{ "id": 7033, "title": "Sample code quickstart", "url": "/competitions/connectomics/discussion/7033", "author_name": "", "post_date": "2014-02-10T14:44:17.907Z", "votes": null, "comment_count": 8, "views": 2685, "content": "

Can someone please post step-by-step instructions for getting started with the sample code and making a submission? Thanks!

", "messages": [ { "id": "38550", "postDate": "02/10/2014 14:44:17", "content": "

Can someone please post step-by-step instructions for getting started with the sample code and making a submission? Thanks!

", "rawMarkdown": "", "votes": null }, { "id": "38560", "postDate": "02/10/2014 15:41:32", "content": "

Hi,

\n

The sample code contains a README file indicating how to start using it (for MATLAB only):

\n

The goal of the challenge is to predict whether there is a (directed) connection between neuron i and neuron j in a network of 1000 neurons (self-connections permitted). We provide one hour of recording of the activity of all neurons as time series and the position of the neurons (arranged on a flat surface). The data, which are simulated, reproduce as faithfully as possible neural activity measured with calcium fluorescence imaging of neural cultures.

\n

The starter kit includes as sample data file from 100 neuron networks, that are substitute for the larger 1000 neuron networks used for validation and testing in the challenge.

\n

1) FLUORESCENCE = fluorescence_mockvalid.csv and fluorescence_mocktest.csv: comma separated files including time series of neural activity, each row representing a sample and each column a neuron. Signal is sampled at 20ms intervals.
2) NETWORK POSITIONS = networkPositions_mockvalid.csv and networkPositions_mocktest.csv: comma separated files, each row representing a neuron. First column is the X position and second column the Y position. Neurons span a 1mm2 square area.
3) NETWORK = network_mockvalid.csv and network_mocktest.csv: comma separated files representing the network architecture. Each row is a connection. The column structure is of the form I,J,W denoting a connection from I to J with weight W. Connections with positive weight (usually 1) are present. Pairs that are absent or have a weight -1 are inexistent or blocked in the simulations (which is the same thing as far as this challenge is concerned).

\n

All data have the same three files, prefixed with fluorescence_, networkPositions_, and network_. The postfix "mockvalid" or "muckiest" is the network name. When you substitute the sample data for the challenge data, this should be replaced.

\n

The main entry point of the starter kit is:
> challengeMain;

\n

The script takes a few minutes to run on the sample network of 100 neurons and a few hours on the actual validation and test networks of 1000 neurons.
It performs the following functions:
1) Load the fluorescence file as a matrix F, neurons in columns; each line is a time sample.
2) Perform various steps to compute scores for neuron i -> neuron j using the GTE algorithm, from Stetter, O., Battaglia, D., Soriano, J. & Geisel, T. Model-free reconstruction of excitatory neuronal connectivity from calcium imaging signals. PLoS Comput Biol 8, e1002653 (2012). This code also produces graphs similar to those of the paper.
The resulting "scores" matrix is a matrix N x N, N being the number of neurons, each entry (i, j) indicating the "confidence" that neuron i -> neuron j.
3) Writes the scores in Kaggle submission format as a 2-column csv file
NET_neuronI_neuronJ Strength indicating the "confidence" that neuron i -> neuron j.

\n

 

\n

 

\n

Also in the data section you will find a sample submission that you can use to test how to submit a file:

\n

https://www.kaggle.com/c/connectomics/data

\n

 

\n

 

", "rawMarkdown": "", "votes": null }, { "id": "38563", "postDate": "02/10/2014 16:30:20", "content": "

 

\n

Source: http://connectomics.chalearn.org
 

\n

 

\n

Javier Orlandi, Mehreen Saeed, Isabelle Guyon

\n

 

\n

Just wanted to pay my compliments to the authors of the sample code and visualizations.  Incredibly well documented and thorough work.  Really a joy to run through. Also even when I ran it on a mac it shot me a warning said I needed windows for the movie!!  Thats just dotting I's and crossing T's above and beyond the call of duty.

\n

 

\n

I hope you guys get what your looking for out of this competition..  

\n

 

\n

-Tim

\n

 

\n

 

", "rawMarkdown": "", "votes": null }, { "id": "38622", "postDate": "02/11/2014 09:02:10", "content": "

Is the code compatible with Octave? 

