written in the value then return NULL('') for the same" + "7. If for data point value specifically Nil is written in the value then return NULL('') for the same" ], "investment_level": { "total_annual_dollar_based_charges": "Total annual dollar based charges is share level data.", @@ -320,7 +320,8 @@ "FOUND \"Cost of product\", IGNORE ALL OF INFORMATION BELOW IT!!! JUST RETURN EMPTY RESPONSE!!!", "The output should be:", "{\"data\": []}", - "L. Do NOT infer or copy investment fees or management fees from examples provided for specific funds to other investment options. Only extract 'management_fee_and_costs' and 'management_fee' if explicitly stated separately for each investment option." + "L. Do NOT infer or copy investment fees or management fees from examples provided for specific funds to other investment options. Only extract 'management_fee_and_costs' and 'management_fee' if explicitly stated separately for each investment option.", + "M. Identify the value of management fee and costs, and if it is written 0% or 0.00% or 0 or 0.00, then extract the same as 0, please don't ignore it." ], "administration_fees":[ "### Administration fees and costs", diff --git a/main.py b/main.py index 324c613..8d2eeda 100644 --- a/main.py +++ b/main.py @@ -1522,8 +1522,8 @@ if __name__ == "__main__": # get_aus_prospectus_document_category() - re_run_extract_data = False - re_run_mapping_data = False + re_run_extract_data = True + re_run_mapping_data = True force_save_total_data = True doc_source = "aus_prospectus" # doc_source = "emea_ar" @@ -1531,46 +1531,44 @@ if __name__ == "__main__": # document_sample_file = ( # r"./sample_documents/aus_prospectus_verify_6_documents_sample.txt" # ) - document_sample_file_list = [ - r"./sample_documents/aus_prospectus_46_documents_sample.txt", - r"./sample_documents/aus_prospectus_verify_6_documents_sample.txt", - ] - for document_sample_file in document_sample_file_list: - logger.info(f"Start to run document sample file: {document_sample_file}") - with open(document_sample_file, "r", encoding="utf-8") as f: - special_doc_id_list = [doc_id.strip() for doc_id in f.readlines() - if len(doc_id.strip()) > 0] - # special_doc_id_list = ["401212184"] - pdf_folder: str = r"/data/aus_prospectus/pdf/" - output_pdf_text_folder: str = r"/data/aus_prospectus/output/pdf_text/" - output_extract_data_child_folder: str = ( - r"/data/aus_prospectus/output/extract_data/docs/" - ) - output_extract_data_total_folder: str = ( - r"/data/aus_prospectus/output/extract_data/total/" - ) - output_mapping_child_folder: str = ( - r"/data/aus_prospectus/output/mapping_data/docs/" - ) - output_mapping_total_folder: str = ( - r"/data/aus_prospectus/output/mapping_data/total/" - ) - drilldown_folder = r"/data/aus_prospectus/output/drilldown/" + document_sample_file = ( + r"./sample_documents/aus_prospectus_46_documents_sample.txt" + ) + logger.info(f"Start to run document sample file: {document_sample_file}") + with open(document_sample_file, "r", encoding="utf-8") as f: + special_doc_id_list = [doc_id.strip() for doc_id in f.readlines() + if len(doc_id.strip()) > 0] + # special_doc_id_list = ["420339794"] + pdf_folder: str = r"/data/aus_prospectus/pdf/" + output_pdf_text_folder: str = r"/data/aus_prospectus/output/pdf_text/" + output_extract_data_child_folder: str = ( + r"/data/aus_prospectus/output/extract_data/docs/" + ) + output_extract_data_total_folder: str = ( + r"/data/aus_prospectus/output/extract_data/total/" + ) + output_mapping_child_folder: str = ( + r"/data/aus_prospectus/output/mapping_data/docs/" + ) + output_mapping_total_folder: str = ( + r"/data/aus_prospectus/output/mapping_data/total/" + ) + drilldown_folder = r"/data/aus_prospectus/output/drilldown/" - batch_run_documents( - doc_source=doc_source, - special_doc_id_list=special_doc_id_list, - pdf_folder=pdf_folder, - output_pdf_text_folder=output_pdf_text_folder, - output_extract_data_child_folder=output_extract_data_child_folder, - output_extract_data_total_folder=output_extract_data_total_folder, - output_mapping_child_folder=output_mapping_child_folder, - output_mapping_total_folder=output_mapping_total_folder, - drilldown_folder=drilldown_folder, - re_run_extract_data=re_run_extract_data, - re_run_mapping_data=re_run_mapping_data, - force_save_total_data=force_save_total_data - ) + batch_run_documents( + doc_source=doc_source, + special_doc_id_list=special_doc_id_list, + pdf_folder=pdf_folder, + output_pdf_text_folder=output_pdf_text_folder, + output_extract_data_child_folder=output_extract_data_child_folder, + output_extract_data_total_folder=output_extract_data_total_folder, + output_mapping_child_folder=output_mapping_child_folder, + output_mapping_total_folder=output_mapping_total_folder, + drilldown_folder=drilldown_folder, + re_run_extract_data=re_run_extract_data, + re_run_mapping_data=re_run_mapping_data, + force_save_total_data=force_save_total_data + ) elif doc_source == "emea_ar": special_doc_id_list = ["321733631"] batch_run_documents( diff --git a/performance.ipynb b/performance.ipynb index 1fe0334..6a2f94c 100644 --- a/performance.ipynb +++ b/performance.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -15,51 +15,51 @@ "from utils.similarity import Similarity\n", "\n", "\n", - "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", - "\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", - " \"Interposed vehicle Performance fee and Costs\": \"interposed_vehicle_performance_fee_cost\",\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", - " \"Performance Fee\": \"PerformanceFeeCharged\",\n", - " \"Minimum Initial Investment\": \"minimum_initial_investment\",\n", - " \"Benchmark\": \"benchmark_name\"\n", - "}\n", - "\n", - "# 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", + "# 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", "\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", + "# \"Interposed vehicle Performance fee and Costs\": \"interposed_vehicle_performance_fee_cost\",\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", + "# \"Sell Spread\": \"sell_spread\",\n", + "# \"Performance Fee\": \"PerformanceFeeCharged\",\n", + "# \"Minimum Initial Investment\": \"minimum_initial_investment\",\n", + "# \"Benchmark\": \"benchmark_name\"\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", + "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", "# path_generated_results = r\"/data/aus_prospectus/output/mapping_data/total/mapping_data_info_46_documents_by_text_20250317.xlsx\"\n", - "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", + "# path_generated_results = r\"/data/aus_prospectus/output/mapping_data/total/mapping_data_info_46_documents_by_text_20250327230323.xlsx\"\n", + "path_generated_results = r\"/data/aus_prospectus/output/mapping_data/total/mapping_data_info_6_documents_by_text_20250328004858.xlsx\"\n", "provider_mapping_file_path = r\"/data/aus_prospectus/ground_truth/phase2_file/46_documents/TopProvidersBiz.xlsx\"\n", "\n" ] }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -349,7 +349,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -363,56 +363,18 @@ "All Providers Results: \n", "Document List File - None\n", "Metric \tF1-Score \tPrecision \tRecall \tAccuracy \tSUPPORT \tTP \tTN \tFP \tFN \n", - "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 – Retail Units', 'Mercer Multi-manager High Growth Fund – Retail Units', 'ANZ OA Inv-OnePath Multi Asset Income EF', 'ANZ OA IP-OnePath Australian Shares', 'ANZ OA IP-OnePath Diversified Fixed Interest', 'ANZ OA IP-OP Diversified Credit EF', 'ANZ OA IP-OP Diversified Credit NE', 'OneAnswer Investment Portfolio - Schroder Strategic Growth -NE', 'OnePath ANZ OA IP-T. Rowe Price Dyna Gl Bond EF', 'OnePath ANZ OA IP-T. Rowe Price Dyna Gl Bond NE', 'OnePath OA Investment Portfolio-BlackRock Tactical Growth EF', 'OnePath OA Inv-Greencape Broadcap EF', 'OnePath OA Inv-Nikko AM Australian Shares EF', 'OnePath OA IP- Pendal Monthly Income Plus-EF/Sel', 'OnePath OA IP- Pendal Monthly Income Plus-NEF', 'OnePath OA IP-Alternatives Growth Fund-EF/Sel', 'OnePath OA IP-Alternatives Growth Fund-NEF', 'OnePath OA IP-ANZ Cash Advantage-EF/Sel', 'OnePath OA IP-ANZ Cash Advantage-NEF', 'OnePath OA IP-Ausbil Australian Emerging Leaders Trust-EF/Sel', 'OnePath OA IP-Bennelong Australian Equities-EF/Sel', 'OnePath OA IP-Bentham Global Income Trust-EF/Sel', 'OnePath OA IP-Bentham Global Income Trust-NEF', 'OnePath OA IP-Fidelity Australian Equities-EF/Sel', 'OnePath OA IP-Investors Mutual Australian Share Trust- EF/Sel', 'OnePath OA IP-Kapstream Absolute Return Income Trust-EF/Sel', 'OnePath OA IP-Kapstream Absolute Return Income Trust-NEF', 'OnePath OA IP-Merlon Australian Share Income-EF/Sel', 'OnePath OA IP-OnePath Active Growth Trust-NEF', 'OnePath OA IP-OnePath High Growth Trust-EF/Sel', 'OnePath OA IP-OnePath High Growth