opensource/galaxy
3
0
Fork 0
mirror of https://github.com/galaxyproject/galaxy.git synced 2026-09-24 16:30:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Various tool fixes, eliminated now unnecessary "refresh_on_change", eliminated old aggregation tool, fixed db conditional in mapping.

Browse Source
This commit is contained in:
Greg Von Kuster
2007-10-12 13:11:17 +00:00
parent 8e3f797331
commit 4f8eb6578b
9 changed files with 18 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/galaxy/model/mapping.py
+2 -4
View File
@@ -241,9 +241,7 @@ def db_next_hid( self ):
History._next_hid = db_next_hid
def init( file_path, url, **kwargs ):
"""
Connect mappings to the database
"""
"""Connect mappings to the database"""
create_tables = kwargs.pop( 'create_tables', False )
# Connect dataset to the file path
Dataset.file_path = file_path
@@ -255,7 +253,7 @@ def init( file_path, url, **kwargs ):
if table.columns.has_key( "update_time" ):
table.columns['update_time'].type = TIMESTAMP()
# Connect the metadata to the database.
if url.find( "sqlite" ) < 0 and url.find( '///' ) >= 0:
elif url.startswith( "postgresql:///" ):
import psycopg
try:
dbconn = url.split('///')
tools/filters/sorter.xml
+1 -1
View File
@@ -2,7 +2,7 @@
<description>data in ascending or descending order</description>
<command interpreter="python">sorter.py -i $input -o $out_file1 -cols $column -order $order -style $style</command>
<inputs>
<param format="tabular" name="input" type="data" label="Sort Query" refresh_on_change="True" />
<param format="tabular" name="input" type="data" label="Sort Query" />
<param name="column" label="on column" type="columnlist" assoc_dataset="input" />
<param name="order" type="select" label="in">
<option value="ASC">Ascending order</option>
tools/filters/uniq.xml
+1 -1
View File
@@ -2,7 +2,7 @@
<description>occurences of each record</description>
<command interpreter="python">uniq.py -i $input -o $out_file1 -c "$column" -d $delim</command>
<inputs>
<param name="input" type="data" format="tabular" label="from query" refresh_on_change="True" help="Query missing? See TIP below"/>
<param name="input" type="data" format="tabular" label="from query" help="Query missing? See TIP below"/>
<param name="column" type="columnlist" assoc_dataset="input" multiple="True" numerical="False" label="Count occurencies of values in column(s)" help="Multi-select list - hold the appropriate key while clicking to select multiple columns" />
<param name="delim" type="select" label="Delimited by">
<option value="T">Tab</option>
tools/plotting/histogram.py
+10 -4
View File
@@ -36,10 +36,16 @@ def main():
if line and not line.startswith( '#' ):
# Extract values and convert to floats
row = []
fields = line.split( "\t" )
val = fields[column]
if val.lower() == "na":
row.append( float( "nan" ) )
try:
fields = line.split( "\t" )
val = fields[column]
if val.lower() == "na":
row.append( float( "nan" ) )
except:
valid = False
skipped_lines += 1
if not first_invalid_line:
first_invalid_line = i+1
else:
try:
row.append( float( val ) )
tools/plotting/histogram2.xml
+1 -1
View File
@@ -2,7 +2,7 @@
<description>of a numeric column</description>
<command interpreter="python">histogram.py $input $out_file1 $numerical_column "$title" "$xlab" $breaks $density</command>
<inputs>
<param name="input" type="data" format="tabular" label="Dataset" refresh_on_change="True" help="Query missing? See TIP below"/>
<param name="input" type="data" format="tabular" label="Dataset" help="Query missing? See TIP below"/>
<param name="numerical_column" type="columnlist" assoc_dataset="input" numerical="True" label="Numerical column for x axis" />
<param name="breaks" type="integer" size="4" value="0" label="Number of breaks (bars)"/>
<param name="title" type="text" size="30" value="Histogram" label="Plot title"/>
tools/plotting/scatterplot.xml
+1 -1
View File
@@ -2,7 +2,7 @@
<description>of two numeric columns</description>
