Implement Head and Tail methods

NAMESPACE

@@ -325,6 +325,7 @@ exportMethods(filters)
 exportMethods(func)
 exportMethods(funcs)
 exportMethods(geo)
+exportMethods(head)
 exportMethods(hide)
 exportMethods(id)
 exportMethods(ids)
@@ -370,6 +371,7 @@ exportMethods(subset)
 exportMethods(subtotalArray)
 exportMethods(subtotals)
 exportMethods(subvariables)
+exportMethods(tail)
 exportMethods(timestamps)
 exportMethods(toVariable)
 exportMethods(transforms)

R/AllGenerics.R

@@ -143,6 +143,8 @@ setGeneric("is.weight<-", function (x, value) standardGeneric("is.weight<-"))
 setGeneric("owner", function (x) standardGeneric("owner"))
 setGeneric("owner<-", function (x, value) standardGeneric("owner<-"))
 
+setGeneric("head", function(x, n=6L, ...) utils::head(x, n, ...))
+setGeneric("tail", function(x, n=6L, ...) utils::tail(x, n, ...))
 setGeneric("dim")
 setGeneric("ncol")
 setGeneric("mean")

R/as-data-frame.R

@@ -83,7 +83,7 @@ as.data.frame.CrunchDataFrame <- function (x,
     ds <- attr(x, "crunchDataset")
     tmp <- tempfile()
     on.exit(unlink(tmp))
-    write.csv(ds, tmp, categorical = "id")
+    tmp <- write.csv(ds, tmp, categorical = "id")
     # TODO: use variableMetadata to provide all `colClasses`?
     # meta <- variableMetadata(ds)
     ds_out <- read.csv(tmp, stringsAsFactors = FALSE)
@@ -192,3 +192,48 @@ as.data.frame.FilterCatalog <- function (x,
                                          ...) {
     catalogToDataFrame(x, keys = keys, row.names = row.names, ...)
 }
+
+#' Head and tail methods for Crunch objects. See [utils::head()] for more details.
+#'
+#' @param x a CrunchDataset, CrunchDataFrame, or CrunchVariable
+#' @param n a single integer representing the length of the returning object.
+#' @param ... ignored
+#' @name head-tail
+#' @aliases head tail
+NULL
+
+#' @rdname head-tail
+#' @export
+setMethod("head", "CrunchDataset", function (x, n=6L, ...) {
+    as.data.frame(x[head(seq_len(nrow(x)), n),], force=TRUE)
+})
+
+#' @rdname head-tail
+#' @export
+setMethod("head", "CrunchDataFrame", function (x, n=6L, ...) {
+    return(head(attr(x, "crunchDataset")))
+})
+
+#' @rdname head-tail
+#' @export
+setMethod("head", "CrunchVariable", function (x, n=6L, ...) {
+    as.vector(x[head(seq_len(length(x)), n)], ...)
+})
+
+#' @rdname head-tail
+#' @export
+setMethod("tail", "CrunchDataset", function (x, n=6L, ...) {
+    as.data.frame(x[tail(seq_len(nrow(x)), n),], force=TRUE)
+})
+
+#' @rdname head-tail
+#' @export
+setMethod("tail", "CrunchDataFrame", function (x, n=6L, ...) {
+    return(tail(attr(x, "crunchDataset")))
+})
+
+#' @rdname head-tail
+#' @export
+setMethod("tail", "CrunchVariable", function (x, n=6L, ...) {
+    as.vector(x[tail(seq_len(length(x)), n)])
+})

R/dataset-extract.R

@@ -54,6 +54,7 @@ setMethod("[", c("CrunchDataset", "logical", "missing"), function (x, i, j, ...,
             }
             i <- CrunchLogicalExpr(dataset_url=datasetReference(x),
                 expression=.dispatchFilter(i))
+            activeFilter(i) <- activeFilter(x)
             return(x[i,])
         } else {
             halt("Logical filter vector is length ", length(i),
@@ -131,6 +132,58 @@ setMethod("[", c("CrunchDataset", "CrunchLogicalExpr", "ANY"), function (x, i, j
     return(x[j])
 })
 
