I'm having problems using the JSONlite package in R to collect Dota2 match data using the Steam API. I am not an experienced developer and really appreciate any help. Thanks!
I have created a script in R. When I check the API call using a web browser it correctly returns the JSON contents, but when I execute the very same API call in R (either in a for loop or as a single call) using the fromJSON() function, I get the following errors:
Error in open.connection(con, "rb") : HTTP error 503.
In addition: Warning message:
closing unused connection 3 (https://api.steampowered.com/IDOTA2Match_570/GetMatchDetails/V001/?match_id=2170111273&key=XXXXXXXXXXPLACEHOLDERXXXXXXXXXXX)
This is the R script I have created to collect multiple JSON responses using the fromJSON command and jsonlite:
# Load required libraries
library(rvest)
library(stringr)
library(magrittr)
library(plyr)
library(dplyr)
library(tidyr)
library(knitr)
library(XML)
library(data.table)
library(foreign)
library(pbapply)
library(jsonlite)
## Set base url components
base.url_0 = "https://api.steampowered.com/IDOTA2Match_570/GetMatchDetails/V001/?match_id="
base.url_0.1 = "&key="
steamAPIkey = "XXXXXXXXXXPLACEHOLDERXXXXXXXXXXX" # Steam API Key
### Create for loop where each "i" is a DOTA2 match ID
for(i in seq(1:length(targets$match_id))) {
base.url = paste0(
base.url_0,
targets$match_id[i],
base.url_0.1,
steamAPIkey)
message("Retrieving page ", targets$match_id[i])
## Get JSON response and store into data.frame
ifelse(
tmp_json <- fromJSON(
txt = base.url,flatten = T), # if the json file exists
as.data.frame(tmp_errors_1$matches) <- base.url # if the json file does not exists
) # close ifelse statement
tmp_json <- try_default(
expr =
as.data.frame(tmp_json), # convert json file into a data frame
default =
as.data.frame(tmp_errors_2$matches) <- base.url, quiet = T) # if error, add match id to a dataframe
## Rbindlist
l = list(results, tmp_json)
results <- rbindlist(l,fill = T)
## Sleep for x seconds
Sys.sleep(runif(1, 2, 3))
## End of loop
}
There are bunch of files in a directory that has json formatted entries in each line. The size of the files varies from 5k to 200MB. I have this code to go though each file, parse the data I am looking for in the json and finally form a data frame. This script is taking a very long time to finish, in fact it never finishes.
Is there any way to speed it up so that I can read the files faster?
Code:
library(jsonlite)
library(data.table)
setwd("C:/Files/")
#data <- lapply(readLines("test.txt"), fromJSON)
df<-data.frame(Timestamp=factor(),Source=factor(),Host=factor(),Status=factor())
filenames <- list.files("Json_files", pattern="*.txt", full.names=TRUE)
for(i in filenames){
print(i)
data <- lapply(readLines(i), fromJSON)
myDf <- do.call("rbind", lapply(data, function(d) {
data.frame(TimeStamp = d$payloadData$timestamp,
Source = d$payloadData$source,
Host = d$payloadData$host,
Status = d$payloadData$status)}))
df<-rbind(df,myDf)
}
This is a sample entry but there are thousands of entries like this in the file:
{"senderDateTimeStamp":"2016/04/08 10:53:18","senderHost":null,"senderAppcode":"app","senderUsecase":"appinternalstats_prod","destinationTopic":"app_appinternalstats_realtimedata_topic","correlatedRecord":false,"needCorrelationCacheCleanup":false,"needCorrelation":false,"correlationAttributes":null,"correlationRecordCount":0,"correlateTimeWindowInMills":0,"lastCorrelationRecord":false,"realtimeESStorage":true,"receiverDateTimeStamp":1460127623591,"payloadData":{"timestamp":"2016-04-08T10:53:18.169","status":"get","source":"STREAM","fund":"JVV","client":"","region":"","evetid":"","osareqid":"","basis":"","pricingdate":"","content":"","msgname":"","recipient":"","objid":"","idlreqno":"","host":"WEB01","servermember":"test"},"payloadDataText":"","key":"app:appinternalstats_prod","destinationTopicName":"app_appinternalstats_realtimedata_topic","hdfsPath":"app/appinternalstats_prod","esindex":"app","estype":"appinternalstats_prod","useCase":"appinternalstats_prod","appCode":"app"}
{"senderDateTimeStamp":"2016/04/08 10:54:18","senderHost":null,"senderAppcode":"app","senderUsecase":"appinternalstats_prod","destinationTopic":"app_appinternalstats_realtimedata_topic","correlatedRecord":false,"needCorrelationCacheCleanup":false,"needCorrelation":false,"correlationAttributes":null,"correlationRecordCount":0,"correlateTimeWindowInMills":0,"lastCorrelationRecord":false,"realtimeESStorage":true,"receiverDateTimeStamp":1460127623591,"payloadData":{"timestamp":"2016-04-08T10:53:18.169","status":"get","source":"STREAM","fund":"JVV","client":"","region":"","evetid":"","osareqid":"","basis":"","pricingdate":"","content":"","msgname":"","recipient":"","objid":"","idlreqno":"","host":"WEB02","servermember":""},"payloadDataText":"","key":"app:appinternalstats_prod","destinationTopicName":"app_appinternalstats_realtimedata_topic","hdfsPath":"app/appinternalstats_prod","esindex":"app","estype":"appinternalstats_prod","useCase":"appinternalstats_prod","appCode":"app"}
