🚀 RELEASE: update cay to 2019q3

Also add new index msi.csv Predictor now goes to 2016q4
eloualiche · Mar 23, 2020 · 48a7572 · 48a7572
1 parent cafb1aa
commit 48a7572
Show file tree

Hide file tree

Showing 13 changed files with 1,047 additions and 897 deletions.
diff --git a/Makefile b/Makefile
@@ -2,32 +2,43 @@
 # Makefile for PREDICTING THE EQUITY RISK PREMIUM
 #
 # Created       on June  04th 2019
-# Last modified on June  14th 2019
+# Last modified on March 23rd 2020
 ## --------------------------------------------------------------------------------------------------------
 
 
+
+## --------------------------------------------------------------------------------------------------------
+## LOAD A FEW OPTIONS
+-include ./rules.mk
+## --------------------------------------------------------------------------------------------------------
+
 # --------------------------------------------------------------------------------------------------------
 ## ALL
 all: output/predict.csv readme.md
 
 ##
 ## DOWNLOAD THE DATA FROM WRDS
+## Edit rules.mk to change your user name under WRDS_USERNAME
 input/msi.sas7bdat: 
-	rsync -aPvzh --stats --human-readable  XXXX@wrds-cloud.wharton.upenn.edu:/wrds/crsp/sasdata/a_stock/msi.sas7bdat ./input/
+	$(call colorecho,"Download stock market index from crsp ...")
+	rsync -aPvzh --stats --human-readable  ${WRDS_USERNAME}@wrds-cloud.wharton.upenn.edu:/wrds/crsp/sasdata/a_stock/msi.sas7bdat ./input/
 	@echo
 
 ## GENERATE PREDICTORS
 tmp/predict.csv: src/import_predictors.R input/cay_current.csv input/msi.sas7bdat
+	$(call colorecho,"Import and merge all return predictors ...")
 	R CMD BATCH $(R_OPTS) src/import_predictors.R log/import_predictors.log.R
 	@echo
 
 ## RUN REGRESSIONS
 output/predict.csv: src/rp_measure.R tmp/predict.csv
+	$(call colorecho,"Estimate predictive regression ...")
 	R CMD BATCH $(R_OPTS) src/rp_measure.R log/rp_measure.log.R
 	@echo
 
 ## OUTPUT RESULTS
-readme.md: src/readme_in.md 
+readme.md: src/readme_in.md output/predict.png tmp/reg_update.txt
+	$(call colorecho,"Update readme file ...")
 	cat src/readme_in.md tmp/reg_update.txt > readme.md
 	@echo
 
@@ -47,10 +58,6 @@ clean:
 	rm -rf readme.md
 
 ##
-## --------------------------------------------------------------------------------------------------------
-SHELL    := /bin/bash
-R_OPTS   := --vanilla
-# DATE     := `date '+%Y-%m-%d %H:%M:%S'`
 # --------------------------------------------------------------------------------------------------------
 
 

diff --git a/input/cay_current.csv b/input/cay_current.csv
diff --git a/log/R-session-info.log.R b/log/R-session-info.log.R
diff --git a/log/import_predictors.log.R b/log/import_predictors.log.R
@@ -1,6 +1,6 @@
 
-R version 3.5.1 (2018-07-02) -- "Feather Spray"
-Copyright (C) 2018 The R Foundation for Statistical Computing
+R version 3.6.2 (2019-12-12) -- "Dark and Stormy Night"
+Copyright (C) 2019 The R Foundation for Statistical Computing
 Platform: x86_64-apple-darwin15.6.0 (64-bit)
 
 R is free software and comes with ABSOLUTELY NO WARRANTY.
@@ -48,18 +48,33 @@ Type 'q()' to quit R.
 Log file for code executed at
 
