hw10

# Load libraries
library(xts)

## Loading required package: zoo

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

library(quantmod)

## Loading required package: TTR

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(dplyr)

## 
## ######################### Warning from 'xts' package ##########################
## #                                                                             #
## # The dplyr lag() function breaks how base R's lag() function is supposed to  #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or       #
## # source() into this session won't work correctly.                            #
## #                                                                             #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop           #
## # dplyr from breaking base R's lag() function.                                #
## #                                                                             #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning.  #
## #                                                                             #
## ###############################################################################

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:xts':
## 
##     first, last

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(readr)

# Set date range
begin_date <- "2013-01-01"
end_date <- "2015-12-31"

# Stock list (AEZS removed)
stock_namelist <- c("AAPL", "AMD", "ADI", "ABBV", "A", "APD", "AA", "CF")

# Initialize an empty list to store stock data
stock_list <- list()

# Download adjusted close prices and store them in the list
for (symbol in stock_namelist) {
  tryCatch({
    stock_data <- Ad(getSymbols(symbol, from = begin_date, to = end_date, auto.assign = FALSE))
    colnames(stock_data) <- symbol
    stock_list[[symbol]] <- stock_data
  }, error = function(e) {
    message(paste("Skipping:", symbol, "— not available."))
  })
}

# Check if we have valid data
if (length(stock_list) == 0) {
  stop("No stock data available. Check tickers or date range.")
}

# Merge all stock data into one xts object
data_set <- do.call(merge, stock_list)

# Check the merged data columns
print("✅ Data columns after merge:")

## [1] "✅ Data columns after merge:"

print(colnames(data_set))

## [1] "AAPL" "AMD"  "ADI"  "ABBV" "A"    "APD"  "AA"   "CF"

# Calculate log returns
X <- diff(log(data_set), na.pad = FALSE)

# Display log returns
print("✅ First few rows of log returns (X):")

## [1] "✅ First few rows of log returns (X):"

print(head(X))

##                    AAPL          AMD          ADI         ABBV            A
## 2013-01-03 -0.012702479 -0.015936577 -0.016267645 -0.008291678  0.003575422
## 2013-01-04 -0.028249359  0.039375128 -0.017947173 -0.012713275  0.019555361
## 2013-01-07 -0.005899884  0.030420658  0.003053182  0.002033301 -0.007259161
## 2013-01-08  0.002687289  0.000000000 -0.010370959 -0.022004723 -0.008022627
## 2013-01-09 -0.015752325 -0.015094611 -0.002609039  0.005620620  0.026649245
## 2013-01-10  0.012320080 -0.003809616  0.012041307  0.002945649  0.007354887
##                      APD           AA           CF
## 2013-01-03 -0.0035001848  0.008859488 -0.004740209
## 2013-01-04  0.0133508004  0.020731800  0.022151682
## 2013-01-07 -0.0009223412 -0.017429398 -0.003753247
## 2013-01-08  0.0018453074  0.000000000 -0.014768444
## 2013-01-09  0.0133907530 -0.002200072  0.034375871
## 2013-01-10 -0.0009103671 -0.012188648  0.014917725

cat("\n✅ Dimensions of X: ", nrow(X), "rows ×", ncol(X), "columns\n")

## 
## ✅ Dimensions of X:  754 rows × 8 columns

# Load Fama-French 5-Factor data (adjust your file path)
ff_data <- read_csv("/cloud/project/F-F_Research_Data_5_Factors_2x3 (1).CSV", skip = 4)

## Rows: 82 Columns: 6

## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl  (5): 0.0862, 0.0204, 0.0247, 0.0018, -0.0191
## date (1): 2018-04-30
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

ff_data <- ff_data[!is.na(as.numeric(ff_data[[1]])), ]

# Rename columns (5 factors only)
colnames(ff_data)[1:6] <- c("Date", "Mkt_RF", "SMB", "HML", "RMW", "CMA")

# Convert types
ff_data <- ff_data %>%
  mutate(
    Date = ymd(as.character(Date)),
    Mkt_RF = as.numeric(Mkt_RF) / 100,
    SMB = as.numeric(SMB) / 100,
    HML = as.numeric(HML) / 100,
    RMW = as.numeric(RMW) / 100,
    CMA = as.numeric(CMA) / 100
  )

# Create xts object for Fama-French factors
fama_lib <- xts(ff_data[, c("Mkt_RF", "SMB", "HML", "RMW", "CMA")], order.by = ff_data$Date)

# Align Fama-French factors with stock returns
F_FamaFrench <- fama_lib[index(X)]

# Check Fama-French data