pvarsh

"""" Basic Behavior

set number              " show line numbers
set relativenumber      " show relative line numbers
set wrap                " wrap lines
set encoding=utf-8      " set encoding to UTF-8 (default was "latin1")
set lazyredraw          " redraw screen only when we need to
set showmatch           " highlight matching parentheses / brackets [{()}]
set laststatus=2        " always show statusline (even with only single window)
set ruler               " show line and column number of the cursor on right side of statusline

pvarsh

pvarsh

alias csvrowcount='for i in `find . -name "*.csv"`; do echo "$i"; csvstat --count $i; done'
alias csvfilecount='find . -name "*.csv" | wc -l'

pvarsh

import csv
import string

def make_csv():
    with open('data.csv', 'wb') as fh:
        writer = csv.writer(fh)
        for i in range(10):
            writer.writerow([i, string.lowercase[i:i+5]])

def process_line(line):

pvarsh

" Syntax highlighting
syntax on
filetype indent plugin on

" ghlight lines over 79 columns (PEP8)
highlight OverLength ctermbg=red ctermfg=white guibg=#351818
match OverLength /\%79v.\+/
 
" Convert tabs to 4 spaces
set tabstop=4

pvarsh

### Removes all rows that are identically ''

import parsekit
 
class FilterEmptyRows(parsekit.Step):

    def run(self, record, metadata):
        criterion = {'', None}
        if not set(record).issubset(criterion):
            return record, metadata

pvarsh

from datetime import datetime
import parsekit

class FilterRows(parsekit.Step):

    start_row = parsekit.Argument(
        "The row to start emitting from.",
        required=True,
        type=int)

pvarsh

import parsekit
 
class FilterEmptyRows(parsekit.Step):

    def run(self, record, metadata):
        criterion = {'', None}
        if not set(record).issubset(criterion):
            return record, metadata

pvarsh

import parsekit
 
class FilterRow(parsekit.Step):

    start_row = parsekit.Argument(
        "The row to start emitting from.",
        required=True,
        type=int)

    def configure(self, options):

pvarsh

## Illinois: skip header rows
## Maine: skipped rows containing only '' or None
## Utah: skip empty rows, skip rows containing certain data in certain column. Specifically the footer row started with the date in first column, so it was filtered out by parsing first column as a date.
## Washington: removed rows that were identically '' from end of file