Cultural consumption places in 2002-2010 St. Petersburg
Arthur Pecherskikh
24 11 2020
What is it about
These graphs were built using the data about the places of cultural consumption in 2002-2010 St. Petersburg gathered from the “Собака” magazine. Not all of them were used for the presentation, though these plots gave my teammates and me some insightful ideas. Let them be here.
Libraries and data
library(dplyr)
library(ggplot2)
library(corrplot)
library(forcats)
library(plyr)
library(cowplot)
library(readxl)data <- read_excel(file.choose("data.xlsx"), sheet = 1)
data <- data %>% select(!`comment (optional)` & !`n (location order)`)
data <- na.omit(data)
summary(data)## name of location address id (magazine issue) year
## Length:742 Length:742 Length:742 Min. :2002
## Class :character Class :character Class :character 1st Qu.:2006
## Mode :character Mode :character Mode :character Median :2007
## Mean :2007
## 3rd Qu.:2009
## Max. :2010
## month format type sphere
## Min. : 1.000 Length:742 Length:742 Length:742
## 1st Qu.: 4.000 Class :character Class :character Class :character
## Median : 7.000 Mode :character Mode :character Mode :character
## Mean : 7.007
## 3rd Qu.:10.000
## Max. :12.000
## cost
## Length:742
## Class :character
## Mode :character
##
##
## cordata <- data %>% mutate_if(is.character, as.factor) %>% mutate_if(is.factor, as.numeric)
corrplot(cor(cordata), method = "square")
Plots (lots of)
data$year = as.character(data$year)
ggplot(data, aes(year)) + geom_bar(fill = "pink") +
theme_classic() +
ggtitle("Records' distribution by years") +
ylab("") +
xlab("")
ggplot(data, aes(year, fill = cost)) +
geom_bar(position = "fill") +
guides(fill=guide_legend("cost")) +
theme_classic() + ggtitle("stacked barchart on years & cost") + xlab("") + ylab("")
data$month = as.factor(data$month)
data <- data %>% arrange(month)
ggplot(data, aes(month)) + geom_bar(fill = "#0F7173") +
theme_classic() +
ggtitle("Records' distribution by month") +
ylab("") +
xlab("month") +
coord_flip()
data$month1 <- data$month
data$month1 <- as.factor(data$month1)
data$month1 <- revalue(data$month1, c("1"="winter", "2" = "winter", "12" = "winter", "3" = "spring", "4" = "spring", "5" = "spring", "6" = "summer", "7" = "summer", "8" = "summer", "9" = "autumn", "10" = "autumn", "11" = "autumn"))
ggplot(data, aes(year, fill = month1)) + geom_bar(position = "fill") +
theme_classic() +
guides(fill=guide_legend("")) +
ggtitle("Records' distribution by years filled with seasons") +
ylab("") +
xlab("") + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89"))
ggplot(data, aes(month, fill = month1)) + geom_bar() + coord_flip() + theme_classic() +
scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) +
ggtitle("Records' distribution by months filled with seasons") +
xlab("") +
ylab("") +
labs(fill = "")
data2002 <- data %>% filter(year == "2002")
data2003 <- data %>% filter(year == "2003")
data2004 <- data %>% filter(year == "2004")
data2005 <- data %>% filter(year == "2005")
data2006 <- data %>% filter(year == "2006")
data2007 <- data %>% filter(year == "2007")
data2008 <- data %>% filter(year == "2008")
data2009 <- data %>% filter(year == "2009")
data2010 <- data %>% filter(year == "2010")
p1 = ggplot(data2002, aes(month, fill = month1)) + geom_bar() + xlab("2002") + ylab("") + theme_classic() + scale_fill_manual(values=c("#F2C078","#7EBC89")) + labs(fill = "")