 > message(format(Sys.time(), "%a %b %d %X %Y"))
-Tue Aug 27 21:49:24 2019
+Mon Mar 23 08:59:59 2020
 > ##################################################################################
 > 
 > 
 > ##################################################################################
 > # APPEND REQUIRED PACKAGES
-> library(crayon)
-> library(devtools)
 > 
-> library(alfred)
-> library(haven)
-> library(dplyr)
+> # See this https://stackoverflow.com/questions/4090169/elegant-way-to-check-for-missing-packages-and-install-them
+> using<-function(...) {
++     libs<-unlist(list(...))
++     req<-unlist(lapply(libs,require,character.only=TRUE))
++     need<-libs[req==FALSE]
++     if(length(need)>0){ 
++         install.packages(need)
++         lapply(need,require,character.only=TRUE)
++     }
++ }
+> 
+> package_to_load <- c("crayon", "devtools", "alfred", "haven", "dplyr", 
++ 	"stringr", "lubridate", "RcppRoll", "statar", "data.table")
+> using(package_to_load)
+Loading required package: crayon
+Loading required package: devtools
+Loading required package: usethis
+Loading required package: alfred
+Loading required package: haven
+Loading required package: dplyr
 
 Attaching package: ‘dplyr’
 
@@ -71,18 +86,18 @@ The following objects are masked from ‘package:base’:
 
     intersect, setdiff, setequal, union
 
-> library(stringr)
-> library(lubridate)
+Loading required package: stringr
+Loading required package: lubridate
 
 Attaching package: ‘lubridate’
 
 The following object is masked from ‘package:base’:
 
     date
 
-> library(RcppRoll)
-> library(statar)
-> library(data.table)
+Loading required package: RcppRoll
+Loading required package: statar
+Loading required package: data.table
 
 Attaching package: ‘data.table’
 
@@ -93,46 +108,57 @@ The following objects are masked from ‘package:lubridate’:
 
 The following objects are masked from ‘package:dplyr’:
 
