knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)
library(readxl)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(knitr)
# Load the data
Valley628 <- read_excel("C:\\Users\\Franco Castagliuolo\\OneDrive - Bentley University\\Neers 24\\Pitchers\\Valley 628\\Valley 628.xlsx")
# Filter the data for the pitcher Kyle Carozza
Kyle_Carozza_data <- Valley628 %>%
filter(Pitcher == "Carozza, Kyle")
# Create a detailed table for each pitch
detailed_pitch_table <- Kyle_Carozza_data %>%
select(AutoPitchType, RelSpeed, SpinRate, SpinAxis, HorzBreak, InducedVertBreak, PitchCall, RelHeight, RelSide, Extension) %>%
rename(
ReleaseSpeed = RelSpeed,
Tilt = SpinAxis,
HorizontalBreak = HorzBreak,
InducedVerticalBreak = InducedVertBreak,
ReleaseHeight = RelHeight,
ReleaseSide = RelSide
) %>%
mutate(
ReleaseSpeed = round(ReleaseSpeed, 2),
SpinRate = round(SpinRate, 2),
Tilt = round(Tilt, 2),
HorizontalBreak = round(HorizontalBreak, 2),
InducedVerticalBreak = round(InducedVerticalBreak, 2),
ReleaseHeight = round(ReleaseHeight, 2),
ReleaseSide = round(ReleaseSide, 2),
Extension = round(Extension, 2),
ClockTilt = round((Tilt / 30) %% 12, 1) # Interpret Tilt as clock face
)
# Display the detailed table
knitr::kable(detailed_pitch_table, caption = "Detailed Pitch Table for Kyle Carozza")
Detailed Pitch Table for Kyle Carozza
| Four-Seam |
89.59 |
2327.11 |
217.23 |
14.09 |
19.77 |
BallCalled |
6.12 |
1.05 |
6.85 |
7.2 |
| Four-Seam |
89.26 |
2319.88 |
216.73 |
14.14 |
20.21 |
StrikeCalled |
6.01 |
1.03 |
7.03 |
7.2 |
| Four-Seam |
90.38 |
2311.51 |
206.17 |
9.96 |
21.46 |
StrikeCalled |
6.01 |
0.92 |
6.91 |
6.9 |
| Four-Seam |
90.11 |
2296.30 |
213.46 |
12.89 |
20.78 |
BallCalled |
6.13 |
0.89 |
6.59 |
7.1 |
| Curveball |
78.60 |
2325.94 |
13.75 |
-1.24 |
-3.51 |
InPlay |
5.86 |
1.11 |
6.36 |
0.5 |
| Four-Seam |
88.60 |
2283.80 |
218.14 |
12.57 |
17.32 |
InPlay |
6.01 |
1.01 |
6.76 |
7.3 |
| Four-Seam |
88.61 |
2316.44 |
192.71 |
4.61 |
21.74 |
FoulBallFieldable |
6.11 |
1.05 |
6.89 |
6.4 |
| Four-Seam |
90.61 |
2344.47 |
202.10 |
7.80 |
20.53 |
FoulBallNotFieldable |
5.97 |
1.13 |
6.71 |
6.7 |
| Curveball |
78.55 |
2409.47 |
41.62 |
-5.30 |
-4.53 |
BallinDirt |
5.83 |
1.23 |
6.45 |
1.4 |
| Four-Seam |
88.57 |
2213.63 |
212.34 |
11.80 |
19.88 |
InPlay |
5.94 |
1.17 |
7.06 |
7.1 |
| Curveball |
76.95 |
2437.66 |
41.63 |
-7.30 |
-7.00 |
StrikeCalled |
5.90 |
1.17 |
6.26 |
1.4 |
| Four-Seam |
89.84 |
2330.10 |
212.62 |
13.67 |
22.59 |
InPlay |
6.00 |
1.02 |
6.73 |
7.1 |
| Four-Seam |
88.90 |
2277.85 |
211.07 |
10.27 |
18.14 |
StrikeSwinging |
5.99 |
1.06 |
7.00 |
7.0 |
| Four-Seam |
85.85 |
2239.11 |
209.21 |
10.26 |
19.55 |
StrikeCalled |
6.09 |
0.83 |
7.21 |
7.0 |
| Curveball |
79.37 |
2496.42 |
45.45 |
-5.32 |
-4.09 |
BallCalled |
5.77 |
1.08 |
6.40 |
1.5 |
| Four-Seam |
88.82 |
2229.89 |
207.57 |
9.58 |
19.45 |
StrikeSwinging |
5.94 |
0.97 |
6.84 |
6.9 |
| Curveball |
77.10 |
2377.30 |
32.39 |
-4.88 |
-6.34 |
StrikeSwinging |
5.84 |
1.11 |
5.97 |
1.1 |
| Curveball |
75.17 |
2224.08 |
22.62 |
-4.81 |
-9.99 |
StrikeCalled |
5.82 |
1.03 |
6.34 |
0.8 |
| Four-Seam |
90.09 |
2281.46 |
208.41 |
10.69 |
21.10 |
BallCalled |
5.96 |
0.94 |
6.59 |
6.9 |
