shunsukeaihara

#!/opt/local/bin/python
# module power iteration clustering

import numpy as NP
from scipy.cluster.vq import kmeans2

def calcNorm1(v):
    return NP.sum(NP.fabs(v))

def calcDelta(v,v2):

rxaviers

People

:bowtie:	😄 :smile:	😆 :laughing:
😊 :blush:	😃 :smiley:	☺️ :relaxed:
😏 :smirk:	😍 :heart_eyes:	😘 :kissing_heart:
😚 :kissing_closed_eyes:	😳 :flushed:	😌 :relieved:
😆 :satisfied:	😁 :grin:	😉 :wink:
😜 :stuck_out_tongue_winking_eye:	😝 :stuck_out_tongue_closed_eyes:	😀 :grinning:
😗 :kissing:	😙 :kissing_smiling_eyes:	😛 :stuck_out_tongue:

vinovator

# pdfTextMiner.py
# Python 2.7.6
# For Python 3.x use pdfminer3k module
# This link has useful information on components of the program
# https://euske.github.io/pdfminer/programming.html
# http://denis.papathanasiou.org/posts/2010.08.04.post.html


''' Important classes to remember
PDFParser - fetches data from pdf file

superjamie

Raspberry Pi VPN Router

This is a quick-and-dirty guide to setting up a Raspberry Pi as a "router on a stick" to PrivateInternetAccess VPN.

Requirements

Install Raspbian Jessie (2016-05-27-raspbian-jessie.img) to your Pi's sdcard.

Use the Raspberry Pi Configuration tool or sudo raspi-config to:

pylover

# Extracted using: $ unzip -p lib/pycharm.jar com/jetbrains/python/PyBundle.properties | grep -B1 INSP.NAME | grep '^#' | sed 's|Inspection||g' | sed -e 's|#\s\{,1\}|# noinspection |'

# noinspection PyPep8
# noinspection PyPep8Naming
# noinspection PyTypeChecker
# noinspection PyAbstractClass
# noinspection PyArgumentEqualDefault
# noinspection PyArgumentList
# noinspection PyAssignmentToLoopOrWithParameter
# noinspection PyAttributeOutsideInit

andrearota

// Problem: creating a Spark UDF that take extra parameter at invocation time.
// Solution: using currying
// http://stackoverflow.com/questions/35546576/how-can-i-pass-extra-parameters-to-udfs-in-sparksql

// We want to create hideTabooValues, a Spark UDF that set to -1 fields that contains any of given taboo values.
// E.g. forbiddenValues = [1, 2, 3]
//      dataframe = [1, 2, 3, 4, 5, 6]
//      dataframe.select(hideTabooValues(forbiddenValues)) :> [-1, -1, -1, 4, 5, 6]
//
// Implementing this in Spark, we find two major issues:

thvitt

#!/bin/sh

if [ "$PYENV_VERSION" -ne "" ]
then
    name=`pyenv version-name`
    python=`pyenv which python`
else
    name=`basename "$VIRTUAL_ENV"`
    python="$VIRTUALENV/bin/python"
fi

bborgesr

library(shiny)
library(shinyjs) 

ui <- fluidPage(
  useShinyjs(),
  fileInput('inFile', 'Choose file'),
  actionButton('reset', 'Reset'),
  tableOutput('tbl')
)

claudinei-daitx

import org.apache.spark.sql.SparkSession

object SparkSessionS3 {
    //create a spark session with optimizations to work with Amazon S3.
    def getSparkSession: SparkSession = {
        val spark = SparkSession
            .builder
            .appName("my spark application name")
            .config("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
            .config("spark.hadoop.fs.s3a.access.key", "my access key")

bgweber

import featuretools as ft
from pyspark.sql.functions import pandas_udf, PandasUDFType

@pandas_udf(schema, PandasUDFType.GROUPED_MAP)
def apply_feature_generation(pandasInputDF):
    
    # create Entity Set representation 
    es = ft.EntitySet(id="events")
    es = es.entity_from_dataframe(entity_id="events", dataframe=pandasInputDF)
    es = es.normalize_entity(base_entity_id="events", new_entity_id="users", index="user_id")