Turning my MongoDB queries into R data.frame type. This code example is written for my blog post: Building up an easy data analysis platform with RStudio server on top of your MongoDB: http://winston.attlin.com/2014/01/building-up-easy-data-analysis-platform.html

rmongo_queries.r

## The collection structure looks like this:
##{
##    "col1": "some value 1",
##    "col2": 1234,
##    "col3": "somevalue 3",
##    "col4": "some value 4",
##    "col5": "some value 5",
##    "col6": [
##        {
##            "some": 1,
##            "other": "other value 1"
##        },
##        {
##            "some": 0,
##            "other": "other value "
##        }
##    ],
##    "col6_1": 456,
##    "col6_2": 6789,
##    "col7": "some value 7"
##}

## Here comes the way to conduct your query:
##
## my_data_frame <- queryIntoDataFrame('col2', 1234)

library(rmongodb)
getCountsByMatch <- function(column_name, column_value){
  mongo <- mongo.create(host='localhost:27018' , db='my_mongodb')
  buf <- mongo.bson.buffer.create()
  mongo.bson.buffer.append(buf, column_name, column_value)
  query <- mongo.bson.from.buffer(buf)
  count <- mongo.count(mongo, "my_mongodb.my_mongodb_collection", query)
  mongo.disconnect(mongo)
  mongo.destroy(mongo)
  if (count < 0) {
    print(paste('mongo.get.err code: ', mongo.get.err(mongo)))
    return (0)
  } else return(count)
}

queryIntoDataFrame <- function(column_name, column_value){
  total_count <- getCountsByMatch(column_name, column_value)
  
  # setup some vectors to hold our results 
  col1 <- vector("character",total_count)
  col2 <- vector("numeric",total_count)
  col3 <- vector("character",total_count)
  col4 <- vector("character",total_count)
  col5 <- vector("character",total_count)
  col6_1 <- vector("numeric",total_count)
  col6_2 <- vector("numeric",total_count)
  col7 <- vector("character",total_count)

  mongo <- mongo.create(host='localhost:27018' , db='my_mongodb')
  buf <- mongo.bson.buffer.create()
  mongo.bson.buffer.append(buf, column_name, column_value)
  query <- mongo.bson.from.buffer(buf)  
  cursor = mongo.find(mongo,"my_mongodb.my_mongodb_collection",query,options=mongo.find.exhaust)
  # queries are faster with mongo.find.exhaust in the options
  
  i <- 1
  while (mongo.cursor.next(cursor)) {
    cval <- mongo.cursor.value(cursor) 
    
    if (is.null(mongo.bson.value(cval,"col1"))) col1[i] <- ''  
    else col1[i] <- mongo.bson.value(cval,"col1")
    
    if (is.null(mongo.bson.value(cval,"col2"))) col2[i] <- ''
    else col2[i] <- mongo.bson.value(cval,"col2")
    
    if (is.null(mongo.bson.value(cval,"col3"))) col3[i] <- ''
    else col3[i] <- mongo.bson.value(cval,"col3")
    
    if (is.null(mongo.bson.value(cval,"col4"))) col4[i] <- ''
    else col4[i] <- mongo.bson.value(cval,"col4")
    
    if (is.null(mongo.bson.value(cval,"col5"))) col5[i] <- ''  
    else col5[i] <- mongo.bson.value(cval,"col5")
    
    # below is an example of extracting data from a bson list, based on the value stored in the list.
    if (is.null(mongo.bson.value(cval,"col6"))) {
      # pick a default -1
      col6_1[i] <- -1
      col6_2[i] <- -1  
    } else {
      for (item in mongo.bson.value(cval,"col6")) {
        # populate col6_1 and col6_2 based on item$some's value
        if (item$some == 0){
          col6_1[i] <- item$other
        } else if (item$some == 1) {
          col6_2[i] <- item$other
        }
      }
      # pick a default -2, just tot show the difference
      if (is.null(col6_1[i])) col6_1[i] <- -2
      if (is.null(col6_2[i])) col6_2[i] <- -2
    }
    
    if (is.null(mongo.bson.value(cval,"col7"))) col7[i] <- ''
    else col7[i] <- mongo.bson.value(cval,"col7")
    
    i <- i + 1
  }
  df <- as.data.frame(list(col1=col1,col2=col2,col3=col3,col4=col4,col5=col5,col6_1=col6_1,col6_2=col6_2,col7=col7))
  mongo.disconnect(mongo)
  mongo.destroy(mongo)
  # return the data frame
  return(df)
}