MOTIRAM_DENISHA_HOMEWORK_2
2024-01-29
setwd('C:/Users/Denis/Documents/RStudio')spain_data <- read.fst("spain_data.fst")
spain_data <- spain_data %>%
mutate(
ppltrst = ifelse(ppltrst %in% c(77, 88, 99), NA, ppltrst), # set values 77, 88, and 99 to NA.
)
table(spain_data$ppltrst)##
## 0 1 2 3 4 5 6 7 8 9 10
## 932 568 1399 2083 1907 4682 2756 2802 1699 287 254spain_data$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
spain_data$year[spain_data$essround == i] <- replacements[i]
}
table(spain_data$year)##
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283trust_by_year <- spain_data %>%
group_by(year) %>%
summarize(mean_trust = mean(ppltrst, na.rm = TRUE))
trust_by_year## # A tibble: 10 × 2
## year mean_trust
## <dbl> <dbl>
## 1 2002 4.86
## 2 2004 4.89
## 3 2006 5.12
## 4 2008 4.90
## 5 2010 5.14
## 6 2012 5.13
## 7 2014 4.83
## 8 2016 4.97
## 9 2018 5.09
## 10 2020 4.50ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
geom_line(color = "blue", size = 1) + # Line to show the trend
geom_point(color = "red", size = 3) + # Points to highlight each year's value
labs(title = "Trust in Parliament in Spain (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-10 scale)") +
ylim(0, 10) + # Setting the y-axis limits from 0 to 10
theme_minimal()## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
geom_line(aes(group = 1), color = "blue", size = 1, linetype = "longdash") + # Dashed line for the trend
# geom_point(aes(color = mean_trust), size = 3) + # if you want to try alternative + strive to keep improving
# scale_color_viridis(option = "D", end = 0.9, direction = -1) + # try the alternative, and try to keep improving
labs(title = "Trust in Parliament in Spain (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-10 scale)") +
ylim(4, 5.5) + # change the numbers to truncate more or less or keep the full 0 to 10 scale
theme_minimal() + # Minimal theme for a clean look
theme(legend.position = "none") # Remove the legend
Task 1: The main takeaway based on this visual is that the mean is
mostly stable, peaking in 2010 and reaching minimum value in 2020.The
average trust fluctuates through the entire dataset.
Task 2: The first main takeaway was that the population that felt close to a political decreased significantly after 1960. In Norway, this statistic is always higher than France and for Italy, it is always lower. The second takeaway is that political orientation in France between Rural and Urban areas was that rural areas were almost equally divided on left vs right and Urban areas were more left-leaning.
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
italy_data <- read.fst("italy_data.fst")
italy_data <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Set anything that is not 1 or 2 to NA
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left", # Left-wing (0 to 3)
lrscale %in% 7:10 ~ "Right", # Right-wing (7 to 10)
TRUE ~ NA_character_ # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA
)
)
lrscale_percentages <- italy_data %>% # Begin with the dataset 'italy_data'
filter(!is.na(lrscale), !is.na(gndr)) %>% # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
group_by(gndr, lrscale) %>% # Group the data by 'gender' and 'lrscale' categories
summarise(count = n(), .groups = 'drop') %>% # Summarise each group to get counts, and then drop groupings
mutate(percentage = count / sum(count) * 100) # Calculate percentage for each group by dividing count by total count and multiplying by 100
lrscale_percentages # The resulting dataframe## # A tibble: 4 × 4
## gndr lrscale count percentage
## <chr> <chr> <int> <dbl>
## 1 Female Left 930 23.9
## 2 Female Right 955 24.5
## 3 Male Left 924 23.7
## 4 Male Right 1084 27.8Task 3: Marginal Percentage of Men who feel close to a political party in Italy is 23.7% left-leaning and 27.8% right-leaning.
