From c2e656552ef400955d2460272c5f3ef54e4365f5 Mon Sep 17 00:00:00 2001
From: ningxixu <33641600+ningxixu@users.noreply.github.com>
Date: Wed, 24 Jan 2018 08:13:21 -0500
Subject: [PATCH] Rename dplyr1 to data manipulation with dplyr

---
 data manipulation with dplyr | 28 ++++++++++++++++++++++++++++
 dplyr1                       | 28 ----------------------------
 2 files changed, 28 insertions(+), 28 deletions(-)
 create mode 100644 data manipulation with dplyr
 delete mode 100644 dplyr1

diff --git a/data manipulation with dplyr b/data manipulation with dplyr
new file mode 100644
index 0000000..36edbef
--- /dev/null
+++ b/data manipulation with dplyr
@@ -0,0 +1,28 @@
+wine = read.csv('wine.csv', stringsAsFactors = F, encoding = 'UTF-8')
+install.packages('dplyr')
+install.packages('ggplot2')
+library(dplyr)
+library(ggplot2)
+wine = wine[,-1]
+wine = wine %>% select(-c(description)) 
+wine %>% group_by(country) %>% summarize(count=n()) %>% arrange(desc(count))
+
+selected_countries = wine %>% group_by(country) %>% summarize(count=n()) %>% arrange(desc(count)) %>% top_n(10) %>% select(country)
+selected_countries = as.character(selected_countries$country)
+select_points=wine %>% filter(country %in% selected_countries) %>% select(country, points) %>% arrange(country)
+ggplot(wine, aes(points,price)) + geom_point() + geom_smooth()
+ggplot(select_points, aes(x=reorder(country,points,median),y=points)) + geom_boxplot(aes(fill=country)) + xlab("Country") + ylab("Points") + ggtitle("Distribution of Top 10 Wine Producing Countries") + theme(plot.title = element_text(hjust = 0.5))
+wine %>% filter(!(country %in% selected_countries)) %>% group_by(country) %>%  summarize(median=median(points)) %>% arrange(desc(median)) 
+top=wine %>% group_by(country) %>% summarize(median=median(points)) %>% arrange(desc(median))
+top=as.character(top$country)
+both=intersect(top,selected_countries)
+
+topwine = wine %>% group_by(variety) %>% summarize(number=n()) %>% arrange(desc(number)) %>% top_n(10)
+topwine=as.character(topwine$variety)
+
+wine %>% filter(variety %in% topwine) %>% group_by(variety)%>% summarize(median=median(points)) %>% ggplot(aes(reorder(variety,median),median)) + geom_col(aes(fill=variety)) + xlab('Variety') + ylab('Median Point') + scale_x_discrete(labels=abbreviate)
+
+top15percent=wine %>% arrange(desc(points)) %>% filter(points > quantile(points, prob = 0.85))
+cheapest15percent=wine %>% arrange(price) %>% head(nrow(top15percent))
+goodvalue = intersect(top15percent,cheapest15percent)
+goodvalue
diff --git a/dplyr1 b/dplyr1
deleted file mode 100644
index 36edbef..0000000
--- a/dplyr1
+++ /dev/null
@@ -1,28 +0,0 @@
-wine = read.csv('wine.csv', stringsAsFactors = F, encoding = 'UTF-8')
-install.packages('dplyr')
-install.packages('ggplot2')
-library(dplyr)
-library(ggplot2)
-wine = wine[,-1]
-wine = wine %>% select(-c(description)) 
-wine %>% group_by(country) %>% summarize(count=n()) %>% arrange(desc(count))
-
-selected_countries = wine %>% group_by(country) %>% summarize(count=n()) %>% arrange(desc(count)) %>% top_n(10) %>% select(country)
-selected_countries = as.character(selected_countries$country)
-select_points=wine %>% filter(country %in% selected_countries) %>% select(country, points) %>% arrange(country)
-ggplot(wine, aes(points,price)) + geom_point() + geom_smooth()
-ggplot(select_points, aes(x=reorder(country,points,median),y=points)) + geom_boxplot(aes(fill=country)) + xlab("Country") + ylab("Points") + ggtitle("Distribution of Top 10 Wine Producing Countries") + theme(plot.title = element_text(hjust = 0.5))
-wine %>% filter(!(country %in% selected_countries)) %>% group_by(country) %>%  summarize(median=median(points)) %>% arrange(desc(median)) 
-top=wine %>% group_by(country) %>% summarize(median=median(points)) %>% arrange(desc(median))
-top=as.character(top$country)
-both=intersect(top,selected_countries)
-
-topwine = wine %>% group_by(variety) %>% summarize(number=n()) %>% arrange(desc(number)) %>% top_n(10)
-topwine=as.character(topwine$variety)
-
-wine %>% filter(variety %in% topwine) %>% group_by(variety)%>% summarize(median=median(points)) %>% ggplot(aes(reorder(variety,median),median)) + geom_col(aes(fill=variety)) + xlab('Variety') + ylab('Median Point') + scale_x_discrete(labels=abbreviate)
-
-top15percent=wine %>% arrange(desc(points)) %>% filter(points > quantile(points, prob = 0.85))
-cheapest15percent=wine %>% arrange(price) %>% head(nrow(top15percent))
-goodvalue = intersect(top15percent,cheapest15percent)
-goodvalue
--
libgit2 0.26.0