如何将python应用程序制作/转换为Rshiny应用程序?这是个脑筋急转弯!在R中找不到UI需要的更改
我是R新手,试图理解Rshiny来构建UI。我正在尝试为我的python应用程序创建一个可以转录多个wav文件的UI。下面有两个部分,第一个是我的python应用程序,第二个是我在R中的闪亮应用程序,它使用网状结构调用我的transcribe.py应用程序。但由于某种原因,我没有收到任何输出 我的Python应用程序工作得很好,不需要代码检查。但是,Rshiny应用程序没有正确执行Python应用程序以产生所需的结果。目标是让用户从UI转录文件,并决定是否要下载csv 我有一个用于转录文件的python应用程序,名为transcribe.py-如何将python应用程序制作/转换为Rshiny应用程序?这是个脑筋急转弯!在R中找不到UI需要的更改,python,r,dplyr,shiny,reticulate,Python,R,Dplyr,Shiny,Reticulate,我是R新手,试图理解Rshiny来构建UI。我正在尝试为我的python应用程序创建一个可以转录多个wav文件的UI。下面有两个部分,第一个是我的python应用程序,第二个是我在R中的闪亮应用程序,它使用网状结构调用我的transcribe.py应用程序。但由于某种原因,我没有收到任何输出 我的Python应用程序工作得很好,不需要代码检查。但是,Rshiny应用程序没有正确执行Python应用程序以产生所需的结果。目标是让用户从UI转录文件,并决定是否要下载csv 我有一个用于转录文件的py
import os
import json
import time
# import threading
from pathlib import Path
import concurrent.futures
# from os.path import join, dirname
from ibm_watson import SpeechToTextV1
from ibm_watson.websocket import RecognizeCallback, AudioSource
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
import pandas as pd
# Replace with your api key.
my_api_key = "abc123"
# You can add a directory path to Path() if you want to run
# the project from a different folder at some point.
directory = Path().absolute()
authenticator = IAMAuthenticator(my_api_key)
service = SpeechToTextV1(authenticator=authenticator)
service.set_service_url('https://api.us-east.speech-to-text.watson.cloud.ibm.com')
# I used this URL.
# service.set_service_url('https://stream.watsonplatform.net/speech-to-text/api')
models = service.list_models().get_result()
#print(json.dumps(models, indent=2))
model = service.get_model('en-US_BroadbandModel').get_result()
#print(json.dumps(model, indent=2))
# get data to a csv
########################RUN THIS PART SECOND#####################################
def process_data(json_data, output_path):
print(f"Processing: {output_path.stem}")
cols = ["transcript", "confidence"]
dfdata = [[t[cols[0]], t[cols[1]]] for r in json_data.get('results') for t in r.get("alternatives")]
df0 = pd.DataFrame(data = dfdata, columns = cols)
df1 = pd.DataFrame(json_data.get("speaker_labels")).drop(["final", "confidence"], axis=1)
# test3 = pd.concat([df0, df1], axis=1)
test3 = pd.merge(df0, df1, left_index = True, right_index = True)
# sentiment
print(f"Getting sentiment for: {output_path.stem}")
transcript = test3["transcript"]
transcript.dropna(inplace=True)
analyzer = SentimentIntensityAnalyzer()
text = transcript
scores = [analyzer.polarity_scores(txt) for txt in text]
# data = pd.DataFrame(text, columns = ["Text"])
data = transcript.to_frame(name="Text")
data2 = pd.DataFrame(scores)
# final_dataset= pd.concat([data, data2], axis=1)
final_dataset = pd.merge(data, data2, left_index = True, right_index = True)
# test4 = pd.concat([test3, final_dataset], axis=1)
test4 = pd.merge(test3, final_dataset, left_index = True, right_index = True)
test4.drop("Text", axis=1, inplace=True)
test4.rename(columns = {
"neg": "Negative",
"pos": "Positive",
"neu": "Neutral",
}, inplace=True)
# This is the name of the output csv file
test4.to_csv(output_path, index = False)
def process_audio_file(filename, output_type = "csv"):
audio_file_path = directory.joinpath(filename)
# Update output path to consider `output_type` parameter.
out_path = directory.joinpath(f"{audio_file_path.stem}.{output_type}")
print(f"Current file: '{filename}'")
with open(audio_file_path, "rb") as audio_file:
data = service.recognize(
audio = audio_file,
speaker_labels = True,
content_type = "audio/wav",
inactivity_timeout = -1,
model = "en-US_NarrowbandModel",
continuous = True,
).get_result()
print(f"Speech-to-text complete for: '{filename}'")
# Return data and output path as collection.
return [data, out_path]
def main():
print("Running main()...")
# Default num. workers == min(32, os.cpu_count() + 4)
n_workers = os.cpu_count() + 2
# Create generator for all .wav files in folder (and subfolders).
file_gen = directory.glob("**/*.wav")
with concurrent.futures.ThreadPoolExecutor(max_workers = n_workers) as executor:
futures = {executor.submit(process_audio_file, f) for f in file_gen}
for future in concurrent.futures.as_completed(futures):
pkg = future.result()
process_data(*pkg)
if __name__ == "__main__":
print(f"Program to process audio files has started.")
t_start = time.perf_counter()
main()
t_stop = time.perf_counter()
print(f"Done! Processing completed in {t_stop - t_start} seconds.")
