This vignettes shows the functions and examples of the TextForecast package. The package functions are based on the Lima, Godeiro, and Mohsin (2018) paper and Godeiro (2018) Ph.D. thesis.
You can install the released version of TextForecast from github with:
install.packages("devtools")
library(devtools)
::install_github("lucasgodeiro/TextForecast")
devtoolsinstall.packages("TextForecast")
This function counts the words of the texts in the PDF format.
corpus_dates: A vector of characters indicating the subfolders where are located the texts.
ntrms: maximum numbers of words that will be filtered by tf-idf. We rank the word by tf-idf in a decreasing order. Then, we select the words with the ntrms highest tf-idf.
st: set 0 to stem the words and 1 otherwise.
path_name: the folders path where the subfolders with the dates are located.
language the texts language. Default is english.
a list containing a matrix with the all words counting and another with a td-idf filtered words couting according to the ntrms.
This is a basic example which shows you how todo a word counting from PDF files. The PDF files contains monthly financial News from The Wall Street Journal and The New York Times between 2017 and 2018.
## Example from function get_words.
library(TextForecast)
=2017
st_year=2018
end_year=system.file("news",package="TextForecast")
path_name=paste0(sort(rep(seq(from=st_year,to=end_year,by=1),12)),
qtc("m1","m2","m3","m4","m5","m6","m7","m8","m9","m10","m11","m12"))
=get_words(corpus_dates=qt[1:6],path_name=path_name,ntrms=10,st=0)
z_wrd=z_wrd[[2]]
zzhead(zz)
This function counts the collocations of the texts in the PDF format. The PDF files contains monthly financial News from The Wall Street Journal and The New York Times between 2017 and 2018.
corpus_dates: a character vector indicating the subfolders where are located the texts.
path_name: the folders path where the subfolders with the dates are located.
ntrms: maximum numbers of collocations that will be filtered by tf-idf. We rank the collocations by tf-idf in a decreasing order. Then, after we select the words with the ntrms highest tf-idf.
ngrams_number: integer indicating the size of the collocations. Defaults to 2, indicating to compute bigrams. If set to 3, will find collocations of bigrams and trigrams.
min_freq: integer indicating the frequency of how many times a collocation should at least occur in the data in order to be returned.
language the texts language. Default is english.
a list containing a matrix with the all collocations counting and another with a td-idf filtered collocations couting according to the ntrms.
library(TextForecast)
=2017
st_year=2018
end_year=system.file("news",package="TextForecast")
path_name=paste0(sort(rep(seq(from=st_year,to=end_year,by=1),12)),
qtc("m1","m2","m3","m4","m5","m6","m7","m8","m9","m10","m11","m12"))
=get_collocations(corpus_dates=qt[1:23],path_name=path_name,
z_collntrms=20,ngrams_number=3,min_freq=10)
=z_coll[[2]]
zz#head(zz)
::kable(head(zz, 23)) knitr
This function counts the terms of the texts in the PDF format.
corpus_dates: a character vector indicating the subfolders where are located the texts.
ntrms_words: maximum numbers of words that will be filtered by tf-idf. We rank the word by tf-idf in a decreasing order. Then, we select the words with the ntrms highest tf-idf.
st: set 0 to stem the words and 1 otherwise.
path.name: the folders path where the subfolders with the dates are located.
ntrms_collocation: maximum numbers of collocations that will be filtered by tf-idf. We rank the collocations by tf-idf in a decreasing order. Then, after we select the words with the ntrms highest tf-idf.
ngrams_number: integer indicating the size of the collocations. Defaults to 2, indicating to compute bigrams. If set to 3, will find collocations of bigrams and trigrams.
min_freq: integer indicating the frequency of how many times a collocation should at least occur in the data in order to be returned.
language the texts language. Default is english.
##Value a list containing a matrix with the all collocations and words couting and another with a td-idf filtered collocations and words counting according to the ntrms.