| Four-Seam |
89.97 |
2247.55 |
206.64 |
9.71 |
20.63 |
BallCalled |
5.98 |
1.02 |
6.57 |
6.9 |
| Curveball |
77.46 |
2225.52 |
10.14 |
-1.11 |
-4.71 |
StrikeSwinging |
5.83 |
1.02 |
6.38 |
0.3 |
| Four-Seam |
85.65 |
2172.59 |
213.94 |
11.53 |
18.52 |
BallCalled |
5.95 |
1.08 |
6.67 |
7.1 |
| Four-Seam |
86.33 |
2202.87 |
217.96 |
12.08 |
16.82 |
BallCalled |
5.94 |
1.09 |
6.72 |
7.3 |
| Four-Seam |
88.61 |
2227.74 |
203.88 |
9.34 |
22.46 |
BallCalled |
6.03 |
1.06 |
6.71 |
6.8 |
| Four-Seam |
86.89 |
2225.15 |
208.36 |
10.01 |
19.91 |
BallCalled |
6.05 |
0.73 |
6.72 |
6.9 |
| Curveball |
77.28 |
2396.78 |
22.66 |
-3.81 |
-7.51 |
BallinDirt |
5.76 |
0.87 |
6.19 |
0.8 |
| Four-Seam |
88.37 |
2176.56 |
203.44 |
6.99 |
17.35 |
FoulBallNotFieldable |
5.96 |
0.98 |
6.87 |
6.8 |
| Curveball |
76.90 |
2391.48 |
18.57 |
-2.59 |
-6.29 |
StrikeSwinging |
5.75 |
1.21 |
6.41 |
0.6 |
| Curveball |
77.43 |
2441.28 |
40.54 |
-7.75 |
-7.70 |
InPlay |
5.78 |
1.20 |
5.97 |
1.4 |
| Four-Seam |
88.47 |
2273.85 |
206.41 |
9.18 |
19.72 |
StrikeSwinging |
5.96 |
0.93 |
6.74 |
6.9 |
| Four-Seam |
88.06 |
2234.33 |
205.49 |
9.62 |
21.40 |
BallCalled |
6.05 |
0.92 |
6.72 |
6.8 |
| Four-Seam |
88.17 |
2194.50 |
207.62 |
9.31 |
19.03 |
BallCalled |
5.96 |
1.08 |
6.94 |
6.9 |
| Four-Seam |
88.16 |
2218.21 |
207.92 |
10.70 |
21.49 |
BallCalled |
5.92 |
0.90 |
6.80 |
6.9 |
| Four-Seam |
87.64 |
2222.22 |
208.68 |
10.21 |
20.07 |
BallCalled |
5.93 |
1.08 |
6.76 |
7.0 |
# Calculate the total number of pitches
total_pitches <- nrow(detailed_pitch_table)
# Create a summary table
pitch_summary <- detailed_pitch_table %>%
group_by(AutoPitchType) %>%
summarise(
TotalPitches = n(),
Usage = sprintf("%.2f%%", n() / total_pitches * 100),
Balls = sum(PitchCall == "BallCalled"),
Strikes = sum(PitchCall != "BallCalled"), # Count everything not a ball as a strike
BallPercentage = sprintf('%.2f%%', Balls / TotalPitches * 100),
StrikePercentage = sprintf('%.2f%%', Strikes / TotalPitches * 100),
AvgVelocity = round(mean(ReleaseSpeed, na.rm = TRUE), 2),
AvgSpinRate = round(mean(SpinRate, na.rm = TRUE), 2),
AvgInducedVertBreak = round(mean(InducedVerticalBreak, na.rm = TRUE), 2),
AvgHorzBreak = round(mean(HorizontalBreak, na.rm = TRUE), 2),
AvgTilt = round(mean(Tilt, na.rm = TRUE), 2),
AvgClockTilt = round(mean(ClockTilt, na.rm = TRUE), 1), # Clock face interpretation
AvgReleaseHeight = round(mean(ReleaseHeight, na.rm = TRUE), 2),
AvgReleaseSide = round(mean(ReleaseSide, na.rm = TRUE), 2),
AvgExtension = round(mean(Extension, na.rm = TRUE), 2)
) %>%
select(AutoPitchType, Usage, everything())
# Display the total number of pitches
cat("Total number of pitches thrown: ", total_pitches, "\n")
## Total number of pitches thrown: 34
# Display the summary table
knitr::kable(pitch_summary, caption = "Summary Pitch Table for Kyle Carozza")
Summary Pitch Table for Kyle Carozza
| Curveball |
29.41% |
10 |
1 |
9 |
10.00% |
90.00% |
77.48 |
2372.59 |
-6.17 |
-4.41 |
28.94 |
1 |
5.81 |
1.1 |
6.27 |
| Four-Seam |
70.59% |
24 |
12 |
12 |
50.00% |
50.00% |
88.56 |
2256.96 |
20.00 |
10.46 |
209.09 |
7 |
6.00 |
1.0 |
6.81 |
# Calculate maximum fastball velocity
max_fb_velocity <- detailed_pitch_table %>%
