diff --git a/data/bd1.csv b/data/bd1.csv
new file mode 100644
index 0000000..c3b291e
--- /dev/null
+++ b/data/bd1.csv
@@ -0,0 +1,206 @@
+7042,x86:
+12912,with
+11865,when
+5074,warning
+24426,use
+5349,update
+7954,up
+6314,unused
+64672,to
+35310,the
+24263,support
+5771,struct
+17728,staging:
+5641,return
+25236,remove
+22372,on
+33225,of
+8410,not
+6360,new
+5016,net:
+6485,move
+5265,missing
+6802,make
+8091,is
+5290,into
+52209,in
+6189,if
+6232,handling
+6055,functions
+7840,function
+16320,from
+65607,for
+44773,fix
+9787,error
+6389,drm/i915:
+11653,driver
+4925,don't
+8701,device
+4773,data
+4951,convert
+6825,comedi:
+12271,code
+5500,cleanup
+7424,check
+4882,by
+27324,and
+28434,add
+16295,a
+10977,[media]
+8469,[SCSI]
+23958,[PATCH]
+4802,Viro
+8044,V4L/DVB
+12237,Use
+6316,USB:
+5630,Thomas
+5093,Sweeten
+7189,Staging:
+16617,Remove
+5837,Peter
+7169,Paul
+5509,Michael
+6541,Mark
+5819,KVM:
+5095,Hartley
+5066,H
+35452,Fix
+6001,Eric
+11559,David
+4974,Carvalho
+5519,Ben
+4835,Al
+30581,Add
+8653,ASoC:
+22353,ARM:
+6378,ALSA:
+13287,9
+16870,8
+18956,7
+25500,6
+30558,5
+46180,4
+65579,3
+4972,20
+109795,2
+5030,19
+5480,18
+5844,17
+6632,16
+6866,15
+7540,14
+8255,13
+9650,12
+9887,11
+12041,10
+300223,1
+13533,-
+17381,
+5458,use,to
+7241,to,the
+5681,the,of
+4791,the,in
+5947,the,for
+11034,support,for
+8995,in,fix
+5795,staging:,comedi:
+4737,for,and
+5710,to,add
+6315,support,add
+8521,for,add
+5093,Sweeten,Hartley
+5019,Sweeten,H
+5019,Hartley,H
+8250,in,Fix
+4798,Viro,Al
+6499,to,Add
+8066,support,Add
+10953,for,Add
+4855,for,ARM:
+6376,to,4
+5054,in,4
+6533,for,4
+9266,to,3
+4944,the,3
+7061,in,3
+9203,for,3
+5984,fix,3
+4731,Fix,3
+5697,use,2
+15203,to,2
+8046,the,2
+5783,support,2
+5814,remove,2
+5113,on,2
+7944,of,2
+12066,in,2
+15440,for,2
+10548,fix,2
+6438,and,2
+6613,add,2
+5719,[PATCH],2
+8403,Fix,2
+7184,Add,2
+5260,ARM:,2
+8276,with,1
+7996,when,1
+15950,use,1
+5134,up,1
+39909,to,1
+22632,the,1
+14217,support,1
+12428,staging:,1
+16443,remove,1
+14623,on,1
+21464,of,1
+5576,not,1
+5341,is,1
+34752,in,1
+4943,function,1
+10171,from,1
+41132,for,1
+30042,fix,1
+6736,error,1
+7065,driver,1
+5522,device,1
+5724,comedi:,1
+7549,code,1
+4967,check,1
+16873,and,1
+17345,add,1
+10262,a,1
+7268,[media],1
+5140,[SCSI],1
+14278,[PATCH],1
+4818,V4L/DVB,1
+8158,Use,1
+4849,Staging:,1
+10720,Remove,1
+24032,Fix,1
+7062,David,1
+18539,Add,1
+6115,ASoC:,1
+14235,ARM:,1
+7163,9,1
+9025,8,1
+9886,7,1
+12804,6,1
+13468,5,1
+19333,4,1
+23745,3,1
+42181,2,1
+5179,12,1
+5231,11,1
+6560,10,1
+8865,1,-
+10917,1,
+5019,Sweeten,Hartley,H
+6447,support,for,1
+6173,in,fix,1
+4948,staging:,comedi:,1
+5152,for,add,1
+5683,in,Fix,1
+6627,for,Add,1
+5587,to,2,1
+5127,in,2,1
+5706,for,2,1
