The data in this example in files named
Admissions data shows all the admission to the facility in the entire run, as well as whether or not the patient admitted imported the disease.
After some iterations of the simulation, the last row of data in this file is not complete. If you see errors when you read in the data, check the .txt file and, if necessary, delete the last record.
# Read admissions.txt and show descriptive info and stats
# Read admissions.txt
admissions_df <- read.table('../data/admissions.demo.txt', header=TRUE, sep=',', stringsAsFactors=FALSE)
# Show structure
cat('Admissions data:')Admissions data:head(admissions_df) time patientid importation
1 -1.00 75 false
2 0.00 76 false
3 0.05 77 false
4 0.06 78 false
5 0.20 79 false
6 1.46 80 falseThis dataset shows the time and patient id of a detection via the clinical (symptoms-base) route. DetectionCount is a check column. In some edge cases a patient may be detected, treated, recovered and detected again, in which case detection count for that patient would be >1.
#read clinical_detections and give descriptive stats.
clinical_detections_df <- read.table('../data/clinicalDetection.demo.txt', header=TRUE, sep=',', stringsAsFactors=FALSE)
#show sample of rows:
head(clinical_detections_df) Time DetectedPatientID DetectionCount
1 26.83 151 1
2 30.60 107 1
3 30.89 137 1
4 31.02 111 1
5 33.95 108 1
6 44.13 198 1#show descriptive stats
summary(clinical_detections_df) Time DetectedPatientID DetectionCount
Min. : 26.83 Min. : 107 Min. :1
1st Qu.:1388.93 1st Qu.: 4909 1st Qu.:1
Median :2651.58 Median : 9331 Median :1
Mean :2695.46 Mean : 9516 Mean :1
3rd Qu.:4014.90 3rd Qu.:14249 3rd Qu.:1
Max. :5467.43 Max. :19151 Max. :1 The output file daily_population_stats.txt shows the total number of patients in the facility on a given day, the number of those who are colonized, detected and isolation. By default, it starts at the end of the burn-in period. There is another sanity check embedded in this file; it should always be the case that detected == isolated. We isolate detected patients, and we don’t isolate anybody else.
# Read daily_population_stats.txt (comma-delimited)
daily_pop_df <- read.table('../data/daily_population_stats.demo.txt', header=TRUE, sep=',', stringsAsFactors=FALSE)
# Show structure and summary
cat('Daily population stats:')Daily population stats:head(daily_pop_df) Time total_population colonized detected isolated
1 3651 96 44 4 4
2 3651 96 44 4 4
3 3652 93 45 6 6
4 3652 93 45 6 6
5 3653 90 43 6 6
6 3653 90 43 6 6cat('\nSummary statistics:')
Summary statistics:summary(daily_pop_df) Time total_population colonized detected
Min. :3651 Min. : 67.00 Min. :20.00 Min. : 0.000
1st Qu.:4107 1st Qu.: 87.00 1st Qu.:33.00 1st Qu.: 3.000
Median :4563 Median : 92.00 Median :38.00 Median : 5.000
Mean :4563 Mean : 92.63 Mean :37.67 Mean : 5.101
3rd Qu.:5019 3rd Qu.: 99.00 3rd Qu.:42.00 3rd Qu.: 7.000
Max. :5475 Max. :128.00 Max. :56.00 Max. :11.000
isolated
Min. : 0.000
1st Qu.: 3.000
Median : 5.000
Mean : 5.101
3rd Qu.: 7.000
Max. :11.000 # Time-series plot: population, colonized, detected vs time
library(ggplot2)
# Assume columns: Time, total_population, colonized, detected
ggplot(daily_pop_df, aes(x = Time)) +
geom_line(aes(y = `total_population`, color = 'Population')) +
geom_line(aes(y = colonized, color = 'Colonized')) +
geom_line(aes(y = detected, color = 'Detected')) +
labs(title = 'Daily Population Time Series', x = 'Time', y = 'Count', color = 'Legend') +
theme_minimal()
These are the distribution of daily samples of the total population of the sim, the colonized and detected counts.
