rename locate_code to stock_locate

DavZim · Dec 17, 2020 · 28cc0e8 · 28cc0e8
1 parent 0734103
commit 28cc0e8
Show file tree

Hide file tree

Showing 12 changed files with 151 additions and 150 deletions.
diff --git a/R/download_stock_directory.R b/R/download_stock_directory.R
@@ -37,7 +37,7 @@ download_stock_directory <- function(exchange, date, quiet = FALSE) {
     url <- paste0(base_url, exchange, "_stocklocate_", format(date, "%Y%m%d"), ".txt")
 
     d <- data.table::fread(url, showProgress = !quiet)
-    data.table::setnames(d, c("ticker", "locate_code"))
+    data.table::setnames(d, c("ticker", "stock_locate"))
     d[, ':=' (exchange = toupper(exchange), date = date)]
   }
 

diff --git a/R/read_functions.R b/R/read_functions.R
@@ -46,7 +46,7 @@
 #'  tries to find the stock_locate based on the \code{stock_directory} argument,
 #'  if this is not found, it will try to extract the stock directory from the file,
 #'  else an error is thrown.
-#' @param stock_directory A data.frame containing the stock-locate_code relationship.
+#' @param stock_directory A data.frame containing the stock-locate code relationship.
 #' As outputted by \code{\link{read_stock_directory}}. 
 #' Only used if \code{filter_stock} is set. To download the stock directory from
 #' NASDAQs FTP server, use \code{\link{download_stock_directory}}.
@@ -213,7 +213,7 @@ read_ITCH <- function(file, type, skip = 0, n_max = -1,
   if (!(length(filter_stock) == 1 && is.na(filter_stock))) {
     if (length(stock_directory) == 1 && is.na(stock_directory)) {
       warning("filter_stock is given, but no stock_directory is specified. Trying to extract stock directory from file\n")
-      stock_directory <- RITCH::read_stock_directory(file, quiet = TRUE)
+      stock_directory <- read_stock_directory(file, quiet = TRUE)
     }
 
     if (!all(filter_stock %chin% stock_directory$stock)) {
@@ -224,7 +224,7 @@ read_ITCH <- function(file, type, skip = 0, n_max = -1,
     }
     # extend locate code by the stocks:
     filter_stock_locate <- c(filter_stock_locate,
-                             stock_directory[stock %chin%filter_stock, locate_code])
+                             stock_directory[stock %chin%filter_stock, stock_locate])
   }
 
   if (!quiet && length(filter_stock_locate) > 0) 

diff --git a/README.Rmd b/README.Rmd
@@ -162,7 +162,7 @@ while (n_parsed < n_messages) {
 }
 ```
 
-You can also filter a dataset directly while reading messages for `msg_type`, `locate_code`, `timestamp` range, as well as `stock`. Note that filtering for a specific stock, is just a shorthand lookup for the stocks `locate_code`s, therefore a `stock_directory` needs to be supplied (either by providing the output from `read_stock_directory()` or `download_locate_code()`) or the function will try to extract the stock directory from the file.
+You can also filter a dataset directly while reading messages for `msg_type`, `stock_locate`, `timestamp` range, as well as `stock`. Note that filtering for a specific stock, is just a shorthand lookup for the stocks `stock_locate`s, therefore a `stock_directory` needs to be supplied (either by providing the output from `read_stock_directory()` or `download_stock_locate()`) or the function will try to extract the stock directory from the file.
 
 ```{r}
 # read in the stock directory as we filter for stock names later on

diff --git a/README.md b/README.md
@@ -73,7 +73,7 @@ orders <- read_orders(file)
 str(orders)
 #> Classes 'data.table' and 'data.frame':   5000 obs. of  13 variables:
 #>  $ msg_type       : chr  "A" "A" "F" "A" ...
-#>  $ locate_code    : int  2 2 2 2 2 2 2 2 2 2 ...
+#>  $ stock_locate   : int  2 2 2 2 2 2 2 2 2 2 ...
 #>  $ tracking_number: int  0 0 0 0 0 0 0 0 0 0 ...
 #>  $ timestamp      :integer64 31139052372053 31141354532167 32813425752711 32826656500150 32827351405783 32893988026867 33067242028997 33300886636321 ... 
 #>  $ order_ref      :integer64 0 100 84836 87020 87040 93032 105532 121012 ... 
@@ -96,7 +96,7 @@ trades <- read_trades(file, n_max = 100)
 str(trades)
 #> Classes 'data.table' and 'data.frame':   100 obs. of  14 variables:
 #>  $ msg_type       : chr  "P" "P" "P" "P" ...
-#>  $ locate_code    : int  2 2 2 2 2 3 3 3 3 3 ...
+#>  $ stock_locate   : int  2 2 2 2 2 3 3 3 3 3 ...
 #>  $ tracking_number: int  2 2 2 2 2 2 4 2 2 2 ...
 #>  $ timestamp      :integer64 34210128591201 34210355475120 34210767188977 34211127433476 34212046014088 34235711475708 34239928637481 34239928703094 ... 
 #>  $ order_ref      :integer64 0 0 0 0 0 0 0 0 ... 
@@ -256,11 +256,11 @@ while (n_parsed < n_messages) {
 ```
 
 You can also filter a dataset directly while reading messages for
-`msg_type`, `locate_code`, `timestamp` range, as well as `stock`. Note
+`msg_type`, `stock_locate`, `timestamp` range, as well as `stock`. Note
 that filtering for a specific stock, is just a shorthand lookup for the
-stocks `locate_code`s, therefore a `stock_directory` needs to be
+stocks `stock_locate`s, therefore a `stock_directory` needs to be
 supplied (either by providing the output from `read_stock_directory()`
-or `download_locate_code()`) or the function will try to extract the
+or `download_stock_locate()`) or the function will try to extract the
 stock directory from the file.
 
 ``` r
@@ -274,11 +274,12 @@ od <- read_orders(
   max_timestamp = 55800000000000, # end at 15:30:00.000000
   filter_stock_locate = 1,        # take only stock with code 1
   filter_stock = "CHAR",          # but also take stock CHAR
-  stock_directory = sdir          # provide the stock_directory to match stock names to locate_codes
+  stock_directory = sdir          # provide the stock_directory to match stock names to stock_locates
 )
-#> [Filter]     'msg_type': 'A'
-#> [Filter]     'timestamp': 43200000000000 - 55800000000000 
-#> [Filter]     'stock_locate': '1', '3'
+#> [Filter]     msg_type: 'A'
+#> [Filter]     timestamp: 43200000000000 - 55800000000000 
+#> [Filter]     stock_locate: '1', '3'
+#> NOTE: as filter arguments were given, the number of messages may be off
 #> [Counting]   5,000 messages found
 #> [Loading]    .
 #> [Converting] to data.table
@@ -290,10 +291,10 @@ od[, .(n = .N), by = msg_type]
 range(od$timestamp)
 #> integer64
 #> [1] 43235810473334 55792143963723
-od[, .(n = .N), by = .(locate_code, stock)]
-#>    locate_code stock   n
-#> 1:           3  CHAR 574
-#> 2:           1   ALC 508
+od[, .(n = .N), by = .(stock_locate, stock)]
+#>    stock_locate stock   n
+#> 1:            3  CHAR 574
+#> 2:            1   ALC 508
 ```
 
 If you are interested in writing `ITCH_50` files or gaining a better

diff --git a/debug/README.Rmd b/debug/README.Rmd
@@ -125,7 +125,7 @@ dbg_hex_to_orders(hex_string)
 ```{r}
 od <- data.table::data.table(
   msg_type = "F",
-  locate_code = 8236L,
+  stock_locate = 8236L,
   tracking_number = 0L,
   timestamp = bit64::as.integer64(25200002107428),
   order_ref = bit64::as.integer64(4),

