perform regression over the dataset of global active power values. You are supposed to take the active power values in the past one hour and predict the next active power value.
-
Performed regression over the dataset of global active power values.
-
Implemented Multilayer Perceptron(MLP) as well as a linear regression model for this question.
-
Compared and contrasted the performance of both the models on metrics like Root Mean Squared Error(RMSE), Mean Absolute Percentage Error(MAPE) score.
-
Considered only the Global active power field.
-
Experimented with different architectures(number of hidden layers, activation functions etc) and see the impact on performance.
-
Also experimented on taking some more window of past power values and reported the performance (For example taking a window of two hours instead of one).
The dataset is available at https://archive.ics.uci.edu/ml/machine-learning-databases/00235/household_power_consumption.zip.