Linux VPS で次の R スクリプトを実行しているため、頻繁にエラーが返され、スクリプトが中断されます。エラーを回避するようにプログラムする方法がわかりません。それらにもかかわらず、スクリプトを強制的に実行し続ける方法があるかどうか疑問に思っていました。エラーは通常、「結果」テーブルの範囲外エラーとして発生します。コードを R< に直接貼り付けるとエラーが引き続き発生しますが、「結果」テーブルへの範囲外参照が発生すると、以前に設定された値 0 のままになるため、コードは意図したとおりに機能します。これを Linux コマンド ラインの例から自動的に実行する方法についてのヘルプ: (Rscript /folder/file.R) は大歓迎です。
library(RMySQL)
library(twitteR)
library(plyr)
library(stringr)
library(sentiment)
Date<-format(Sys.time(),"%Y-%m-%d %H:%M")
Time<-format(Sys.time(),"%H:%M")
tweets.con<-dbConnect(MySQL(),user="xxxxxxxxxxxx",password="xxxxxxxxxxxx",dbname="xxxxxxxxxx",host="xxxxxxxxxxxxxxxxxxxx.com")
Feel<-dbGetQuery(tweets.con,"select `tweet_text` from `tweets` where `created_at` BETWEEN timestamp(DATE_ADD(NOW(), INTERVAL 49 MINUTE)) AND timestamp(DATE_ADD(NOW(), INTERVAL 60 MINUTE))")
length(as.matrix(Feel))
n<-length(as.matrix(Feel))
Total_Count<-length(as.matrix(Feel))
results.con<-dbConnect(MySQL(),user="xxxxxxxxxxx",password="xxxxxxxxxxxxxxxxxx",dbname="xxxxxxxxxxxxxx",host="xxxxxxxxxxxxxxxxxx")
last.results.alt<-dbGetQuery(results.con,"select `Neg_Prop_Alt`,`Neu_Prop_Alt`,`Pos_Prop_Alt`,`neg5_Prop`,`neg4_Prop`,`neg3_Prop`,`neg2_Prop`,`neg1_Prop`,`zero_Prop`,`pos1_Prop`,`pos2_Prop`,`pos3_Prop`,`pos4_Prop`,`pos5_Prop` from `results_10m_alt` ORDER BY Date DESC LIMIT 1")
# function score.sentiment
score.sentiment = function(sentences, pos.words, neg.words, .progress='none')
{
# Parameters
# sentences: vector of text to score
# pos.words: vector of words of postive sentiment
# neg.words: vector of words of negative sentiment
# .progress: passed to laply() to control of progress bar
# create simple array of scores with laply
scores = laply(sentences,
function(sentence, pos.words, neg.words)
{
# remove retweet entities
sentence = gsub("(RT|via)((?:\\b\\W*@\\w+)+)", "", sentence)
# remove at people
sentence = gsub("@\\w+", "", sentence)
# remove punctuation
sentence = gsub("[[:punct:]]", "", sentence)
# remove numbers
sentence = gsub("[[:digit:]]", "", sentence)
# remove control characters
sentence = gsub("[[:cntrl:]]", "", sentence)
# remove html links
sentence = gsub("http\\w+", "", sentence)
# remove unnecessary spaces
sentence = gsub("[ \t]{2,}", "", sentence)
sentence = gsub("^\\s+|\\s+$", "", sentence)
# define error handling function when trying tolower
tryTolower = function(x)
{
# create missing value
y = NA
# tryCatch error
try_error = tryCatch(tolower(x), error=function(e) e)
# if not an error
if (!inherits(try_error, "error"))
y = tolower(x)
# result
return(y)
}
# use tryTolower with sapply
sentence = sapply(sentence, tryTolower)
# split sentence into words with str_split (stringr package)
word.list = str_split(sentence, "\\s+")
words = unlist(word.list)
# compare words to the dictionaries of positive & negative terms
pos.matches = match(words, pos.words)
neg.matches = match(words, neg.words)
# get the position of the matched term or NA
# we just want a TRUE/FALSE
pos.matches = !is.na(pos.matches)
neg.matches = !is.na(neg.matches)
# final score
score = sum(pos.matches) - sum(neg.matches)
return(score)
}, pos.words, neg.words, .progress=.progress )
# data frame with scores for each sentence
scores.df = data.frame(text=sentences, score=scores)
return(scores.df)
}
# import positive and negative words
pos = readLines("/home/jgraab/R/scripts/positive_words.txt")
neg = readLines("/home/jgraab/R/scripts/negative_words.txt")
Feel_txt = sapply(Feel, function(x) gettext(x))
scores.df = score.sentiment(Feel_txt, pos, neg, .progress='text')
results<-table(scores.df[,2])+.0001
#Set Table Defaults
Neg_Count_Alt<-0
Neg_Prop_Alt<-0
Neg_Change_Alt<-0
Neu_Count_Alt<-0
Neu_Prop_Alt<-0
Neu_Change_Alt<-0
Pos_Count_Alt<-0