+#' @rdname dataset-extract
+#' @export
+setMethod("[", c("CrunchDataset", "numeric", "missing"), function (x, i, j, ..., drop=FALSE) {
+    if (nargs() == 2L) {
+        ## x[i]. So subset the variables, list-wise
+        x@variables <- variables(x)[i]
+        return(x)
+    }
+    filt <- activeFilter(x)
+    if (!is.null(filt)) {
+        return(harmonizeFilters(x, filt, i))
+    } else {
+        return(x[seq_len(nrow(x)) %in% i, ])
+    }
+})
+
+
+#' Sometimes you want to subset a filtered object using a numeric vector. In order
+#' to do this on a crunch object we need to first get the rows which match the filter
+#' and then apply the numeric vector. For instance if you have a dataset filter such
+#' that `ds_filt <- ds[ds$var == 5, ]` then `ds_filt[1:5]` should return the first
+#' five rows where `ds$var == 5`. This function takes a filtered object and returns
+#' the correctly subsetted filtered object.
+#' @rdname dataset-extract
+#' @keywords internal
+#' @param x a filtered Dataset or vector
+#' @param filt the object's filter
+#' @param i A numeric vector to harmonize with that filter
+#' @return a properly filtered dataset or vector
+harmonizeFilters <- function (x, filt, i){
+    filt_lgl <- as.vector(filt)
+    unfiltered <- x
+    activeFilter(unfiltered) <- NULL
+    if (is.dataset(x)){
+        out <- unfiltered[seq_len(nrow(unfiltered)) %in% which(filt_lgl)[i], ]
+    } else if (is.variable(x)) {
+        out <- unfiltered[seq_len(length(unfiltered)) %in% which(filt_lgl)[i]]
+    } else {
+        halt("Unsupported object type")
+    }
+    activeFilter(out) <- filt & activeFilter(out)
+    return(out)
+}
+
+#' @rdname dataset-extract
+#' @export
+setMethod("[", c("CrunchDataset", "numeric", "ANY"), function (x, i, j, ..., drop=FALSE) {
+    ## Do the filtering of rows, then cols
+    x <- x[i,]
+    return(x[j])
+})
+
 #' @rdname dataset-extract
 #' @export
 setMethod("subset", "CrunchDataset", function (x, ...) {

R/variable.R

@@ -69,6 +69,15 @@ setMethod("digits<-", "CrunchVariable", function (x, value) {
     halt("digit specifications can only be set for numeric variables")
 })
 
+#' @rdname describe
+#' @export
+setMethod("length", "CrunchVariable", function (x) {
+    ds <- loadDataset(datasetReference(x))
+    activeFilter(ds) <- activeFilter(x)
+    return(nrow(ds))
+})
+
+
 #' Get and set Categories on Variables
 #'
 #' @param x a Variable
@@ -226,9 +235,12 @@ setMethod("[", c("CrunchVariable", "CrunchExpr"), .updateActiveFilter)
 #' @rdname variable-extract
 #' @export
 setMethod("[", c("CrunchVariable", "numeric"), function (x, i, ...) {
-    i <- CrunchLogicalExpr(dataset_url=datasetReference(x),
-        expression=.dispatchFilter(i))
-    return(x[i])
+    filt <- activeFilter(x)
+    if (!is.null(filt)) {
+        return(harmonizeFilters(x, filt, i))
+    } else {
+        return(x[seq_len(length(x)) %in% i])
+    }
 })
 #' @rdname variable-extract
 #' @export

