Salinger

## mecab_test.py
#!/usr/bin/env python
#-*- coding:utf-8 -*-
import MeCab

m = MeCab.Tagger("-Ochasen")
string = u"それサバンナでも同じ事言えんの？"

# MeCabでUnicode文字列を扱う場合は、一度エンコードする必要がある。
# この際、
# node = tagger.parseToNode(string.encode("utf-8"))

## libsvm_test.py
#!/usr/bin/env python
#-*- coding:utf-8 -*-

from svm import *
from svmutil import *

# For learning
t_label = [1,-1,1,-1]
t_data = [
    [1.0, 2.0, 3.0],

## gold_coin.R
library(ggplot2) # For Plot
library(kernlab) # For SVM

auth = read.table("./CodeIQ_auth.txt",header=F,sep=" ")
names(auth) <- c("volume","weight","truth") # 0 is Fake

my_coins = read.table("./CodeIQ_mycoins.txt",header=F,sep=" ")
names(my_coins) <- c("volume","weight")

g = ggplot(auth,aes(x=volume,y=weight)) + geom_point(aes(color=truth))

## mecab_cabocha.rb
m = MeCab::Tagger.new "-Ochasen -u lib/wikipedia_user.dic"
mecab_str = m.parse(string)

c = CaboCha::Parser.new "-f4 -I1"
lines = c.parseToString(mecab_str).force_encoding("UTF-8")

## bq_tweet.json
[
  {
    "name": "log_time",
    "type": "INTEGER"
    },
  {
    "name": "created_at",
    "type": "STRING"
    },
  {

## bq_tweet.json
[
  {
    "name": "log_time",
    "type": "INTEGER"
    },
  {
    "name": "created_at",
    "type": "STRING"
    },
  {

## svm_sample_code.py
#!/usr/bin/env python
#-*- coding:utf-8 -*-

### Library
import MySQLdb
import pandas.io.sql as psql
import pandas as pd
import numpy as np
import MeCab
from gensim import corpora

## member_count.csv

          
            time
            count

            
              0
              42

            
              4
              42

            
              8
              42

            
              12
              42

            
              16
              41

            
              20
              41

            
              24
              41

            
              28
              41

            
              32
              41

## 01_100values.csv
64
90
145
152
214
93
98
66
116
129

## 02_smoke.csv

          
            member
            is_smoking

            
              A
              1

            
              B
              0

            
              C
              0

            
              D
              1

            
              E
              0

            
              F
              0

            
              G
              0

            
              H
              0

            
              I
              0
	#!/usr/bin/env python
	#-- coding:utf-8 --
	import MeCab

	m = MeCab.Tagger("-Ochasen")
	string = u"それサバンナでも同じ事言えんの？"

	# MeCabでUnicode文字列を扱う場合は、一度エンコードする必要がある。
	# この際、
	# node = tagger.parseToNode(string.encode("utf-8"))
	#!/usr/bin/env python
	#-- coding:utf-8 --

	from svm import *
	from svmutil import *

	# For learning
	t_label = [1,-1,1,-1]
	t_data = [
	[1.0, 2.0, 3.0],
	library(ggplot2) # For Plot
	library(kernlab) # For SVM

	auth = read.table("./CodeIQ_auth.txt",header=F,sep=" ")
	names(auth) <- c("volume","weight","truth") # 0 is Fake

	my_coins = read.table("./CodeIQ_mycoins.txt",header=F,sep=" ")
	names(my_coins) <- c("volume","weight")

	g = ggplot(auth,aes(x=volume,y=weight)) + geom_point(aes(color=truth))
	m = MeCab::Tagger.new "-Ochasen -u lib/wikipedia_user.dic"
	mecab_str = m.parse(string)

	c = CaboCha::Parser.new "-f4 -I1"
	lines = c.parseToString(mecab_str).force_encoding("UTF-8")
	[
	{
	"name": "log_time",
	"type": "INTEGER"
	},
	{
	"name": "created_at",
	"type": "STRING"
	},
	{
	#!/usr/bin/env python
	#-- coding:utf-8 --

	### Library
	import MySQLdb
	import pandas.io.sql as psql
	import pandas as pd
	import numpy as np
	import MeCab
	from gensim import corpora