p2 = ggplot(data2003, aes(month, fill = month1)) + geom_bar() + xlab("2003") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p3 = ggplot(data2004, aes(month, fill = month1)) + geom_bar() + xlab("2004") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p4 = ggplot(data2005, aes(month, fill = month1)) + geom_bar() + xlab("2005") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p5 = ggplot(data2006, aes(month, fill = month1)) + geom_bar() + xlab("2006") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p6 = ggplot(data2007, aes(month, fill = month1)) + geom_bar() + xlab("2007") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p7 = ggplot(data2008, aes(month, fill = month1)) + geom_bar() + xlab("2008") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p8 = ggplot(data2009, aes(month, fill = month1)) + geom_bar() + xlab("2009") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
p9 = ggplot(data2010, aes(month, fill = month1)) + geom_bar() + xlab("2010") + ylab("") + theme_classic() + scale_fill_manual(values = c("#F2C078", "#FAEDCA", "#C1DBB3", "#7EBC89")) + labs(fill = "")
plot_grid(p1, p2, p3, p4, p5, p6, p7, p8, p9) + theme_classic() + ggtitle("Year records' distributions & seasons") + theme(plot.title = element_text(size = 16))
data1 <- data %>% filter(type != "интерьер бутик" & type != "бизнес школа" & type != "workshop" & type != "univeristy" & type != "theater" & type != "studio" & type != "stadium" & type != "show" & type != "services" & type != "school" & type != "public space" & type != "park" & type != "other" & type != "model agency" & type != "hall" & type != "gallery" & type != "cinema" & type != "championship" & type != "cafe" & type != "art space")
ggplot(data1, aes(x = type)) + geom_bar(fill = "pink") + coord_flip() + theme_classic() + xlab("") + ggtitle("Comparing the location types") + ylab("")
data2 <- data %>% filter(sphere != "technology" & sphere != "sport" & sphere != "shopping" & sphere != "health" & sphere != "design" & sphere != "dance" & sphere != "circus" & sphere != "cinema" & sphere != "art, gastronomic" & sphere != "art, design, music, cinema")
ggplot(data2, aes(sphere)) + geom_bar(fill = "pink") + coord_flip() + theme_classic() + xlab("") + ggtitle("Comparing the sphere types")
data_graph <- data %>% filter(type %in% c("bar(s)", "club"))
data_graph$type <-revalue(data_graph$type,c("club"="clubs","bar(s)" = "bars"))
ggplot(data_graph, aes(year, fill = type)) + geom_bar(position = "stack") + theme_classic() + ggtitle("Bars & clubs appearances among the years") + theme(plot.title = element_text(size = 16)) + labs(fill = "") + xlab("") + ylab("") + scale_fill_manual(values = c("pink", "#add8e6"))
ggplot(data_graph, aes(year, fill = type)) + geom_bar(position = "dodge") + theme_classic() + ggtitle("Bars & clubs appearances among the years") + theme(plot.title = element_text(size = 16)) + labs(fill = "") + xlab("") + ylab("") + scale_fill_manual(values = c("pink", "#add8e6"))
hip <- read_excel(file.choose("data.xlsx"), sheet = 1)
hip$type <- revalue(hip$type, c("modern" = "modern art exhibitions", "classic" = "museum funds exhibitions", "festival" = "festivals", "theatre" = "theatrical premieres"))
ggplot(hip, aes(year, n, fill = type)) + geom_bar(stat="identity") +
theme_classic() + ggtitle("Cultural life in St. Petersburg,
2009-2019") +
xlab("") + ylab("") +
scale_fill_manual(values = c("#C4D6B0", "#FFA552", "#BA5624", "#381D2A")) +
labs(fill = "") + labs(caption = "The results from https://www.gov.spb.ru/gov/otrasl/c_culture/culture_statistics/")
yul1 <- filter(data, year == "2002" | year == "2003" | year == "2010")
yul1$year <- revalue(yul1$year, c("2002" = "2002-2003", "2003" = "2002-2003"))
ggplot(yul1, aes(sphere, fill = year)) + geom_bar() + theme_classic() + xlab("") + ylab("") + coord_flip() + ggtitle("Spheres of cultural consumption in the time perspective") + theme(plot.title = element_text(size = 14)) + scale_fill_manual(values = c("#5D576B", "#8884FF"))+ labs(fill = "") + geom_bar() 