diff --git a/ARIMA_2_1_2_simulation.Rmd b/ARIMA_2_1_2_simulation.Rmd
new file mode 100644
index 0000000..0ea161d
--- /dev/null
+++ b/ARIMA_2_1_2_simulation.Rmd
@@ -0,0 +1,90 @@
+---
+title: "Simulate Time Series"
+runtime: shiny
+output: html_document
+---
+
+This is an interactive document.  It interactively simmulates a Moving average order 2 model.
+The same code that could simulate the series non interactively is also included.
+
+Make sure you have the following packages installed on your system.
+```{r,echo=FALSE,message=FALSE}
+# load packages ####
+# if you do not have these packages - install.packages('package name')
+library(tidyquant)
+library(forecast)
+library(quantmod)
+library(dplyr)
+library(tidyverse)
+library(ggplot2)
+library(lubridate)
+library(xts)
+library(shiny)
+```
+
+```{r,echo=FALSE}
+inputPanel(
+  sliderInput("phi_1","Correlation in First MA component: ",min=0, max=0.99999,value=0.5,step = 0.01),
+  sliderInput("phi_2","Correlation in Second MA component: ",min=0, max=0.99999,value=0.5,step = 0.01)
+)
+``` 
+
+```{r,echo=FALSE}
+x <- reactive({ 
+  date <- seq.Date(as.Date("2001/01/01"),as.Date("2013/01/01"),"days") 
+  l <- length(date) 
+  y <-arima.sim(model=list(ma=c(input$phi_1,input$phi_2)),n=l) 
+  d <- data.frame(date=date,y=y) 
+  x <- xts(d[,-1],order.by = d[,1]) 
+})
+```
+
+```{r,echo=FALSE,message=FALSE}
+renderPlot({
+  plot(x())
+})
+``` 
+```{r,echo=FALSE}
+renderPlot({
+acf(x())
+})
+```
+```{r,echo=FALSE}
+renderPlot({
+pacf(x())
+})
+```
+
+```{r}
+renderPrint({
+fit_2 <- auto.arima(x())
+broom::tidy(fit_2) 
+})
+
+```
+
+
+```{r}
+renderPrint({
+  arima(x(),order = c(0,0,2)) 
+})
+```
+
+```{r,echo=FALSE,include=FALSE,eval=FALSE}
+  date <- seq.Date(as.Date("2001/01/01"),as.Date("2013/01/01"),"days") 
+  l <- length(date) 
+  y <-arima.sim(model=list(ma=c(0.9)),n=l) 
+  x <- data.frame(date=date,y=y) 
+  x <- xts(x[,-1],order.by = x[,1]) 
+```
+
+```{r,echo=FALSE,message=FALSE,include=FALSE,eval=FALSE}
+  plot(x)
+``` 
+
+```{r,echo=FALSE,include=FALSE,eval=FALSE}
+print(acf(x))
+print(pacf(x) )
+print(arima(x,order=c(0,0,1)))
+```
+
diff --git a/Introduction to tidyquant.Rmd b/Introduction to tidyquant.Rmd
new file mode 100644
index 0000000..29c2265
--- /dev/null
+++ b/Introduction to tidyquant.Rmd	
@@ -0,0 +1,87 @@
+---
+title: "Introduction to tidyquant"
+runtime: shiny
+output: html_notebook
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(
+	echo = FALSE,
+	message = FALSE,
+	warning = FALSE
+)
+```
+
+```{r}
+library(tidyverse)
+library(magrittr)
+library(tidyquant)
+```
+
+
+Copied from Matt Dancho
+
+tidyquant is a package that integrates other R package resourses for collecting and analyzing financial 
+data into a tidy framework.
+
+Three packages integrated
+: xts, zoo, quantmod, TTR, PerfomanceAnalytics
+
+## tq_index()
+Financial index data can be collected using `tq_index`.  A list of the indexes available can 
+be listed with `tq_index_options()`. 