{"senderDateTimeStamp":"2016/04/08 10:55:18","senderHost":null,"senderAppcode":"app","senderUsecase":"appinternalstats_prod","destinationTopic":"app_appinternalstats_realtimedata_topic","correlatedRecord":false,"needCorrelationCacheCleanup":false,"needCorrelation":false,"correlationAttributes":null,"correlationRecordCount":0,"correlateTimeWindowInMills":0,"lastCorrelationRecord":false,"realtimeESStorage":true,"receiverDateTimeStamp":1460127623591,"payloadData":{"timestamp":"2016-04-08T10:53:18.169","status":"get","source":"STREAM","fund":"JVV","client":"","region":"","evetid":"","osareqid":"","basis":"","pricingdate":"","content":"","msgname":"","recipient":"","objid":"","idlreqno":"","host":"WEB02","servermember":""},"payloadDataText":"","key":"app:appinternalstats_prod","destinationTopicName":"app_appinternalstats_realtimedata_topic","hdfsPath":"app/appinternalstats_prod","esindex":"app","estype":"appinternalstats_prod","useCase":"appinternalstats_prod","appCode":"app"}
With your example data in "c:/tmp.txt":
> df <- jsonlite::fromJSON(paste0("[",paste0(readLines("c:/tmp.txt"),collapse=","),"]"))$payloadData[c("timestamp","source","host","status")]
> df
timestamp source host status
1 2016-04-08T10:53:18.169 STREAM WEB01 get
2 2016-04-08T10:53:18.169 STREAM WEB02 get
3 2016-04-08T10:53:18.169 STREAM WEB02 get
So to adapt your code to get a list of dataframes:
dflist <- lapply(filenames, function(i) {
jsonlite::fromJSON(
paste0("[",
paste0(readLines(i),collapse=","),
"]")
)$payloadData[c("timestamp","source","host","status")]
})
The idea is to transform your lines (from readLines) into a big json array and then create the dataframe by parsing it as json.
As lmo already showcased, using lapply on your filenmaes list procide you with a list of dataframes, if you really want only one dataframe at end you can load the data.table packages and then use rbindlist on dflist to get only one dataframe.
Or if you're short in memory this thread may help you.
One speed up is to replace your for loop with lapply Then drop the final rbind. the speed up here would be that R would not have to repeatedly copy an increasingly large file, df over your "bunch" of files. The result would be stored in a convenient list that you could either use as is or convert to a data.frame in one go:
# create processing function
getData <- function(i) {
print(i)
data <- lapply(readLines(i), fromJSON)
myDf <- do.call("rbind", lapply(data, function(d) {
data.frame(TimeStamp = d$payloadData$timestamp,
Source = d$payloadData$source,
Host = d$payloadData$host,
Status = d$payloadData$status)}))
}
# lapply over files
myDataList <- lapply(filenames, getData)
I am trying to use R's rjson library to upload a 200MB JSON file into R , but I got the Cannot fit vector over 1KB error.
Here's the code I used to load the JSON file into R:
UnpackJSON <- function(filePath)
{
con <- file(filePath, "r")
input <- readLines(con, -1L)
# jsonData <- fromJSON(paste(input, collapse=""))
jsonData <- sapply(input, fromJSON)
close(con)
df <- data.frame(jsonData)
temp <- rownames(df)
df <- as.data.frame(t(df))
colnames(df) <- temp
rownames(df) <- NULL
return(df)
}
Is there a way to optimize this code or another way to load such a large file into R? I appreciate any input.
Why would you process the JSON data line per line using sapply? Couldn't you just say fromJSON(input)? I suspect a problem could be that the garbage collector waits for the entire sapply loop to finish before deleting any copies that are made in the analysis process (see also the comments here). So when vectorization does not work (which is greatly preferred), you could try and change the sapply loop to a for loop and see if that helps.
I am trying to grab tweets using the Topsy Otter api, so I can perform some data mining on it for my dissertation.
So far, I have got:
library(RJSONIO)
library(RCurl)
tweet_data <- getURL("http://otter.topsy.com/search.json?q=PSN&mintime=1301634000&perpage=10&maxtime=1304226000&apikey=xxx")
fromJSON(tweet_data)
Which works fine. Now however, I want to return just a couple details from this file, 'content' and 'trackback_date'. I cannot seem to figure out how - I have tried cobbling a couple of examples together, but unable to extract what I want.