\n

I'm currently getting this error:

\n

octave:1> challengeMain
error: @randomScore: no function and no method found
error: evaluating argument list element number 1
error: called from:
error: MatlabSampleCode/challengeMain.m at line 33, column 16

", "rawMarkdown": "", "votes": null }, { "id": "38651", "postDate": "02/11/2014 20:20:57", "content": "

The code was not tested with Octave. But Octave seems to have similar function handles as Matlab. Your problem seems more like a path problem. You may want to check whether randomScore is found in your path by typing:

\n

> which randomScore

", "rawMarkdown": "", "votes": null }, { "id": "38825", "postDate": "02/14/2014 19:37:32", "content": "

Thanks for the help, Javier. Here are a few more pointers for others getting started (others can feel free to correct me, I did some of this a few days ago and might be forgetting steps):

\n
    \n
  1. Download the data (valid.tgz and test.tgz), uncompress it, and put it in the SampleCode/data directory
    2. \n
  2. In challengeFastBaseline.m on line 29, change mockvalid and mocktest to valid and test.
    3. \n
  3. Open up matlab and run challengeFastBaseline;
    4. \n
  4. This will produce a file Correlation_valid_test_XX.csv with 2000001 rows. Upload this as your submission to Kaggle.
    5. \n
\n

 

", "rawMarkdown": "", "votes": null }, { "id": "39140", "postDate": "02/20/2014 14:39:21", "content": "

any updates on the python sample code?

", "rawMarkdown": "", "votes": null }, { "id": "41808", "postDate": "04/12/2014 18:29:35", "content": "

Hi There, I really appreciate your response but in my case when i change the values on 29th row in challengeFastBaseline.m as prescribed ,and on running challengeFastBaseline the I am getting Memory Error.any suggestions.

", "rawMarkdown": "", "votes": null }, { "id": "42294", "postDate": "04/18/2014 06:49:00", "content": "

@Abhishek: See https://www.kaggle.com/c/connectomics/forums/t/7698/python-scripts-for-correlation-benchmarks/42293#post42293 :)

", "rawMarkdown": "", "votes": null } ], "comments": [ { "id": 38560, "author_name": "orlandi", "author_url": "", "post_date": "02/10/2014 15:41:32", "content": "

Hi,

\n

The sample code contains a README file indicating how to start using it (for MATLAB only):

\n

The goal of the challenge is to predict whether there is a (directed) connection between neuron i and neuron j in a network of 1000 neurons (self-connections permitted). We provide one hour of recording of the activity of all neurons as time series and the position of the neurons (arranged on a flat surface). The data, which are simulated, reproduce as faithfully as possible neural activity measured with calcium fluorescence imaging of neural cultures.

\n

The starter kit includes as sample data file from 100 neuron networks, that are substitute for the larger 1000 neuron networks used for validation and testing in the challenge.

\n

1) FLUORESCENCE = fluorescence_mockvalid.csv and fluorescence_mocktest.csv: comma separated files including time series of neural activity, each row representing a sample and each column a neuron. Signal is sampled at 20ms intervals.
2) NETWORK POSITIONS = networkPositions_mockvalid.csv and networkPositions_mocktest.csv: comma separated files, each row representing a neuron. First column is the X position and second column the Y position. Neurons span a 1mm2 square area.
3) NETWORK = network_mockvalid.csv and network_mocktest.csv: comma separated files representing the network architecture. Each row is a connection. The column structure is of the form I,J,W denoting a connection from I to J with weight W. Connections with positive weight (usually 1) are present. Pairs that are absent or have a weight -1 are inexistent or blocked in the simulations (which is the same thing as far as this challenge is concerned).

\n

All data have the same three files, prefixed with fluorescence_, networkPositions_, and network_. The postfix "mockvalid" or "muckiest" is the network name. When you substitute the sample data for the challenge data, this should be replaced.

