-
-
Save mcku/b7f96047c28228055136 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| term<-c("egypt","jordan","israel","saudi") | |
| term_vec<-foreach(i=1:length(all_score_frames),.combine=rbind) %do% | |
| { | |
| score_row<-rep(0,length(term)) | |
| for(z in 1:length(score_row)) | |
| { | |
| sel_score<-all_score_frames[[i]][all_score_frames[[i]]$term==term[z],"score"] | |
| sel_score[is.na(sel_score)]<-0 | |
| if(length(sel_score)==0) | |
| sel_score<-0 | |
| score_row[z]<-round(sel_score,5) | |
| } | |
| as.numeric(c(date_max_list[i],score_row)) | |
| } | |
| term_vec<-as.data.frame(term_vec) | |
| names(term_vec)<-c("year",term) | |
| term_df <- melt(term_vec, id.vars="year") | |
| term_means<-sapply(all_score_frames,function(x) mean(x$score)) | |
| text_size<-40 | |
| ggplot(data=term_df,aes(x=year, y=value, colour=variable))+geom_line(size=1) + geom_line(aes(x = as.numeric(date_max_list), y = term_means), colour = "black",size=1.5) + ylab("sentiment") + opts(title = expression("US Sentiment (+/-) Over Time"),legend.text=theme_text(size=text_size),legend.title=theme_text(size=0),plot.title=theme_text(size=text_size),axis.text.y=theme_text(size=text_size),axis.text.x=theme_text(size=text_size),axis.title.y=theme_text(size=text_size,angle=90),axis.title.x=theme_text(size=text_size),legend.key.size=unit(2,"cm")) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| load_or_install(c("RODBC","corpora","ggplot2","tm","foreach","RColorBrewer","wordcloud","lsa","MASS","openNLP")) | |
| channel <- odbcConnect(db_name, uid = "", pwd = "") | |
| all_score_frames<-list() | |
| ri_cols<-30000 | |
| max_cables_to_sample<-15000 | |
| for(z in 1:length(date_min_list)) | |
| { | |
| date_min<-paste(date_min_list[z],"-01-01",sep="") | |
| date_max<-paste(date_max_list[z],"-01-01",sep="") | |
| print(date_min) | |
| cable_frame<-sqlQuery(channel, paste("SELECT * from cable WHERE date > '",date_min,"' AND date <'",date_max,"'",sep=""),stringsAsFactors=FALSE,errors=TRUE) | |
| ppatterns<-c("\\n","\\r") | |
| sampled_indices<-sample(1:nrow(cable_frame),min(max_cables_to_sample,nrow(cable_frame))) | |
| combined<-tolower(gsub(paste("(",paste(ppatterns,collapse="|"),")",sep=""),"",cable_frame$content[sampled_indices])) | |
| combined<-sentDetect(combined) | |
| combined<-combined[!is.na(combined)] | |
| combined<-combined[nchar(combined)>5] | |
| tokenized_combined<-lapply(combined,scan_tokenizer) | |
| ri_mat<-matrix(0,length(full_term_list),ri_cols) | |
| rownames(ri_mat)<-full_term_list | |
| gc() | |
| for(i in 1:length(combined)) | |
| { | |
| if(i%%10000==0) | |
| print(i) | |
| tokens<-tokenized_combined[[i]] | |
| tokens<-tokens[nchar(tokens)>4 & nchar(tokens)<20] | |
| tokens<-tokens[tokens %in% full_term_list] | |
| set.seed(i) | |
| sample_vec<-rep(0,ri_cols) | |
| s_inds<-sample(1:length(sample_vec),5) | |
| sample_vec[s_inds]<-1 | |
| ri_mat[tokens,]<-ri_mat[tokens,]+sample_vec | |
| } | |
| gc() | |
| ri_mat<-ri_mat[rowSums(ri_mat)>0,] | |
| gc() | |
| neg_vec<-colSums(ri_mat[rownames(ri_mat) %in% afinn_list$word[afinn_list$score< -2],]) | |
| pos_vec<-colSums(ri_mat[rownames(ri_mat) %in% afinn_list$word[afinn_list$score> 2],]) | |
| ri_mat<-ri_mat[!rownames(ri_mat) %in% afinn_list$word,] | |
| neg_scores<-apply(ri_mat,1,function(x)cosine(x,neg_vec)) | |
| pos_scores<-apply(ri_mat,1,function(x)cosine(x,pos_vec)) | |
| score_frame<-data.frame(term=rownames(ri_mat),pos_scores,neg_scores,score=pos_scores-neg_scores) | |
| sorted_score_frame<-score_frame[order(score_frame$score),] | |
| all_score_frames[[z]]<-sorted_score_frame | |
| rm(ri_mat) | |
| gc() | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment