Update curated.py

curated.py

@@ -456,6 +456,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("ArXiv"),
+        P("The ArXiv dataset is a vast collection of preprint research papers primarily in Mathematics, Computer Science, and Physics. Established in 1991, it offers high-quality text and mathematical knowledge, making it an invaluable resource for academic and scientific research. ArXiv papers are typically written in LaTeX, a popular typesetting system for these fields. We have extracted the information from latex and converted it into a text format."),
         H4("Download and Extraction"),
         P("All the data was downloaded in original latex format from Arxiv official S3 dump ", A("s3://arxic/src", href="s3://arxic/src"), ". We try to encode the downloaded data into utf-8 or guess encoding using chardet library. After that pandoc was used to extract information from the latex files and saved as markdown format",  D_code("pandoc -s {tex} -o out/{out_name}.md --wrap=none", language="python"), ". All markdowns were combined to create jsonl files."),
         H4("Filtering"),
@@ -472,6 +473,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("S2ORC - NEED TO MAKE S2ORC ABSTRACT AND UPDATE THIS FILTERING SECTION"),
+        P("The Semantic Scholar Open Research Corpus (S2ORC) is a comprehensive dataset designed for natural language processing (NLP) and text-mining research over scientific papers. It includes rich metadata, and abstract and full-text content for millions of academic papers across various disciplines. This dataset is further divided into two components, S2ORC abstract and S2ORC full text."),
         H4("Download and Extraction"),
         Ol(
             Li("This was downloaded directly in zip format using S2ORC api key and normal get request. code: response = urllib.request.urlopen(url)"),
@@ -509,6 +511,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("PubMed - need to update with abstract vs central"),
+        P(""),
         H4("Download and Extraction"),
         Ol(
             Li("First all the urls of PMC and PMA files are parsed and stored as text file from FTP server https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_package/"),
@@ -540,6 +543,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("Phil Papers"),
+        P("Papers from the PhilPapers database, a comprehensive index and bibliography of philosophy research maintained by the Center for Digital Philosophy at the University of Western Ontario."),
         H4("Download and Extraction"),
         P("Original PDF files download from", A("https://philarchive.org/oai.pl", href="https://philarchive.org/oai.pl"), ". All available PDF's were downloaded. Each PDF was converted to text using java", D_code("-jar ../philpapers_resources/src/pdfbox-app-2.0.21.jar ExtractText {f0} {FOUT.name}", language="java"), ". After converting to text formatting, a language was detected and added using the langdetect (citation needed) library."),
         H4("Filtering"),
@@ -552,6 +556,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("Europarl"),
+        P("A collection of multilingual parallel corpora of parliamentary debates from the European Parliament. This is a high-quality legacy dataset earlier used for translation tasks."),
         H4("Download and Extraction"),
         P("Original dataset was downloaded from", A("http://www.statmt.org/europarl/v7/europarl.tgz", href="http://www.statmt.org/europarl/v7/europarl.tgz"),". The files were converted to jsonl lines for filtering."),
         H4("Filtering"),
@@ -562,6 +567,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("HackerNews"),
+        P("High-quality dialog-based dataset where user comments on the links as the head post aggregated by Y Combinator."),
         H4("Download and Extraction"),
         P("The dataset was downloaded from the HackerNews repo here:", A("https://hacker-news.firebaseio.com/v0/item/", href="https://hacker-news.firebaseio.com/v0/item/"), ". The dataset was parsed using the Story ID. In this dataset each post is a story, and each reply is considered subsequent story. Story IDs were considered between ID 1 to 37500000.  The URL for all Story IDs was pinged. If that ID returned an error, the ID was removed. Each request was given a 2 second wait to account for network time."),
         P("The HackerNews dataset contains a vast amount of stories and is known for lively discussions. Due to the number of replies a story may contain, only longest threads included stories from the 3rd level onwards. All stories included the title (1st level) and all direct replies (2nd level). Replies to the replies (3rd level) are only included for X STORIES."),