diff --git a/debug/debug_tools.cpp b/debug/debug_tools.cpp
@@ -534,7 +534,7 @@ uint64_t parse_orders_at(unsigned char * buf, Rcpp::DataFrame df,
                         uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::NumericVector   order_ref       = df["order_ref"];
@@ -549,7 +549,7 @@ uint64_t parse_orders_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -572,7 +572,7 @@ uint64_t parse_trades_at(unsigned char * buf, Rcpp::DataFrame df,
                          uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::NumericVector   order_ref       = df["order_ref"];
@@ -588,7 +588,7 @@ uint64_t parse_trades_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -636,7 +636,7 @@ uint64_t parse_modifications_at(unsigned char * buf, Rcpp::DataFrame df,
                                 uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::NumericVector   order_ref       = df["order_ref"];
@@ -651,7 +651,7 @@ uint64_t parse_modifications_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -697,7 +697,7 @@ uint64_t parse_system_events_at(unsigned char * buf, Rcpp::DataFrame df,
                                 uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::CharacterVector event_code      = df["event_code"];
@@ -707,7 +707,7 @@ uint64_t parse_system_events_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -722,7 +722,7 @@ uint64_t parse_stock_directory_at(unsigned char * buf, Rcpp::DataFrame df,
                                   uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type             = df["msg_type"];
-  Rcpp::IntegerVector   locate_code          = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate          = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number      = df["tracking_number"];
   Rcpp::NumericVector   timestamp            = df["timestamp"];
   Rcpp::CharacterVector stock                = df["stock"];
@@ -745,7 +745,7 @@ uint64_t parse_stock_directory_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -774,7 +774,7 @@ uint64_t parse_trading_status_at(unsigned char * buf, Rcpp::DataFrame df,
                                  uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type         = df["msg_type"];
-  Rcpp::IntegerVector   locate_code      = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate      = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number  = df["tracking_number"];
   Rcpp::NumericVector   timestamp        = df["timestamp"];
   Rcpp::CharacterVector stock            = df["stock"];
@@ -789,7 +789,7 @@ uint64_t parse_trading_status_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -820,7 +820,7 @@ uint64_t parse_reg_sho_at(unsigned char * buf, Rcpp::DataFrame df,
                           uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::CharacterVector stock           = df["stock"];
@@ -831,7 +831,7 @@ uint64_t parse_reg_sho_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -847,7 +847,7 @@ uint64_t parse_market_participants_states_at(unsigned char * buf, Rcpp::DataFram
                                              uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type          = df["msg_type"];
-  Rcpp::IntegerVector   locate_code       = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate       = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number   = df["tracking_number"];
   Rcpp::NumericVector   timestamp         = df["timestamp"];
   Rcpp::CharacterVector mpid              = df["mpid"];
@@ -861,7 +861,7 @@ uint64_t parse_market_participants_states_at(unsigned char * buf, Rcpp::DataFram
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -880,7 +880,7 @@ uint64_t parse_mwcb_at(unsigned char * buf, Rcpp::DataFrame df,
                       uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::NumericVector   level1          = df["level1"];
@@ -893,7 +893,7 @@ uint64_t parse_mwcb_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -921,7 +921,7 @@ uint64_t parse_ipo_at(unsigned char * buf, Rcpp::DataFrame df,
                       uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type          = df["msg_type"];
-  Rcpp::IntegerVector   locate_code       = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate       = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number   = df["tracking_number"];
   Rcpp::NumericVector   timestamp         = df["timestamp"];
   Rcpp::CharacterVector stock             = df["stock"];
@@ -934,7 +934,7 @@ uint64_t parse_ipo_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -952,7 +952,7 @@ uint64_t parse_luld_at(unsigned char * buf, Rcpp::DataFrame df,
                        uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::CharacterVector stock           = df["stock"];
@@ -966,7 +966,7 @@ uint64_t parse_luld_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -986,7 +986,7 @@ uint64_t parse_noii_at(unsigned char * buf, Rcpp::DataFrame df,
                        uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type            = df["msg_type"];
-  Rcpp::IntegerVector   locate_code         = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate         = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number     = df["tracking_number"];
   Rcpp::NumericVector   timestamp           = df["timestamp"];
   Rcpp::NumericVector   paired_shares       = df["paired_shares"];
@@ -1004,7 +1004,7 @@ uint64_t parse_noii_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
@@ -1030,7 +1030,7 @@ uint64_t parse_rpii_at(unsigned char * buf, Rcpp::DataFrame df,
                        uint64_t msg_num) {
 
   Rcpp::CharacterVector msg_type        = df["msg_type"];
-  Rcpp::IntegerVector   locate_code     = df["locate_code"];
+  Rcpp::IntegerVector   stock_locate     = df["stock_locate"];
   Rcpp::IntegerVector   tracking_number = df["tracking_number"];
   Rcpp::NumericVector   timestamp       = df["timestamp"];
   Rcpp::CharacterVector stock           = df["stock"];
@@ -1041,7 +1041,7 @@ uint64_t parse_rpii_at(unsigned char * buf, Rcpp::DataFrame df,
   const char msg = Rcpp::as<char>(msg_type[msg_num]);
   buf[i++] = msg;
 
-  i += set2bytes(&buf[i], locate_code[msg_num]);
+  i += set2bytes(&buf[i], stock_locate[msg_num]);
   i += set2bytes(&buf[i], tracking_number[msg_num]);
 
   std::memcpy(&val64, &(timestamp[msg_num]), sizeof(int64_t));
-Original file line number
+Diff line change
@@ Expand Up / @@ -162,7 +162,7 @@ while (n_parsed < n_messages) { @@
     }
     ```
-    You can also filter a dataset directly while reading messages for `msg_type`, `locate_code`, `timestamp` range, as well as `stock`. Note that filtering for a specific stock, is just a shorthand lookup for the stocks `locate_code`s, therefore a `stock_directory` needs to be supplied (either by providing the output from `read_stock_directory()` or `download_locate_code()`) or the function will try to extract the stock directory from the file.
+    You can also filter a dataset directly while reading messages for `msg_type`, `stock_locate`, `timestamp` range, as well as `stock`. Note that filtering for a specific stock, is just a shorthand lookup for the stocks `stock_locate`s, therefore a `stock_directory` needs to be supplied (either by providing the output from `read_stock_directory()` or `download_stock_locate()`) or the function will try to extract the stock directory from the file.
     ```{r}
     # read in the stock directory as we filter for stock names later on
@@ Expand Down @@