#from 00 notebook
!head ../data/Piura_v1_GOslim.csv

!perl -e '$count=0; $len=0; while(<>) {s/\r?\n//; s/\t/ /g; if (s/^>//) { if ($. != 1) {print "\n"} s/ |$/\t/; $count++; $_ .= "\t";} else {s/ //g; $len += length($_)} print $_;} print "\n"; warn "\nConverted $count FASTA records in $. lines to tabular format\nTotal sequence length: $len\n\n";' \
../data/Piura_v1_contigs.fa > ../data/Piura_v1_contigs.tab

!head -1 ../data/Piura_v1_contigs.tab

#temp replace name so c or g will not confound
!sed 's/PiuraChilensis_v1_contig/999999/g' <../data/Piura_v1_contigs.tab> ../data/Piura_v1-99_contigs.tab


!head -1 ../data/Piura_v1-99_contigs.tab

#add column with length of sequence
!perl -e '$col = 2;' -e 'while (<>) { s/\r?\n//; @F = split /\t/, $_; $len = length($F[$col]); print "$_\t$len\n" } warn "\nAdded column with length of column $col for $. lines.\n\n";' \
../data/Piura_v1-99_contigs.tab > ../data/Piura_v1-99-l_contigs.tab

!head -1 ../data/Piura_v1-99-l_contigs.tab

!awk -F\CG '{print NF-1}' ../data/Piura_v1-99-l_contigs.tab > ../data/Piura_v1-99-l_contigs__CG.tab
!awk -F\C '{print NF-1}' ../data/Piura_v1-99-l_contigs.tab > ../data/Piura_v1-99-l_contigs__C.tab
!awk -F\G '{print NF-1}' ../data/Piura_v1-99-l_contigs.tab > ../data/Piura_v1-99-l_contigs__G.tab
!paste ../data/Piura_v1-99-l_contigs.tab \
../data/Piura_v1-99-l_contigs__CG.tab \
../data/Piura_v1-99-l_contigs__C.tab \
../data/Piura_v1-99-l_contigs__G.tab \
> ../data/Piura_v1-99-l_contigs__C-G.tab
!head -1 ../data/Piura_v1-99-l_contigs__C-G.tab


!awk '{print $1, "\t", (($4)/($5*$6))*(($3**2)/($3-1))}' \
../data/Piura_v1-99-l_contigs__C-G.tab \
| sed 's/999999/PiuraChilensis_v1_contig/g' > ../data/Piura_v1_CpG.tab
!head ../data/Piura_v1_CpG.tab

!ls ../data

!rm ../data/Piura_v1-99*

!head ../data/Piura_v1_GOslim.csv

!tr ',' "\t" <../data/Piura_v1_GOslim.csv> ../data/Piura_v1_GOslim.tab

!sort ../data/Piura_v1_GOslim.tab | tail -n +2 > ../data/Piura_v1_GOslim.sorted
!awk -F $'\t' '{print $1, "\t", $2}' ../data/Piura_v1_GOslim.sorted > ../data/Piura_v1_GOslim.sortedtab
!head ../data/Piura_v1_GOslim.sortedtab

!sort ../data/Piura_v1_CpG.tab > ../data/Piura_v1_CpG.sorted
!awk -F $'\t' '{print $1, "\t", $2}' ../data/Piura_v1_CpG.sorted > ../data/Piura_v1_CpG.sortedtab
!head ../data/Piura_v1_CpG.sortedtab

!head ../data/Piura_v1_CpG-GOslim.csv

!tr ',' "\t" <../data/Piura_v1_CpG-GOslim.csv> ../data/Piura_v1_CpG-GOslim.tab

!head ../data/Piura_v1_CpG-GOslim.tab

!awk -F $'\t' '{print $1, "\t", $2," \t", $4}' ../data/Piura_v1_CpG-GOslim.tab | tail -n +2 > ../data/Piura_v1_CpG-slim.tab
!head ../data/Piura_v1_CpG-slim.tab


import pandas as pd

Piura = pd.read_table('../data/Piura_v1_CpG-slim.tab', header=None)


Piura

%matplotlib inline


import matplotlib.pyplot as plt 

Piura.groupby(2)[1].mean().plot(kind='barh', color=list('myb'))
plt.axis([0.7, 0.9, 0, 15])

# pandas density plot
Piura[1].plot(kind='kde', linewidth=3);
plt.axis([0.2, 1.5, 0, 1.9])