<command interpreter="python">scatterplot.py $input $out_file1 $col1 $col2 "$title" "$xlab" "$ylab"</command>
<inputs>
<param name="input" type="data" format="tabular" label="Dataset" refresh_on_change="True" help="Query missing? See TIP below"/>
<param name="input" type="data" format="tabular" label="Dataset" help="Query missing? See TIP below"/>
<param name="col1" type="columnlist" assoc_dataset="input" numerical="True" label="Numerical column for x axis" />
<param name="col2" type="columnlist" assoc_dataset="input" numerical="True" label="Numerical column for y axis" />
<param name="title" size="30" type="text" value="Scatterplot" label="Plot title"/>
tools/stats/aggregate_scores_in_intervals.xml
-60
View File
@@ -1,60 +0,0 @@
<tool id="aggregate_scores_in_intervals1" description="from the table browser (equivalent to wiggle format)." name="Aggregate datapoints">
<description>Appends the average, min, max, sum, and count of datapoints per interval</description>
<command interpreter="python2.4">aggregate_scores_in_intervals.py $input2 $input1 $input1_chromCol $input1_startCol $input1_endCol $out_file1</command>
<inputs>
<page>
<param format="wig" name="input2" type="data" label="Datapoints from table browser"/>
<param format="interval" name="input1" type="data" label="Interval file"/>
</page>
</inputs>
<outputs>
<data format="interval" name="out_file1" metadata_source="input2"/>
</outputs>
<!-- TODO: This tool is currently not being used, uncomment and correct the tests if it ever is...
<tests>
<test>
<param name="input1" value="aggregate_binned_scores_in_intervals.bed" />
<param name="datasets" value="aggregate_binned_scores_in_intervals.wig" />
<output name="out_file1" file="aggregate_binned_scores_in_intervals.out" />
</test>
</tests> -->
<help>
.. class:: warningmark
This tool currently only works with data from genome builds hg16, hg17 or hg18.
.. class:: warningmark
This tool expects 2 input datasets, the first in wiggle format and the second in interval format.
-----
.. class:: infomark
**TIP:** Aggregating data may throw exceptions if the data type (e.g., string, integer) in every line of the columns is not appropriate for the computation (e.g., attempting numerical calculations on strings). If an exception is thrown, computation is stopped and an error message is displayed.
-----
**Syntax**
This tool returns aggregated data per interval in the form of the average, minimum and maximum of the data points for each given interval.
Note: Datapoints must be in the format returned by the table browser.
.. image:: ../../static/images/dat_points_table_brows_1.png
-----
**Example**
*Input*
.. image:: ../../static/images/aggregate_history1.png
*Result*
.. image:: ../../static/images/aggregate_history2.png
</help>
</tool>
tools/stats/cor.xml
+1 -1
View File
@@ -2,7 +2,7 @@
<description>for numeric columns</description>
<command interpreter="python">cor.py $input1 $out_file1 $numeric_columns $method</command>
<inputs>
<param format="tabular" name="input1" type="data" label="Dataset" refresh_on_change="True" help="Query missing? See TIP below"/>
<param format="tabular" name="input1" type="data" label="Dataset" help="Query missing? See TIP below"/>
<param name="numeric_columns" label="Numerical columns" type="columnlist" numerical="True" multiple="True" assoc_dataset="input1" help="Multi-select list - hold the appropriate key while clicking to select multiple columns" />
<param name="method" type="select" label="Method">
<option value="pearson">Pearson</option>
tools/stats/grouping.xml
+1 -1
View File
@@ -11,7 +11,7 @@
#end for
</command>
<inputs>
<param format="tabular" name="input1" type="data" label="Select data" refresh_on_change="True" help="Query missing? See TIP below."/>
<param format="tabular" name="input1" type="data" label="Select data" help="Query missing? See TIP below."/>
<param name="groupcol" label="Group by column" type="columnlist" assoc_dataset="input1" />
<repeat name="operations" title="Operation">
<param name="optype" type="select" label="Type">