diff --git a/data/phase1.csv b/data/phase1.csv
new file mode 100644
index 0000000..c3b291e
--- /dev/null
+++ b/data/phase1.csv
@@ -0,0 +1,206 @@
+7042,x86:
+12912,with
+11865,when
+5074,warning
+24426,use
+5349,update
+7954,up
+6314,unused
+64672,to
+35310,the
+24263,support
+5771,struct
+17728,staging:
+5641,return
+25236,remove
+22372,on
+33225,of
+8410,not
+6360,new
+5016,net:
+6485,move
+5265,missing
+6802,make
+8091,is
+5290,into
+52209,in
+6189,if
+6232,handling
+6055,functions
+7840,function
+16320,from
+65607,for
+44773,fix
+9787,error
+6389,drm/i915:
+11653,driver
+4925,don't
+8701,device
+4773,data
+4951,convert
+6825,comedi:
+12271,code
+5500,cleanup
+7424,check
+4882,by
+27324,and
+28434,add
+16295,a
+10977,[media]
+8469,[SCSI]
+23958,[PATCH]
+4802,Viro
+8044,V4L/DVB
+12237,Use
+6316,USB:
+5630,Thomas
+5093,Sweeten
+7189,Staging:
+16617,Remove
+5837,Peter
+7169,Paul
+5509,Michael
+6541,Mark
+5819,KVM:
+5095,Hartley
+5066,H
+35452,Fix
+6001,Eric
+11559,David
+4974,Carvalho
+5519,Ben
+4835,Al
+30581,Add
+8653,ASoC:
+22353,ARM:
+6378,ALSA:
+13287,9
+16870,8
+18956,7
+25500,6
+30558,5
+46180,4
+65579,3
+4972,20
+109795,2
+5030,19
+5480,18
+5844,17
+6632,16
+6866,15
+7540,14
+8255,13
+9650,12
+9887,11
+12041,10
+300223,1
+13533,-
+17381,
+5458,use,to
+7241,to,the
+5681,the,of
+4791,the,in
+5947,the,for
+11034,support,for
+8995,in,fix
+5795,staging:,comedi:
+4737,for,and
+5710,to,add
+6315,support,add
+8521,for,add
+5093,Sweeten,Hartley
+5019,Sweeten,H
+5019,Hartley,H
+8250,in,Fix
+4798,Viro,Al
+6499,to,Add
+8066,support,Add
+10953,for,Add
+4855,for,ARM:
+6376,to,4
+5054,in,4
+6533,for,4
+9266,to,3
+4944,the,3
+7061,in,3
+9203,for,3
+5984,fix,3
+4731,Fix,3
+5697,use,2
+15203,to,2
+8046,the,2
+5783,support,2
+5814,remove,2
+5113,on,2
+7944,of,2
+12066,in,2
+15440,for,2
+10548,fix,2
+6438,and,2
+6613,add,2
+5719,[PATCH],2
+8403,Fix,2
+7184,Add,2
+5260,ARM:,2
+8276,with,1
+7996,when,1
+15950,use,1
+5134,up,1
+39909,to,1
+22632,the,1
+14217,support,1
+12428,staging:,1
+16443,remove,1
+14623,on,1
+21464,of,1
+5576,not,1
+5341,is,1
+34752,in,1
+4943,function,1
+10171,from,1
+41132,for,1
+30042,fix,1
+6736,error,1
+7065,driver,1
+5522,device,1
+5724,comedi:,1
+7549,code,1
+4967,check,1
+16873,and,1
+17345,add,1
+10262,a,1
+7268,[media],1
+5140,[SCSI],1
+14278,[PATCH],1
+4818,V4L/DVB,1
+8158,Use,1
+4849,Staging:,1
+10720,Remove,1
+24032,Fix,1
+7062,David,1
+18539,Add,1
+6115,ASoC:,1
+14235,ARM:,1
+7163,9,1
+9025,8,1
+9886,7,1
+12804,6,1
+13468,5,1
+19333,4,1
+23745,3,1
+42181,2,1
+5179,12,1
+5231,11,1
+6560,10,1
+8865,1,-
+10917,1,
+5019,Sweeten,Hartley,H
+6447,support,for,1
+6173,in,fix,1
+4948,staging:,comedi:,1
+5152,for,add,1
+5683,in,Fix,1
+6627,for,Add,1
+5587,to,2,1
+5127,in,2,1
+5706,for,2,1