inst/app.crunch.io/api/datasets/1/export/csv-3a22fd-POST.R

@@ -0,0 +1,71 @@
+structure(list(url = "https://app.crunch.io/api/datasets/1/export/csv/",
+    status_code = 202L, headers = structure(list(allow = "GET, HEAD, OPTIONS, POST",
+        `content-encoding` = "gzip", `content-type` = "application/json;charset=utf-8",
+        date = "Fri, 12 Jan 2018 14:23:13 GMT", location = "dataset_exports/test-ds.csv?Signature=SKknqNLKd2vJu3EcxKhOJxOjp4c%3D&Expires=1515770593&AWSAccessKeyId=AKIAJT4CEBNJXNPF3NZA",
+        server = "nginx", `set-cookie` = "REDACTED", vary = "Cookie, Accept-Encoding",
+        `x-timing` = "", `content-length` = "141", connection = "keep-alive"), .Names = c("allow",
+    "content-encoding", "content-type", "date", "location", "server",
+    "set-cookie", "vary", "x-timing", "content-length", "connection"
+    ), class = c("insensitive", "list")), all_headers = list(
+        structure(list(status = 202L, version = "HTTP/1.1", headers = structure(list(
+            allow = "GET, HEAD, OPTIONS, POST", `content-encoding` = "gzip",
+            `content-type` = "application/json;charset=utf-8",
+            date = "Fri, 12 Jan 2018 14:23:13 GMT", location = "dataset_exports/test-ds.csv?Signature=SKknqNLKd2vJu3EcxKhOJxOjp4c%3D&Expires=1515770593&AWSAccessKeyId=AKIAJT4CEBNJXNPF3NZA",
+            server = "nginx", `set-cookie` = "REDACTED", vary = "Cookie, Accept-Encoding",
+            `x-timing` = "", `content-length` = "141", connection = "keep-alive"), .Names = c("allow",
+        "content-encoding", "content-type", "date", "location",
+        "server", "set-cookie", "vary", "x-timing", "content-length",
+        "connection"), class = c("insensitive", "list"))), .Names = c("status",
+        "version", "headers"))), cookies = structure(list(domain = ".crunch.io",
+        flag = TRUE, path = "/", secure = FALSE, expiration = structure(1547302993, class = c("POSIXct",
+        "POSIXt")), name = "token", value = "REDACTED"), .Names = c("domain",
+    "flag", "path", "secure", "expiration", "name", "value"), row.names = c(NA,
+    -1L), class = "data.frame"), content = as.raw(c(0x7b, 0x22,
+    0x65, 0x6c, 0x65, 0x6d, 0x65, 0x6e, 0x74, 0x22, 0x3a, 0x20,
+    0x22, 0x73, 0x68, 0x6f, 0x6a, 0x69, 0x3a, 0x76, 0x69, 0x65,
+    0x77, 0x22, 0x2c, 0x20, 0x22, 0x73, 0x65, 0x6c, 0x66, 0x22,
+    0x3a, 0x20, 0x22, 0x68, 0x74, 0x74, 0x70, 0x73, 0x3a, 0x2f,
+    0x2f, 0x61, 0x70, 0x70, 0x2e, 0x63, 0x72, 0x75, 0x6e, 0x63,
+    0x68, 0x2e, 0x69, 0x6f, 0x2f, 0x61, 0x70, 0x69, 0x2f, 0x64,
+    0x61, 0x74, 0x61, 0x73, 0x65, 0x74, 0x73, 0x2f, 0x34, 0x31,
+    0x36, 0x32, 0x32, 0x35, 0x61, 0x35, 0x63, 0x38, 0x38, 0x37,
+    0x34, 0x33, 0x66, 0x65, 0x61, 0x30, 0x37, 0x65, 0x62, 0x36,
+    0x38, 0x31, 0x31, 0x37, 0x63, 0x61, 0x34, 0x37, 0x61, 0x64,
+    0x2f, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x2f, 0x63, 0x73,
+    0x76, 0x2f, 0x22, 0x2c, 0x20, 0x22, 0x76, 0x61, 0x6c, 0x75,
+    0x65, 0x22, 0x3a, 0x20, 0x22, 0x68, 0x74, 0x74, 0x70, 0x73,
+    0x3a, 0x2f, 0x2f, 0x61, 0x70, 0x70, 0x2e, 0x63, 0x72, 0x75,
+    0x6e, 0x63, 0x68, 0x2e, 0x69, 0x6f, 0x2f, 0x61, 0x70, 0x69,
+    0x2f, 0x70, 0x72, 0x6f, 0x67, 0x72, 0x65, 0x73, 0x73, 0x2f,
+    0x73, 0x75, 0x63, 0x63, 0x65, 0x73, 0x73, 0x2f, 0x22, 0x7d
+    )), date = structure(1515766993, class = c("POSIXct", "POSIXt"
+    ), tzone = "GMT"), times = structure(c(0, 0.129607, 0.23883,
+    0.501342, 0.629068, 0.629116), .Names = c("redirect", "namelookup",
+    "connect", "pretransfer", "starttransfer", "total")), request = structure(list(
+        method = "POST", url = "https://app.crunch.io/api/datasets/1/export/csv/",
+        headers = structure(c("application/json, text/xml, application/xml, */*",
+        "", "libcurl/7.54.0 curl/3.0 httr/1.3.1 rcrunch/1.19.1"
+        ), .Names = c("Accept", "Content-Type", "user-agent")),
+        fields = NULL, options = structure(list(useragent = "libcurl/7.54.0 r-curl/3.0 httr/1.3.1",
+            post = TRUE, postfieldsize = 131L, postfields = as.raw(c(0x7b,
+            0x22, 0x66, 0x69, 0x6c, 0x74, 0x65, 0x72, 0x22, 0x3a,
+            0x7b, 0x22, 0x66, 0x75, 0x6e, 0x63, 0x74, 0x69, 0x6f,
+            0x6e, 0x22, 0x3a, 0x22, 0x62, 0x65, 0x74, 0x77, 0x65,
+            0x65, 0x6e, 0x22, 0x2c, 0x22, 0x61, 0x72, 0x67, 0x73,
+            0x22, 0x3a, 0x5b, 0x7b, 0x22, 0x66, 0x75, 0x6e, 0x63,
+            0x74, 0x69, 0x6f, 0x6e, 0x22, 0x3a, 0x22, 0x72, 0x6f,
+            0x77, 0x22, 0x2c, 0x22, 0x61, 0x72, 0x67, 0x73, 0x22,
+            0x3a, 0x5b, 0x5d, 0x7d, 0x2c, 0x7b, 0x22, 0x76, 0x61,
+            0x6c, 0x75, 0x65, 0x22, 0x3a, 0x30, 0x7d, 0x2c, 0x7b,
+            0x22, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x22, 0x3a, 0x36,
+            0x7d, 0x5d, 0x7d, 0x2c, 0x22, 0x6f, 0x70, 0x74, 0x69,
+            0x6f, 0x6e, 0x73, 0x22, 0x3a, 0x7b, 0x22, 0x75, 0x73,
+            0x65, 0x5f, 0x63, 0x61, 0x74, 0x65, 0x67, 0x6f, 0x72,
+            0x79, 0x5f, 0x69, 0x64, 0x73, 0x22, 0x3a, 0x74, 0x72,
+            0x75, 0x65, 0x7d, 0x7d)), postredir = 3), .Names = c("useragent",
+        "post", "postfieldsize", "postfields", "postredir")),
+        output = structure(list(), class = c("write_memory",
+        "write_function"))), .Names = c("method", "url", "headers",
+    "fields", "options", "output"), class = "request")), .Names = c("url",
+"status_code", "headers", "all_headers", "cookies", "content",
+"date", "times", "request"), class = "response")

