Working version.

scripts/illumina2ftsv/illumina2ftsv

@@ -1,6 +1,7 @@
 #!/usr/bin/python
 
 import getopt
+import numpy
 import sys
 
 from laydi import dataset
@@ -16,7 +17,7 @@ def parse_options():
 def read_illumina_file(fn):
     fd = open(fn)
     line = fd.readline()
-    if line != "Illumina Inc. GenomeStudio version 1.7.0":
+    if line.strip() != "Illumina Inc. GenomeStudio version 1.7.0":
         raise Exception("File cannot be recognized as Illumina textual data")
 
     headers = {}
@@ -31,15 +32,38 @@ def read_illumina_file(fn):
     values = []
     line = fd.readline()
     while line != "":
-        values.append[x.strip() for x in line.split('\t')
+        values.append([x.strip() for x in line.split('\t')])
+        line = fd.readline()
 
-    probe_col = col_headers.find("ProbeID")
+    probe_col = col_headers.index("ProbeID")
+    print "probe id column:"   
 
+    header_cols = []
+    samples = []
+    for i, colname in enumerate(col_headers):
+        if colname.startswith("AVG_Signal-"):
+            header_cols.append(i)
+            samples.append(colname.split("-", 1)[1])
 
+    print header_cols
+    print samples
 
+    a = numpy.array(values)
+    m = numpy.array(a[:,header_cols], dtype='d')
+    print m
+    
+    probe_ids = list(a[:, probe_col])
+
+    print "samples: ", len(samples)
+    print "probe_ids: ", len(probe_ids)
+    print "shape: ", m.shape
+
+    ds = dataset.Dataset(m.transpose(), [('samples', samples), ('probe-ids', probe_ids)], name="Average Expr.")
+    dataset.write_ftsv("test.ftsv", ds)
 
 if __name__ == '__main__':
-    fn = params[0]
+    
+    fn = parse_options()[0]
     read_illumina_file(fn)