diff ensemble.xml @ 44:fce065687d98 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb

--- a/ensemble.xml	Thu Aug 11 07:56:55 2022 +0000
+++ b/ensemble.xml	Wed Aug 09 11:26:43 2023 +0000
@@ -1,4 +1,4 @@
-<tool id="sklearn_ensemble" name="Ensemble methods" version="@VERSION@" profile="20.05">
+<tool id="sklearn_ensemble" name="Ensemble methods" version="@VERSION@" profile="@PROFILE@">
     <description>for classification and regression</description>
     <macros>
         <import>main_macros.xml</import>
@@ -17,12 +17,12 @@
 import json
 import numpy as np
 import pandas
-import pickle
 import sys
 
 from scipy.io import mmread
 import sklearn.ensemble
-from galaxy_ml.utils import load_model, get_X_y
+from galaxy_ml.model_persist import dump_model_to_h5, load_model_from_h5
+from galaxy_ml.utils import clean_params, get_X_y
 
 
 N_JOBS = int(__import__('os').environ.get('GALAXY_SLOTS', 1))
@@ -57,11 +57,6 @@
             options["select_max_features"].pop("num_max_features")
         options["max_features"] = options["select_max_features"]["max_features"]
         options.pop("select_max_features")
-    if "presort" in options:
-        if options["presort"] == "true":
-            options["presort"] = True
-        if options["presort"] == "false":
-            options["presort"] = False
     if "min_samples_leaf" in options and options["min_samples_leaf"] == 1.0:
         options["min_samples_leaf"] = 1
     if "min_samples_split" in options and options["min_samples_split"] > 1.0:
@@ -72,12 +67,11 @@
     my_class = getattr(sklearn.ensemble, algorithm)
     estimator = my_class(**options)
     estimator.fit(X,y)
-    with open(outfile_fit, 'wb') as out_handler:
-        pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)
+    dump_model_to_h5(estimator, outfile_fit)
 
 else:
-    with open(infile_model, 'rb') as model_handler:
-        classifier_object = load_model(model_handler)
+    classifier_object = load_model_from_h5(infile_model)
+    classifier_object = clean_params(classifier_object)
     header = 'infer' if params["selected_tasks"]["header"] else None
     data = pandas.read_csv(infile_data, sep='\t', header=header, index_col=None, parse_dates=True, encoding=None)
     prediction = classifier_object.predict(data)
@@ -89,7 +83,7 @@
         </configfile>
     </configfiles>
     <inputs>
-        <expand macro="sl_Conditional" model="zip">
+        <expand macro="sl_Conditional" model="h5mlm">
             <param name="selected_algorithm" type="select" label="Select an ensemble method:">
                 <option value="RandomForestClassifier" selected="true">Random forest classifier</option>
                 <option value="AdaBoostClassifier">Ada boost classifier</option>
@@ -153,7 +147,6 @@
                     <expand macro="verbose" />
                     <expand macro="warm_start" checked="false" />
                     <expand macro="random_state" />
-                    <expand macro="presort" />
                 </section>
             </when>
             <when value="RandomForestRegressor">
@@ -216,7 +209,6 @@
                     <expand macro="verbose" />
                     <expand macro="warm_start" checked="false" />
                     <expand macro="random_state" />
-                    <expand macro="presort" />
                 </section>
             </when>
         </expand>
@@ -236,7 +228,7 @@
             <output name="outfile_fit" file="rfc_model01" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile_model" value="rfc_model01" ftype="zip" />
+            <param name="infile_model" value="rfc_model01" ftype="h5mlm" />
             <param name="infile_data" value="test.tabular" ftype="tabular" />
             <param name="selected_task" value="load" />
             <output name="outfile_predict" file="rfc_result01" />
@@ -252,7 +244,7 @@
             <output name="outfile_fit" file="rfr_model01" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile_model" value="rfr_model01" ftype="zip" />
+            <param name="infile_model" value="rfr_model01" ftype="h5mlm" />
             <param name="infile_data" value="regression_test.tabular" ftype="tabular" />
             <param name="selected_task" value="load" />
             <output name="outfile_predict" file="rfr_result01" />
@@ -272,7 +264,7 @@
             <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile_model" value="gbr_model01" ftype="zip" />
+            <param name="infile_model" value="gbr_model01" ftype="h5mlm" />
             <param name="infile_data" value="regression_test_X.tabular" ftype="tabular" />
             <param name="selected_task" value="load" />
             <param name="header" value="True" />
@@ -288,7 +280,7 @@
             <output name="outfile_fit" file="gbc_model01" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile_model" value="gbc_model01" ftype="zip" />
+            <param name="infile_model" value="gbc_model01" ftype="h5mlm" />
             <param name="infile_data" value="test.tabular" ftype="tabular" />
             <param name="selected_task" value="load" />
             <output name="outfile_predict" file="gbc_result01" />
@@ -304,7 +296,7 @@
             <output name="outfile_fit" file="abc_model01" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile_model" value="abc_model01" ftype="zip" />
+            <param name="infile_model" value="abc_model01" ftype="h5mlm" />
             <param name="infile_data" value="test.tabular" ftype="tabular" />
             <param name="selected_task" value="load" />
             <output name="outfile_predict" file="abc_result01" />
@@ -320,7 +312,7 @@
             <output name="outfile_fit" file="abr_model01" compare="sim_size" delta="5" />
         </test>
         <test>
-            <param name="infile_model" value="abr_model01" ftype="zip" />
+            <param name="infile_model" value="abr_model01" ftype="h5mlm" />
             <param name="infile_data" value="regression_test.tabular" ftype="tabular" />
             <param name="selected_task" value="load" />
             <output name="outfile_predict" file="abr_result01" />