Teng Peng tengpeng

p < 0.05

tengpeng / gist:d78c2184f3f29ec749c3

Created March 24, 2015 22:01

Loop 5.24e

	FantasyBaseball3 <- log(FantasyBaseball[, -1])
	est_mean <- colMeans(FantasyBaseball3)
	k=1
	for (i in 1:7){
	for (j in (i+1) : 8){
	est <- est_mean[i]-est_mean[j]
	pair <- paste(names(est_mean[i]), names(est_mean[j]), sep="~")
	Lower <- est-margin
	Upper <- est+margin
	result[k, ]<- c(pair, est, Lower, Upper)

tengpeng / gist:2fa57a3addc95ef4e733

Created April 5, 2015 05:01

Haase Diagram TikZ

tengpeng / SQL-Movie-Rating.sql

Last active September 14, 2015 03:06

My answers to SQL exercises for db-class.org /Part 1/

	/* Delete the tables if they already exist */
	drop table if exists Movie;
	drop table if exists Reviewer;
	drop table if exists Rating;

	/* Create the schema for our tables */
	create table Movie(mID int, title text, year int, director text);
	create table Reviewer(rID int, name text);
	create table Rating(rID int, mID int, stars int, ratingDate date);

tengpeng / SQL-Social-Network.sql

Last active September 14, 2015 21:49

My answers to SQL exercises for db-class.org /Part 2/

tengpeng / gist:fb6809717361319d8bde

Created January 30, 2016 05:17

knnImputation

	function (data, k = 10, scale = T, meth = "weighAvg", distData = NULL)
	{
	n <- nrow(data)
	if (!is.null(distData)) {
	distInit <- n + 1
	data <- rbind(data, distData)
	}
	else distInit <- 1
	N <- nrow(data)
	ncol <- ncol(data)

tengpeng / a.rb

Created January 31, 2016 03:15

https://gist.github.com/ac2b8cc202712d12595d

tengpeng / a.rb

Created January 31, 2016 03:17

test

	import numpy
	#data = numpy.random.random(100)
	bins = numpy.linspace(15, 100, 5)
	group_names = ['1', '2', '3', '4','5']
	#digitized = numpy.digitize(df_all['age'], bins)
	categories = pd.cut(df_all['age'], bins, labels=group_names)
	df['categories'] = pd.cut(df['postTestScore'], bins, labels=group_names)
	categories
	#bin_means = [data[digitized == i].mean() for i in range(1, len(bins))]
	#df_all['age']

tengpeng / a.rb

Created January 31, 2016 22:46

hist python

	import seaborn as sns
	sns.set_style("white", {'ytick.major.size': 10.0})
	sns.set_context("poster", font_scale=1.1)
	income = df_train.MonthlyIncome.dropna()
	income = income[income < 20000]
	sns.distplot(income, color='#FD5C64')
	#df[(df.T != 0).any()]
	plt.xlabel('Income')
	sns.despine()

tengpeng / a.rb

Created January 31, 2016 22:47

concat py

pd.concat((train_users, test_users), axis=0, ignore_index=True)

tengpeng / a.rb

Created January 31, 2016 22:47

drop py

users.drop('id',axis=1, inplace=True)

	/* Delete the tables if they already exist */
	drop table if exists Highschooler;
	drop table if exists Friend;
	drop table if exists Likes;

	/* Create the schema for our tables */
	create table Highschooler(ID int, name text, grade int);
	create table Friend(ID1 int, ID2 int);
	create table Likes(ID1 int, ID2 int);