stefanthoss

import json
from pyspark.sql.types import *

# Define the schema
schema = StructType(
    [StructField("name", StringType(), True), StructField("age", IntegerType(), True)]
)

# Write the schema
with open("schema.json", "w") as f:

towo

define theme:
  description = "gruvbox.theme: A gruvbox-inspired theme"
  colors:
    exclusion = "color on color8"
    today = "color208"
    holiday = "color13"
    label = "color243"
    ids = "color4"
    debug = "color14"
  palette:

LeCoupa

# Redis Cheatsheet
# All the commands you need to know


redis-server /path/redis.conf  # start redis with the related configuration file
redis-cli                      # opens a redis prompt


# Strings.

samuelsmal

from pyspark.sql.functions import udf
from pyspark.sql.types import BooleanType

def regex_filter(x):
    regexs = ['.*ALLYOURBASEBELONGTOUS.*']
    
    if x and x.strip():
        for r in regexs:
            if re.match(r, x, re.IGNORECASE):
                return True

joshlk

import pandas as pd

def _map_to_pandas(rdds):
    """ Needs to be here due to pickling issues """
    return [pd.DataFrame(list(rdds))]

def toPandas(df, n_partitions=None):
    """
    Returns the contents of `df` as a local `pandas.DataFrame` in a speedy fashion. The DataFrame is
    repartitioned if `n_partitions` is passed.

evenv

# 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 *

#creating dataframes
df = sqlContext.createDataFrame([(1, 4), (2, 5), (3, 6)], ["A", "B"]) # from manual data

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: