vignesh-saptarishi

import pandas
import random
import time

# creating fake dataset
sample_size = 10000
cat1_pop = range(1, 2001)
cat2_pop = ['a', 'b', 'c', 'd', 'e']
cat1_vals = [random.choice(cat1_pop) for _ in range(sample_size)]
cat2_vals = [random.choice(cat2_pop) for _ in range(len(cat1_pop))]

vignesh-saptarishi

import numpy
import pandas
import matplotlib.pyplot as plt
import seaborn as sns
from ggplot import *
plt.style.use('ggplot')


def get_histogram_xy(data, bins=10):
    """Returns x,y coordinates for Histogram data.

vignesh-saptarishi

import pandas

def map_columns(df=None, col1=None, col2=None):
    """
    Returns a mapping dictionary based on two columns:
        key = col1 values
        value = col2 values
        
    Mapping as a dict is useful only as long as we have unique values for keys.
    """

vignesh-saptarishi

"""
Use:
  >>> pandas.DataFrame.mask = mask
  >>> df.mask('Col1', 'is', value).mask('Col3', 'not', value)
"""

import pandas

def mask(df, key=None, op='is', val=None):
    if op == 'is':

vignesh-saptarishi

import xlrd
import csv
import os

def csv_from_xlsx(xlfile):
    """
    Convert Microsoft Excel File .xls(x) to csv
    """
    workbook = xlrd.open_workbook(xlfile)
    sheet = workbook.sheet_by_index(0)

vignesh-saptarishi

from IPython.display import HTML

HTML('''<script>
code_show=true; 
function code_toggle() {
 if (code_show){
 $('div.input').hide();
 } else {
 $('div.input').show();
 }

vignesh-saptarishi

import json
import argparse

def generate_py(ipynb_file, op_file):
    # get data
    with open(ipynb_file) as ipynb:
        data = json.load(ipynb)
    # check language in metadata
    if data['metadata']['kernelspec']['language'] != 'python':
        print 'Warning. Language not python.'