sweden_data <- read.fst("sweden_data.fst")
sweden_data <- sweden_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Set anything that is not 1 or 2 to NA
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left", # Left-wing (0 to 3)
lrscale %in% 7:10 ~ "Right", # Right-wing (7 to 10)
TRUE ~ NA_character_ # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA
)
)
lrscale_percentages <- sweden_data %>% # Begin with the dataset 'sweden_data'
filter(!is.na(lrscale), !is.na(gndr)) %>% # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
group_by(gndr, lrscale) %>% # Group the data by 'gender' and 'lrscale' categories
summarise(count = n(), .groups = 'drop') %>% # Summarise each group to get counts, and then drop groupings
mutate(percentage = count / sum(count) * 100) # Calculate percentage for each group by dividing count by total count and multiplying by 100
lrscale_percentages # The resulting dataframe## # A tibble: 4 × 4
## gndr lrscale count percentage
## <chr> <chr> <int> <dbl>
## 1 Female Left 2296 23.0
## 2 Female Right 2530 25.3
## 3 Male Left 2062 20.6
## 4 Male Right 3107 31.1lrscale_plot <- ggplot(lrscale_percentages, aes(x = lrscale, y = percentage, fill = lrscale)) +
geom_bar(stat = "identity", position = position_dodge()) + # Dodged bar chart
facet_wrap(~ gndr, scales = "fixed") + # Fixed scales for y-axis across facets
scale_fill_brewer(palette = "Set1") + # Distinct colors for Left and Right
labs(
title = "Political Orientation (Left vs. Right) by Gender in France",
x = "Political Orientation",
y = "Percentage of Respondents",
fill = "Orientation"
) +
theme_minimal() + # Minimal theme for clarity
theme(legend.position = "bottom") # Legend at the bottom
# Display the ggplot object
lrscale_plot
# Create a ggplot object for horizontal bar chart with the specified style
lrscale_plot_v2 <- ggplot(lrscale_percentages,
aes(x = percentage, # Use percentage directly
y = reorder(gndr, -percentage), # Order bars within each gender
fill = gndr)) + # Fill color based on Gender
# Create horizontal bar chart
geom_col() + # Draws the bars using the provided data
coord_flip() + # Flip coordinates to make bars horizontal
# Remove fill color legend
guides(fill = "none") + # Removes legend for the fill aesthetic
# Split the plot based on Political Orientation
facet_wrap(~ lrscale, nrow = 1) + # Separate plots for Left/Right
# Labels and titles for the plot
labs(x = "Percentage of Respondents", # X-axis label
y = NULL, # Remove Y-axis label
title = "Political Orientation by Gender", # Main title
subtitle = "Comparing the percentage distribution of left vs. right for Sweden (2002-2020)") + # Subtitle
# Adjust visual properties of the plot
theme(plot.title = element_text(size = 16, face = "bold"), # Format title
plot.subtitle = element_text(size = 12), # Format subtitle
axis.title.y = element_blank(), # Remove Y-axis title
legend.position = "bottom") # Position the legend at the bottom
# Display the ggplot object
lrscale_plot_v2
hungary_data <- read.fst("hungary_data.fst")
hungary_data <- hungary_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Set anything that is not 1 or 2 to NA
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left", # Left-wing (0 to 3)
lrscale %in% 7:10 ~ "Right", # Right-wing (7 to 10)
TRUE ~ NA_character_ # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA
)
)
# Recode clsprty and geo variables, removing NAs
hungary_data <- hungary_data %>%
mutate(
geo = recode(as.character(domicil),
'1' = "Urban",
'2' = "Urban",
'3' = "Rural",
'4' = "Rural",
'5' = "Rural",
'7' = NA_character_,
'8' = NA_character_,
'9' = NA_character_)
) %>%
filter(!is.na(lrscale), !is.na(geo)) # Removing rows with NA in clsprty or geo
cond <- hungary_data %>%
count(lrscale, geo) %>%
group_by(geo) %>%
mutate(prob = n / sum(n))
cond## # A tibble: 4 × 4
## # Groups: geo [2]
## lrscale geo n prob
## <chr> <chr> <int> <dbl>
## 1 Left Rural 1653 0.349
## 2 Left Urban 893 0.408
## 3 Right Rural 3087 0.651
## 4 Right Urban 1297 0.592# Plot conditional probabilities
plot <- ggplot(cond, aes(x = lrscale, y = prob, fill = lrscale)) +
geom_bar(stat = "identity", position = "dodge") +
scale_fill_viridis_d(name = "Political Orientation") +
labs(y = "Conditional Probability",
x = "Feels Close to a Party",
title = "Conditional Probability of Political Orientation in Hungary",
subtitle = "by Geographical Area: Urban vs. Rural") +
facet_wrap(~ geo, nrow = 1) +
theme(legend.position = "bottom",
legend.title = element_blank(),
plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 12),
axis.text.x = element_text(angle = 45, hjust = 1))
# Display the plot
plot
Task 5: The conditional probability of not feeling close to a political
party in rural Hungary is about 21%.
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.