Trust-NEF', 'OnePath OA IP-OnePath Managed Growth Trust-EF/Sel', 'OnePath OA IP-OnePath Managed Growth Trust-NEF', 'OnePath OA IP-OptiMix Australian Fixed Interest Trust-EF/Sel', 'OnePath OA IP-OptiMix Australian Fixed Interest Trust-NEF', 'OnePath OA IP-OptiMix Australian Share Trust-EF/Sel', 'OnePath OA IP-OptiMix Australian Share Trust-NEF', 'OnePath OA IP-OptiMix Global Emerging Markets Share-EF/Sel', 'OnePath OA IP-OptiMix Global Emerging Markets Share-NEF', 'OnePath OA IP-OptiMIx Global Share Trust-EF/Sel', 'OnePath OA IP-OptiMIx Global Share Trust-NEF', 'OnePath OA IP-OptiMix High Growth Trust-EF/Sel', 'OnePath OA IP-OptiMix High Growth Trust-NEF', 'OnePath OA IP-OptiMix Property Securities Trust-EF/Sel', 'OnePath OA IP-OptiMix Property Securities Trust-NEF', 'OnePath OA IP-Perpetual Balanced Growth Trust-EF/Sel', 'OnePath OA IP-Perpetual Balanced Growth Trust-NEF', 'OnePath OA IP-Perpetual Conservative Growth Trust-EF/Sel', 'OnePath OA IP-Perpetual Conservative Growth Trust-NEF', 'OnePath OA IP-Schroder Fixed Income-EF/Sel', 'OnePath OA IP-Schroder Fixed Income-NEF', 'OnePath OA IP-UBS Balanced Trust-EF/Sel', 'OnePath OA IP-UBS Balanced Trust-NEF', 'OnePath OA IP-UBS Defensive Trust-EF/Sel', 'OnePath OA IP-UBS Defensive Trust-NEF', 'OnePath OA IP-UBS Diversified Fixed Income Trust-EF/Sel', 'OnePath OA IP-UBS Diversified Fixed Income Trust-NEF', 'OnePath OneAnswer Investment Portfolio - Ardea Real Outcome -EF/Sel', 'OnePath OneAnswer Investment Portfolio - Ardea Real Outcome -NE', 'OnePath OneAnswer Investment Portfolio - Barrow Hanley Concentrated Global Shares Hedged -EF/Sel', 'OnePath OneAnswer Investment Portfolio - Barrow Hanley Concentrated Global Shares Hedged -NE', 'OnePath OneAnswer Investment Portfolio - BlackRock Advantage Australian Equity -EF/Sel', 'OnePath OneAnswer Investment Portfolio - BlackRock Advantage Australian Equity -NE', 'OnePath OneAnswer Investment Portfolio - BlackRock Diversified ESG Growth -EF/Sel', 'OnePath OneAnswer Investment Portfolio - BlackRock Diversified ESG Growth -NE', 'OnePath OneAnswer Investment Portfolio - First Sentier Imputation -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Australian Shares Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Balanced Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Balanced Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath Conservative Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Conservative Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath Diversified Bond Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Diversified Bond Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath Growth Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath High Growth Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath High Growth Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath International Shares Index (Hedged) -EF/Sel', 'OnePath OneAnswer Investment Portfolio - Schroder Strategic Growth -EF/Sel', 'OnePath Schroder Real Return Trust (Entry Fee)', 'OnePath Schroder Real Return Trust (Nil Entry Fee)', 'OnePath OA IP-Ausbil Australian Emerging Leaders Trust-NEF', 'Telstra Growth Pen', 'First Sentier Concentrated Aus Share', 'First Sentier Australian Small Companies', 'First Sentier Imputation', 'First Sentier Global Property Securities', 'First Sentier Australian Share', 'CFS FC-Investors Mutual Future Leaders', 'Stewart Worldwide Leaders Sustainability', 'First Sentier Property Securities', 'MyNorth Index Defensive', 'MLC MKPF - Inflation Plus - Conservative', 'MLC MasterKey Super Fundamentals - Perpetual Australian Share', 'MLC MKSF - Perpetual WS Ethical SRI Fund', 'MLC MasterKey Super Fundamentals - Perpetual Small Co Fund No.2', 'MLC MKSF - PIMCO Div. Fixed Interest Wholesale Class', 'MLC MKSF - Platinum Asia Fund', 'MLC MKSF - Platinum International Fund', 'MLC MKSF - PM CAPITAL Global Companies', 'MLC MKSF - Schroder WS Australian Equity', 'MLC MasterKey Pension Fundamentals (Pre Retirement) - MLC Aust Property Index', 'MLC MasterKey Super Fundamentals - MLC Australian Property Index', 'MLC MKSF - Vanguard Intl Shr Indx (Hgd)', 'MLC MKSF - Vanguard Intl Shr Indx', 'HOSTPLUS Fixed Interest Indexed Super', 'Lifeplan Investment Bond Perpetual Balanced Growth', 'Lifeplan Investment Bond Perpetual Conservative Growth', 'Lifeplan Investment Bond Perpetual Industrial Share', 'Lifeplan Investment Bond Vanguard® Australian Shares