Outliers

Analyzing IoT Data in Python

Matthias Voppichler

IT Developer

Outliers

Reasons why outliers appear in Datasets:

Measurement error
Manipulation
Extreme Events

Outliers

temp_mean = data["temperature"].mean() 
temp_std = data["temperature"].std()

data["mean"] = temp_mean
data["upper_limit"] = temp_mean + (temp_std * 3)
data["lower_limit"] = temp_mean - (temp_std * 3) 

print(data.iloc[0]["upper_limit"])
print(data.iloc[0]["mean"])
print(data.iloc[0]["lower_limit"])

29.513933116002725
14.5345
-0.44493311600272456

Outlier plot

data.plot()

Mean, Upper and lower limits using 3 * standard deviation

Autocorrelation

from statsmodels.graphics import tsaplots

tsaplots.plot_acf(data['temperature'], lags=50)

Picture with autocorrelation

Autocorrelation

from statsmodels.graphics import tsaplots

tsaplots.plot_acf(data['temperature'], lags=50)

Picture with autocorrelation, having an arrow point to lag24

Let's practice!

Analyzing IoT Data in Python