-    between, coalesce, first, last
+    between, first, last
 
 > 
 > check_file = file.exists("log/R-session-info.log.R")
 > sink("log/R-session-info.log.R", append=check_file)
 > cat(bold("\n\n# -----\n# Session info for import_predictors\n\n")) 
 > session_info()
-Session info ------------------------------------------------------------------
-Packages ----------------------------------------------------------------------
 > sink()
 > ##################################################################################
 > 
 > 
 > ##################################################################################
 > # 1. TREASURIES
-> dt_tbill <- get_fred_series("TB3MS", "rf", observation_start = "1950-01-01", observation_end = "2019-05-31") %>% data.table
+> dt_tbill <- get_fred_series("TB3MS", "rf", observation_start = "1950-01-01", observation_end = "2020-12-31") %>% data.table
 > dt_tbill <- dt_tbill[, .(dateym=year(date)*100+month(date), rf=rf/100)]
+> dt_tbill[]
+     dateym     rf
+  1: 195001 0.0107
+  2: 195002 0.0112
+  3: 195003 0.0112
+  4: 195004 0.0115
+  5: 195005 0.0116
+ ---              
+838: 201910 0.0165
+839: 201911 0.0154
+840: 201912 0.0154
+841: 202001 0.0152
+842: 202002 0.0152
 > # fwrite(dt_tbill, "./input/tbill.csv")
 > ##################################################################################
 > 
 > 
 > ##################################################################################
 > # 2. CAY
-> dt_cay <- fread("./input/cay_current.csv", skip=1, header=T)
-> dt_cay <- dt_cay[, .(date_y=as.integer(str_sub(date, 1, 4)), 
-+ 	                 quarter=as.integer(str_sub(date, 5, 6)), cay=cay) ]
-> dt_cay <- dt_cay[, .(dateym=date_y*100+quarter*3, cay) ]
-> dt_cay
+> dt_cay <- fread("./input/cay_current.csv", skip=0, header=T)
+> setnames(dt_cay, c("date", "c", "w", "y", "cay"))
+> dt_cay <- dt_cay[, .(date_y=year(date), month = month(date), cay) ]
+> dt_cay <- dt_cay[, .(dateym=date_y*100+month, cay) ]
+> dt_cay[]
      dateym         cay
-  1: 195203  0.01646544
-  2: 195206  0.02551783
-  3: 195209  0.01633620
-  4: 195212  0.02542006
-  5: 195303  0.02543387
+  1: 195203  0.01510493
+  2: 195206  0.02483727
+  3: 195209  0.01484008
+  4: 195212  0.02216598
+  5: 195303  0.02152118
  ---                   
-259: 201609 -0.02916950
-260: 201612 -0.02042846
-261: 201703 -0.02529660
-262: 201706 -0.02655350
-263: 201709 -0.02760623
+267: 201809 -0.02934508
+268: 201812 -0.02020734
+269: 201903 -0.04435449
+270: 201906 -0.03764155
+271: 201909 -0.03665922
 > ##################################################################################
 > 
 > 
@@ -161,11 +187,11 @@ Packages ----------------------------------------------------------------------
    4: 192603         NA
    5: 192604         NA
   ---                  
-1113: 201808 0.02033382
-1114: 201809 0.02040150
-1115: 201810 0.02047582
-1116: 201811 0.02050859
-1117: 201812 0.02114445
+1125: 201908 0.02129861
+1126: 201909 0.02150184
+1127: 201910 0.02149657
+1128: 201911 0.02113526
+1129: 201912 0.02085788
 > ##################################################################################
 > 
 > 
@@ -185,18 +211,18 @@ Packages ----------------------------------------------------------------------
 > 
 > dt_rmrf <- dt_rmrf[, .(dateym, rmrf_y3) ]
 > dt_rmrf[ !is.na(rmrf_y3) ]
-     dateym    rmrf_y3
-  1: 195001 0.19164596
-  2: 195002 0.18441326
-  3: 195003 0.17389623
-  4: 195004 0.14728401
-  5: 195005 0.13288460
- ---                  
-788: 201508 0.13987039
-789: 201509 0.15268617
-790: 201510 0.09634409
-791: 201511 0.10151984
-792: 201512 0.07465740
+     dateym   rmrf_y3
+  1: 195001 0.1916460
+  2: 195002 0.1844133
+  3: 195003 0.1738962
+  4: 195004 0.1472840
+  5: 195005 0.1328846
+ ---                 
+800: 201608 0.0992516
+801: 201609 0.1035328
+802: 201610 0.1184933
+803: 201611 0.1160087
+804: 201612 0.1191020
 > ##################################################################################
 > 
 > 
@@ -209,17 +235,17 @@ Packages ----------------------------------------------------------------------
 > dt_predict <- dt_predict[ !is.na(cay) ]
 > dt_predict[]
      dateym         dp     rf    rmrf_y3         cay
-  1: 195203 0.05817138 0.0159 0.18092953  0.01646544
-  2: 195206 0.05739649 0.0170 0.21642173  0.02551783
-  3: 195209 0.05709103 0.0171 0.23193277  0.01633620
-  4: 195212 0.05522191 0.0209 0.22202729  0.02542006
-  5: 195303 0.05455042 0.0201 0.26058722  0.02543387
+  1: 195203 0.05817138 0.0159 0.18092953  0.01510493
+  2: 195206 0.05739649 0.0170 0.21642173  0.02483727
+  3: 195209 0.05709103 0.0171 0.23193277  0.01484008
+  4: 195212 0.05522191 0.0209 0.22202729  0.02216598
+  5: 195303 0.05455042 0.0201 0.26058722  0.02152118
  ---                                                
-252: 201412 0.02094913 0.0003 0.09787760 -0.02747550
-253: 201503 0.02111608 0.0003 0.08734601 -0.03462231
-254: 201506 0.02111542 0.0002 0.09928718 -0.03462943
-255: 201509 0.02153820 0.0002 0.15268617 -0.02656083
-256: 201512 0.02191271 0.0023 0.07465740 -0.03519129
+256: 201512 0.02191273 0.0023 0.07466284 -0.02350179
+257: 201603 0.02265601 0.0029 0.11699368 -0.02321807
+258: 201606 0.02307582 0.0027 0.11884748 -0.01823511
+259: 201609 0.02297658 0.0029 0.10353283 -0.01942223
+260: 201612 0.02284611 0.0051 0.11910203 -0.01902802
 > 
 > fwrite(dt_predict, "./tmp/predict.csv")
 > ##################################################################################
@@ -240,4 +266,4 @@ Packages ----------------------------------------------------------------------
 > 
 > proc.time()
    user  system elapsed 
-  1.400   0.153   2.169 
+  2.462   0.335   4.291