Index', '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_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", - "Total Shares Not Matched - 18\n", - "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 – Retail Units', 'Mercer Multi-manager High Growth Fund – Retail Units', 'ANZ OA Inv-OnePath Multi Asset Income EF', 'ANZ OA IP-OnePath Australian Shares', 'ANZ OA IP-OnePath Diversified Fixed Interest', 'ANZ OA IP-OP Diversified Credit EF', 'ANZ OA IP-OP Diversified Credit NE', 'OneAnswer Investment Portfolio - Schroder Strategic Growth -NE', 'OnePath ANZ OA IP-T. Rowe Price Dyna Gl Bond EF', 'OnePath ANZ OA IP-T. Rowe Price Dyna Gl Bond NE', 'OnePath OA Investment Portfolio-BlackRock Tactical Growth EF', 'OnePath OA Inv-Greencape Broadcap EF', 'OnePath OA Inv-Nikko AM Australian Shares EF', 'OnePath OA IP- Pendal Monthly Income Plus-EF/Sel', 'OnePath OA IP- Pendal Monthly Income Plus-NEF', 'OnePath OA IP-Alternatives Growth Fund-EF/Sel', 'OnePath OA IP-Alternatives Growth Fund-NEF', 'OnePath OA IP-ANZ Cash Advantage-EF/Sel', 'OnePath OA IP-ANZ Cash Advantage-NEF', 'OnePath OA IP-Ausbil Australian Emerging Leaders Trust-EF/Sel', 'OnePath OA IP-Bennelong Australian Equities-EF/Sel', 'OnePath OA IP-Bentham Global Income Trust-EF/Sel', 'OnePath OA IP-Bentham Global Income Trust-NEF', 'OnePath OA IP-Fidelity Australian Equities-EF/Sel', 'OnePath OA IP-Investors Mutual Australian Share Trust- EF/Sel', 'OnePath OA IP-Kapstream Absolute Return Income Trust-EF/Sel', 'OnePath OA IP-Kapstream Absolute Return Income Trust-NEF', 'OnePath OA IP-Merlon Australian Share Income-EF/Sel', 'OnePath OA IP-OnePath Active Growth Trust-NEF', 'OnePath OA IP-OnePath High Growth Trust-EF/Sel', 'OnePath OA IP-OnePath High Growth Trust-NEF', 'OnePath OA IP-OnePath Managed Growth Trust-EF/Sel', 'OnePath OA IP-OnePath Managed Growth Trust-NEF', 'OnePath OA IP-OptiMix Australian Fixed Interest Trust-EF/Sel', 'OnePath OA IP-OptiMix Australian Fixed Interest Trust-NEF', 'OnePath OA IP-OptiMix Australian Share Trust-EF/Sel', 'OnePath OA IP-OptiMix Australian Share Trust-NEF', 'OnePath OA IP-OptiMix Global Emerging Markets Share-EF/Sel', 'OnePath OA IP-OptiMix Global Emerging Markets Share-NEF', 'OnePath OA IP-OptiMIx Global Share Trust-EF/Sel', 'OnePath OA IP-OptiMIx Global Share Trust-NEF', 'OnePath OA IP-OptiMix High Growth Trust-EF/Sel', 'OnePath OA IP-OptiMix High Growth Trust-NEF', 'OnePath OA IP-OptiMix Property Securities Trust-EF/Sel', 'OnePath OA IP-OptiMix Property Securities Trust-NEF', 'OnePath OA IP-Perpetual Balanced Growth Trust-EF/Sel', 'OnePath OA IP-Perpetual Balanced Growth Trust-NEF', 'OnePath OA IP-Perpetual Conservative Growth Trust-EF/Sel', 'OnePath OA IP-Perpetual Conservative Growth Trust-NEF', 'OnePath OA IP-Schroder Fixed Income-EF/Sel', 'OnePath OA IP-Schroder Fixed Income-NEF', 'OnePath OA IP-UBS Balanced Trust-EF/Sel', 'OnePath OA IP-UBS Balanced Trust-NEF', 'OnePath OA IP-UBS Defensive Trust-EF/Sel', 'OnePath OA IP-UBS Defensive Trust-NEF', 'OnePath OA IP-UBS Diversified Fixed Income Trust-EF/Sel', 'OnePath OA IP-UBS Diversified Fixed Income Trust-NEF', 'OnePath OneAnswer Investment Portfolio - Ardea Real Outcome -EF/Sel', 'OnePath OneAnswer Investment Portfolio - Ardea Real Outcome -NE', 'OnePath OneAnswer Investment Portfolio - Barrow Hanley Concentrated Global Shares Hedged -EF/Sel', 'OnePath OneAnswer Investment Portfolio - Barrow Hanley Concentrated Global Shares Hedged -NE', 'OnePath OneAnswer Investment Portfolio - BlackRock Advantage Australian Equity -EF/Sel', 'OnePath OneAnswer Investment Portfolio - BlackRock Advantage Australian Equity -NE', 'OnePath OneAnswer Investment Portfolio - BlackRock Diversified ESG Growth -EF/Sel', 'OnePath OneAnswer Investment Portfolio - BlackRock Diversified ESG Growth -NE', 'OnePath OneAnswer Investment Portfolio - First Sentier Imputation -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Australian Shares Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Balanced Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Balanced Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath Conservative Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Conservative Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath Diversified Bond Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath Diversified Bond Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath Growth Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath High Growth Index -EF/Sel', 'OnePath OneAnswer Investment Portfolio - OnePath High Growth Index -NE', 'OnePath OneAnswer Investment Portfolio - OnePath International Shares Index (Hedged) -EF/Sel', 'OnePath OneAnswer Investment Portfolio - Schroder Strategic Growth -EF/Sel', 'OnePath Schroder Real Return Trust (Entry Fee)', 'OnePath Schroder Real Return Trust (Nil Entry Fee)', 'OnePath OA IP-Ausbil Australian Emerging Leaders Trust-NEF', 'Telstra Growth Pen', 'First Sentier Concentrated Aus Share', 'First Sentier Australian Small Companies', 'First Sentier Imputation', 'First Sentier Global Property Securities', 'First Sentier Australian Share', 'CFS FC-Investors Mutual Future Leaders', 'Stewart Worldwide Leaders Sustainability', 'First Sentier Property Securities', 'MyNorth Index Defensive', 'MLC MKPF - Inflation Plus - Conservative', 'MLC MasterKey Super Fundamentals - Perpetual Australian Share', 'MLC MKSF - Perpetual WS Ethical SRI Fund', 'MLC MasterKey Super Fundamentals - Perpetual Small Co Fund No.2', 'MLC MKSF - PIMCO Div. Fixed Interest Wholesale Class', 'MLC MKSF - Platinum Asia Fund', 'MLC MKSF - Platinum International Fund', 'MLC MKSF - PM CAPITAL Global Companies', 'MLC MKSF - Schroder WS Australian Equity', 'MLC MasterKey Pension Fundamentals (Pre Retirement) - MLC Aust Property Index', 'MLC MasterKey Super Fundamentals - MLC Australian Property Index', 'MLC MKSF - Vanguard Intl Shr Indx (Hgd)', 'MLC MKSF - Vanguard Intl Shr Indx', 'HOSTPLUS Fixed Interest Indexed Super', 'Lifeplan Investment Bond Perpetual Balanced Growth', 'Lifeplan Investment Bond Perpetual Conservative Growth', 'Lifeplan Investment Bond Perpetual Industrial Share', 'Lifeplan Investment Bond Vanguard® Australian Shares Index']\n" + "management_fee_and_costs \t0.9515 \t0.9074 \t1.0000 \t0.9074 \t54 \t49 \t0 \t5 \t0 \n", + "management_fee \t0.9515 \t0.9074 \t1.0000 \t0.9074 \t54 \t49 \t0 \t5 \t0 \n", + "performance_fee_costs \t0.9796 \t0.9796 \t0.9796 \t0.9630 \t50 \t48 \t4 \t1 \t1 \n", + "administration_fees \t1.0000 \t1.0000 \t1.0000 \t1.0000 \t54 \t54 \t0 \t0 \t0 \n", + "total_annual_dollar_based_charges \t1.0000 \t1.0000 \t1.0000 \t1.0000 \t16 \t16 \t38 \t0 \t0 \n", + "buy_spread \t1.0000 \t1.0000 \t1.0000 \t1.0000 \t20 \t20 \t34 \t0 \t0 \n", + "sell_spread \t1.0000 \t1.0000 \t1.0000 \t1.0000 \t20 \t20 \t34 \t0 \t0 \n", + "TOTAL \t0.9832 \t0.9706 \t0.9971 \t0.9683 \t268 \t256 \t110 \t11 \t1 \n", + "Total Shares Matched - 54\n", + "Total Shares Not Matched - 16\n", + "Percentage of Shares Matched - 77.14285714285715\n", + "Not Matched Shares Name List - ['Vision Balanced Growth Pen', 'CFS FC W PSup-FirstRate Term Dep (10yr)', 'CFS FC W PSup-FirstRate Term Dep (15yr)', 'CFS FC W PSup-FirstRate Term Dep (2yr)', 'CFS FC W PSup-FirstRate Term Dep (3yr)', 'CFS FC W PSup-FirstRate Term Dep (5yr)', 'CFS FC W PSup-FirstRate Term Dep (7yr)', 'AV Australian Shares TTR', 'AV Balanced Growth TTR', 'AV Cash TTR', 'AV Conservative Growth TTR', 'AV Diversified Index TTR', 'AV Growth TTR', 'AV High Growth TTR', 'AV International Shares TTR', 'AV Stable Growth TTR']\n" ] } ], @@ -468,8 +430,9 @@ "print(\"\\n\")\n", "print(\"\\n\")\n", "document_list_file_list = [None, \n", - " \"./sample_documents/aus_prospectus_29_documents_sample.txt\", \n", - " \"./sample_documents/aus_prospectus_17_documents_sample.txt\"]\n", + " # \"./sample_documents/aus_prospectus_29_documents_sample.txt\", \n", + " # \"./sample_documents/aus_prospectus_17_documents_sample.txt\"\n", + " ]\n", "# document_list_file_list = [None]\n", "for document_list_file in document_list_file_list:\n", " document_list = None\n", @@ -514,150 +477,9 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'data_point': 'performance_fee_costs', 'doc_id': 377377369, 'sec_name': 'SPDR® S&P Emerging Markets Carbon Control Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'ANZ OA Inv-OnePath Multi Asset Income NEF', 'truth': '0', 'generated': '0.11', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'ANZ OA IP-OnePath Australian Shares NE', 'truth': '0', 'generated': '0.07', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'OnePath OA Investment Portfolio-BlackRock Tactical Growth NE', 'truth': '0', 'generated': '0.33', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'OnePath OneAnswer Investment Portfolio - OnePath Growth Index -NE', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard Index Diversified