library(ggplot2)
library(lubridate)
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
# Read CSV files
drone_data8 <- read.csv("Drone_data_VLask(Launch 8).csv", stringsAsFactors = FALSE)
new_drone_data8 <- read.csv("New_Drone_Data_VLask(Launch 8).csv", stringsAsFactors = FALSE)
# Inspect the data
head(drone_data8)
## time_since_epoch lat lon altitude_m_MSL wind_direction_deg
## 1 1712587205 45.05322 -71.39005 520.27 241.6336
## 2 1712587206 45.05322 -71.39005 520.31 241.4537
## 3 1712587206 45.05322 -71.39005 520.31 241.4873
## 4 1712587207 45.05322 -71.39005 520.27 241.4849
## 5 1712587207 45.05322 -71.39005 520.21 241.7519
## 6 1712587208 45.05322 -71.39005 520.17 241.9309
## wind_speed_ms timestamp air_temperature_C dew_point_temperature_C
## 1 3.699043 40:05.2 9.88 -2.810304
## 2 3.716799 40:05.7 9.88 -2.767154
## 3 3.727116 40:06.2 9.83 -2.747943
## 4 3.724167 40:06.7 9.81 -2.817960
## 5 3.699454 40:07.2 9.79 -2.832368
## 6 3.684914 40:07.7 9.84 -2.911016
## relative_humidity_perc air_pressure_hPa X Profile.Data. X.1
## 1 40.84774 958.5313 NA Time UTC Time
## 2 40.97883 958.5170 NA [sec] [HH:mm:ss]
## 3 41.17509 958.5310 NA 0 14:30:11
## 4 41.01653 958.4945 NA 2 14:30:13
## 5 41.02765 958.4985 NA 4 14:30:15
## 6 40.65206 958.5361 NA 6 14:30:17
## Team.2.launch.21..14.30Z. X.2 X.3 X.4 X.5 X.6 X.7 X.8 X.9
## 1 P T Hu Ws Wd Geopot Dewp. NA NA
## 2 [hPa] [\xb0C] [%] [m/s] [\xb0] [m] [\xb0C] NA NA
## 3 970.9 8 51 1.3 313 407 -1.5 NA NA
## 4 969.2 7.9 47 2.7 277 421 -2.6 NA NA
## 5 967.4 7.6 44 2.7 277 436 -3.9 NA NA
## 6 965.7 7.4 44 2.7 277 451 -4.1 NA NA
## X.10 X.11 X.12 Dwell.Period.Data. X.13 X.14 X.15
## 1 NA NA NA altitude_m_MSL wind_direction_deg wind_speed_ms timestamp
## 2 NA NA NA 478.98 229.5387115 2.093972206 40:24.2
## 3 NA NA NA 478.91 230.6852112 2.121026516 40:24.7
## 4 NA NA NA 478.89 232.6106644 2.136803389 40:25.2
## 5 NA NA NA 478.91 237.2016373 2.111566067 40:26.2
## 6 NA NA NA 478.89 239.3268356 2.101919889 40:26.7
## X.16
## 1 air_temperature_C
## 2 8.99
## 3 9
## 4 9.06
## 5 9.05
## 6 9.06
head(new_drone_data8)
## air_temperature_BME280 air_temperature_TMP117 relative_humidity_BME280
## 1 16.42000 16.00920 28.22880
## 2 16.34054 15.95261 28.26973
## 3 16.25946 15.89405 28.31027
## 4 16.24000 15.81423 28.35654
## 5 16.21527 15.75427 28.34802
## 6 16.18092 15.70466 28.31748
## wind_speed wind_direction air_pressure air_pressure_int air_temperature_int
## 1 3.479669 242.1625 960.1223 952.3733 55.67040
## 2 3.416935 241.5843 960.1757 952.4787 55.65676
## 3 3.356676 241.0400 960.2193 952.5840 55.64324
## 4 3.302984 240.6851 960.3317 952.6862 55.62538
## 5 3.260545 240.4377 960.4312 952.7893 55.61176
## 6 3.221676 240.2088 960.5174 952.8930 55.60031
## time lat lon vertical_speed flight_number
## 1 1712587210 45.05322 -71.39006 -0.486400 8
## 2 1712587211 45.05322 -71.39006 -1.259279 8
## 3 1712587212 45.05322 -71.39006 -2.034054 8
## 4 1712587212 45.05322 -71.39005 -1.357692 8
## 5 1712587212 45.05322 -71.39005 -1.474198 8
## 6 1712587213 45.05322 -71.39005 -2.077252 8
## dew_point_temperature_BME280 altitude air_temperature_pp
## 1 16.36835 525.22 9.834339
## 2 16.28832 524.22 9.759588
## 3 16.20666 523.22 9.681679
## 4 16.18712 522.22 9.635377
## 5 16.16218 521.22 9.599789
## 6 16.12751 520.22 9.565736
## dew_point_temperature_pp relative_humidity_pp altitude_agl datetime
## 1 -5.985304 32.26389 112 40:10.1
## 2 -6.051595 32.26246 111 40:10.9
## 3 -6.121738 32.25837 110 40:11.6
## 4 -6.145116 32.30109 109 40:12.1
## 5 -6.211840 32.21376 108 40:12.5
## 6 -6.300370 32.06976 107 40:12.9
# Assuming both datasets have a 'temperature' column
summary(drone_data8$air_temperature_C)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 8.58 8.81 9.14 9.21 9.64 9.98 5
summary(new_drone_data8$air_temperature_pp)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 9.349 9.453 9.540 9.661 9.760 10.709
# Visual comparison with boxplots
boxplot(drone_data8$air_temperature_C, new_drone_data8$air_temperature_pp,
names = c("Original", "Post-Processed"),
main = "Temperature Comparison",
ylab = "Temperature")
# Histogram for both datasets
hist(drone_data8$air_temperature_C, col = rgb(1, 0, 0, 0.5), main = "Temperature Distribution", xlab = "Temperature")
hist(new_drone_data8$air_temperature_pp, col = rgb(0, 0, 1, 0.5), add = TRUE)
legend("topright", legend = c("Original", "Post-Processed"), fill = c(rgb(1, 0, 0, 0.5), rgb(0, 0, 1, 0.5)))
# Check for equal length
if (length(drone_data8$air_temperature_C) == length(new_drone_data8$air_temperature_pp)) {
# Perform paired t-test
t_test_result <- t.test(drone_data8$air_temperature_C, new_drone_data8$air_temperature_pp, paired = TRUE)
print(t_test_result)
} else {
print("Datasets have different lengths, can't perform paired t-test.")
}
## [1] "Datasets have different lengths, can't perform paired t-test."
# Convert relevant columns to numeric safely
convert_to_numeric <- function(column) {
suppressWarnings(as.numeric(column))
}
drone_data8$air_temperature_C <- convert_to_numeric(drone_data8$air_temperature_C)
new_drone_data8$air_temperature_pp <- convert_to_numeric(new_drone_data8$air_temperature_pp)
# Determine the shortest length to match both datasets
n <- min(nrow(drone_data8), nrow(new_drone_data8), na.rm = TRUE)
drone_data8 <- drone_data8[1:n, ]
new_drone_data8 <- new_drone_data8[1:n, ]
# Add an index for x-axis
drone_data8$Index <- seq_len(n)
new_drone_data8$Index <- seq_len(n)
# Combine data for plotting
valid_data <- rbind(
data.frame(Index = drone_data8$Index, Temperature = drone_data8$air_temperature_C, Source = "Original"),
data.frame(Index = new_drone_data8$Index, Temperature = new_drone_data8$air_temperature_pp, Source = "New")
)
valid_data <- valid_data[complete.cases(valid_data), ]
# Plot the comparison
ggplot(valid_data, aes(x = Index, y = Temperature, color = Source)) +
geom_line(size = 1.2, alpha = 0.8) +
geom_point(size = 2, alpha = 0.7) +
scale_color_manual(values = c("Original" = "blue", "New" = "red")) +
labs(title = "Comparison of Temperature Measurements",
y = "Temperature (°C)",
color = "Dataset") +
theme_minimal() +
theme(axis.title.x = element_blank(), axis.text.x = element_blank(), axis.ticks.x = element_blank(),
legend.position = "top", legend.title = element_blank(),
panel.grid.major = element_line(color = "grey80"),
panel.grid.minor = element_line(color = "grey90"))
## 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.