在Rstudio,我试过-
R.UI文件
library(shiny)
library(reticulate) # for reading Python code
library(dplyr)
library(stringr)
library(formattable) # for adding color to tables
library(shinybusy) # for busy bar
library(DT) # for dataTableOutput
use_python("/usr/lib/python3")
ui <- fluidPage(
add_busy_bar(color = "#5d98ff"),
fileInput("wavFile", "SELECT .WAV FILE", accept = ".wav"),
uiOutput("downloadData"),
dataTableOutput("transcript"),
)
server <- function(input, output) {
# .WAV File Selector ------------------------------------------------------
file <- reactive({
file <- input$wavFile # Get file from user input
gsub("\\\\","/",file$datapath) # Access the file path. Convert back slashes to forward slashes.
})
# Transcribe and Clean ----------------------------------------------------
transcript <- reactive({
req(input$wavFile) # Require a file before proceeding
source_python('transcribe.py') # Load the Python function # COMMENT LINE OUT WHEN TESTING NON-TRANSCRIPTION FUNCTIONALITY
transcript <- data.frame(transcribe(file())) # Transcribe the file # COMMENT LINE OUT WHEN TESTING NON-TRANSCRIPTION FUNCTIONALITY
# load('transcript.rdata') # Loads a dummy transcript # UNCOMMENT LINE OUT WHEN TESTING NON-TRANSCRIPTION FUNCTIONALITY
transcript$transcript <- unlist(transcript$transcript) # Transcript field comes in as a list. Unlist it.
transcript <- transcript[which(!(is.na(transcript$confidence))),] # Remove empty lines
names(transcript) <- str_to_title(names(transcript)) # Capitalize column headers
transcript # Return the transcript
})
# Use a server-side download button ---------------------------------------
# ...so that the download button only appears after transcription
output$downloadData <- renderUI({
req(transcript())
downloadButton("handleDownload","Download CSV")
})
output$handleDownload <- downloadHandler(
filename = function() {
paste('Transcript ',Sys.Date(), ".csv", sep = "")
},
content = function(file) {
write.csv(transcript(), file, row.names = FALSE)
}
)
# Transcript table --------------------------------------------------------
output$transcript <- renderDataTable({
as.datatable(formattable(
transcript() %>%
select(Transcript,
Confidence,
Negative,
Positive
),
list(Confidence = color_tile('#ffffff','#a2b3c8'),
Negative = color_tile('#ffffff', '#e74446'),
Positive = color_tile('#ffffff', "#499650")
)
), rownames = FALSE, options =list(paging = FALSE)
)
})
# END ---------------------------------------------------------------------
}
库(闪亮)
库(网状)#用于阅读Python代码
图书馆(dplyr)
图书馆(stringr)
库(formattable)#用于为表格添加颜色
图书馆(shinybusy)#用于繁忙的酒吧
库(DT)#用于dataTableOutput
使用python(“/usr/lib/python3”)
ui在shiny中,您需要在python脚本中正确地传递参数。一种简单的方法是在python脚本中定义一个函数,并在脚本中调用该函数
这是您修改过的python脚本(编辑过的进程\数据函数和添加的运行\脚本函数)-
闪亮代码
在服务器文件中调用run_script函数,而不是转录。确保transcribe.py文件位于工作目录中。更正了输出$transcript中的一些输入错误
library(shiny)
library(reticulate) # for reading Python code
library(dplyr)
library(stringr)
library(formattable) # for adding color to tables
library(shinybusy) # for busy bar
library(DT) # for dataTableOutput
use_python("C:/Users/ap396/Anaconda3/python")
ui <- fluidPage(
add_busy_bar(color = "#5d98ff"),
fileInput("wavFile", "SELECT .WAV FILE", accept = ".wav",multiple = T),
uiOutput("downloadData"),
dataTableOutput("transcript")
)
server <- function(input, output) {
# .WAV File Selector ------------------------------------------------------
file <- reactive({
req(input$wavFile) # Require a file before proceeding
files <- input$wavFile # Get file from user input
file = NULL
for (i in 1:nrow(files)){
print(file)
file = c(file,gsub("\\\\","/",files$datapath[i])) # Access the file path. Convert back slashes to forward slashes.