Bond Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard Index Australian Shares Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard High Yield Australian Shares Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard Index Australian Property Securities Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Macquarie Income Opps', 'truth': '0.03', 'generated': '0.12', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Perpetual Diversified Inc', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Schroder Fixed Income', 'truth': '0', 'generated': '0.01', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Perpetual Share Plus L/S', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Global Fund (Long Only)', 'truth': '0.24', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Global Fund (Long Only) P Class', 'truth': '0.24', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Fund', 'truth': '0.15', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Asia Fund', 'truth': '0.27', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Brands Fund', 'truth': '0.03', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Brands Fund P Class', 'truth': '0.03', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Healthcare Fund', 'truth': '0.86', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Technology Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum European Fund', 'truth': '0.24', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Japan Fund', 'truth': '0.15', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 397107472, 'sec_name': 'AMP Capital Specialist Diversified Fixed Income Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Ausbil Aus. Emrging Leaders', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Investors Mutual Aus. Shre', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Macquarie Inc Opportunities', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MasterKey Pension Fundamentals (Pre Retirement) - MLC Cash', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Global Share Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - IncomeBuilder', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - Hedged Global Share Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Hedged Global Share Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - PIMCO Div. Fixed Interest Wholesale Class', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - PIMCO Global Bond Wholesale Class', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - PIMCO Global Bond Wholesale Class', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - PM CAPITAL Global Companies', 'truth': '1.54', 'generated': '1.45', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 446324179, 'sec_name': 'Lifeplan Investment Bond - Allan Gray Australian Equity Fund Class A', 'truth': '0.28', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 446324179, 'sec_name': 'Lifeplan Investment Bond MLC Horizon 2-Capital Stable Open', 'truth': '0.05', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Core Equity Trust', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Small Company Trust', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Value Trust -Active ETF', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Australian Value Trust - Active ETF', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Core Equity Tr AUDHdg', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock Australian Fixed Interest Index', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock Australian Equity Index', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP Generations - AMP Cash Mgmt', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock Property Securities Index', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock International Equity Index (Unhedged)', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock International Equity Index (Hedged)', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539241700, 'sec_name': 'North Professional Balanced', 'truth': '0', 'generated': '0.05', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539261734, 'sec_name': 'ipac life choices Income Generator', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active High Growth Units', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Moderately Defensive', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Growth Units', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Balanced', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Defensive