From 8977152b8dc46e9629e88c2e7d77fec4b12c9648 Mon Sep 17 00:00:00 2001
From: Tianyu Yao <yaotianyu@berkeley.edu>
Date: Wed, 4 May 2022 18:10:33 -0400
Subject: [PATCH 1/2] update 02

---
 02-data.Rmd | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/02-data.Rmd b/02-data.Rmd
index 60fdb58..c7aa6eb 100644
--- a/02-data.Rmd
+++ b/02-data.Rmd
@@ -6,7 +6,7 @@ Tianyu is responsible to determine the cryptocurencies we are focus on. Juntian
 
 ## Data Collection
 
-We use [coinmarketcap](https://coinmarketcap.com) api to verified top 5 cryptocurrencies by market cap, and then pulled each cryptocurrency dataset from yahoo finance, including 1 year long trading information (2021 May - 2022 May).
+We use [coinmarketcap](https://coinmarketcap.com) api to verified top 5 cryptocurrencies by market cap, and then pulled each cryptocurrency dataset from [coingecko](https://www.coingecko.com), including historical trading information.
 
 ```{r}
 library(tidyverse)
@@ -26,26 +26,23 @@ We then explore multiple financial sources and yahoo finance is the most tangibl
 
 ## Dataset Information
 
-We downloaded 5 datasets and each corresponding to one of the major cryptocurrencies we observed above. Each dataset include 366 rows and 7 columns.
+We downloaded 5 datasets and each corresponding to one of the major cryptocurrencies we observed above. Each dataset include 7 columns and up to 3292 rows.
 
 ### Format
 
 The format of each dataset:
 
-| Date | Open | High | Low | Close | Adj.Close | Volume |
-| :----: | :----: | :----: | :----: | :----: | :----: | :----: |
+| date | price | market_cap | total_volume |
+| :----: | :----: | :----: | :----: |
 | record |
 
 ### Column Details
 
-* Date: date of the crypto record
-* Open: open price
-* High: highest price
-* Close: close price
-* Adj.Close: close price after adjustment
-* Volume: the number of shares traded
+* date: date of the crypto record
+* price: trading price (USD)
+* market_cap: total market cap
+* total_volume: the number of shares traded
 
-(all price are in USD)
 
 ## Issue
 

From 40bb996ecf028d9a75df7471be0be0cf0beb164a Mon Sep 17 00:00:00 2001
From: Tianyu Yao <yaotianyu@berkeley.edu>
Date: Wed, 4 May 2022 18:44:34 -0400
Subject: [PATCH 2/2] update missing value analysis

---
 04-missing.Rmd | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/04-missing.Rmd b/04-missing.Rmd
index 66adb2b..2c9cdd4 100644
--- a/04-missing.Rmd
+++ b/04-missing.Rmd
@@ -5,8 +5,16 @@ library(redav)
 ```
 
 ```{r}
-plot_missing(df.close)
+plot_missing(df.cryto)
 ```
 
-Observed that there is no missing value.
+Observed that volatility and return contains missing values. Take a look into number of missing value in columns we found:
+
+```{r}
+colSums(is.na(df.cryto)) %>%
+  sort(decreasing = TRUE)
+```
+
+
+Calculating volatility requires 15 days data beforehand and return need 1 day  data beforehand. Thus each cryptocurrency return variable missed one rows and volatility missed 15 rows of data. In total we have 75 volatility values and 5 return values missing.