pull

exercise-1/exercise.R

@@ -2,108 +2,107 @@
 
 # Install and load `ggplot2`
 # You will also want to load `dplyr`
-install.packages("ggplot2")
 library("ggplot2")
 library("dplyr")
 
 # For this exercise you'll be working with the `diamonds` data set included in the ggplot2 library
 # Use `?diamonds` to get more information about this data set (including the column descriptions
 # Also check the _column names_ and the _number of rows_ in the data set
-?diamonds
-colnames(diamonds)
-nrow(diamonds)
 
-# This data set has a lot of rows. To make things a bit more readable, 
+
+# This data set has a lot of rows. To make things a bit more readable,
 # use dplyr's `sample_n()` function to get a random 1000 rows from the data set
 # Store this sample in a variable `diamonds.sample`
 diamonds.sample <- sample_n(diamonds, 1000)
+ggplot(data = diamonds.sample) +
+  geom_point(mapping = aes(x = carat, y = price, color = clarity))
 
 # Start by making a new `ggplot` with the `diamonds.sample` as the data (no geometry yet)
 # What do you see?
-ggplot(data = diamonds.sample)
 
-# Draw a scatter plot (with point geometry) with for the `diamonds.sample` set, 
+
+# Draw a scatter plot (with point geometry) with for the `diamonds.sample` set,
 # with the `carat` mapped to the x-position and `price` mapped to the y-position.
-ggplot(data = diamonds.sample) +
-  geom_point(mapping = aes(x = carat, y = price))
+
 
 # Draw the same plot as above, but color each of the points based on their clarity.
-ggplot(data = diamonds.sample) +
-  geom_point(mapping = aes(x = carat, y = price, color=clarity))
+
 
 # Draw the same plot as above, but for the entire `diamonds` data set. Note this may take
 # a few seconds to generate.
 ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = carat, y = price, color=clarity))
+  geom_point(mapping = aes(x = carat, y = price, color = clarity))
+
 
 # Draw another scatter plot for `diamonds.sample` of price (y) by carat (x),
 # but with all of the dots colored "blue".
 # Hint: you'll need to set the color channel, not map a value to it!
-ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = carat, y = price), color="blue")
+ggplot(data = diamonds.sample) +
+  geom_point(mapping = aes(x = carat, y = price), color = "blue")
 
 # Draw a scatter plot for `diamonds.sample` of `price` by `carat`, where each
 # point has an aesthetic _shape_ based on the diamond's `cut`.
-ggplot(data = diamonds.sample) +
-  geom_point(mapping = aes(x = carat, y = price, shape=cut))
+ggplot(data = diamonds.sample) + 
+  geom_point(mapping = aes(x = carat, y = price, shape = cut))
 
 # Draw a scatter plot for `diamonds.sample` of *`cut`* by `carat`, where each
 # point has an aesthetic _size_ based on the diamond's *`price`*
-ggplot(data = diamonds.sample) +
-  geom_point(mapping = aes(x = carat, y = cut, size=price))
+ggplot(data = diamonds.sample) + 
+  geom_point(mapping = aes(x = carat, y = cut, size = price, color = price))
+
 
 # Try coloring the above plot based on the diamond's price!
-ggplot(data = diamonds.sample) +
-  geom_point(mapping = aes(x = carat, y = cut, size=price, color=price))
+
 
 # Draw a line plot (with line geometry) for `diamonds.sample`. The x-position should be mapped to
 # carat, y-position to price, and color to carat.
-ggplot(data = diamonds.sample) +
-  geom_line(mapping = aes(x = carat, y = price, color=cut))
+ggplot(data = diamonds.sample) + 
+  geom_line(mapping = aes(x = carat, y = price, color = carat))
+
 
 # That's kind of messy. Try using `smooth` geometry instead.
-ggplot(data = diamonds.sample) +
-  geom_smooth(mapping = aes(x = carat, y = price, color=cut))
+ggplot(data = diamonds.sample) + 
+  geom_smooth(mapping = aes(x = carat, y = price, color = carat))
+
 
