Repository 'sklearn_numeric_clustering'
hg clone https://toolshed.g2.bx.psu.edu/repos/bgruening/sklearn_numeric_clustering

Changeset 13:40f3318b61c2 (2018-07-09)
Previous changeset 12:3bd31820d63e (2018-07-01) Next changeset 14:6bbf5cb20652 (2018-07-10)
Commit message:
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 5d71c93a3dd804b1469852240a86021ab9130364
modified:
main_macros.xml
numeric_clustering.xml
b
diff -r 3bd31820d63e -r 40f3318b61c2 main_macros.xml
--- a/main_macros.xml Sun Jul 01 03:19:41 2018 -0400
+++ b/main_macros.xml Mon Jul 09 14:32:01 2018 -0400
[
@@ -64,6 +64,45 @@
   return new_selector
   </token>
 
+  <token name="@GET_X_y_FUNCTION@">
+def get_X_y(params, file1, file2):
+  input_type = params["selected_tasks"]["selected_algorithms"]["input_options"]["selected_input"]
+  if input_type=="tabular":
+    header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header1"] else None
+    column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_1"]["selected_column_selector_option"]
+    if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
+      c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_1"]["col1"]
+    else:
+      c = None
+    X = read_columns(
+      file1,
+      c = c,
+      c_option = column_option,
+      sep='\t',
+      header=header,
+      parse_dates=True
+    )
+  else:
+    X = mmread(open(file1, 'r'))
+
+  header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header2"] else None
+  column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["selected_column_selector_option2"]
+  if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
+    c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["col2"]
+  else:
+    c = None
+  y = read_columns(
+    file2,
+    c = c,
+    c_option = column_option,
+    sep='\t',
+    header=header,
+    parse_dates=True
+  )
+  y=y.ravel()
+  return X, y
+  </token>
+
   <xml name="python_requirements">
       <requirements>
           <requirement type="package" version="2.7">python</requirement>
@@ -81,34 +120,6 @@
 
 
   <!--Generic interface-->
-  <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt">
-    <conditional name="selected_tasks">
-        <param name="selected_task" type="select" label="Select a Classification Task">
-            <option value="train" selected="true">Train a model</option>
-            <option value="load">Load a model and predict</option>
-        </param>
-        <when value="load">
-            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
-            <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
-            <conditional name="prediction_options">
-                <param name="prediction_option" type="select" label="Select the type of prediction">
-                    <option value="predict">Predict class labels</option>
-                    <option value="advanced">Include advanced options</option>
-                </param>
-                <when value="predict">
-                </when>
-                <when value="advanced">
-                </when>
-            </conditional>
-        </when>
-        <when value="train">
-            <param name="infile_train" type="data" format="@TRAIN@" label="Training samples (tabular)"/>
-            <conditional name="selected_algorithms">
-                <yield />
-            </conditional>
-        </when>
-    </conditional>
-  </xml>
 