\n

The main entry point of the starter kit is:
> challengeMain;

\n

The script takes a few minutes to run on the sample network of 100 neurons and a few hours on the actual validation and test networks of 1000 neurons.
It performs the following functions:
1) Load the fluorescence file as a matrix F, neurons in columns; each line is a time sample.
2) Perform various steps to compute scores for neuron i -> neuron j using the GTE algorithm, from Stetter, O., Battaglia, D., Soriano, J. & Geisel, T. Model-free reconstruction of excitatory neuronal connectivity from calcium imaging signals. PLoS Comput Biol 8, e1002653 (2012). This code also produces graphs similar to those of the paper.
The resulting "scores" matrix is a matrix N x N, N being the number of neurons, each entry (i, j) indicating the "confidence" that neuron i -> neuron j.
3) Writes the scores in Kaggle submission format as a 2-column csv file
NET_neuronI_neuronJ Strength indicating the "confidence" that neuron i -> neuron j.

\n

 

\n

 

\n

Also in the data section you will find a sample submission that you can use to test how to submit a file:

\n

https://www.kaggle.com/c/connectomics/data

\n

 

\n

 

", "votes": null, "replies": [] }, { "id": 38563, "author_name": "scharf", "author_url": "", "post_date": "02/10/2014 16:30:20", "content": "

 

\n

Source: http://connectomics.chalearn.org
 

\n

 

\n

Javier Orlandi, Mehreen Saeed, Isabelle Guyon

\n

 

\n

Just wanted to pay my compliments to the authors of the sample code and visualizations.  Incredibly well documented and thorough work.  Really a joy to run through. Also even when I ran it on a mac it shot me a warning said I needed windows for the movie!!  Thats just dotting I's and crossing T's above and beyond the call of duty.

\n

 

\n

I hope you guys get what your looking for out of this competition..  

\n

 

\n

-Tim

\n

 

\n

 

", "votes": null, "replies": [] }, { "id": 38622, "author_name": "tf6452", "author_url": "", "post_date": "02/11/2014 09:02:10", "content": "

Is the code compatible with Octave? 

\n

I'm currently getting this error:

\n

octave:1> challengeMain
error: @randomScore: no function and no method found
error: evaluating argument list element number 1
error: called from:
error: MatlabSampleCode/challengeMain.m at line 33, column 16

", "votes": null, "replies": [] }, { "id": 38651, "author_name": "iguyon", "author_url": "", "post_date": "02/11/2014 20:20:57", "content": "

The code was not tested with Octave. But Octave seems to have similar function handles as Matlab. Your problem seems more like a path problem. You may want to check whether randomScore is found in your path by typing:

\n

> which randomScore

", "votes": null, "replies": [] }, { "id": 38825, "author_name": "sethflaxman", "author_url": "", "post_date": "02/14/2014 19:37:32", "content": "

Thanks for the help, Javier. Here are a few more pointers for others getting started (others can feel free to correct me, I did some of this a few days ago and might be forgetting steps):

\n
    \n
  1. Download the data (valid.tgz and test.tgz), uncompress it, and put it in the SampleCode/data directory
    2. \n
  2. In challengeFastBaseline.m on line 29, change mockvalid and mocktest to valid and test.
    3. \n
  3. Open up matlab and run challengeFastBaseline;
    4. \n
  4. This will produce a file Correlation_valid_test_XX.csv with 2000001 rows. Upload this as your submission to Kaggle.
    5. \n
\n

 

", "votes": null, "replies": [] }, { "id": 39140, "author_name": "abhishek", "author_url": "", "post_date": "02/20/2014 14:39:21", "content": "

any updates on the python sample code?

", "votes": null, "replies": [] }, { "id": 41808, "author_name": "deepakchaturvedi1", "author_url": "", "post_date": "04/12/2014 18:29:35", "content": "

Hi There, I really appreciate your response but in my case when i change the values on 29th row in challengeFastBaseline.m as prescribed ,and on running challengeFastBaseline the I am getting Memory Error.any suggestions.

", "votes": null, "replies": [] }, { "id": 42294, "author_name": "glouppe", "author_url": "", "post_date": "04/18/2014 06:49:00", "content": "

@Abhishek: See https://www.kaggle.com/c/connectomics/forums/t/7698/python-scripts-for-correlation-benchmarks/42293#post42293 :)

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "38550": "", "38560": "", "38563": "", "38622": "", "38651": "", "38825": "", "39140": "", "41808": "", "42294": "" }, "source": "meta" }