Units', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 527969661, 'sec_name': 'JPMorgan Global Equity Premium Income (Hedged) Complex ETF', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557526129, 'sec_name': 'Fortlake Real-Income Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557526129, 'sec_name': 'Fortlake Real-Higher Income Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 531373053, 'sec_name': 'Dimensional Australian Value Trust - Active ETF', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 531373053, 'sec_name': 'Dimensional Global Small Company Trust', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 541356150, 'sec_name': 'JPMorgan Global Research Enhanced Index Equity Trust - Class I', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 541356150, 'sec_name': 'JPMorgan Global Research Enhanced Index Equity Trust - Class I (Hedged)', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557362553, 'sec_name': 'JPMorgan Global Select Equity Active ETF', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 550522985, 'sec_name': 'RQI Global Value – Class A', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557362556, 'sec_name': 'JPMorgan Global Select Equity Fund - Class A (Hedged) Units', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557362556, 'sec_name': 'JPMorgan Global Select Equity Fund - Class A Units', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Core Equity Trust', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Small Company Trust', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Value Trust -Active ETF', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Australian Value Trust - Active ETF', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 530101994, 'sec_name': 'Dimensional Global Core Equity Tr AUDHdg', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock Australian Fixed Interest Index', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock Australian Equity Index', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP Generations - AMP Cash Mgmt', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock Property Securities Index', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock International Equity Index (Unhedged)', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266893, 'sec_name': 'AMP - Generations - BlackRock International Equity Index (Hedged)', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539241700, 'sec_name': 'North Professional Balanced', 'truth': '0', 'generated': '0.05', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539261734, 'sec_name': 'ipac life choices Income Generator', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active High Growth Units', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Moderately Defensive', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Growth Units', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Balanced', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 539266874, 'sec_name': 'SUMMIT Select - Active Defensive Units', 'truth': '0', 'generated': '0.06', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 527969661, 'sec_name': 'JPMorgan Global Equity Premium Income (Hedged) Complex ETF', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557526129, 'sec_name': 'Fortlake Real-Income Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557526129, 'sec_name': 'Fortlake Real-Higher Income Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 531373053, 'sec_name': 'Dimensional Australian Value Trust - Active ETF', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 531373053, 'sec_name': 'Dimensional Global Small Company Trust', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 541356150, 'sec_name': 'JPMorgan Global Research Enhanced Index Equity Trust - Class I', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 541356150, 'sec_name': 'JPMorgan Global Research Enhanced Index Equity Trust - Class I (Hedged)', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557362553, 'sec_name': 'JPMorgan Global Select Equity Active ETF', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 550522985, 'sec_name': 'RQI Global Value – Class A', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557362556, 'sec_name': 'JPMorgan Global Select Equity Fund - Class A (Hedged) Units', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 557362556, 