DS607_Merge_Classification_Data

library(tidyverse)

## ── Attaching packages ──────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.1.0       ✔ purrr   0.3.0  
## ✔ tibble  2.0.1       ✔ dplyr   0.8.0.1
## ✔ tidyr   0.8.2       ✔ stringr 1.4.0  
## ✔ readr   1.3.1       ✔ forcats 0.4.0

## ── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(stringr)
library(lubridate)

## 
## Attaching package: 'lubridate'

## The following object is masked from 'package:base':
## 
##     date

library(kableExtra)

## 
## Attaching package: 'kableExtra'

## The following object is masked from 'package:dplyr':
## 
##     group_rows

library(knitr)

Overview

This markdown merges the corrected (of 102 x 5 data frame of FOMC statements) with the classification data. We assume the fomc_data.rds and the raw classification file is located in the working directory.

d4<-readRDS(file = "fomc_data.rds")
dim(d4)

## [1] 102   5

str(d4)

## 'data.frame':    102 obs. of  5 variables:
##  $ year             : chr  "2007" "2007" "2007" "2007" ...
##  $ statement.dates  : chr  "20070131" "20070321" "20070509" "20070628" ...
##  $ links            : chr  "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070131a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070321a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070509a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070618a.htm" ...
##  $ statement.content: chr  "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ ...
##  $ statement.length : int  181 167 168 179 207 130 260 304 281 255 ...

Raw Classification File

We explicitly override the Date column to be imported as string because we will join these two dataframes on this data.

classificationFile = "Classification_FOMC_Statements.csv"

cls = read_csv(classificationFile , col_types = cols( Date = col_character() ) )

cls %>% rename( Economic.Growth = "Economic Growth", Employment.Growth = "Employment Growth", Medium.Term.Rate = "Medium Term Rate", Policy.Rate = "Policy Rate") -> cls

str(cls)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 102 obs. of  8 variables:
##  $ Index            : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ Date2            : chr  "1/31/07" "3/21/07" "5/9/07" "6/28/07" ...
##  $ Date             : chr  "20070131" "20070321" "20070509" "20070628" ...
##  $ Economic.Growth  : chr  "Up" "Flat" "Down" "Up" ...
##  $ Employment.Growth: chr  "Flat" "Flat" "Flat" "Flat" ...
##  $ Inflation        : chr  "Down" "Up" "Up" "Down" ...
##  $ Medium.Term.Rate : chr  "Hawk" "Hawk" "Hawk" "Hawk" ...
##  $ Policy.Rate      : chr  "Flat" "Flat" "Flat" "Flat" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Index = col_double(),
##   ..   Date2 = col_character(),
##   ..   Date = col_character(),
##   ..   `Economic Growth` = col_character(),
##   ..   `Employment Growth` = col_character(),
##   ..   Inflation = col_character(),
##   ..   `Medium Term Rate` = col_character(),
##   ..   `Policy Rate` = col_character()
##   .. )

Merging FOMC data and Classification Data

d4 %>% inner_join( cls , by = c("statement.dates" = "Date")) %>%
  mutate( date_mdy = mdy(Date2)) %>%
  select(Index, 
         year ,
         statement.dates, 
         links, 
         statement.content, 
         statement.length ,
         date_mdy,
         Economic.Growth,
         Employment.Growth,
         Inflation,
         Medium.Term.Rate,
         Policy.Rate ) -> mgData


str(mgData)

## 'data.frame':    102 obs. of  12 variables:
##  $ Index            : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ year             : chr  "2007" "2007" "2007" "2007" ...
##  $ statement.dates  : chr  "20070131" "20070321" "20070509" "20070628" ...
##  $ links            : chr  "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070131a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070321a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070509a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070618a.htm" ...
##  $ statement.content: chr  "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ ...
##  $ statement.length : int  181 167 168 179 207 130 260 304 281 255 ...
##  $ date_mdy         : Date, format: "2007-01-31" "2007-03-21" ...
##  $ Economic.Growth  : chr  "Up" "Flat" "Down" "Up" ...
##  $ Employment.Growth: chr  "Flat" "Flat" "Flat" "Flat" ...
##  $ Inflation        : chr  "Down" "Up" "Up" "Down" ...
##  $ Medium.Term.Rate : chr  "Hawk" "Hawk" "Hawk" "Hawk" ...
##  $ Policy.Rate      : chr  "Flat" "Flat" "Flat" "Flat" ...

Let us view the sample data from the statements

mgData %>% select( Index, date_mdy, Economic.Growth, Employment.Growth, Inflation, Medium.Term.Rate, Policy.Rate) %>% kable() %>% kable_styling(bootstrap_options = c("hover", "striped")) %>%
scroll_box(width = "90%", height = "300px")

Index	date_mdy	Economic.Growth	Employment.Growth	Inflation	Medium.Term.Rate	Policy.Rate
1	2007-01-31	Up	Flat	Down	Hawk	Flat
2	2007-03-21	Flat	Flat	Up	Hawk	Flat
3	2007-05-09	Down	Flat	Up	Hawk	Flat
4	2007-06-28	Up	Flat	Down	Hawk	Flat
5	2007-08-07	Up	Flat	Flat	Hawk	Flat
6	2007-08-17	Down	Flat	Flat	Dove	Flat
7	2007-09-18	Flat	Flat	Down	Dove	Lower
8	2007-10-31	Up	Flat	Down	Dove	Lower
9	2007-12-11	Down	Flat	Down	Dove	Lower
10	2008-01-22	Down	Down	Flat	Dove	Lower
11	2008-01-30	Down	Down	Flat	Dove	Lower
12	2008-03-18	Down	Down	Up	Dove	Lower
13	2008-04-30	Down	Down	Up	Dove	Lower
14	2008-06-25	Up	Down	Up	Hawk	Flat
15	2008-08-05	Up	Down	Up	Hawk	Flat
16	2008-09-16	Down	Down	Up	Dove	Flat
17	2008-10-08	Down	Flat	Down	Dove	Lower
18	2008-10-29	Down	Flat	Down	Dove	Lower
19	2008-12-16	Down	Down	Down	Dove	Lower
20	2009-01-28	Down	Down	Down	Dove	Flat
21	2009-03-18	Down	Down	Down	Dove	Flat
22	2009-04-29	Down	Down	Flat	Dove	Flat
23	2009-06-24	Down	Down	Down	Dove	Flat
24	2009-08-12	Flat	Down	Down	Dove	Flat
25	2009-09-23	Up	Down	Down	Dove	Flat
26	2009-11-04	Up	Down	Down	Dove	Flat
27	2009-12-16	Up	Flat	Down	Dove	Flat
28	2010-01-27	Flat	Flat	Down	Dove	Flat
29	2010-03-16	Flat	Flat	Down	Dove	Flat
30	2010-04-28	Flat	Flat	Flat	Dove	Flat
31	2010-06-23	Flat	Up	Down	Dove	Flat
32	2010-08-10	Down	Down	Down	Dove	Flat
33	2010-09-21	Down	Down	Flat	Dove	Flat
34	2010-11-03	Flat	Flat	Down	Dove	Flat
35	2010-12-14	Flat	Down	Down	Dove	Flat
36	2011-01-26	Flat	Down	Down	Dove	Flat
37	2011-03-15	Up	Flat	Up	Dove	Flat
38	2011-04-27	Up	Flat	Up	Dove	Flat
39	2011-06-22	Flat	Down	Up	Dove	Flat
40	2011-08-09	Flat	Down	Down	Dove	Flat
41	2011-09-21	Flat	Down	Down	Dove	Flat
42	2011-11-02	Up	Down	Flat	Dove	Flat
43	2011-12-13	Up	Flat	Down	Dove	Flat
44	2012-01-25	Up	Up	Flat	Dove	Flat
45	2012-03-13	Up	Up	Flat	Dove	Flat
46	2012-04-25	Up	Up	Up	Dove	Flat
47	2012-06-20	Up	Flat	Down	Dove	Flat
48	2012-08-01	Down	Flat	Down	Dove	Flat
49	2012-09-13	Up	Flat	Flat	Dove	Flat
50	2012-10-24	Up	Flat	Up	Dove	Flat
51	2012-12-12	Up	Up	Flat	Dove	Flat
52	2013-01-30	Flat	Up	Flat	Dove	Flat
53	2013-03-20	Up	Up	Flat	Dove	Flat
54	2013-05-01	Up	Up	Flat	Dove	Flat
55	2013-06-19	Up	Up	Down	Dove	Flat
56	2013-07-31	Up	Up	Flat	Dove	Flat
57	2013-09-18	Up	Up	Flat	Dove	Flat
58	2013-10-30	Up	Up	Flat	Dove	Flat
59	2013-12-18	Up	Up	Flat	Dove	Flat
60	2014-01-29	Up	Up	Flat	Dove	Flat
61	2014-03-19	Down	Up	Flat	Dove	Flat
62	2014-04-30	Up	Up	Flat	Dove	Flat
63	2014-06-18	Up	Up	Flat	Dove	Flat
64	2014-07-30	Up	Up	Up	Dove	Flat
65	2014-09-17	Up	Up	Flat	Dove	Flat
66	2014-10-29	Up	Up	Down	Dove	Flat
67	2014-12-17	Up	Up	Down	Dove	Flat
68	2015-01-28	Up	Up	Down	Dove	Flat
69	2015-03-18	Flat	Up	Down	Dove	Flat
70	2015-04-29	Down	Flat	Flat	Dove	Flat
71	2015-06-17	Up	Up	Flat	Dove	Flat
72	2015-07-29	Up	Up	Flat	Dove	Flat
73	2015-09-17	Up	Up	Down	Dove	Flat
74	2015-10-28	Up	Flat	Down	Dove	Flat
75	2015-12-16	Up	Up	Flat	Dove	Raise
76	2016-01-27	Down	Up	Down	Dove	Flat
77	2016-03-16	Up	Up	Up	Dove	Flat
78	2016-04-27	Down	Up	Flat	Dove	Flat
79	2016-06-15	Up	Flat	Down	Dove	Flat
80	2016-07-27	Up	Up	Flat	Dove	Flat
81	2016-09-21	Up	Up	Flat	Dove	Flat
82	2016-11-02	Flat	Up	Flat	Dove	Flat
83	2016-12-14	Up	Up	Up	Dove	Raise
84	2017-02-01	Up	Up	Up	Dove	Flat
85	2017-03-15	Up	Up	Flat	Hawk	Raise
86	2017-05-03	Down	Up	Down	Hawk	Flat
87	2017-06-14	Up	Up	Down	Hawk	Raise
88	2017-07-26	Up	Up	Down	Hawk	Flat
89	2017-09-20	Up	Up	Down	Hawk	Flat
90	2017-11-01	Up	Up	Down	Hawk	Flat
91	2017-12-13	Up	Up	Down	Hawk	Raise
92	2018-01-31	Up	Up	Flat	Hawk	Flat
93	2018-03-21	Up	Up	Up	Hawk	Raise
94	2018-05-02	Up	Up	Flat	Hawk	Flat
95	2018-06-13	Up	Up	Flat	Hawk	Raise
96	2018-08-01	Up	Up	Flat	Hawk	Flat
97	2018-09-26	Up	Up	Flat	Hawk	Raise
98	2018-11-08	Up	Up	Flat	Hawk	Flat
99	2018-12-19	Up	Up	Flat	Hawk	Raise
100	2019-01-30	Up	Up	Down	Dove	Flat
101	2019-03-20	Flat	Flat	Down	Dove	Flat
102	2019-05-01	Up	Up	Flat	Dove	Flat