+
+```{r,include=FALSE}
+index_options <- tq_index_options()
+inputPanel(
+  selectInput("index_options", label = "tq_index_options:",
+              choices = index_options, selected = index_options[1])
+)
+```
+
+```{r,include=FALSE}
+renderDataTable({
+  tq_index(input$index_options)
+})
+```
+
+
+A list of the exchanges available through `tq_exchange()` can be listed using `tq_exchange_options()`
+
+```{r}
+exchange_options <- tq_exchange_options()
+inputPanel(
+  selectInput("exchange_options", label = "tq_exchange_options:",
+              choices = exchange_options, selected = exchange_options[1])
+)
+actionButton("list_exchange","List Selected Exchange")
+```
+
+```{r,include=TRUE}
+exchange_list <-eventReactive(input$list_exchange,{ 
+  tq_exchange(input$exchange_options)  
+})
+exchange_options <-eventReactive(input$list_exchange,{ 
+    exchange_list() %>%  
+    select(symbol,company)  %$% 
+    structure(as.character(symbol), names = as.character(company))
+})
+
+renderDataTable({   exchange_list()  })  
+```
+
+```{r,include=FALSE}
+renderPrint({ exchange_options() })
+```
+
+```{r,include=FALSE}
+renderUI({
+   selectInput("exchange_index", label = "Exchange Index:",
+              choices = exchange_options(), selected = exchange_options()[1]) 
+})
+
+```
+
+
+
+
diff --git a/Time_Series_Analysis.Rmd b/Time_Series_Analysis.Rmd
new file mode 100644
index 0000000..53865c1
--- /dev/null
+++ b/Time_Series_Analysis.Rmd
@@ -0,0 +1,195 @@
+---
+title: "Time Series Analysis"
+author: "Harlan A Nelson"
+output:
+  html_document:
+    df_print: paged
+---
+
+This notebook compiles information from a variety of web sources regarding time series analysis.
+This code is from the tidyquant tutorial.
+
+
+There are a few packages related to time series analysis.  
+* zoo
+* xts
+* quantmod
+* TTR
+* PerformanceAnalytics
+* tidyquant
+
+This notebook starts with tidyquant
+```{r}
+library(tidyquant)
+```
+
+```{r}
+tq_transmute_fun_options()
+```
+```{r}
+data("FANG")
+```
+
+```{r}
+FANG
+```
+```{r}
+FANG_annual_returns <- FANG %>% 
+  group_by(symbol) %>% 
+  tq_transmute(select = adjusted,
+               mutate_fun = periodReturn,
+               period = "yearly",
+               type = "arithmetic")
+FANG_annual_returns
+```
+
+```{r}
+FANG_annual_returns %>% 
+  ggplot(aes(x = date, y = yearly.returns, fill = symbol)) +
+  geom_bar(stat = "identity") +
+  geom_hline(yintercept = 0, color = palette_light()[[1]]) +
+  scale_y_continuous(labels = scales::percent) +
+  labs(title = "FANG: Annual Returns",
+       subtitle = "Get annual returns quickly with tq_transmute!",
+       y = "Annual Returns", x = "") +
+  facet_wrap(~ symbol, ncol = 2) +
+  theme_tq()  +
+  scale_fill_tq()
+```
+
+
+```{r}
+FANG_daily_log_returns <- FANG %>% 
+  group_by(symbol) %>% 
+  tq_transmute(select = adjusted,
+               mutate_fun = periodReturn,
+               period = "daily",
+               type = "log",
+               col_rename = "monthly.returns")
+```
+```{r}
+FANG_daily_log_returns %>% 
+  ggplot() +
+  aes(x = monthly.returns, fill = symbol) +
+  geom_density(alpha = 0.5) +
+  labs(title = "FANG: Charting the Daily Log Returns",
+       x = "Monthly Returns",
+       y = "Density") +
+  theme_tq() +
+  scale_fill_tq() +
+  facet_wrap(~ symbol, ncol = 2)
+```
+
+
+```{r}
+FANG %>% 
+  group_by(symbol) %>% 
+  tq_transmute(select = open:volume,
+               mutate_fun = to.period,
+               period = "months")
+```
+```{r}
+FANG_daily <- FANG %>% 
+  group_by(symbol)
+
+FANG_daily %>% 
+  ggplot() +
+  aes(x = date, y = adjusted, color = symbol) +
+  geom_line(size = 1) +
+  labs(title = "Daily Stock Prices",