##Example
This function counts the words and collocations of the texts in the PDF format. The PDF files contains monthly financial News from The Wall Street Journal and The New York Times between 2017 and 2018.
library(TextForecast)
=2017
st_year=2018
end_year=system.file("news",package="TextForecast")
path_name=paste0(sort(rep(seq(from=st_year,to=end_year,by=1),12)),
qtc("m1","m2","m3","m4","m5","m6","m7","m8","m9","m10","m11","m12"))
=get_terms(corpus_dates=qt[1:23],path.name=path_name,ntrms_words=10,
z_termsngrams_number=3,st=0,ntrms_collocation=10,min_freq=10)
=z_terms[[2]]
zz#head(zz,23)
::kable(head(zz, 23)) knitr
This function computes the terms tf-idf.
x: a input matrix x of terms counting.
a list with the terms tf-idf and the terms tf-idf in descending order.
library(TextForecast)
data("news_data")
=as.matrix(news_data[,2:ncol(news_data)])
X=tf_idf(X)
tf_idfhead(tf_idf[[1]])
This functions computes the optimal alphas.
x: A matrix of variables to be selected by shrinkrage methods.
w: Optional Argument. A matrix or vector of variables that cannot be selected(no shrinkrage).
y: response variable.
grid_alphas: a grid of alphas between 0 and 1.
cont_folds: Set TRUE for contiguous folds used in time depedent data.
family The glmnet family.
lambdas_opt: a vector with the optimal alpha and lambda.
library(TextForecast)
set.seed(1)
data("stock_data")
data("news_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("news_data")
=news_data[,2:ncol(news_data)]
X=as.matrix(X)
x=seq(by=0.05,to=0.95,from=0.05)
grid_alphas=TRUE
cont_folds=length(y)
t=optimal_alphas(x[1:(t-1),],w[1:(t-1),],y[2:t],grid_alphas,TRUE,"gaussian")
optimal_alphasprint(optimal_alphas)
This functions selects from $X $ the most predictive terms $X^{} $ using supervised machine learning techniques(Elastic Net).
x: A matrix of variables to be selected by shrinkrage methods.
w: Optional Argument. A matrix or vector of variables that cannot be selected(no shrinkrage).
y: response variable.
alpha: the alpha required in glmnet.
lambda: the lambda required in glmnet.
newx: Matrix that selection will applied. Useful for time series, when we need the observation at time t.
family: the glmnet family.
$ X_{t}^{}$: a list with the coefficients and a matrix with the most predictive terms.
This example select the most predictive words from the news database. The news database contains the terms counting of the Wall street journal and the New York Times financial news.
library(TextForecast)
set.seed(1)
data("stock_data")
data("news_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("news_data")
=news_data[,2:ncol(news_data)]
X=as.matrix(X)
x=seq(by=0.05,to=0.95,from=0.05)
grid_alphas=TRUE
cont_folds=length(y)
t=optimal_alphas(x=x[1:(t-1),],w=w[1:(t-1),],y=y[2:t],grid_alphas=grid_alphas,cont_folds=TRUE,family="gaussian")
optimal_alphas=tv_dictionary(x=x[1:(t-1),],w=w[1:(t-1),],y=y[2:t],alpha=optimal_alphas[1],lambda=optimal_alphas[2],newx=x,family="gaussian")
x_star=optimal_alphas(x=x[1:(t-1),],y=y[2:t],grid_alphas=grid_alphas,cont_folds=TRUE,family="gaussian")
optimal_alphas1=tv_dictionary(x=x[1:(t-1),],y=y[2:t],alpha=optimal_alphas1[1],lambda=optimal_alphas1[2],newx=x,family="gaussian") x_star1
This function computes the optimal number of factors according to Ahn and Horenstein (2013).
X: a input matrix X.
kmax: the maximum number of factors.
a list with the optimal factors.
library(TextForecast)
data("optimal_x")
<- TextForecast::optimal_factors(optimal_x,8)
optimal_factor head(optimal_factor[[1]])
#Hard thresholding function
This function carries out the hard thresholding according to Bai and Ng (2008)
x: the input matrix x.
w: Optional Argument. The optional input matrix w, that cannot be selected.
y: the response variable.
p_value: the threshold p-value.
newx: matrix that selection will applied. Useful for time series, when we need the observation at time t.
the variables less than p-value.
library(TextForecast)
data("stock_data")
data("optimal_factors")
=as.matrix(stock_data[,2])
y=as.vector(y)
y=as.matrix(stock_data[,3])
w=as.matrix(optimal_factors)
pc=length(y)
t<- hard_thresholding(w=w[1:(t-1),],
news_factor x=pc[1:(t-1),],y=y[2:t],p_value = 0.01,newx = pc)
This functions computes the \(h\) step ahead forecast based on textual and/or economic data.
x: the input matrix x.
y: the response variable
h: the forecast horizon
intercept: TRUE for include intercept in the forecast equation.
