DSFM (version 1.0.1)

AirQuality: Air Quality Data Set (UCI)

Description

Measurements of air quality variables in an Italian city collected over several months in 2004--2005. The data includes hourly averaged responses from chemical sensors embedded in an air quality chemical multi-sensor device.

Usage

data(AirQuality)

Format

A data frame with 9358 observations on the following 15 variables. Some variable names use parentheses, which may need to be quoted with backticks in R.

• Date: Date (in DD/MM/YYYY format)

• Time: Time (in HH.MM.SS format)

• CO.GT.: Carbon Monoxide concentration (mg/m³)

• PT08.S1.CO.: Sensor 1 response

• NMHC.GT.: Non-methane hydrocarbons (µg/m³)

• C6H6.GT.: Benzene concentration (µg/m³)

• PT08.S2.NMHC.: Sensor 2 response

• NOx.GT.: Nitric oxide concentration (ppb)

• PT08.S3.NOx.: Sensor 3 response

• NO2.GT.: Nitrogen dioxide concentration (µg/m³)

• PT08.S4.NO2.: Sensor 4 response

• PT08.S5.O3.: Sensor 5 response

• T: Temperature (°C)

• RH: Relative Humidity (%)

• AH: Absolute Humidity

Some variables contain missing values coded as -200.

Details

The dataset contains air quality data recorded in a densely populated area of an Italian city between March 2004 and February 2005. The data were collected using an array of chemical sensors and meteorological instruments.

This dataset is frequently used for tasks such as missing value imputation, time series analysis, regression, and machine learning model evaluation.

References

De Vito, S., Massera, E., Piga, M., Martinotto, L., & Di Francia, G. (2008).\ Semi-Supervised Learning Techniques in Artificial Olfaction: A Novel Approach to Classification Problems and Drift Counteraction.\ IEEE Sensors Journal, 8(12), 2030--2038.

Examples

data(AirQuality)

# Replace missing values (-200) with NA
AirQuality[AirQuality == -200] <- NA

# Check if there are non-NA values before plotting
if (sum(!is.na(AirQuality$CO.GT.)) > 0) {
  plot(AirQuality$CO.GT., type = "l", ylab = "CO (mg/m³)",
       main = "Hourly CO Concentration")
} else {
  message("No non-NA values in CO.GT. column to plot")
}