diff --git a/README.md b/README.md old mode 100644 new mode 100755 index 9bbad88..6c68b83 --- a/README.md +++ b/README.md @@ -1,47 +1,68 @@ - -**tabtk_xlsx** - -interface: - - $ tabtk_xlsx - Usage: tabtk_xlsx [] - version: 0.0.1 - - benchmark and usage: - - $ time tabtk_xlsx.py ncbi.map.xlsx ncbi:ncbi.map - real 2m47.532s - user 2m46.537s - sys 0m0.829s - - $time tabtk_xlsx ncbi.map.xlsx ncbi:ncbi.map - real 0m12.577s - user 0m11.980s - sys 0m0.582s - - $ tabtk_xlsx taxonomy.xlsx phylum:phylum.txt order:order.txt genus:genus.txt species:species.txt - -**tabtk_join** - -interface: - - $ tabtk_join - Usage: tabtk_join [options] [text ...] - Options: - -p CHAR placehold for missing value, default: ['-']; - -v print version number - -**tabtk_agg** - -interface: - - $ tabtk_agg - Usage: tabtk_agg [options] [label:text ...] - Options: - -k STR the keys fields pattern: 1:2:3, default: [1]; - -t STR the titles for keys: key_1:key_2:key_3, default: [catalog]; - -c INT the target column default: [2]; - -p CHAR placehold for missing value: default ['0']; - -i ignore the head line; - -v print version number - + +# tsv-utils: tools for manipulate tsv file. + +Author: LEI ZHANG + +current version: `version:0.0.1-r2` + +### main commond line interface + + $ tsv-utils + + + Usage: tsv-utils + Version: 0.0.1-r2 + + Command: + -- Combination + agg combinate multi-file. + join join tables with primery key. + tsv2xlsx convert (multi-)tsv file to Excel file. + + -- Numeric data frame + rank rank/merge for numeric table. + abundance calculate relative abundance for numeric table. + norm normalization with counts map and normalization + factor for numeric table. + stand standardization for numeric table. + melt merge values with bin table file. + distribution calculate bins feature distribution. + trim trim rows using cutoff.(sum operation). + nfilter filter using value with specied collum. op: >= | <= . + + -- Editing + annotation annotating specify collum with key/value(s) db. + links transform annotation with links map and definitions. + associate associate with links map. + definition adding definition collum with key/value(s) db. + replace replace specify collum elements with key/value(s) db. + reorder reorder rows by specify key in specify collum. + subset retrieve ids in/not in list file [row]. + subcolumn retrieve ids in/not in list file [collum]. + collapse collapse '\t' separator to specify delim. + add_headline add headline. + groupline add groupline. + placehold fill empty cell with specify STR. + reshape reshape and bin using map file. + + -- Matrix Operation + transpose matrix transpose. + submatrix submatrix by id. + matrix2tab binary format. + matrix2melt elements in submatrix using metadata. + + -- Summary + cut print selected parts of lines. + bins uniq/bin/summary. + uniq unique specify collum and counts. + nlines calculate lines of file. + stats calculate stats for selected collum. + unpack unpack the bins files. + + -- auxiliary utils. + view View text file, ignor comments and blank lines. + + Licenced: + (c) 2018-2020 - LEI ZHANG + Logic Informatics Co.,Ltd. + zhanglei@logicinformatics.com diff --git a/tabtk_agg b/tabtk_agg deleted file mode 100644 index ca03b2f..0000000 Binary files a/tabtk_agg and /dev/null differ diff --git a/tabtk_bins b/tabtk_bins deleted file mode 100644 index 486497f..0000000 Binary files a/tabtk_bins and /dev/null differ diff --git a/tabtk_decorate b/tabtk_decorate deleted file mode 100644 index 8d81d8d..0000000 Binary files a/tabtk_decorate and /dev/null differ diff --git a/tabtk_join b/tabtk_join deleted file mode 100644 index ca48110..0000000 Binary files a/tabtk_join and /dev/null differ diff --git a/tabtk_nlines b/tabtk_nlines deleted file mode 100644 index b36c6fc..0000000 Binary files a/tabtk_nlines and /dev/null differ diff --git a/tabtk_subset b/tabtk_subset deleted file mode 100644 index 18d4451..0000000 Binary files a/tabtk_subset and /dev/null differ diff --git a/tabtk_uniq b/tabtk_uniq deleted file mode 100644 index 23f7cfc..0000000 Binary files a/tabtk_uniq and /dev/null differ diff --git a/tabtk_xlsx b/tabtk_xlsx deleted file mode 100644 index 5fcb7a7..0000000 Binary files a/tabtk_xlsx and /dev/null differ