Mercurial > repos > bgruening > sklearn_numeric_clustering
diff numeric_clustering.xml @ 40:06d772036a62 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 9981e25b00de29ed881b2229a173a8c812ded9bb
author | bgruening |
---|---|
date | Wed, 09 Aug 2023 13:11:48 +0000 |
parents | 816b65d52c33 |
children |
line wrap: on
line diff
--- a/numeric_clustering.xml Thu Aug 11 08:51:18 2022 +0000 +++ b/numeric_clustering.xml Wed Aug 09 13:11:48 2023 +0000 @@ -1,4 +1,4 @@ -<tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="20.05"> +<tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="@PROFILE@"> <description></description> <macros> <import>main_macros.xml</import> @@ -42,10 +42,12 @@ if 'n_jobs' in cluster_object.get_params(): cluster_object.set_params( n_jobs=N_JOBS ) +header = None #if $input_types.selected_input_type == "sparse": data_matrix = mmread("$infile") #else: -data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None) +data = pandas.read_csv("$infile", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None) + header = 'infer' if params["input_types"]["header"] else None column_option = params["input_types"]["column_selector_options"]["selected_column_selector_option"] if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]: @@ -183,6 +185,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_input_type" value="tabular" /> <param name="selected_algorithm" value="KMeans" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="n_clusters" value="4" /> <param name="init" value="k-means++" /> @@ -193,6 +196,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="KMeans" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="n_clusters" value="4" /> <param name="init" value="random" /> @@ -203,6 +207,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="DBSCAN" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="algorithm" value="kd_tree" /> <param name="leaf_size" value="10" /> @@ -213,6 +218,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="Birch" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="n_clusters" value="4" /> <param name="threshold" value="0.008" /> @@ -222,6 +228,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="Birch" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="branching_factor" value="20" /> <output name="outfile" file="cluster_result05.txt" /> @@ -230,6 +237,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="AffinityPropagation" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="affinity" value="euclidean" /> <param name="copy" value="false" /> @@ -239,6 +247,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="AffinityPropagation" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="damping" value="0.8" /> <output name="outfile" file="cluster_result07.txt" /> @@ -247,6 +256,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="MeanShift" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="min_bin_freq" value="3" /> <output name="outfile" file="cluster_result08.txt" /> @@ -255,6 +265,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="MeanShift" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="cluster_all" value="False" /> <output name="outfile" file="cluster_result09.txt" /> @@ -263,6 +274,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="AgglomerativeClustering" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="affinity" value="euclidean" /> <param name="linkage" value="average" /> @@ -273,6 +285,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="AgglomerativeClustering" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="linkage" value="complete" /> <param name="n_clusters" value="4" /> @@ -283,6 +296,7 @@ <param name="selected_algorithm" value="SpectralClustering" /> <param name="selected_input_type" value="tabular" /> <param name="col" value="2,3,4" /> + <param name="header" value="false" /> <param name="eigen_solver" value="arpack" /> <param name="n_neighbors" value="12" /> <param name="n_clusters" value="4" /> @@ -295,6 +309,7 @@ <param name="selected_algorithm" value="SpectralClustering" /> <param name="selected_input_type" value="tabular" /> <param name="col" value="2,3,4" /> + <param name="header" value="false" /> <param name="assign_labels" value="discretize" /> <param name="random_state" value="100" /> <param name="degree" value="2" /> @@ -304,6 +319,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="MiniBatchKMeans" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="2,3,4" /> <param name="tol" value="0.5" /> <param name="random_state" value="100" /> @@ -313,6 +329,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="MiniBatchKMeans" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="n_init" value="5" /> <param name="col" value="2,3,4" /> <param name="batch_size" value="10" /> @@ -325,6 +342,7 @@ <param name="infile" value="numeric_values.tabular" ftype="tabular" /> <param name="selected_algorithm" value="KMeans" /> <param name="selected_input_type" value="tabular" /> + <param name="header" value="false" /> <param name="col" value="1" /> <param name="n_clusters" value="4" /> <param name="random_state" value="100" />