+       x     = "", 
+       y     = "Adjusted Proces", 
+       color = "") +
+  facet_wrap( ~ symbol, ncol = 2, scales = "free_y") +
+  scale_y_continuous(labels = scales::dollar) +
+  theme_tq() + 
+  scale_color_tq()
+```
+```{r}
+FANG_monthly <- FANG %>% 
+  group_by(symbol) %>% 
+  tq_transmute(select = adjusted,
+               mutate_fun = to.period,
+               period = "months")
+
+FANG_monthly %>% 
+  ggplot() +
+  aes(x = date, y = adjusted, color = symbol) +
+  geom_line(size = 1) +
+  labs(title = "Monthly Stock Prices",
+       x = "", y = "Adjusted Prices", color = "") +
+  facet_wrap(~ symbol, ncol = 2, scales = "free_y") +
+  scale_y_continuous(labels = scales::dollar) + 
+  theme_tq() + 
+  scale_color_tq()
+
+```
+
+
+```{r}
+FANG_returns_monthly <- FANG %>% 
+  group_by(symbol) %>% 
+  tq_transmute(select     = adjusted,
+               mutate_fun = periodReturn,
+               period     = "monthly")
+```
+```{r}
+baseline_returns_monthly <- "XLK"  %>% 
+  tq_get(get   = "stock.prices",
+         from  = "2013-01-01",
+         to    = "2016-12-31") %>% 
+  tq_transmute(select = adjusted,
+               mutate_fun = periodReturn,
+               period = "monthly")  
+```
+
+```{r}
+returns_joined <- left_join(FANG_returns_monthly,
+                            baseline_returns_monthly,
+                            by = "date")
+returns_joined
+```
+
+
+```{r}
+FANG_rolling_corr <- returns_joined %>% 
+  tq_transmute_xy(x = monthly.returns.x,
+                  y = monthly.returns.y,
+                  mutate_fun = runCor,
+                  n = 6,
+                  col_rename = "rolling.corr.6")
+```
+
+```{r}
+FANG_rolling_corr %>% 
+  ggplot() +
+  aes(x = date, y = rolling.corr.6, color = symbol) +
+  geom_hline(yintercept = 0, color = palette_light()[1]) +
+  geom_line(size = 1) +
+  labs(title = "FANG: Six Month Rolling Correlations to XLK",
+       x = "", y = "Correlation", color = "") +
+  facet_wrap(~ symbol, ncol = 2) +
+  theme_tq() +
+  scale_color_tq()
+```
+```{r}
+names(returns_joined )
+FANG_rolling_corr <- returns_joined %>% 
+  tq_transmute_xy(x=monthly.returns.x,y=monthly.returns.y,
+                  mutate_fun = runCor,
+                  n = 6,
+                  col_rename = "rolling.corr.6")
+```
+
+```{r}
+FANG_rolling_corr %>% 
+  ggplot() +
+  aes(x = date, y = rolling.corr.6, color = symbol) +
+  geom_hline(yintercept = 0, color = palette_light()[1]) +
+  geom_line(size = 1) +
+  labs(title = "FANG: Six Month Rolling Correlations to XLK",
+       x = "", y = "Correlation", color = "") +
+  facet_wrap(~ symbol, ncol = 2) +
+  theme_tq() +
+  scale_color_tq()
+```
diff --git a/Time_Series_Simulation_And_Fitting.Rmd b/Time_Series_Simulation_And_Fitting.Rmd
new file mode 100644
index 0000000..cc23e1e
--- /dev/null
+++ b/Time_Series_Simulation_And_Fitting.Rmd
@@ -0,0 +1,70 @@
+---
+title: "Time Series Simulation and Fitting"
+output: html_notebook
+---
+
+The xts package is called Extensible Time Series.
+Load needed Libraries
+```{r}
+library(glue)
+library(xts)
+```
+Set parameters for the simulation.
+```{r}
+l=10000
+```
+Look at LC_TIME.
+```{r}
+Sys.getlocale("LC_TIME")
+```
+A time series contains two pieces, a `Index` containing a date index and `Data`.
+Use `read.zoo` to read a file from the zoo package.  The file was downloaded from
+`https://raw.githubusercontent.com/cran/zoo/master/vignettes/demo1.txt`
+to my project directory `data`.
+The format uses the standard date formating codes.
+%d
+: Numeric day: 13
+%b
+: Three diget month: Feb
+%Y: Four digit year: 2005
+sep
+: Separator in the text file between the *Time* index and the *Data* value.
