seanjtaylor

chriddyp

# See official docs at https://dash.plotly.com
# pip install dash pandas

from dash import Dash, dcc, html, Input, Output
import plotly.express as px

import pandas as pd

df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/gapminderDataFiveYear.csv')

bigorn0

You can use select with varargs including *:

import spark.implicits._

df.select($"*" +: Seq("A", "B", "C").map(c => 
  sum(c).over(Window.partitionBy("ID").orderBy("time")).alias(s"cum$c")
): _*)
This:

Maps columns names to window expressions with Seq("A", ...).map(...)

duckworth

CREATE EXTERNAL TABLE IF NOT EXISTS alb_logs (
	type string, 
	timestamp string, 
	elb string, 
	client_ip string, 
	client_port int,
	target_ip string,
	target_port int, 
	request_processing_time double, 
	target_processing_time double,

bigsnarfdude

wcchin

# -*- coding: utf-8 -*-

## EXPORTING TO PDF FROM revealjs OR jupyter notebook slides

## using nbconvert and decktape (https://github.com/astefanutti/decktape)
## to export pdf and/or html(revealjs)
## from jupyter notebook / revealjs html
## phantomjs must be included in path, and decktape directory must be place beside this export_reveal.py file
## for more detail, please check:
## nbconvert - https://github.com/jupyter/nbconvert

mrahul17

# credits @mmueller     https://www.kaggle.com/mmueller/liberty-mutual-group-property-inspection-prediction/xgb-feature-importance-python/code
import pandas as pd
import xgboost as xgb
import operator
from matplotlib import pylab as plt

def ceate_feature_map(features):
    outfile = open('xgb.fmap', 'w')
    i = 0
    for feat in features:

rbren

DataFire Daemon: Sync GitHub Issues to Trello

Create a Trello list for every Milestone, and a card for every Issue

View on DataFire

[metadata]: ./ '{"links":[{"connection":"564cb90e2a034b0e0f1255fe","operation":{"method":"get","path":"/members/{idMember}/boards"}},{"connection":"563b9b84ea9ad5f345e97505","operation":{"method":"get","path":"/repos/{ownerId}/{repoId}/issues"}},{"connection":"564cb90e2a034b0e0f1255fe","operation":{"method":"get","path":"/boards/{idBoard}/cards"}},{"connection":"564cb90e2a034b0e0f1255fe","operation":{"method":"get","path":"/boards/{idBoard}/lists"}},{"connection":"563b9b84ea9ad5f345e97505","operation":{"method":"get","path":"/repos/{ownerId}/{repoId}/milestones"}},{"connection":"564cb90e2a034b0e0f1255fe","operation":{"method":"post","path":"/lists"}},{"connection":"564cb90e2a034b0e0f1255fe","operation":{"method":"post","path":"/cards"}},{"connection":"564cb90e2a034b0e0f1255fe","operation":{"method":"put","path":"/cards/{i

narphorium

feynmanliang

import org.apache.spark.ml.feature.{CountVectorizer, RegexTokenizer, StopWordsRemover}
import org.apache.spark.mllib.clustering.{LDA, OnlineLDAOptimizer}
import org.apache.spark.mllib.linalg.Vector

import sqlContext.implicits._

val numTopics: Int = 100
val maxIterations: Int = 100
val vocabSize: Int = 10000