PICA - Revision history

Norman at 14:39, 1 June 2010

2010-06-01T14:39:24Z

Norman at 18:01, 28 May 2010

2010-05-28T18:01:08Z

Norman at 18:00, 28 May 2010

2010-05-28T18:00:21Z

Norman at 17:58, 28 May 2010

2010-05-28T17:58:55Z

Norman at 17:39, 28 May 2010

2010-05-28T17:39:35Z

Norman at 17:38, 28 May 2010

2010-05-28T17:38:04Z

Norman at 17:37, 28 May 2010

2010-05-28T17:37:34Z

Norman at 12:48, 13 April 2010

2010-04-13T12:48:27Z

Norman at 12:44, 13 April 2010

2010-04-13T12:44:34Z

Norman at 12:39, 13 April 2010

2010-04-13T12:39:06Z

@@ Line 19: / Line 19: @@
 The samples file is a tab-separated format without a header line.  Each line is a single sample, with the sample identifier in the first column.  The rest of the line are features for input.
 Example:
    Escherichia_coli_CFT07                COG0007	COG0006	COG0004	COG0005	COG0001 ...
@@ Line 26: / Line 27: @@
 The class label file is a standard tab separated format.  A header line is required.  The first column must contain sample identifiers that map to the samples file. Not all class label lines must map to a sample.  This allows us to use a single class label file for all classes and possible training testing subsets of the genotype file.  To exclude a sample from a given class analysis, set the column value to NULL.
 Example:
    organism	                       MOTILE  HALO  GRAMNEGATIVE ...
@@ Line 31: / Line 33: @@
    Streptococcus_pyogenes_str._Manfredo  NULL    NO    NULL
    ...
 == Command-line Interface==

@@ Line 8: / Line 8: @@
 * [[Media:PICA_v1_0_1.zip|PICA v1.0.1]] PICA source code and example datasets (Updated documentation from version 1.0.0)
-* [[Media:PICA_v1_0_0.zip|PICA v1.0.0]]
+* [[Media:PICA_v1_00.zip|PICA v1.0.0]]
 == Setup ==

@@ Line 6: / Line 6: @@
 == Downloads ==
 Example genotype dataset was compiled from the [http://www.string-db.org/ STRING database] version 8.0.  Example phenotype data is from the [http://img.jgi.doe.gov/cgi-bin/pub/main.cgi DOE JGI IMG] and [http://www.ncbi.nlm.nih.gov/genomes/lproks.cgi NCBI lproks].  Example taxonomic data is from the [http://www.ncbi.nlm.nih.gov/Taxonomy/ NCBI Taxonomy] database.
 * [[Media:PICA_v1_0_1.zip|PICA v1.0.1]] PICA source code and example datasets (Updated documentation from version 1.0.0)
 == Setup ==

@@ Line 7: / Line 7: @@
 Example genotype dataset was compiled from the [http://www.string-db.org/ STRING database] version 8.0.  Example phenotype data is from the [http://img.jgi.doe.gov/cgi-bin/pub/main.cgi DOE JGI IMG] and [http://www.ncbi.nlm.nih.gov/genomes/lproks.cgi NCBI lproks].  Example taxonomic data is from the [http://www.ncbi.nlm.nih.gov/Taxonomy/ NCBI Taxonomy] database.
-* [[Media:PICA_v1_00.zip|PICA v1.00]] PICA source code and example datasets
 == Setup ==

@@ Line 29: / Line 29: @@
    Escherichia_coli_CFT07                YES     NULL  YES
    Streptococcus_pyogenes_str._Manfredo  NULL    NO    NULL
 == Command-line Interface==

@@ Line 13: / Line 13: @@
 Unzip the folder to the desired location and run from the command line.  To access the API, make sure the pica folder is on your Python path.
 == Command-line Interface==
@@ Line 19: / Line 35: @@
 * train: Train a given data mining algorithm and output model to file.
 Example usage:
-   train.py --algorithm cpar.CPARTrainer
+   python train.py --algorithm cpar.CPARTrainer
-           --samples examples/genotype_prokaryote.profile
+                  --samples examples/genotype_prokaryote.profile
-           --classes examples/phenotype.profile
+                  --classes examples/phenotype.profile
-           --targetclass THERM
+                  --targetclass THERM
-           --output output.rules
+                  --output output.rules
 * test:  Test a model with a classification algorithm and given model.
 Example usage:
-   test.py --algorithm cpar.CPARClassifier
+   python test.py --algorithm cpar.CPARClassifier
-          --samples examples/genotype_prokaryote.profile
+                 --samples examples/genotype_prokaryote.profile
-          --classes examples/phenotype.profile
+                 --classes examples/phenotype.profile
-          --targetclass THERM
+                 --targetclass THERM
-          --model_filename output.rules
+                 --model_filename output.rules
-          --model_accuracy laplace
+                 --model_accuracy laplace
 * crossvalidate:  Replicated cross-validation with the given training and testing algorithms.
 Example usage:
-   crossvalidate.py --training_algorithm cpar.CPARTrainer
+   python crossvalidate.py --training_algorithm cpar.CPARTrainer
-                   --classification_algorithm cpar.CPARClassifier
+                          --classification_algorithm cpar.CPARClassifier
-                   --accuracy_measure laplace
+                          --accuracy_measure laplace
-                   --replicates 10
+                          --replicates 10
-                   --folds 5
+                          --folds 5
-                   --samples examples/genotype_prokaryote.profile
+                          --samples examples/genotype_prokaryote.profile
-                   --classes examples/phenotype.profile
+                          --classes examples/phenotype.profile
-                   --targetclass THERM
+                          --targetclass THERM
-                   --output_filename results.txt
+                          --output_filename results.txt
-                   --metadata examples/taxonomic_confounders_propagated.txt
+                          --metadata examples/taxonomic_confounders_propagated.txt
 Another example of crossvalidate is to use the CPAR2SVMTrainer, which trains with CPAR, then breaks down the rules found into individual features and subsequently trains and tests with LIBSVM.  This could also be performed more generally (with feature selection as a separate step) using the Python API below.
-   crossvalidate.py --training_algorithm cpar.CPAR2SVMTrainer
+   python crossvalidate.py --training_algorithm cpar.CPAR2SVMTrainer
-                   --classification_algorithm libsvm.libSVMClassifier
+                          --classification_algorithm libsvm.libSVMClassifier
-                   --replicates 10
+                          --replicates 10
-                   --folds 5
+                          --folds 5
-                   --samples examples/genotype_prokaryote.profile
+                          --samples examples/genotype_prokaryote.profile
-                   --classes examples/phenotype.profile
+                          --classes examples/phenotype.profile
-                   --targetclass THERM
+                          --targetclass THERM
-                   --output_filename results.txt
+                          --output_filename results.txt
-                   --metadata examples/taxonomic_confounders_propagated.txt
+                          --metadata examples/taxonomic_confounders_propagated.txt
 == Python API ==

@@ Line 2: / Line 2: @@
 == License ==
-PICA was developed by Norman MacDonald (norman@cs.dal.ca) and is released under the  [http://creativecommons.org/licenses/by-sa/3.0/ Creative Commons Share-Alike Attribution 3.0 License].
+PICA is released under the  [http://creativecommons.org/licenses/by-sa/3.0/ Creative Commons Share-Alike Attribution 3.0 License].
 == Downloads ==
@@ Line 96: / Line 96: @@
    # the paired comparisons that can be accessed through its methods.
    crossvalidator.crossvalidate()