@@ -577,6 +583,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("USPTO"),
+        P("Patent documents from the United States Patent and Trademark Office."),
         H4("Download and Extraction"),
         P("Data was downloaded and extracted using tags from", A("https://bulkdata.uspto.gov/data/patent/grant/redbook/fulltext/", href="https://bulkdata.uspto.gov/data/patent/grant/redbook/fulltext/"),". There were three different formats that needed three different functions to download and extract the data based on year: I(Pre_2002), 2002_to_2004, and post_2004."),
         H4("Filtering"),
@@ -591,6 +598,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("FreeLaw"),
+        P("Legal documents and court cases from various jurisdictions provided by US-registered non-profit firm Free Law Project. We have included data from CourtListener which included millions of legal opinions from federal and state courts."),
         H4("Download and Extraction"),
         #P("The dataset was downloaded from:" A("https://storage.courtlistener.com/bulk-data/", href="https://storage.courtlistener.com/bulk-data/"), )#". There are 19 CSV files which contain overlapping content. CSV files can contain content in multiple columns requiring a holistic extraction approach. Text was extracted from the following using html2text function. The block below shows how each text type was extracted."), 
         D_code("""
@@ -619,6 +627,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("StackExchange"),
+        P("A network of question-and-answer websites on various subjects, including programming, science, mathematics, and more. This is one of the largest publicly available repositories for question-answer pairs. We have included comments also to include an overall discussion on each post."),
         H4("Download and Extraction"),
         P("The archive dataset was used to download all data from StackExchange and StackExchange's sub URLs including: ", A("math.stackexchange.com", href="math.stackexchange.com"),". Raw data was extracted an XML format and only two files Posts.xml and Comments.xml were considered. To match the StackExchange hierarchy, each file was parsed using post_id to connect questions to answers and then to comments."),
         P("""
@@ -642,6 +651,7 @@ filtering_process = Div(
     Section(
         Div(
         H3("Ubuntu IRC"),
+        P("Chat logs from the Ubuntu Internet Relay Chat (IRC) channels on the Freenode IRC chat server. This data is also another form of dialog dataset on niche topics."),
         H4("Download and Extraction"),
         P("The dataset was downloaded from:", A("https://irclogs.ubuntu.com/{date.year}/{date.month:02d}/{date.day:02d}/", href="https://irclogs.ubuntu.com/{date.year}/{date.month:02d}/{date.day:02d}/"), " based on the year."),
         P("During extraction, the logs were cleaned using following functions:"),
@@ -669,6 +679,7 @@ filtering_process = Div(
     Section(
        Div(
         H3("DM Math"),
+        P("DeepMind Math dataset with generated questions from various topics like algebra, calculus, geometry, etc. Maths data is included to improve model reasoning abilities in the downstream tasks."),
         H4("Download and Extraction"),
         P("The dataset was downloaded rirectly downloaded from the Huggingface repo:", A("https://huggingface.co/datasets/deepmind/math_dataset",href="https://huggingface.co/datasets/deepmind/math_dataset"), ". The data was converted to the jsonl format where lines is represented as:"),
         D_code(""" 
@@ -687,7 +698,8 @@ filtering_process = Div(
     ),
     Section(
         Div(
-        H3("PG19"),
+        H3("PG-19"),
+        P("A collection of books from Project Gutenberg, a digital library of public domain works. This contains all the books that were published before 1919."),
         H4("Download and Extraction"),
         Ol(
             Li("The dataset was downloaded directly from Huggingface:", A("https://huggingface.co/datasets/deepmind/pg19", href="https://huggingface.co/datasets/deepmind/pg19"), "."),
@@ -821,47 +833,6 @@ data_pipeline_table = pd.DataFrame(
 table_html_data_pipe = data_pipeline_table.to_html(index=False, border=0)
 table_div_data_pipe = Div(NotStr(table_html_data_pipe), style="margin: 40px;")
 
-data_descriptions = pd.DataFrame(
-    {
-        "Source": [
-            "Papers - ArXiv",