'sec_name': 'JPMorgan Global Select Equity Fund - Class A Units', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 377377369, 'sec_name': 'SPDR® S&P Emerging Markets Carbon Control Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'ANZ OA Inv-OnePath Multi Asset Income NEF', 'truth': '0', 'generated': '0.11', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'ANZ OA IP-OnePath Australian Shares NE', 'truth': '0', 'generated': '0.07', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'OnePath OA Investment Portfolio-BlackRock Tactical Growth NE', 'truth': '0', 'generated': '0.33', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 401212184, 'sec_name': 'OnePath OneAnswer Investment Portfolio - OnePath Growth Index -NE', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard Index Diversified Bond Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard Index Australian Shares Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard High Yield Australian Shares Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 409723592, 'sec_name': 'Vanguard Index Australian Property Securities Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Macquarie Income Opps', 'truth': '0.03', 'generated': '0.12', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Perpetual Diversified Inc', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Schroder Fixed Income', 'truth': '0', 'generated': '0.01', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 411062815, 'sec_name': 'Perpetual WFP-Perpetual Share Plus L/S', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Global Fund (Long Only)', 'truth': '0.24', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Global Fund (Long Only) P Class', 'truth': '0.24', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Fund', 'truth': '0.15', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Asia Fund', 'truth': '0.27', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Brands Fund', 'truth': '0.03', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Brands Fund P Class', 'truth': '0.03', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Healthcare Fund', 'truth': '0.86', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum International Technology Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum European Fund', 'truth': '0.24', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 414751292, 'sec_name': 'Platinum Japan Fund', 'truth': '0.15', 'generated': '0', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 397107472, 'sec_name': 'AMP Capital Specialist Diversified Fixed Income Fund', 'truth': '', 'generated': '0', 'error': 'Truth is null and generated is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Ausbil Aus. Emrging Leaders', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Investors Mutual Aus. Shre', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Macquarie Inc Opportunities', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MasterKey Pension Fundamentals (Pre Retirement) - MLC Cash', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Global Share Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - IncomeBuilder', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - Hedged Global Share Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - Hedged Global Share Fund', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - PIMCO Div. Fixed Interest Wholesale Class', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - PIMCO Global Bond Wholesale Class', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPFPR - PIMCO Global Bond Wholesale Class', 'truth': '0', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 420339794, 'sec_name': 'MLC MKPF - PM CAPITAL Global Companies', 'truth': '1.54', 'generated': '1.45', 'error': 'Truth is not equal with generated'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 446324179, 'sec_name': 'Lifeplan Investment Bond - Allan Gray Australian Equity Fund Class A', 'truth': '0.28', 'generated': '', 'error': 'Generated is null and truth is not null'}\n", - "{'data_point': 'performance_fee_costs', 'doc_id': 446324179, 'sec_name': 'Lifeplan Investment Bond MLC Horizon 2-Capital Stable Open', 'truth': '0.05', 'generated': '', 'error': 'Generated is null and truth is not null'}\n" - ] - } - ], + "outputs": [], "source": [ "for message_list_element in message_list:\n", " if message_list_element[\"data_point\"] == \"performance_fee_costs\":\n",