filter(AutoPitchType %in% c("Four-Seam", "Two-Seam", "Sinker", "Cutter")) %>%
summarise(MaxFBVelocity = max(ReleaseSpeed, na.rm = TRUE)) %>%
pull(MaxFBVelocity)
# Display the maximum fastball velocity
cat("Kyle Carozza maximum FB velocity: ", max_fb_velocity, "mph\n")
## Kyle Carozza maximum FB velocity: 90.61 mph
# Prepare data for plotting pitch locations
pitch_location_data <- Kyle_Carozza_data %>%
select(AutoPitchType, PlateLocHeight, PlateLocSide, PitchCall) %>%
rename(
PitchHeight = PlateLocHeight,
PitchSide = PlateLocSide
) %>%
mutate(
SwingTake = ifelse(PitchCall %in% c("StrikeSwinging", "FoulBallNonSwinging", "FoulBallFieldable", "FoulBallNotFieldable", "InPlay"), "Swing", "Take"),
Chase = ifelse(SwingTake == "Swing" & (PitchSide < -0.75 | PitchSide > 0.75 | PitchHeight < 1.5 | PitchHeight > 3.5), "Chase", "Non-Chase")
)
# Create the scatter plot with specified strike zone boxes
ggplot(pitch_location_data, aes(x = PitchSide, y = PitchHeight, color = SwingTake, shape = Chase)) +
geom_point(size = 3) + # Increase point size
geom_rect(aes(xmin = -0.5, xmax = 0.5, ymin = 1.75, ymax = 3.25), fill = NA, color = "red", linetype = "solid", size = 1) + # Red box
geom_rect(aes(xmin = -0.75, xmax = 0.75, ymin = 1.5, ymax = 3.5), fill = NA, color = "black", linetype = "solid", size = 1) + # Black box
geom_rect(aes(xmin = -1.25, xmax = 1.25, ymin = 1.25, ymax = 3.75), fill = NA, color = "gray", linetype = "solid", size = 1) + # Gray box
scale_x_continuous(limits = c(-2, 2)) +
scale_y_continuous(limits = c(0, 5)) +
coord_fixed(ratio = 1) + # Adjust ratio to shrink vertical distance
labs(title = "Pitch Locations for Kyle Carozza",
x = "Horizontal Location (feet)",
y = "Vertical Location (feet)",
color = "Swing/Take",
shape = "Chase") +
facet_wrap(~ AutoPitchType) + # Create individual graphs for each pitch type
theme_minimal() +
theme(
legend.position = "right",
panel.grid.major = element_line(color = "grey80"),
panel.grid.minor = element_line(color = "grey90"),
axis.text = element_text(color = "black"),
axis.title = element_text(color = "black"),
plot.title = element_text(color = "black"),
legend.background = element_rect(fill = "white", color = NA),
legend.key = element_rect(fill = "white", color = NA),
legend.text = element_text(color = "black"),
legend.title = element_text(color = "black")
)
# Create the scatter plot for horizontal and vertical breaks
ggplot(detailed_pitch_table, aes(x = HorizontalBreak, y = InducedVerticalBreak, color = AutoPitchType)) +
geom_point(size = 3) + # Increase point size
labs(title = "Pitch Movement for Kyle Carozza",
x = "Horizontal Break (inches)",
y = "Induced Vertical Break (inches)",
color = "Pitch Type") +
theme_minimal() +
theme(
legend.position = "right",
panel.grid.major = element_line(color = "grey80"),
panel.grid.minor = element_line(color = "grey90"),
axis.text = element_text(color = "black"),
axis.title = element_text(color = "black"),
plot.title = element_text(color = "black"),
legend.background = element_rect(fill = "white", color = NA),
legend.key = element_rect(fill = "white", color = NA),
legend.text = element_text(color = "black"),
legend.title = element_text(color = "black")
)