+```{r}
+z <- read.zoo(file.path("data","demo1.txt"),sep = "|", format="%d %b %Y")
+glue("The class of z is {class(z)}")
+str(z)
+```
+
+
+```{r}
+dates <-xts::timeBasedSeq('20060204//m',length=l)
+```
+
+Simulate a time series that is observed every day instead of every month using '2006//d'.
+```{r}
+parameters <- list(  model=list(ar=c(0,0,0,0.8), ma=c(0.5)),   n=l)
+y <- ts(do.call(arima.sim,parameters),frequency=4)
+fit_y <- arima(y, order=c(0,0,1), seasonal=list(order=c(1,0,0)), include.mean=FALSE)
+c(coef(fit_y), sigma2 = fit_y$sigma2)
+x <-xts(y,order.by = dates,descr="Simulated xts object")
+colnames(x) <- c("rate")
+attr(x,'frequency') 
+
+# Fit without the frequency.  Seasonal adjustment will be wrong.
+fit_auto <- auto.arima(x)
+broom::tidy(fit_auto)
+sweep::sw_tidy(fit_auto)
+sweep::sw_tidy(x)
+
+attr(x,'frequency') <-4
+attr(x,'frequency') 
+
+fit_x    <- arima(x, order=c(0,0,1), seasonal=list(order=c(1,0,0)),include.mean=FALSE)
+c(coef(fit_x), sigma2 = fit_x$sigma2)
+
+fit_auto <- auto.arima(x)
+broom::tidy(fit_auto)
+install.packages('tsdecomp')
+library(tsdecomp)
+roots.allocation(fit_auto)
+```
diff --git a/lecture_1_time_series.Rmd b/lecture_1_time_series.Rmd
new file mode 100644
index 0000000..db205e8
--- /dev/null
+++ b/lecture_1_time_series.Rmd
@@ -0,0 +1,224 @@
+---
+title: "Time Series Analysis"
+subtitle: Session 1
+output:
+  html_document:
+    df_print: paged
+---
+
+This R notebook provides code to accompany the first *Time Series* lecture.  
+
+Attach libraries.  These packages are referenced below.
+```{r}
+library(devtools)
+library(zoo)
+library(timeSeries)
+library(forecast)
+library(tidyquant)
+library(tidyverse)
+library(plotly)
+```
+
+Reference
+: See *Time Series Data* on the Sollers Site.
+
+# Time Series Analysis
+## Time Series Data.
+Time series data represent observations of an outcome measured over time.  We will start by
+reviewing facilities in R to get time series data and then to plot that data.  
+Later we will learn how to model, predict and forcast time series data.  
+
+We will use examples and note what technique each example demonostrates.  
+## Gas prices. 
+The package `tidyquant` has some useful facilities for getting data.  It tries to provide
+a link between time series analysis packages and tidyverse packages.  
+
+In addition to `tidyquant`, `tidyverse` is a fundemental set of packages.
+The tidyverse is a name given to a set of packages and the concept of keeping data organized in
+a table of one row per observation.  Data analysis requires keeping the data in a useful 
+structure and the tidyverse standard is an attempt to make that happen.
+
+Here the `tidyquant::tq_get` function is used to get the Natual Gas Index(NGI).
+The data will be extracted and plotted. Note the class if the returned object.
+
+```{r}
+ngi <- tq_get("NGI",complete_cases = TRUE)
+class(ngi)
+```
+Take a look at the last few observations of the data frame.
+```{r}
+tail(ngi)
+```
+Note that there is a date field as well as other measures.  The format is supposed to look like a table 
+you would see in a spreadsheet program. It is `tidy`.
+
+```{r}
+class(ngi)
+```
+
+Next we can create a typical time series plot.  We will start with a static plot.
+The function `plot` adjusts for the class of the object being plotted. 
+It is a good start.
+
+```{r}
+plot(ngi)
+```
+We can do better with the plot by constructing our own.
+Here is a fairly popular plotting function `ggplot2`. 
+
+`ggplot` uses aesthetic (aes), which defines how the data is mapped to the grid.
+Then geometry specifies how the data is displayed.
+```{r}
+p <- ngi %>%  
+  ggplot() + 
+  aes(x=date,y=open) +
+  geom_point() + 
+  labs(title = "Natural Gas Index", subtitle = "adjusted",
+       x = "Date",y = "Open Price")
+p
+```
+There is another package that will take the output of `ggplot` and add tool tips.
+The package `plotly` adds some interactive abilities to the plot.  
+`plotly` does a lot of other stuff and is probably better than ggplot.
+`plotly` translates `ggplot` syntax because `ggplot` is so popular, but 
+it also has its own plot layering syntax.
+
+Here a ggplot object is converted to a plotly object.  Notice that you can hover over the
+points and there is a tool bar.  
+```{r}
+ggplotly(p)
+```
+Here is a data set of rain in LA.  There is a data function that can be use to load data sets.
+Package writers can include data using the R Data package. 
+```{r}
+library(TSA)
+data(larain)
+```
+
+`larain` is a time series object. 
+A time series object has a date index and a data column.
+Even in the more advanced representations of a time series, 
+there is a date index and data.  Here there is only one column of data,
+in `tidyquant` there can be many columns of data.  
+Keeping the date or time index associated with the data is what makes 
+the time series structure unique.  This also makes it more difficult to 
+work with than other `data.frame` objects.
+```{r}
+class(larain)
+```
+The index is the date part.
+```{r}
+index(larain)
+```
+The data can be extracted using `coredata`
+```{r}
+coredata(larain)
+```
+One important property of a time series is frequency. 
+A time series has a frequency.  For example if the data is monthly and there is some periodicity,
+then the frequency will be 12.  The larain data is yearly and the frequency is 1.
+```{r}
+frequency(larain)
+```
+
+There is a plot method for this data.  
+```{r}
+plot(larain,main="LA Rain Data")
+```
+
+The function actually called is `plot.zoo`. `plot` is a generic function that looks for the 
+right method to fit the class of the data.
+```{r}
+plot.zoo(larain,main="LA Rain")
+```
+Base r has a `ts` function. `larain` is a ts object.
+There is also a package called `zoo`.  Most more advanced time series objects 
+extend `zoo`.  Extend means the take the methods of zoo and add to them.  
+```{r}
+larain_z <- zoo(larain)
+class(larain_z)
+```
+```{r}
+print(larain_z)
+```
+```{r}
+plot(larain_z,main="LA Rain")
+```
+The zoo package alows you to do much more with the time series data 
+```{r}
+methods(class="ts")
+```
+```{r}
+methods(class="zoo")
+```
+You can see that zoo adds a lot including date functions like `as.POSIXct` and the 
+ability to handle multiple columns and conversion to a data frame using `as.data.frame`.
+
+```{r}
+methods(class="yearmon")
+```
+If you need a `data.frame` for things like ploting, you can use `fortify`.
+The fortify function will separate the date index and the core data so the 
+date can be plotted on the x axis and the core data on the y-axis.
+```{r}
+larain_f <- fortify(larain)
+head(larain_f)
+```
+The result is a `data.frame`.
+```{r}
+class(larain_f)
+```
+```{r}
+larain_f %>% 
+  ggplot() +
+  aes(x=x,y=y) +
+  geom_point() +
+   labs(title = "LA Rain")
+```
+
+There is an extension of the `zoo` package called `xts` for extensible time series.  
+
+```{r}
+larain_zoo <- zoo(larain) 
+class(larain_zoo)
+```
+Here is what it looks like.
+```{r}
+head(larain_zoo)
+```
+There is a `as.data.frame` method in zoo used to convert to a data frame.
+```{r}
+as.data.frame(larain_zoo)
+```
+There is also a fortify method.
+Note that the fortify method produces a column withe the date index whereas 
+`as.data.frame` does not.
+```{r}
+larain_zoo_fortify <- fortify(larain_zoo)
+larain_zoo_fortify
+```
+If is possible to modify the names of the result
+```{r}
+names(larain_zoo_fortify) <- c("Date","rain")
+head(larain_zoo_fortify)
+```
+```{r}
+larain_zoo_fortify %>% 
+  ggplot() +
+  aes(x=Date,y=rain) +
+  geom_point() +  
+  labs(title = "LA Rain")
+```
+There is a package called `forecast` that provides some modeling abilities.
