hellpanderrr

def break_list_by_code_words(l, words):
    '''Breaks 1-d list in groups by code words.
        ['Code_word_1,'abc','123','sd','Code_word_2','34253','123','Code_word_3','1231','4545'] -->
        [[Code_word_1,'abc','123','sd'], ['Code_word_2','34253','123'] ,['Code_word_3','1231','4545'] ]
    
    '''
    flag = False
    ret = []
    block = []
    for i in l:

hellpanderrr

# you might need to install cmake


#!/bin/bash
#
# [email protected], 2014-02-07

# which is not ideal, see http://stackoverflow.com/a/677212/1392758
python=`which python`
if type python2 > /dev/null 2>&1; then

hellpanderrr

sudo apt-get install nginx

sudo pip install gunicorn

/home/ubuntu/my_project -- path to the folder containing manage.py

/home/ubuntu/my_project/my_project -- path to the folder containing settings.py

$USER -- your username

hellpanderrr

### http://www.peterbe.com/plog/uniqifiers-benchmark

def uniqify(seq):
    seen = set()
    seen_add = seen.add
    return [x for x in seq if not (x in seen or seen_add(x))]

hellpanderrr

#'Iterable' means object has an __iter__() method.

isiterable = lambda obj: isinstance(obj, basestring) or bool(getattr(obj, '__iter__', False))

from collections import Iterable
isiterable = lambda obj: isinstance(obj, Iterable)

#https://docs.python.org/3/library/collections.abc.html#collections.abc.Iterable

hellpanderrr

def fix_string(string):
    ret = ''
    for char in string:
        try:
            ret += char.encode('cp1252').decode('cp1251')
        except:
            ret += char
    return ret

hellpanderrr

#models.py

from django.db.models import Aggregate

class Concat(Aggregate):
    def add_to_query(self, query, alias, col, source, is_summary):
        #we send source=CharField to prevent Django from casting string to int
        aggregate = SQLConcat(col, source=models.CharField(), is_summary=is_summary, **self.extra)
        query.aggregates[alias] = aggregate
    def __init__(self, col, distinct=False, **extra):

hellpanderrr

from sklearn.feature_extraction import DictVectorizer as DV

vectorizer = DV(sparse = False)
v = vectorizer.fit_transform(df.T.to_dict().values())
new_df = pd.DataFrame(v, columns=vectorizer.feature_names_)

hellpanderrr

def sort_df(df, column_idx, key):
    '''Takes dataframe, column index and custom function for sorting, 
    returns dataframe sorted by this column using this function'''
    
    col = df.ix[:,column_idx]
    temp = pd.DataFrame([])
    temp[0] = col
    temp[1] = df.index
    temp = temp.values.tolist()
    df = df.ix[[i[1] for i in sorted(temp, key=key)]]

hellpanderrr

def get_filelist(path, extension=None,only_folders=False):
    '''Returns list of files in a given folder, without going further
    Parameters
    ---------
    extension: Collect only files with this extension
    
    only_folders: Collect only folders names
    '''
    filenames = []
    if not only_folders: