From ec8af72205126027888d79ffc3838144089d764b Mon Sep 17 00:00:00 2001
From: Lishan Gao <gshan068@gmail.com>
Date: Mon, 18 Sep 2023 14:45:12 -0500
Subject: [PATCH] Lishan

---
 .DS_Store                    | Bin 6148 -> 8196 bytes
 submissions/Final Exercise.R |  48 +++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)
 create mode 100644 submissions/Final Exercise.R

diff --git a/.DS_Store b/.DS_Store
index fcf486dbb9ada5725243a6aa0c44d7c8ca46b34e..0d346ef2fbe8b1207f6b97230f1b571edabd2b40 100644
GIT binary patch
delta 800
zcmb`FL2DCH5XWb;o6QSJF~v3p8cW1$+-|m}B3{~P4n2s{EqYK{-gZM>yM1p-HVrj|
zUV5_h5FTDyQAG4Ar5Evo_*F`KQ0Hw^NEW;~%VXv-znOXaXZFqg<q`lWjjmS%kRib%
zeIYlb#i4O)c3$T34zK|fwjqQ&V4Y5rqIMD<s$VjM3`1>CQrE!+j$brRf(aHZf&pt-
z*~aXf)qrof0e9sPJS%vNKe1s1pn->TBA^NG`@gtgvu2C3wsmhRuH1zhI5>wv0J}K%
zE%*>l_EK(+_Y%LgVmSdEBmr@xeM>^;6VTIiSuCf2CZN>j1jO`tagqLNWKoVL{`w<$
zjNU+5y~!8EvV0uLB98UBxkO&dF`nOZd!2A3>kl^!{7z(=zm$}!rS%NSkQ{kszvewV
zqEWZgpzRm(w$6FrUd7aX=C^uIVdf!c5%pQC9T)gs3z3)4edh6AgLj$NiEHi41j&-D
zQz-SD{kmyYD^|Tes8;&-Ewfs=ySOwMWXbI9g$HZSR<O<ZJA5>ng8LNP)W~1C1MxvW
z6`%AQ`5n8>0?wp*$_Z6d)9NKt%As${^~4oCQ^mEJRq-TG2zHd43&P32ul=8~pK0nZ
DJ!H@W

delta 138
zcmZp1XfcprU|?W$DortDU=RQ@Ie-{Mvv5r;6q~50C@2Dw2Z`mR8wMxm=N4=%T+PfV
zGPz2idUB%R&dEVSyC%B{FP$7LB0kwebmqj;9gEpHI0Tu2+JHcS8%Vf<jN4fFoq009
Vj3>x&1}2C_AiEhh$Mei#1^|-V8*2an

diff --git a/submissions/Final Exercise.R b/submissions/Final Exercise.R
new file mode 100644
index 0000000..42e3965
--- /dev/null
+++ b/submissions/Final Exercise.R	
@@ -0,0 +1,48 @@
+# Final Bootcamp Project
+
+# Task 1. import dataseet:
+nys_schools <- read.csv("nys_schools.csv", stringsAsFactors=FALSE)
+nys_acs <- read.csv("nys_acs.csv", stringsAsFactors=FALSE)
+
+# Tasl 2. Explore Data
+summary(nys_schools)
+summary(nys_acs)
+
+# Task 3.1 Replace missing data:
+# Check number of missing data:
+sum(nys_schools == -99)   
+sum(nys_acs == -99)  
+# Replace missing data:
+missing <- apply(nys_schools,1,function(row) any(row==-99))
+nys_schools <-nys_schools[-which(missing),]
+
+# Task 3.2
+nys_acs$rank_poverty[nys_acs$county_per_poverty<=0.10903] <- "Low"
+nys_acs$rank_poverty[(nys_acs$county_per_poverty<0.14929)&(nys_acs$county_per_poverty>0.10903)] <- "Medium"
+nys_acs$rank_poverty[nys_acs$county_per_poverty>= 0.14929] <- "High"
+
+# Task 3.3
+group_by(nys_schools$year)
+zscore<-nys_schools %>% 
+  group_by(year) %>% 
+  mutate(zscore_math=(mean_math_score-mean(mean_math_score))/sd(mean_math_score)) %>% 
+  mutate(zscore_ela=(mean_ela_score-mean(mean_ela_score))/sd(mean_ela_score)) 
+  
+# Task 4. Merge datasets
+merged_df <- merge(nys_acs, zscore, by.x = c("county_name","year"), by.y = c("county_name","year"),all.x = TRUE)
+merged_df
+
+#Task 5.1
+long_merged_energy %>%
+  ggplot() + 
+  geom_line(aes(x=datetime, y=output, group=source, col=source)) + 
+  labs(title="Output by energy source over time", subtitle="Hourly data from September 3-9, 2018", x="Hour", y="Output (MW)")
+
+#Create a line plot that compares generation of wind, solar, and geothermal energy over time.
+# Bonus: Set the line size to 1.5.
+long_merged_energy %>%
+  filter(source=="wind"|source=="solar"|source=="geothermal") %>% 
+  ggplot() + 
+  geom_line(aes(x=datetime, y=output, group=source, col=source), size=1.5) + 
+  labs(title="Wind vs. Solar vs. Geothermal generation", subtitle="Hourly data from September 3-9, 2018", x="Hour", y="Output (MW)")
+