The h step ahead forecast
library(TextForecast)
set.seed(1)
data("stock_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("optimal_factors_data")
=as.matrix(optimal_factors)
pc=cbind(w,pc)
z=text_forecast(z,y,1,TRUE)
fcstsprint(fcsts)
This function computes the nowcast h=0.
x: the input matrix x.
y: the response variable
intercept: TRUE for include intercept in the forecast equation.
the nowcast h=0 for the variable y.
library(TextForecast)
set.seed(1)
data("stock_data")
data("news_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("news_data")
data("optimal_factors_data")
=as.matrix(optimal_factors)
pc=cbind(w,pc)
z=length(y)
t=text_nowcast(z,y[1:(t-1)],TRUE)
ncstsprint(ncsts)
This function computes the highest k predictive words by using the highest absolute coefficient value.
x: the input matrix of terms to be selected.
w: optional argument. the input matrix of structured data to not be selected.
y: the response variable
alpha: the glmnet alpha
lambda: the glmnet lambda
k: the k top terms
wordcloud: set TRUE to plot the wordcloud
max.words: the maximum number of words in the wordcloud
scale: the wordcloud size.
rot.per: wordcloud proportion 90 degree terms
family: glmnet family
the top k terms and the corresponding wordcloud.
library(TextForecast)
set.seed(1)
data("stock_data")
data("news_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("news_data")
=news_data[,2:ncol(news_data)]
X=as.matrix(X)
x=seq(by=0.05,to=0.95,from=0.05)
grid_alphas=TRUE
cont_folds=length(y)
t=optimal_alphas(x[1:(t-1),],w[1:(t-1),],
optimal_alphas2:t],grid_alphas,TRUE,"gaussian")
y[<- top_terms(x[1:(t-1),],w[1:(t-1),],y[2:t],optimal_alphas[[1]],
top_trms2]],10,TRUE,10,c(2,0.3),.15,"gaussian") optimal_alphas[[
x: A matrix of variables to be selected by shrinkrage methods.
w: Optional Argument. A matrix of variables to be selected by shrinkrage methods.
y: the response variable.
alpha: the alpha required in glmnet.
lambda: the lambda required in glmnet.
newx: Matrix that selection will applied. Useful for time series, when we need the observation at time t.
family: the glmnet family.
k: the highest positive and negative coefficients to be used.
The time-varying sentiment index. The index is based on the k word/term counting and is computed using: tv_index=(pos-neg)/(pos+neg).
library(TextForecast)
set.seed(1)
data("stock_data")
data("news_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("news_data")
=news_data[,2:ncol(news_data)]
X=as.matrix(X)
x=seq(by=0.05,to=0.95,from=0.05)
grid_alphas=TRUE
cont_folds=length(y)
t=optimal_alphas(x[1:(t-1),],w[1:(t-1),],
optimal_alphas2:t],grid_alphas,TRUE,"gaussian")
y[<- tv_sentiment_index(x[1:(t-1),],w[1:(t-1),],
tv_index 2:t],optimal_alphas[[1]],optimal_alphas[[2]],x,"gaussian",2)
y[head(tv_index)
Unlike the TV sentiment index functions, this function uses all positive and negative coefficiens to compute the index.
x: A matrix of variables to be selected by shrinkrage methods.
w: Optional Argument. A matrix of variables to be selected by shrinkrage methods.
y: the response variable.
alpha: the alpha required in glmnet.
lambda: the lambda required in glmnet.
newx: Matrix that selection will applied. Useful for time series, when we need the observation at time t.
family: the glmnet family.
k_mov_avg: The moving average order.
type_mov_avg: The type of moving average. See .
A list with the net, postive and negative sentiment index. The net time-varying sentiment index. The index is based on the word/term counting and is computed using: tv_index=(pos-neg)/(pos+neg). The postive sentiment index is computed using: tv_index_pos=pos/(pos+neg) and the negative tv_index_neg=neg/(pos+neg).
set.seed(1)
data("stock_data")
data("news_data")
=as.matrix(stock_data[,2])
y=as.matrix(stock_data[,3])
wdata("news_data")
=news_data[,2:ncol(news_data)]
X=as.matrix(X)
x=0.15
grid_alphas=TRUE
cont_folds=length(y)
t=optimal_alphas(x=x[1:(t-1),],
optimal_alphasy=y[2:t],grid_alphas=grid_alphas,cont_folds=TRUE,family="gaussian")
=tv_sentiment_index_all_coefs(x=x[1:(t-1),],y=y[2:t],alpha = optimal_alphas[1],lambda = optimal_alphas[2],newx=x,
tv_idxscaled = TRUE,k_mov_avg = 4,type_mov_avg = "s")