+```{r}
+methods(class="forecast")
+```
+
+```{r}
+forecast(larain_zoo)
+```
+```{r}
+fit <- auto.arima(larain)
+forecast(fit)
+```
+
diff --git a/practice_1.Rmd b/practice_1.Rmd
new file mode 100644
index 0000000..54a815d
--- /dev/null
+++ b/practice_1.Rmd
@@ -0,0 +1,85 @@
+---
+title: "R Notebook"
+output: html_notebook
+---
+
+```{r}
+source('library.R')
+```
+
+```{r}
+tq_get_options()
+```
+```{r}
+from <- today() - years(1)
+AAPL <- tq_get("AAPL", get = "stock.prices", from = from)
+AAPL
+```
+```{r}
+# Get of list of the tq_mutate() options
+tq_mutate_fun_options() %>% 
+  select(zoo) %>% 
+  str()
+```
+```{r}
+AAPL %>% 
+  tq_mutate(ohlc_fun = Cl, mutate_fun = SMA, n = 15) %>% 
+  rename(SMA.15 = SMA) %>% 
+  tq_mutate(ohlc_fun = Cl, mutate_fun = SMA, n = 50) %>% 
+  rename(SMA.50 = SMA)
+```
+```{r}
+AAPL %>% 
+  tq_mutate_xy(x = close, mutate_fun = SMA, n = 15) %>% 
+  rename(SMA.15 = SMA) %>% 
+  tq_mutate_xy(x = close, mutate_fun = SMA, n = 50) %>% 
+  rename(SMA.50 = SMA)
+```
+```{r}
+AAPL %>% 
+  mutate(SMA.15 = SMA(close,n=10))
+```
+
+
+```{r}
+
+```
+
+
+
+
+```{r}
+1 + 4
+```
+
+
+```{r}
+aapl_stock_prices<- tq_get("AAPL")
+```
+```{r}
+mult_stocks <- tq_get(c("FB","AMZN"), 
+get = "stock.prices",
+from = "2016-01-01",
+to  = "2017-01-01")
+```
+
+
+```{r}
+acf(mult_stocks$open)
+```
+```{r}
+pacf(mult_stocks$open )
+```
+```{r}
+stats::Box.test(mult_stocks$open)
+```
+
+
+
+```{r}
+arima(mult_stocks$open,order = (1 0 2))
+```
+
+
+
+
diff --git a/practice_2.Rmd b/practice_2.Rmd
new file mode 100644
index 0000000..099a811
--- /dev/null
+++ b/practice_2.Rmd
@@ -0,0 +1,34 @@
+---
+title: "R Notebook"
+output: html_notebook
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(
+	echo = FALSE,
+	message = FALSE,
+	warning = FALSE
+)
+```
+```{r}
+source('library.R')
+```
+```{r}
+library(tidyverse)
+```
+
+
+```{r}
+count = 1000
+average <- 14
+theta_1 <- 0.7
+theta_2 <- 0.5
+omega <- rnorm(count)
+
+
+test <- tibble(date = seq.Date(from = today("EST") - count +1, to = today("EST"), "days"),
+               average = average,
+               omega = rnorm)
+
+```
+
diff --git a/practice_3.Rmd b/practice_3.Rmd
new file mode 100644
index 0000000..7243eb9
--- /dev/null
+++ b/practice_3.Rmd
@@ -0,0 +1,80 @@
+---
+title: "R Notebook"
+output: html_notebook
+---
+```{r}
+#install_github("vqv/ggbiplot")
+library(ggbiplot)
+data(iris)
+pca.obj <- prcomp(iris[,1:4], center=TRUE, scale.=TRUE)
+str(pca.obj)
+P <- ggbiplot(pca.obj,
+         obs.scale = 1, 
+         var.scale=1,
+         ellipse=T,
+         circle=F,
+         varname.size=3,
+         var.axes=T,
+         groups=iris$Species, #no need for coloring, I'm making the points invisible
+         alpha=0) #invisible points, I add them below
+P$layers <- c(geom_point(aes(color=iris$Species), cex=5), P$layers) #add geom_point in a layer underneath (only way I have to change the size of the points in ggbiplot)
+png(filename="test.png", height=600, width=600)
+print(#or ggsave()
+    P
+)
+dev.off()
+```
+```{r}
+library(magrittr)
+```
+
+```{r}
+#introduce NAs