   <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
     <conditional name="selected_tasks">
b
diff -r 3bd31820d63e -r 40f3318b61c2 numeric_clustering.xml
--- a/numeric_clustering.xml Sun Jul 01 03:19:41 2018 -0400
+++ b/numeric_clustering.xml Mon Jul 09 14:32:01 2018 -0400
[
b'@@ -22,6 +22,8 @@\n from sklearn import metrics\n from scipy.io import mmread\n \n+@COLUMNS_FUNCTION@\n+\n input_json_path = sys.argv[1]\n params = json.load(open(input_json_path, "r"))\n \n@@ -37,17 +39,22 @@\n data_matrix = mmread(open("$infile", \'r\'))\n #else:\n data = pandas.read_csv("$infile", sep=\'\\t\', header=0, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False )\n-\n-start_column = $input_types.start_column\n-end_column = $input_types.end_column\n-\n-if end_column and start_column:\n-    if  end_column >= start_column:\n-        data_matrix = data.values[:, start_column-1:end_column]\n-    else:\n-        data_matrix = data.values\n+header = \'infer\' if params["input_types"]["header"] else None\n+column_option = params["input_types"]["column_selector_options"]["selected_column_selector_option"]\n+if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:\n+    c = params["input_types"]["column_selector_options"]["col"]\n else:\n-    data_matrix = data.values\n+    c = None\n+data_matrix = read_columns(\n+    "$infile",\n+    c = c,\n+    c_option = column_option,\n+    sep=\'\\t\',\n+    header=header,\n+    parse_dates=True,\n+    encoding=None,\n+    tupleize_cols=False\n+)\n #end if\n \n prediction = cluster_object.fit_predict( data_matrix )\n@@ -82,8 +89,10 @@\n             </when>\n             <when value="tabular">\n                 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>\n-                <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />\n-                <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />\n+                <param name="header" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="True" label="Does the dataset contain header:" />\n+                <conditional name="column_selector_options">\n+                    <expand macro="samples_column_selector_options" col_name="col" multiple="true" infile="infile"/>\n+                </conditional>\n                 <!--expand macro="clustering_algorithms_options"-->\n                 <conditional name="algorithm_options">\n                     <param name="selected_algorithm" type="select" label="Clustering Algorithm">\n@@ -168,8 +177,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_input_type" value="tabular"/>\n             <param name="selected_algorithm" value="KMeans"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="n_clusters" value="4" />\n             <param name="init" value="k-means++" />\n             <param name="random_state" value="100"/>\n@@ -179,8 +187,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="KMeans"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="n_clusters" value="4" />\n             <param name="init" value="random" />\n             <param name="random_state" value="100"/>\n@@ -190,8 +197,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="DBSCAN"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="algorithm" value="kd_tree"/>\n             <param name="leaf_size" value="10"/>\n             <param name="eps" value="1.0"/>\n@@ -201,8 +207,7 @@\n             '..b' />\n             <param name="cluster_all" value="False"/>\n             <output name="outfile" file="cluster_result09.txt"/>\n         </test>\n@@ -257,8 +257,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="AgglomerativeClustering"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="affinity" value="euclidean"/>\n             <param name="linkage" value="average"/>\n             <param name="n_clusters" value="4"/>\n@@ -268,8 +267,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="AgglomerativeClustering"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="linkage" value="complete"/>\n             <param name="n_clusters" value="4"/>\n             <output name="outfile" file="cluster_result11.txt"/>\n@@ -278,8 +276,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="SpectralClustering"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="eigen_solver" value="arpack"/>\n             <param name="n_neighbors" value="12"/>\n             <param name="n_clusters" value="4"/>\n@@ -291,8 +288,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="SpectralClustering"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="assign_labels" value="discretize"/>\n             <param name="random_state" value="100"/>\n             <param name="degree" value="2"/>\n@@ -302,8 +298,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="MiniBatchKMeans"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="tol" value="0.5"/>\n             <param name="random_state" value="100"/>\n             <output name="outfile" file="cluster_result14.txt"/>\n@@ -313,8 +308,7 @@\n             <param name="selected_algorithm" value="MiniBatchKMeans"/>\n             <param name="selected_input_type" value="tabular"/>\n             <param name="n_init" value="5"/>\n-            <param name="start_column" value="2" />\n-            <param name="end_column" value="4" />\n+            <param name="col" value="2,3,4" />\n             <param name="batch_size" value="10"/>\n             <param name="n_clusters" value="4"/>\n             <param name="random_state" value="100"/>\n@@ -325,8 +319,7 @@\n             <param name="infile" value="numeric_values.tabular" ftype="tabular"/>\n             <param name="selected_algorithm" value="KMeans"/>\n             <param name="selected_input_type" value="tabular"/>\n-            <param name="start_column" value="1" />\n-            <param name="end_column" value="1" />\n+            <param name="col" value="1" />\n             <param name="n_clusters" value="4" />\n             <param name="random_state" value="100"/>\n             <output name="outfile" file="cluster_result16.txt"/>\n'