Exporting the Merged Data Frame

We export the merged dataframe as a single RDS object for research use.

rds_filename = "fomc_merged_data_v2.rds"

saveRDS(mgData, file = rds_filename)

Let us also validate its contents.

mgData_validated = readRDS(rds_filename)

str(mgData_validated)

## 'data.frame':    102 obs. of  12 variables:
##  $ Index            : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ year             : chr  "2007" "2007" "2007" "2007" ...
##  $ statement.dates  : chr  "20070131" "20070321" "20070509" "20070628" ...
##  $ links            : chr  "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070131a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070321a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070509a.htm" "https://www.federalreserve.gov/newsevents/pressreleases/monetary20070618a.htm" ...
##  $ statement.content: chr  "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ "The Federal Open Market Committee decided today to keep its target for the federal funds rate at 5-1/4 percent."| __truncated__ ...
##  $ statement.length : int  181 167 168 179 207 130 260 304 281 255 ...
##  $ date_mdy         : Date, format: "2007-01-31" "2007-03-21" ...
##  $ Economic.Growth  : chr  "Up" "Flat" "Down" "Up" ...
##  $ Employment.Growth: chr  "Flat" "Flat" "Flat" "Flat" ...
##  $ Inflation        : chr  "Down" "Up" "Up" "Down" ...
##  $ Medium.Term.Rate : chr  "Hawk" "Hawk" "Hawk" "Hawk" ...
##  $ Policy.Rate      : chr  "Flat" "Flat" "Flat" "Flat" ...

DS607_Merge_Classification_Data_v2

Alexander Ng

5/11/2019

Overview

Raw Classification File

Merging FOMC data and Classification Data

Exporting the Merged Data Frame