inst/app.crunch.io/api/datasets/1/summary-10d0ac.json

@@ -0,0 +1,17 @@
+{
+    "element":
+    "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/summary/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A19%7D%2C%7B%22value%22%3A25%7D%5D%7D",
+    "value": {
+        "unweighted": {
+            "filtered": 6,
+            "total": 25
+        },
+        "variables": 6,
+        "weighted": {
+            "filtered": 6,
+            "total": 25
+        },
+        "columns": 6
+    }
+}

inst/app.crunch.io/api/datasets/1/summary-57a14f.json

@@ -0,0 +1,16 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/summary/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A0%7D%2C%7B%22value%22%3A6%7D%5D%7D",
+    "value": {
+        "unweighted": {
+            "filtered": 6,
+            "total": 25
+        },
+        "variables": 6,
+        "weighted": {
+            "filtered": 6,
+            "total": 25
+        },
+        "columns": 6
+    }
+}

inst/app.crunch.io/api/datasets/1/variables/gender/values-686a6e.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/gender/values/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A0%7D%2C%7B%22value%22%3A6%7D%5D%7D&offset=0&limit=5000",
+    "value": ["w", "n", "x", "b", "q", "s"]
+}

inst/app.crunch.io/api/datasets/1/variables/gender/values-80c80e.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/gender/values/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A0%7D%2C%7B%22value%22%3A4%7D%5D%7D&offset=0&limit=200000",
+    "value": [2, 2, {"?": -1}, 2]
+}

