view discriminant.xml @ 3:b6f35bef5b59 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 99231ce3ef238975a6614926f2fa6326b9454ee8
author bgruening
date Tue, 13 Mar 2018 06:31:58 -0400
parents e0067d9baffc
children f46da2feb233
line wrap: on
line source

<tool id="sklearn_discriminant_classifier" name="Discriminant Analysis" version="@VERSION@">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
        <!--macro name="priors"-->
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python "$discriminant_script" '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs"/>
        <configfile name="discriminant_script">
<![CDATA[
import sys
import json
import numpy as np
import sklearn.discriminant_analysis
import pandas
import pickle

input_json_path = sys.argv[1]
params = json.load(open(input_json_path, "r"))


#if $selected_tasks.selected_task == "load":

classifier_object = pickle.load(open("$infile_model", 'r'))

data = pandas.read_csv("$selected_tasks.infile_data", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )
prediction = classifier_object.predict(data)
prediction_df = pandas.DataFrame(prediction)
res = pandas.concat([data, prediction_df], axis=1)
res.to_csv(path_or_buf = "$outfile_predict", sep="\t", index=False)

#else:

data_train = pandas.read_csv("$selected_tasks.infile_train", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )

data = data_train.ix[:,0:len(data_train.columns)-1]
labels = np.array(data_train[data_train.columns[len(data_train.columns)-1]])

options = params["selected_tasks"]["selected_algorithms"]["options"]
selected_algorithm = params["selected_tasks"]["selected_algorithms"]["selected_algorithm"]

my_class = getattr(sklearn.discriminant_analysis, selected_algorithm)
classifier_object = my_class(**options)
classifier_object.fit(data,labels)
pickle.dump(classifier_object,open("$outfile_fit", 'w+'), pickle.HIGHEST_PROTOCOL)

#end if
]]>
        </configfile>
    </configfiles>
    <inputs>
        <expand macro="train_loadConditional" model="zip">
            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="LinearDiscriminantAnalysis" selected="true">Linear Discriminant Classifier</option>
                <option value="QuadraticDiscriminantAnalysis">Quadratic Discriminant Classifier</option>
            </param>
            <when value="LinearDiscriminantAnalysis">
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="solver" type="select" optional="true" label="Solver" help="">
                        <option value="svd" selected="true">Singular Value Decomposition</option>
                        <option value="lsqr">Least Squares Solution</option>
                        <option value="eigen">Eigenvalue Decomposition</option>
                    </param>
                    <!--param name="shrinkage"-->
                    <!--expand macro="priors"/-->
                    <param argument="n_components" type="integer" optional="true" value="" label="Number of components"
                        help="Number of components for dimensionality reduction. ( always less than  n_classes - 1 )"/>
                    <expand macro="tol" default_value="0.0001" help_text="Rank estimation threshold used in SVD solver."/>
                    <param argument="store_covariance" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false"
                        label="Store covariance" help="Compute class covariance matrix."/>
                </section>
            </when>
            <when value="QuadraticDiscriminantAnalysis">
                <section name="options" title="Advanced Options" expanded="False">
                    <!--expand macro="priors"/-->
                    <param argument="reg_param" type="float" optional="true" value="0.0" label="Regularization coefficient" help="Covariance estimate regularizer."/>
                    <expand macro="tol" default_value="0.00001" help_text="Rank estimation threshold used in SVD solver."/>
                    <param argument="store_covariances" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false"
                        label="Store covariances" help="Compute class covariance matrixes."/>
                </section>
            </when>
        </expand>
    </inputs>
    <expand macro="output"/>
    <tests>
        <test>
            <param name="infile_train" value="train.tabular" ftype="tabular"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis"/>
            <param name="solver" value="svd" />
            <param name="store_covariances" value="True"/>
            <output name="outfile_fit" file="lda_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_train" value="train.tabular" ftype="tabular"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis"/>
            <param name="solver" value="lsqr"/>
            <output name="outfile_fit" file="lda_model02" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_train" value="train.tabular" ftype="tabular"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="QuadraticAnalysis"/>
            <output name="outfile_fit" file="qda_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="lda_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="lda_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="lda_model02" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="lda_prediction_result02.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="qda_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="qda_prediction_result01.tabular"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
Linear and Quadratic Discriminant Analysis are two classic classifiers with a linear and a quadratic decision surface respectively. These classifiers are fast and easy to interprete.


 **1 - Training input**

 When you choose to train a model, discriminant analysis tool expects a tabular file with numeric values, the order of the columns being as follows:

 ::

 "feature_1"	"feature_2"	"..."	"feature_n"	"class_label"

 **Example for training data**
 The following training dataset contains 3 feature columns and a column containing class labels:

 ::

  4.01163365529    -6.10797684314    8.29829894763     1
  10.0788438916    1.59539821454     10.0684278289     0
  -5.17607775503   -0.878286135332   6.92941850665     2
  4.00975406235    -7.11847496542    9.3802423585      1
  4.61204065139    -5.71217537352    9.12509610964     1


 **2 - Trainig output**

 Based on your choice, this tool fits a sklearn discriminant_analysis.LinearDiscriminantAnalysis or discriminant_analysis.QuadraticDiscriminantAnalysis on the traning data and outputs the trained model in the form of pickled object in a text file.


 **3 - Prediction input**

 When you choose to load a model and do prediction, the tool expects an already trained Discriminant Analysis estimator and a tabular dataset as input. The dataset is a tabular file with new samples which you want to classify. It just contains feature columns.

 **Example for prediction data**

 ::

  8.26530668997    2.96705005011     8.88881190248
  2.96366327113    -3.76295851562    11.7113372463
  8.13319631944    -0.223645298585   10.5820605308

 .. class:: warningmark

 The number of feature columns must be the same in training and prediction datasets!


 **3 - Prediction output**
 The tool predicts the class labels for new samples and adds them as the last column to the prediction dataset. The new dataset then is output as a tabular file. The prediction output format should look like the training dataset.

Discriminant Analysis is based on sklearn.discriminant_analysis library from Scikit-learn.
For more information please refer to `Scikit-learn site`_.

.. _`Scikit-learn site`: http://scikit-learn.org/stable/modules/lda_qda.html

    ]]></help>
    <expand macro="sklearn_citation"/>
</tool>