Here is what I've tried so far:
trackback_date <- lapply(tweet_data$result, function(x){x$trackback_date})
content <- lapply(tweet_data$result, function(x){x$content})
Any help would be greatly appreciated, thank you.
edit
I have also tried:
library("rjson")
# use rjson
tweet_data <- fromJSON(paste(readLines("http://otter.topsy.com/search.json?q=PSN&mintime=1301634000&perpage=10&maxtime=1304226000&apikey=xxx"), collapse=""))
# get a data from Topsy Otter API
# convert JSON data into R object using fromJSON()
trackback_date <- lapply(tweet_data$result, function(x){x$trackback_date})
content <- lapply(tweet_data$result, function(x){x$content})
Basic processing of Topsy Otter API response:
library(RJSONIO)
library(RCurl)
tweet_data <- getURL("http://otter.topsy.com/search.json?q=PSN&mintime=1301634000&perpage=10&maxtime=1304226000&apikey=xxx")
#
# Addition to your code
#
tweets <- fromJSON(tweet_data)$response$list
content <- sapply(tweets, function(x) x$content)
trackback_date <- sapply(tweets, function(x) x$trackback_date)
EDIT: Processing multiple pages
Function gets 100 items from specified page:
pagetweets <- function(page){
url <- paste("http://otter.topsy.com/search.json?q=PSN&mintime=1301634000&page=",page,
"&perpage=100&maxtime=1304226000&apikey=xxx",
collapse="", sep="")
tweet_data <- getURL(url)
fromJSON(tweet_data)$response$list
}
Now we can apply it to multiple pages:
tweets <- unlist(lapply(1:10, pagetweets), recursive=F)
And, voila, this code:
content <- sapply(tweets, function(x) x$content)
trackback_date <- sapply(tweets, function(x) x$trackback_date)
returns you 1000 records.
This question already has answers here:
Parse JSON with R
(6 answers)
Closed 2 years ago.
Is there a way to import data from a JSON file into R? More specifically, the file is an array of JSON objects with string fields, objects, and arrays. The RJSON Package isn't very clear on how to deal with this http://cran.r-project.org/web/packages/rjson/rjson.pdf.
First install the rjson package:
install.packages("rjson")
Then:
library("rjson")
json_file <- "http://api.worldbank.org/country?per_page=10®ion=OED&lendingtype=LNX&format=json"
json_data <- fromJSON(paste(readLines(json_file), collapse=""))
Update: since version 0.2.1
json_data <- fromJSON(file=json_file)
jsonlite will import the JSON into a data frame. It can optionally flatten nested objects. Nested arrays will be data frames.
> library(jsonlite)
> winners <- fromJSON("winners.json", flatten=TRUE)
> colnames(winners)
[1] "winner" "votes" "startPrice" "lastVote.timestamp" "lastVote.user.name" "lastVote.user.user_id"
> winners[,c("winner","startPrice","lastVote.user.name")]
winner startPrice lastVote.user.name
1 68694999 0 Lamur
> winners[,c("votes")]
[[1]]
ts user.name user.user_id
1 Thu Mar 25 03:13:01 UTC 2010 Lamur 68694999
2 Thu Mar 25 03:13:08 UTC 2010 Lamur 68694999
An alternative package is RJSONIO. To convert a nested list, lapply can help:
l <- fromJSON('[{"winner":"68694999", "votes":[
{"ts":"Thu Mar 25 03:13:01 UTC 2010", "user":{"name":"Lamur","user_id":"68694999"}},
{"ts":"Thu Mar 25 03:13:08 UTC 2010", "user":{"name":"Lamur","user_id":"68694999"}}],
"lastVote":{"timestamp":1269486788526,"user":
{"name":"Lamur","user_id":"68694999"}},"startPrice":0}]'
)
m <- lapply(
l[[1]]$votes,
function(x) c(x$user['name'], x$user['user_id'], x['ts'])
)
m <- do.call(rbind, m)
gives information on the votes in your example.
If the URL is https, like used for Amazon S3, then use getURL
json <- fromJSON(getURL('https://s3.amazonaws.com/bucket/my.json'))
First install the RJSONIO and RCurl package:
install.packages("RJSONIO")
install.packages("(RCurl")
Try below code using RJSONIO in console
library(RJSONIO)
library(RCurl)
json_file = getURL("https://raw.githubusercontent.com/isrini/SI_IS607/master/books.json")
json_file2 = RJSONIO::fromJSON(json_file)
head(json_file2)
load the packages:
library(httr)
library(jsonlite)
I have had issues converting json to dataframe/csv. For my case I did:
Token <- "245432532532"
source <- "http://......."
header_type <- "applcation/json"
full_token <- paste0("Bearer ", Token)
response <- GET(n_source, add_headers(Authorization = full_token, Accept = h_type), timeout(120), verbose())
text_json <- content(response, type = 'text', encoding = "UTF-8")
jfile <- fromJSON(text_json)
df <- as.data.frame(jfile)
then from df to csv.
In this format it should be easy to convert it to multiple .csvs if needed.
The important part is content function should have type = 'text'.
import httr package
library(httr)
Get the url
url <- "http://www.omdbapi.com/?apikey=72bc447a&t=Annie+Hall&y=&plot=short&r=json"
resp <- GET(url)
Print content of resp as text
content(resp, as = "text")
Print content of resp
content(resp)
Use content() to get the content of resp, but this time do not specify
a second argument. R figures out automatically that you're dealing
with a JSON, and converts the JSON to a named R list.