# Histogram of Total Population
ggplot(daily_pop_df, aes(x = total_population)) +
geom_histogram(binwidth = 1, fill = 'skyblue', color = 'black') +
labs(title = 'Histogram of Total Population', x = 'total_population', y = 'Frequency') +
theme_minimal()
# Histogram of Colonized
ggplot(daily_pop_df, aes(x = colonized)) +
geom_histogram(binwidth = 1, fill = 'orange', color = 'black') +
labs(title = 'Histogram of Colonized', x = 'colonized', y = 'Frequency') +
theme_minimal()
# Histogram of Detected
ggplot(daily_pop_df, aes(x = detected)) +
geom_histogram(binwidth = 1, fill = 'purple', color = 'black') +
labs(title = 'Histogram of Detected', x = 'detected', y = 'Frequency') +
theme_minimal()
These represent patients who’s colonization with the organism has ceased.
# Read decolonization.demo.txt (comma-delimited)
decolonization_df <- read.table('../data/decolonization.demo.txt', header=TRUE, sep=',', stringsAsFactors=FALSE)
# Show structure and summary
cat('Decolonization events:')Decolonization events:head(decolonization_df) time decolonized_patient_id
1 23.89 159
2 28.70 96
3 30.87 75
4 39.25 114
5 48.79 183
6 57.77 194cat('\nSummary statistics:')
Summary statistics:summary(decolonization_df) time decolonized_patient_id
Min. : 23.89 Min. : 75
1st Qu.:1475.74 1st Qu.: 5145
Median :2817.95 Median : 9883
Mean :2775.86 Mean : 9751
3rd Qu.:4091.78 3rd Qu.:14463
Max. :5470.71 Max. :19207 # Read detection_verification.demo.txt (comma-delimited)
detection_verification_df <- read.table('../data/detection_verification.demo.txt', header=TRUE, sep=',', stringsAsFactors=TRUE)
# Show structure and summary
cat('Detection verification events:')Detection verification events:head(detection_verification_df) time patient_id source colonized detection_count
1 26.83 151 CLINICAL true 1
2 30.60 107 CLINICAL true 1
3 30.89 137 CLINICAL true 1
4 31.02 111 CLINICAL true 1
5 33.95 108 CLINICAL true 1
6 44.13 198 CLINICAL true 1cat('\nSummary statistics:')
Summary statistics:summary(detection_verification_df) time patient_id source colonized detection_count
Min. : 26.83 Min. : 107 CLINICAL:1541 true:1541 Min. :1
1st Qu.:1388.93 1st Qu.: 4909 1st Qu.:1
Median :2651.58 Median : 9331 Median :1
Mean :2695.46 Mean : 9516 Mean :1
3rd Qu.:4014.90 3rd Qu.:14249 3rd Qu.:1
Max. :5467.43 Max. :19151 Max. :1 This is every surveillance test run after the end of the burn-in period.
# Read surveillance.demo.txt (comma-delimited)
# Check if file exists and has data
if (file.size('../data/surveillance.demo.txt') > 0) {
surveillance_df <- read.table('../data/surveillance.demo.txt', header=TRUE, sep=',', stringsAsFactors=FALSE)
# Show structure and summary
cat('Surveillance events:')
head(surveillance_df)
cat('\nSummary statistics:')
summary(surveillance_df)
} else {
cat('No surveillance events in this dataset.\n')
}No surveillance events in this dataset.# Read transmission.demo.txt (comma-delimited)
transmission_df <- read.table('../data/transmissions.demo.txt', header=TRUE, sep=',', stringsAsFactors=FALSE)Warning in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,
: number of items read is not a multiple of the number of columns# Show structure and summary
cat('Transmission events:')Transmission events:head(transmission_df) time from_patientID to_patientID
1 6.96 100 92
2 7.71 99 75
3 9.26 110 108
4 9.77 90 89
5 10.34 100 107
6 12.39 92 76cat('\nSummary statistics:')
Summary statistics:summary(transmission_df) time from_patientID to_patientID
Min. : 6.96 Min. : 90 Min. : 75
1st Qu.:1310.46 1st Qu.: 4580 1st Qu.: 4641
Median :2582.28 Median : 9087 Median : 9117
Mean :2539.28 Mean : 8972 Mean : 8992
3rd Qu.:3792.70 3rd Qu.:13426 3rd Qu.:13456
Max. :5069.72 Max. :17848 Max. :17878
NA's :1 NA's :1