+iris$Sepal.Length[sample(1:150, 5)] <- NA
+iris$Sepal.Width[sample(1:150, 5)] <- NA
+iris$Petal.Length[sample(1:150, 5)] <- NA
+iris$Petal.Width[sample(1:150, 5)] <- NA
+#pca.obj2 <- prcomp(iris[,1:4], center=TRUE, scale.=TRUE) #cannot use prcomp with NAs
+#source("https://bioconductor.org/biocLite.R")
+#biocLite("pcaMethods")
+library(pcaMethods)
+pca.obj2 <- pcaMethods::pca(iris[,1:4], method="nipals", nPcs=3, center=TRUE, scale.=TRUE)
+class(pca.obj2)  #class pcaRes pcaMethods
+pca.obj2
+str(pca.obj2)
+ggbiplot(pca.obj2)
+pca.obj2 %>% na.omit() %>%  ggbiplot()
+```
+```{r}
+library(pcaMethods)
+```
+```{r}
+data("metaboliteDataComplete")
+mdc <- scale(metaboliteDataComplete, center=TRUE, scale=FALSE)
+length(mdc)
+class(mdc)
+cond <- runif(length(mdc)) < 0.05
+mdcOut <- mdc 
+mdcOut[cond] <- 10
+```
+```{r}
+resSvd <- pca(mdc, method = "svd", nPcs = 5, center = FALSE)
+resSvdOut <- pca(mdcOut, method = "svd", nPcs = 5, center = FALSE)
+resRobSvd <- pca(mdcOut, method = "robustPca", nPcs = 5, center = FALSE)
+```
+
+```{r}
+par(mfrow=c(2,2))
+plot(loadings(resSvd)[,1], loadings(resSvdOut)[,1], 
+xlab = "Loading 1 SVD", ylab = "Loading 1 SVD with outliers")
+plot(loadings(resSvd)[,1], loadings(resRobSvd)[,1],
+xlab = "Loading 1 SVD", ylab = "Loading 1 robustSVD with outliers")
+plot(loadings(resSvd)[,1], loadings(resPPCA)[,1],
+xlab = "Loading 1 SVD", ylab = "Loading 1 PPCA with outliers = NA")
+plot(loadings(resRobSvd)[,1], loadings(resPPCA)[,1],
+xlab = "Loading 1 roubst SVD with outliers", ylab = "Loading 1 svdImpute with outliers = NA")
+
+```
+
+
+
diff --git a/tidyquant_Tutorial.Rmd b/tidyquant_Tutorial.Rmd
new file mode 100644
index 0000000..ce83927
--- /dev/null
+++ b/tidyquant_Tutorial.Rmd
@@ -0,0 +1,87 @@
+---
+title: "tidyquant Tutorial Workthrough"
+subtitle: Work through the tidyquant Tutorial
+output:
+  html_document:
+    df_print: paged
+---
+
+This is a work through of the tutorial at
+source: https://quantdev.ssri.psu.edu/sites/qdev/files/tidyquant_tutorial_Gray.html .
+
+# Install needed Libraries
+```{r}
+library(tidyquant)
+library(ggplot2)
+```
+
+Download data using tq_get
+
+```{r}
+google <- tq_get(x = "GOOG")
+head(google)
+```
+```{r}
+syse <- tq_exchange("NYSE")
+```
+
+```{r}
+head(syse)
+```
+```{r}
+nyse <- syse
+```
+
+```{r}
+nyse$symbol
+```
+```{r}
+nyse$symbol[1]
+```
+
+```{r}
+full <- tq_get(x = nyse$symbol[1], get = "stock.prices")  %>% 
+  add_column(symbol = nyse$symbol[1])
+```
+
+```{r}
+for (s in nyse$symbol[2:20]){
+  single <- try(tq_get(x = s, get = "stock.prices") %>% 
+                  add_column(symbol = s))
+  full <- try(rbind(full, single))
+}
+```
+
+```{r}
+head(full)
+```
+
+```{r}
+str(full)
+```
+```{r}
+unique(full$symbol)
+```
+
+```{r}
+ggplot(data = full) +
+  aes(x = date, y = adjusted, color = symbol) +
+  geom_line(aes(group = symbol)) +
+  theme_classic() +
+  theme(legend.position = "none") +
+  ylab("Adjusted Price") +
+  ggtitle("10 Years of NYSE Stock Prices")
+```
+
+
+
+```{r}
+getwd()
+write.csv(full, file = "nyse_stock_prices.csv")
+```
+
+
+
+
+
+