inst/app.crunch.io/api/datasets/1/variables/starttime/values-0b0abd.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/starttime/values/?filter=%7B%22function%22%3A%22in%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22column%22%3A%5B0%2C17%5D%7D%5D%7D&offset=0&limit=100000",
+    "value": ["1956-02-13", "1956-01-28"]
+}

inst/app.crunch.io/api/datasets/1/variables/starttime/values-0f7a5b.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/starttime/values/?filter=%7B%22function%22%3A%22in%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22column%22%3A%5B0%2C1%2C16%2C17%5D%7D%5D%7D&offset=0&limit=100000",
+    "value": ["1956-02-13", "1955-12-28", "1955-12-30", "1956-01-28"]
+}

inst/app.crunch.io/api/datasets/1/variables/starttime/values-ff7207.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/starttime/values/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A0%7D%2C%7B%22value%22%3A25%7D%5D%7D&offset=0&limit=100000",
+    "value": ["1956-02-13", "1955-12-28", "1955-11-17", "1956-02-08", "1956-01-17", "1956-01-21", "1956-02-07", "1955-12-25", "1956-01-17", "1955-12-12", "1955-11-21", "1955-12-06", "1956-01-19", "1955-12-15", "1956-02-07", "1956-02-08", "1955-12-30", "1956-01-28", "1956-01-01", "1956-01-15", "1955-11-13", "1955-11-17", "1955-11-09", "1955-12-22", "1955-12-20"]
+}

inst/app.crunch.io/api/datasets/1/variables/textVar/values-0ba86f.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/textVar/values/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A0%7D%2C%7B%22value%22%3A25%7D%5D%7D&offset=0&limit=5000",
+    "value": ["w", "n", "x", "b", "q", "s", "l", "v", "v", "y", "m", "t", "s", "e", "z", "k", "n", "w", "v", "i", "h", "z", "m", "c", "x"]
+}

inst/app.crunch.io/api/datasets/1/variables/textVar/values-686a6e.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/textVar/values/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A0%7D%2C%7B%22value%22%3A6%7D%5D%7D&offset=0&limit=5000",
+    "value": ["w", "n", "x", "b", "q", "s"]
+}

inst/app.crunch.io/api/datasets/1/variables/textVar/values-9d21bb.json

@@ -0,0 +1,5 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/textVar/values/?filter=%7B%22function%22%3A%22between%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22value%22%3A19%7D%2C%7B%22value%22%3A25%7D%5D%7D&offset=0&limit=5000",
+    "value": ["i", "h", "z", "m", "c", "x"]
+}

inst/app.crunch.io/api/datasets/1/variables/textVar/values-a28816.json

@@ -0,0 +1,4 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1/variables/textVar/values/?filter=%7B%22function%22%3A%22in%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22column%22%3A%5B0%2C17%5D%7D%5D%7D&offset=0&limit=5000", "value": ["w", "w"]
+}

inst/app.crunch.io/api/datasets/1/variables/textVar/values-e05e28.json

@@ -0,0 +1,3 @@
+{"element": "shoji:view",
+"self": "https://app.crunch.io/api/datasets/1/variables/textVar/values/?filter=%7B%22function%22%3A%22in%22%2C%22args%22%3A%5B%7B%22function%22%3A%22row%22%2C%22args%22%3A%5B%5D%7D%2C%7B%22column%22%3A%5B0%2C1%2C16%2C17%5D%7D%5D%7D&offset=0&limit=5000",
+"value": ["w", "n", "n", "w"]}

inst/app.crunch.io/api/datasets/1streaming/summary-73a614.json

@@ -0,0 +1,13 @@
+{
+    "element": "shoji:view",
+    "self": "https://app.crunch.io/api/datasets/1streaming/summary/?filter=%7B%7D",
+    "value": {
+        "unweighted": {
+            "filtered": 25,
+            "total": 25},
+        "variables": 6,
+        "weighted": {
+            "filtered": 25,
+            "total": 25},
+        "columns": 6}
+}

inst/app.crunch.io/api/progress/success.json

@@ -0,0 +1 @@
+{"element": "shoji:view", "self": "https://app.crunch.io/api/progress/success/", "views": {"result": "https://app.crunch.io/api/progress/success/result/"}, "value": {"progress": 100, "message": "complete"}}