-            "Papers - PhilPapers",
-            "Papers - S2ORC",
-            "Papers - PubMed Central",
-            "Papers - PubMed Abstract",
-            "Wikipedia",
-            "StackExchange",
-            "EuroParl",
-            "Ubuntu IRC",
-            "Freelaw",
-            "PG-19",
-            "USPTO",
-            "HackerNews",
-            "DM Maths",
-        ],
-        "Description": [
-            "The ArXiv dataset is a vast collection of preprint research papers primarily in Mathematics, Computer Science, and Physics. Established in 1991, it offers high-quality text and mathematical knowledge, making it an invaluable resource for academic and scientific research. ArXiv papers are typically written in LaTeX, a popular typesetting system for these fields. We have extracted the information from latex and converted it into a text format.",
-            "Papers from the PhilPapers database, a comprehensive index and bibliography of philosophy research maintained by the Center for Digital Philosophy at the University of Western Ontario.",
-            "The Semantic Scholar Open Research Corpus (S2ORC) is a comprehensive dataset designed for natural language processing (NLP) and text-mining research over scientific papers. It includes rich metadata, and abstract and full-text content for millions of academic papers across various disciplines. This dataset is further divided into two components, S2ORC abstract and S2ORC full text.",
-            "The PubMed Central (PMC) dataset is a comprehensive collection of full-text biomedical and life sciences journal articles run by the United States of America’s National Center for Biotechnology Information (NCBI). It provides open access to a wealth of scientific literature, facilitating research and discovery in the medical and biological fields starting from 2008 by the NIH Public Access Policy. Articles in PMC are available for text mining and other secondary analyses, making it an invaluable resource for researchers and developers and other downstream tasks.",
-            "Abstracts of more than 30 million publications of biomedical literature from various sources mainly including biomedical articles run by the National Library of Medicine. ",
-            "Wikipedia is an encyclopedia form of high-quality text data used for language modeling. We have included filtered and deduplicated versions of complete Wikipedia data directly provided by the Wikipedia Foundation for more than 350 languages.",
-            "A network of question-and-answer websites on various subjects, including programming, science, mathematics, and more. This is one of the largest publicly available repositories for question-answer pairs. We have included comments also to include an overall discussion on each post.",
-            "A collection of multilingual parallel corpora of parliamentary debates from the European Parliament. This is a high-quality legacy dataset earlier used for translation tasks.",
-            "Chat logs from the Ubuntu Internet Relay Chat (IRC) channels on the Freenode IRC chat server. This data is also another form of dialog dataset on niche topics.",
-            "Legal documents and court cases from various jurisdictions provided by US-registered non-profit firm Free Law Project. We have included data from CourtListener which included millions of legal opinions from federal and state courts.",
-            "A collection of books from Project Gutenberg, a digital library of public domain works. This contains all the books that were published before 1919.",
-            "Patent documents from the United States Patent and Trademark Office.",
-            "High-quality dialog-based dataset where user comments on the links as the head post aggregated by Y Combinator.",
-            "DeepMind Maths dataset with generated questions from various topics like algebra, calculus, geometry, etc. Maths data is included to improve model reasoning abilities in the downstream tasks.",
-        ],
-
-    }
-)
-
-table_html_desc = data_descriptions.to_html(index=False, border=0)
-table_desc = Div(NotStr(table_html_desc), style="margin: 40px;")
-
 
 data_sources = [
     "Freelaw",
@@ -1135,8 +1106,6 @@ def curated(request):
             overview_text,
             copyright_disclaimer,
             plotly2fasthtml(treemap_chart),
-            H2("Curated Sources Defined"),
-            table_desc,
             data_preprocessing_div,
             plotly2fasthtml(diff2_stacked_bar),
             H2("Curated Sources Processing"),