 # Draw a plot with bar geometry (a bar chart), mapping the diamond's `cut` to the x-axis
-ggplot(data = diamonds) +  # full data set example
+ggplot(data = diamonds.sample) + 
   geom_bar(mapping = aes(x = cut))
 
+
 # Add an aesthetic property that will _fill_ each bar geometry based on the `clarity` of the diamonds
 # What kind of chart do you get?
-ggplot(data = diamonds.sample) +
-  geom_bar(mapping = aes(x = cut, fill=clarity))
+ggplot(data = diamonds.sample) + 
+  geom_bar(mapping = aes(x = cut, fill = clarity))
 
 # Draw a histogram of diamond prices.
 # Try mapping each bar based on clarity as well!
-ggplot(data = diamonds.sample) +
-  geom_histogram(aes(x=price, fill=clarity))
+ggplot(data = diamonds.sample) + 
+  geom_histogram(mapping = aes(x = price, fill = clarity))
+
 
 # (For a more traditional "bell-curve", make a histogram of diamond `depths`)
 
 # Draw a plot of the `diamonds.sample` data (price by carat), with both points for each
 # diamond AND smoothed lines for each cut (hint: in a separate color)
 # Making the points have some `alpha` transparency will make the plot look nicer
+ggplot(data = diamonds.sample) + 
+  geom_point(mapping = aes(x = carat, y = price, alpha = 0.8)) +
+  geom_smooth(mapping = aes(x = carat, y = price, alpha = 0, color = cut))
+
 
 # multiple geoms (point & smooth)
-ggplot(data = diamonds.sample) +
-  geom_point(mapping = aes(x = carat, y = price, color=cut), alpha=0.1) + 
-  geom_smooth(mapping = aes(x = carat, y = price, color=cut), se=FALSE)
+
 
 ## Bonus
 # Draw a bar chart of average diamond prices by clarity, and include "error bars" marking
 # the standard error of each measurement.
 #
-# You can calculate standard error as the _standard deviation_ divided by the square root 
+# You can calculate standard error as the _standard deviation_ divided by the square root
 # of the number of measurements (prices)
 
 # Start by creating a data frame `diamond.summary` that includes summarized data for each clarity group.
 # Your summary data shuld include the mean price and the standard error of the price.
-diamond.summary <- diamonds %>% 
-  group_by(clarity) %>% 
-  summarize(mean = mean(price), sd = sd(price), se = sd/sqrt(length(price)))
+
 
 # Then draw the plot. The error bars should stretch from the mean-error to the mean+error.
-ggplot(data = diamond.summary, mapping = aes(x=clarity, y=mean)) +
-  geom_bar(aes(fill=clarity), stat="identity") +
-  geom_errorbar(data = diamond.summary, aes(ymin=(mean-se), ymax=(mean+se)))

exercise-2/exercise.R

@@ -6,27 +6,26 @@ library("ggplot2")
 
 # For this exercise you will again be working with the `diamonds` data set.
 # Use `?diamonds` to review details about this data set
-?diamonds
 
 
 ## Statistical Transformations
 
 # Draw a bar chart of the diamonds data, organized by cut
 # The height of each bar is based on the "count" (number) of diamonds with that cut
-ggplot(data = diamonds) +
-  geom_bar(mapping = aes(x=cut))
+ggplot(data = diamonds) + 
+  geom_bar(mapping = aes(x = cut))
 
 # Use the `stat_count` to apply the statistical transformation "count" to the diamonds
 # by cut. You do not need a separate geometry layer!
-ggplot(data = diamonds) +
-  stat_count(mapping = aes(x=cut))
+ggplot(data = diamonds) + 
+  stat_count(mapping = aes(x = cut))
 
