sky_limit mrvege

## testSet.txt
-0.017612	-14.053064	0.0
-1.395634	-4.662541	1.0
-0.752157	-6.53862	0.0
-1.322371	-7.152853	0.0
0.423363	-11.054677	0.0
0.406704	-7.067335	1.0
0.667394	-12.741452	0.0
-2.46015	-6.866805	1.0
0.569411	-9.548755	0.0
-0.026632	-10.427743	0.0

## logistic_regression.py
#!/usr/bin/env python
# encoding: utf-8

from numpy import *
import matplotlib.pyplot as plt

def logistic(wTx):
    return 1.0/(1.0 + exp(-wTx))

def file2matrix(filename,delimiter):

## gist:6be2823f21af6dc66381

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                mrvege
                / gist:6be2823f21af6dc66381
            
            
              Created
              January 27, 2016 05:55
                — forked from entaroadun/gist:1653794
            
              
                Recommendation and Ratings Public Data Sets For Machine Learning 
              
          
    Movies Recommendation:

MovieLens - Movie Recommendation Data Sets http://www.grouplens.org/node/73
Yahoo! - Movie, Music, and Images Ratings Data Sets http://webscope.sandbox.yahoo.com/catalog.php?datatype=r
Jester - Movie Ratings Data Sets (Collaborative Filtering Dataset) http://www.ieor.berkeley.edu/~goldberg/jester-data/
Cornell University - Movie-review data for use in sentiment-analysis experiments http://www.cs.cornell.edu/people/pabo/movie-review-data/

Music Recommendation:

Last.fm - Music Recommendation Data Sets http://www.dtic.upf.edu/~ocelma/MusicRecommendationDataset/index.html


## pd_boxplot.py
import pandas as pd
import numpy as np
%matplotlib inline

fig, ax = plt.subplots()
df = pd.read_csv("author_coauthor_number.csv")
df.boxplot(ax=ax)
plt.savefig("coauthor.png", dpi=400)

## bisecting.scala
/**
 * bisecting <master> <input> <nNodes> <subIterations>
 *
 * divisive hierarchical clustering using bisecting k-means
 * assumes input is a text file, each row is a data point
 * given as numbers separated by spaces
 *
 */

import org.apache.spark.SparkContext

## NAStatCounter.scala
/**
 * Created by cmy on 12/14/15.
 */
import org.apache.spark.util.StatCounter

class NAStatCounter extends Serializable{
  val stats: StatCounter = new StatCounter()
  var missing: Long = 0

  def add(x: Double): NAStatCounter = {

## 美团-天平.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                mrvege
                / 美团-天平.md
            
            
              Created
              December 14, 2015 02:06
            
              
                美团-天平
              
          
    #我们用一个等臂天平来称物体的质量,如果我们要称的物体质量范围在1到40克(整数),请问我们最少需要几块砝码可以完成这项物体质量的称量?

3
4
5
6
7

##answer:
答案是四个。

  
## ipython_pyspark
IPYTHON=ipython IPYTHON_OPTS=qtconsole ./bin/pyspark

## filterPunct.py
#!/usr/bin/env python
# encoding: utf-8
__author__ = 'dm'

punct = set(u''':!),.:;?]}¢'"、。〉》」』】〕〗〞︰︱︳﹐､﹒
﹔﹕﹖﹗﹚﹜﹞！），．：；？｜｝︴︶︸︺︼︾﹀﹂﹄﹏､～￠
々‖•·ˇˉ―--′’”([{£¥'"‵〈《「『【〔〖（［｛￡￥〝︵︷︹︻
︽︿﹁﹃﹙﹛﹝（｛“‘-—_…''')
# 对str/unicode
filterpunt = lambda s : ''.join(filter(lambda x : x not in punct , s))
	-0.017612 -14.053064 0.0
	-1.395634 -4.662541 1.0
	-0.752157 -6.53862 0.0
	-1.322371 -7.152853 0.0
	0.423363 -11.054677 0.0
	0.406704 -7.067335 1.0
	0.667394 -12.741452 0.0
	-2.46015 -6.866805 1.0
	0.569411 -9.548755 0.0
	-0.026632 -10.427743 0.0
	#!/usr/bin/env python
	# encoding: utf-8

	from numpy import *
	import matplotlib.pyplot as plt

	def logistic(wTx):
	return 1.0/(1.0 + exp(-wTx))

	def file2matrix(filename,delimiter):
	import pandas as pd
	import numpy as np
	%matplotlib inline

	fig, ax = plt.subplots()
	df = pd.read_csv("author_coauthor_number.csv")
	df.boxplot(ax=ax)
	plt.savefig("coauthor.png", dpi=400)
	/**
	* bisecting <master> <input> <nNodes> <subIterations>
	*
	* divisive hierarchical clustering using bisecting k-means
	* assumes input is a text file, each row is a data point
	* given as numbers separated by spaces
	*
	*/

	import org.apache.spark.SparkContext
	/**
	* Created by cmy on 12/14/15.
	*/
	import org.apache.spark.util.StatCounter

	class NAStatCounter extends Serializable{
	val stats: StatCounter = new StatCounter()
	var missing: Long = 0

	def add(x: Double): NAStatCounter = {
	#!/usr/bin/env python
	# encoding: utf-8
	__author__ = 'dm'

	punct = set(u''':!),.:;?]}¢'"、。〉》」』】〕〗〞︰︱︳﹐､﹒
	﹔﹕﹖﹗﹚﹜﹞！），．：；？｜｝︴︶︸︺︼︾﹀﹂﹄﹏､～￠
	々‖•·ˇˉ―--′’”([{£¥'"‵〈《「『【〔〖（［｛￡￥〝︵︷︹︻
	︽︿﹁﹃﹙﹛﹝（｛“‘-—_…''')
	# 对str/unicode
	filterpunt = lambda s : ''.join(filter(lambda x : x not in punct , s))