elena-roff

Vim cheat sheet

Starting Vim

vim [file1] [file2] ...

---

DGrady

"""
The schemas that Spark produces for DataFrames are typically
nested, and these nested schemas are quite difficult to work with
interactively. In many cases, it's possible to flatten a schema
into a single level of column names.
"""

import typing as T

import cytoolz.curried as tz

AlessandroChecco

# A simple cheat sheet of Spark Dataframe syntax
# Current for Spark 1.6.1

# import statements
#from pyspark.sql import SQLContext
#from pyspark.sql.types import *
#from pyspark.sql.functions import *
from pyspark.sql import functions as F

#SparkContext available as sc, HiveContext available as sqlContext.

rmoff

subfuzion

Common Options

-#, --progress-bar Make curl display a simple progress bar instead of the more informational standard meter.

-b, --cookie <name=data> Supply cookie with request. If no =, then specifies the cookie file to use (see -c).

-c, --cookie-jar <file name> File to save response cookies to.

jiffyclub

"""
Convert Pandas DFs in an HDFStore to parquet files for better compatibility
with Spark.

Run from the command line with:

spark-submit --driver-memory 4g --master 'local[*]' hdf5_to_parquet.py

"""
import pandas as pd

LeCoupa

#!/bin/bash
#####################################################
# Name: Bash CheatSheet for Mac OSX
# 
# A little overlook of the Bash basics
#
# Usage:
#
# Author: J. Le Coupanec
# Date: 2014/11/04

bshyong

class BSTnode(object):
    """
Representation of a node in a binary search tree.
Has a left child, right child, and key value, and stores its subtree size.
"""
    def __init__(self, parent, t):
        """Create a new leaf with key t."""
        self.key = t
        self.parent = parent
        self.left = None

kachayev

from collections import defaultdict
from heapq import *

def dijkstra(edges, f, t):
    g = defaultdict(list)
    for l,r,c in edges:
        g[l].append((c,r))

    q, seen, mins = [(0,f,())], set(), {f: 0}
    while q:

MLnick

import sys

from pyspark.context import SparkContext
from numpy import array, random as np_random
from sklearn import linear_model as lm
from sklearn.base import copy

N = 10000   # Number of data points
D = 10      # Numer of dimensions
ITERATIONS = 5