Trjtdtk

Is it fair for a professor to grade us on the possession of past papers?

Can I cast Passwall to drop an enemy into a 20-foot pit?

How to tell that you are a giant?

Compare a given version number in the form major.minor.build.patch and see if one is less than the other

String `!23` is replaced with `docker` in command line

How do I keep my slimes from escaping their pens?

Why am I getting the error "non-boolean type specified in a context where a condition is expected" for this request?

Error "illegal generic type for instanceof" when using local classes

What does the "x" in "x86" represent?

How to remove list items depending on predecessor in python

Shortening trees list with (setcdr (nthcdr 2 trees) nil)

Installing Debian packages from Stretch DVD 2 and 3 after installation using apt?

Amount of permutations on an NxNxN Rubik's Cube

How come Sam didn't become Lord of Horn Hill?

How can I make names more distinctive without making them longer?

What causes the direction of lightning flashes?

Using audio cues to encourage good posture

Dating a Former Employee

Do I really need recursive chmod to restrict access to a folder?

Sci-Fi book where patients in a coma ward all live in a subconscious world linked together

Is the Standard Deduction better than Itemized when both are the same amount?

How to override model in magento2?

51k Euros annually for a family of 4 in Berlin: Is it enough?

What exactly is a "Meth" in Altered Carbon?

Financial SEC Filling Table data Extraction Using Machine Learning

1

$begingroup$

I am trying to build a ML system which extracts financial data from Tables.

Sample table is like below.

From the above image you can see Net sales is an attribute along with two values 2707.1 and 1994.5 for 2 different quarters. So I want to extract those data with meta data like The date, Quarter, Currency value etc.,. Like below image.

Normally if it is in Free Text I use Entity extraction methods using Spacy or other modules.
We can not apply rules because there will be many variety of table from which we have to extract from.

Edit:
The data are from HTML file.

A sample website

machine-learning

share|improve this question

edited Apr 3 at 10:33

The6thSense

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  If tables are from 10K/10Q types of statements, ML might not be required since tools can already extract these kind of tables (E.g: tabula.technology)
  $endgroup$
  – Shamit Verma
  Mar 28 at 14:12
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  It depends on how the data is stored (e.g., pdf, html, plain text, LaTeX, MS Word, Pages, ...). Please be more specific.
  $endgroup$
  – Brian Spiering
  Mar 28 at 18:10
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @BrianSpiering apologies for the inconvenience caused I have added the source for reference
  $endgroup$
  – The6thSense
  Mar 29 at 7:18
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @ShamitVerma Thanks I will look at it and let you know. My requirement it not just about extracting table. I also want to map the attributes so that I can extract attributes with meaning from them. I.e.) Net Sales: 2707.1 for weeks third weeks ended quarter third quarter and date February etc.,.
  $endgroup$
  – The6thSense
  Mar 29 at 7:46
  
  

  
  
  
  

add a comment | 

1

$begingroup$

I am trying to build a ML system which extracts financial data from Tables.

Sample table is like below.

From the above image you can see Net sales is an attribute along with two values 2707.1 and 1994.5 for 2 different quarters. So I want to extract those data with meta data like The date, Quarter, Currency value etc.,. Like below image.

Normally if it is in Free Text I use Entity extraction methods using Spacy or other modules.
We can not apply rules because there will be many variety of table from which we have to extract from.

Edit:
The data are from HTML file.

A sample website

machine-learning

share|improve this question

edited Apr 3 at 10:33

The6thSense

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  If tables are from 10K/10Q types of statements, ML might not be required since tools can already extract these kind of tables (E.g: tabula.technology)
  $endgroup$
  – Shamit Verma
  Mar 28 at 14:12
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  It depends on how the data is stored (e.g., pdf, html, plain text, LaTeX, MS Word, Pages, ...). Please be more specific.
  $endgroup$
  – Brian Spiering
  Mar 28 at 18:10
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @BrianSpiering apologies for the inconvenience caused I have added the source for reference
  $endgroup$
  – The6thSense
  Mar 29 at 7:18
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @ShamitVerma Thanks I will look at it and let you know. My requirement it not just about extracting table. I also want to map the attributes so that I can extract attributes with meaning from them. I.e.) Net Sales: 2707.1 for weeks third weeks ended quarter third quarter and date February etc.,.
  $endgroup$
  – The6thSense
  Mar 29 at 7:46
  
  

  
  
  
  

add a comment | 

$begingroup$

I am trying to build a ML system which extracts financial data from Tables.

Sample table is like below.

From the above image you can see Net sales is an attribute along with two values 2707.1 and 1994.5 for 2 different quarters. So I want to extract those data with meta data like The date, Quarter, Currency value etc.,. Like below image.

Normally if it is in Free Text I use Entity extraction methods using Spacy or other modules.
We can not apply rules because there will be many variety of table from which we have to extract from.

Edit:
The data are from HTML file.

A sample website

machine-learning

share|improve this question

edited Apr 3 at 10:33

The6thSense

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397

$endgroup$

share|improve this question

edited Apr 3 at 10:33

The6thSense

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397

share|improve this question

edited Apr 3 at 10:33

The6thSense

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397

asked Mar 28 at 13:21

The6thSenseThe6thSense

1397