}
return(file)
})
# Transcribe and Clean ----------------------------------------------------
source_python('transcribe.py')
transcript <- reactive({
dft= data.frame(NULL)
for(j in 1:length(file())){
t0 = Sys.time()
transcript <- run_script(file()[j]) # Transcribe the file # COMMENT LINE OUT WHEN TESTING NON-TRANSCRIPTION FUNCTIONALITY
t1 = Sys.time() - t0
transcript$File = j; transcript$Time = t1
dft = rbind(dft,transcript)
}
return(dft) # Return the transcript
})
# Use a server-side download button ---------------------------------------
# ...so that the download button only appears after transcription
output$downloadData <- renderUI({
req(transcript())
downloadButton("handleDownload","Download CSV")
})
output$handleDownload <- downloadHandler(
filename = function() {
paste('Transcript ',Sys.Date(), ".csv", sep = "")
},
content = function(file) {
write.csv(transcript(), file, row.names = FALSE)
}
)
# Transcript table --------------------------------------------------------
output$transcript <- renderDataTable({
as.datatable(formattable(
transcript() %>%
select(File,
Time,
transcript,
confidence,
Negative,
Positive
),
list(Confidence = color_tile('#ffffff','#a2b3c8'),
Negative = color_tile('#ffffff', '#e74446'),
Positive = color_tile('#ffffff', "#499650")
)
), rownames = FALSE, options =list(paging = FALSE)
)
})
# END ---------------------------------------------------------------------
}
# Return a Shiny app object
shinyApp(ui = ui, server = server)
库(闪亮)
库(网状)#用于阅读Python代码
图书馆(dplyr)
图书馆(stringr)
库(formattable)#用于为表格添加颜色
图书馆(shinybusy)#用于繁忙的酒吧
库(DT)#用于dataTableOutput
使用python(“C:/Users/ap396/Anaconda3/python”)
ui Tryreq(input$wavFile)
在文件中,如果您不需要创建Watson API密钥就可以重现问题,那么您可能会增加获得答案的机会。你能不能提供一个假的transcript()
在一些Sys.sleep(…)
之后仅仅返回预期的结果?当我在shiny中运行UI时,我在tag(“div”,list(…)中得到错误:缺少参数,没有默认值UI.R代码中有一个额外的逗号。删除这一行中的逗号,它应该可以工作dataTableOutput(“transcript”),因为某些原因,代码在我的系统中工作得很好。请参阅关于此问题的帖子-更新了ui代码您只需在代码中添加一行时间差,即可为每个文件添加时间。此外,您还可以在输入中添加多个文件。您只需在fileinput中指定multiple=T,并相应地修改服务器脚本。关于下载,您只需在Rstudio应用程序中单击“在浏览器中打开”,即可在浏览器中打开应用程序。请参阅附加的应用程序输出。您将在顶部找到“在浏览器中打开”链接。我已经更新了添加时间和多个输入的代码。您可以根据需要进行修改。在发布之前,阅读闪亮的文档或谷歌查询。干杯要上载多个文件,只需在“浏览”中选择所有文件即可。
library(shiny)
library(reticulate) # for reading Python code
library(dplyr)
library(stringr)
library(formattable) # for adding color to tables
library(shinybusy) # for busy bar
library(DT) # for dataTableOutput
use_python("C:/Users/ap396/Anaconda3/python")
ui <- fluidPage(
add_busy_bar(color = "#5d98ff"),
fileInput("wavFile", "SELECT .WAV FILE", accept = ".wav",multiple = T),
uiOutput("downloadData"),
dataTableOutput("transcript")
)
server <- function(input, output) {
# .WAV File Selector ------------------------------------------------------
file <- reactive({
req(input$wavFile) # Require a file before proceeding
files <- input$wavFile # Get file from user input
file = NULL
for (i in 1:nrow(files)){
print(file)
file = c(file,gsub("\\\\","/",files$datapath[i])) # Access the file path. Convert back slashes to forward slashes.
}
return(file)
})
# Transcribe and Clean ----------------------------------------------------
source_python('transcribe.py')
transcript <- reactive({
dft= data.frame(NULL)
for(j in 1:length(file())){
t0 = Sys.time()
transcript <- run_script(file()[j]) # Transcribe the file # COMMENT LINE OUT WHEN TESTING NON-TRANSCRIPTION FUNCTIONALITY
t1 = Sys.time() - t0
transcript$File = j; transcript$Time = t1
dft = rbind(dft,transcript)
}
return(dft) # Return the transcript
})
# Use a server-side download button ---------------------------------------
# ...so that the download button only appears after transcription
output$downloadData <- renderUI({
req(transcript())
downloadButton("handleDownload","Download CSV")
})
output$handleDownload <- downloadHandler(
filename = function() {
paste('Transcript ',Sys.Date(), ".csv", sep = "")
},
content = function(file) {
write.csv(transcript(), file, row.names = FALSE)
}
)
# Transcript table --------------------------------------------------------
output$transcript <- renderDataTable({
as.datatable(formattable(
transcript() %>%
select(File,
Time,
transcript,
confidence,
Negative,
Positive
),
list(Confidence = color_tile('#ffffff','#a2b3c8'),
Negative = color_tile('#ffffff', '#e74446'),
Positive = color_tile('#ffffff', "#499650")
)
), rownames = FALSE, options =list(paging = FALSE)
)
})
# END ---------------------------------------------------------------------
}
# Return a Shiny app object
shinyApp(ui = ui, server = server)