Pos_Prop_Alt<-0
Pos_Change_Alt<-0
neg5_Count<-0
neg5_Prop<-0
neg5_Change<-0
neg4_Count<-0
neg4_Prop<-0
neg4_Change<-0
neg3_Count<-0
neg3_Prop<-0
neg3_Change<-0
neg2_Count<-0
neg2_Prop<-0
neg2_Change<-0
neg1_Count<-0
neg1_Prop<-0
neg1_Change<-0
zero_Count<-0
zero_Prop<-0
zero_Change<-0
pos1_Count<-0
pos1_Prop<-0
pos1_Change<-0
pos2_Count<-0
pos2_Prop<-0
pos2_Change<-0
pos3_Count<-0
pos3_Prop<-0
pos3_Change<-0
pos4_Count<-0
pos4_Prop<-0
pos4_Change<-0
pos5_Count<-0
pos5_Prop<-0
pos5_Change<-0
#Get Table Results
neg5_Count<-results[["-5"]]
neg5_Prop<-neg5_Count/Total_Count
neg5_Change<-(neg5_Prop-as.numeric(last.results.alt[[4]]))/as.numeric(last.results.alt[[4]])*100
neg4_Count<-results[["-4"]]
neg4_Prop<-neg4_Count/Total_Count
neg4_Change<-(neg4_Prop-as.numeric(last.results.alt[[5]]))/as.numeric(last.results.alt[[5]])*100
neg3_Count<-results[["-3"]]
neg3_Prop<-neg3_Count/Total_Count
neg3_Change<-(neg3_Prop-as.numeric(last.results.alt[[6]]))/as.numeric(last.results.alt[[6]])*100
neg2_Count<-results[["-2"]]
neg2_Prop<-neg2_Count/Total_Count
neg2_Change<-(neg2_Prop-as.numeric(last.results.alt[[7]]))/as.numeric(last.results.alt[[7]])*100
neg1_Count<-results[["-1"]]
neg1_Prop<-neg1_Count/Total_Count
neg1_Change<-(neg1_Prop-as.numeric(last.results.alt[[8]]))/as.numeric(last.results.alt[[8]])*100
zero_Count<-results[["0"]]
zero_Prop<-zero_Count/Total_Count
zero_Change<-(zero_Prop-as.numeric(last.results.alt[[9]]))/as.numeric(last.results.alt[[9]])*100
pos1_Count<-results[["1"]]
pos1_Prop<-pos1_Count/Total_Count
pos1_Change<-(pos1_Prop-as.numeric(last.results.alt[[10]]))/as.numeric(last.results.alt[[10]])*100
pos2_Count<-results[["2"]]
pos2_Prop<-pos2_Count/Total_Count
pos2_Change<-(pos2_Prop-as.numeric(last.results.alt[[11]]))/as.numeric(last.results.alt[[11]])*100
pos3_Count<-results[["3"]]
pos3_Prop<-pos3_Count/Total_Count
pos3_Change<-(pos3_Prop-as.numeric(last.results.alt[[12]]))/as.numeric(last.results.alt[[12]])*100
pos4_Count<-results[["4"]]
pos4_Prop<-pos4_Count/Total_Count
pos4_Change<-(pos4_Prop-as.numeric(last.results.alt[[13]]))/as.numeric(last.results.alt[[13]])*100
pos5_Count<-results[["5"]]
Pos5_Prop<-pos5_Count/Total_Count
Pos5_Change<-(pos5_Prop-as.numeric(last.results.alt[[14]]))/as.numeric(last.results.alt[[14]])*100
#Get Negative, Neutral, and Positive Totals
Neg_Count_Alt<-neg5_Count+neg4_Count+neg3_Count+neg2_Count+neg1_Count
Neg_Prop_Alt<-Neg_Count_Alt/Total_Count
Neg_Change_Alt<-(Neg_Prop_Alt-as.numeric(last.results.alt[[1]]))/as.numeric(last.results.alt[[1]])*100
Neu_Count_Alt<-zero_Count
Neu_Prop_Alt<-Neu_Count_Alt/Total_Count
Neu_Change_Alt<-(Neu_Prop_Alt-as.numeric(last.results.alt[[2]]))/as.numeric(last.results.alt[[2]])*100
Pos_Count_Alt<-pos1_Count+pos2_Count+pos3_Count+pos4_Count+pos5_Count
Pos_Prop_Alt<-Pos_Count_Alt/Total_Count
Pos_Change_Alt<-(Pos_Prop_Alt-as.numeric(last.results.alt[[3]]))/as.numeric(last.results.alt[[3]])*100
Mean<-(-5*neg5_Count-4*neg4_Count-3*neg3_Count-2*neg2_Count-neg1_Count+pos1_Count+2*pos2_Count+3*pos3_Count+4*pos4_Count+5*pos5_Count)/Total_Count
Feel_alt.df<-data.frame(Date,Time,Total_Count,Mean,Neg_Count_Alt,Neg_Prop_Alt,Neg_Change_Alt,Neu_Count_Alt,Neu_Prop_Alt,Neu_Change_Alt,Pos_Count_Alt,Pos_Prop_Alt,Pos_Change_Alt,
neg5_Count,neg5_Prop,neg5_Change,neg4_Count,neg4_Prop,neg4_Change,neg3_Count,neg3_Prop,neg3_Change,neg2_Count,neg2_Prop,neg2_Change,neg1_Count,neg1_Prop,neg1_Change,
zero_Count,zero_Prop,zero_Change,pos1_Count,pos1_Prop,pos1_Change,pos2_Count,pos2_Prop,pos2_Change,pos3_Count,pos3_Prop,pos3_Change,pos4_Count,pos4_Prop,pos4_Change,pos5_Count,pos5_Prop,pos5_Change)
dbWriteTable(results.con,name="results_10m_alt",Feel_alt.df,append=T,overwrite=F,row.names=F)