 # Use the `stat_summary` function to draw a chart with a summary layer.
 # Map the x-position to diamond `cut`, and the y-position to diamond `depth`
 # Bonus: use `min` as the function ymin, `max` as the function ymax, and `median` as the function y
-ggplot(data = diamonds) +
-  stat_summary(mapping = aes(x = cut, y = depth),
-               fun.ymin = min, fun.ymax = max, fun.y = median)
+ggplot(data = diamonds) + 
+  stat_summary(mapping = aes(x = cut, y = depth), fun.ymin = min, fun.ymax = max, fun.y = median)
+
 
 
 ## Position Adjustments
@@ -40,87 +39,68 @@ ggplot(data = diamonds) +
 ggplot(data = diamonds) +
   geom_bar(mapping = aes(x = cut, fill = clarity), position = "fill")
 
-# Draw the same chart again, but with each element positioned to "dodge" each other
+# Draw the same chart again, but with each element positioned to "dodge" each other" the y axis
 ggplot(data = diamonds) +
-  geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")
+geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")
 
 # Draw a plot with point geometry with the x-position mapped to `cut` and the y-position mapped to `clarity`
 # This creates a "grid" grouping the points
-ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = cut, y = clarity))
+
 
 # Use the "jitter" position adjustment to keep the points from all overlapping!
 # (This works a little better with a sample of diamond data, such as from the previous exercise).
-ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = cut, y = clarity), position = "jitter")
+
 
 
 ## Scales
 
 # Draw a "boxplot" (with `geom_boxplot()`) for the diamond's price (y) by color (x)
-ggplot(data = diamonds) +
-  geom_boxplot(mapping = aes(x=color, y=price))
+
 
 # This has a lot of outliers, making it harder to read. To fix this, draw the same plot but
 # with a _logarithmic_ scale for the y axis.
-ggplot(data = diamonds) +
-  geom_boxplot(mapping = aes(x=color, y=price)) +
-  scale_y_log10()
+
 
 # For another version, draw the same plot but with `violin` geometry instead of `boxplot` geometry!
 # How does the logarithmic scale change the data presentation?
-ggplot(data = diamonds) +
-  geom_violin(mapping = aes(x=color, y=price)) +
-  scale_y_log10()
+
 
 # Another interesting plot: draw a plot of the diamonds price (y) by carat (x), using a heatmap of 2d bins
 # (geom_bin2d)
 # What happens when you make the x and y channels scale logarithmically?
-ggplot(data = diamonds) +
-  geom_bin2d(mapping = aes(x=carat, y=price)) +
-  scale_x_log10() +
-  scale_y_log10()
+
 
 # Draw a scatter plot for the diamonds  price (y) by carat (x). Color each point by the clarity
 # (Remember, this will take a while. Use a sample of the diamonds for faster results)
-ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = carat, y = price, color = clarity))
+
 
 # Change the color of the previous plot using a ColorBrewer scale of your choice. What looks nice?
-ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = carat, y = price, color = clarity)) +
-  scale_color_brewer(palette = "Spectral")
+
 
 
 ## Coordinate Systems
 
 # Draw a bar chart with x-position and fill color BOTH mapped to cut
 # For best results, SET the `width` of the geometry to be 1 (fill plot, no space between)
 # You can save this to a variable for easier modifications
-bar <- ggplot(data = diamonds) +
-  geom_bar(mapping = aes(x = cut, fill = cut), width=1)
-bar
+
 
 # Draw the same chart, but with the coordinate system flipped
-bar + coord_flip()
+
 
 # Draw the same chart, but in a polar coordinate system. Now you have a Coxcomb chart!
-bar + coord_polar()
+
 
 
 ## Facets
 
 # Take the scatter plot of price by carat data (colored by clarity) and add _facets_ based on
 # the diamond's `color`
-ggplot(data = diamonds) +
-  geom_point(mapping = aes(x = carat, y = price, color = clarity)) +
-  scale_color_brewer(palette = "Spectral") +
-  facet_wrap(~color)
+
 
 
 ## Saving Plots
 
 # Use the `ggsave()` function to save one of your plots (the most recent one generated) to disk.
 # Name the output file "my-plot.png".
 # Make sure you've set the working directory!!
-ggsave("my-plot.png")