HussainGhonem/AlgerianFireClassification

The data set is timeseries record for forest fires in two different regions in Algeria Bejaia Region Dataset and Sidi-Bel Abbes Region Dataset. The goal of the classifier is to classify the data in order to give a warning before forest fire erupts. Forest fires is considered a major disaster that threatens the earth’s lungs which cause a lot of pollution and lead to multiple loses in resources both natural and human resource # AlgerianFireClassification The data set is timeseries record for forest fires in two different regions in Algeria Bejaia Region Dataset and Sidi-Bel Abbes Region Dataset. The goal of the classifier is to classify the data in order to give a warning before forest fire erupts. Forest fires is considered a major disaster that threatens the earth’s lungs which cause a lot of pollution and lead to multiple loses in resources both natural and human resource The data set is timeseries record for forest fires in two different regions in Algeria Bejaia Region Dataset and Sidi-Bel Abbes Region Dataset. The goal of the classifier is to classify the data in order to give a warning before forest fire erupts. Forest fires is considered a major disaster that threatens the earth’s lungs which cause a lot of pollution and lead to multiple loses in resources both natural and human resources. The data set was written in a bad way that I did need to clean it before using it. The header of the data set wasn’t fixed to the columns so I had to adjusted to have the columns as the header of the data set. The column’s names had an extra space which I had to fix it by giving new column name which describes the column’s values without spaces. There was a null value in the data since the data was divided to two data sets. The data set was poorly written that in index 167 there's an issue in column DC that it contains the column's value and the value of the column after it so I had to fix this issue also by exploring the error then fixes it. The values of the “Classes” column was mainly two values “fire” and “not fire” but I was surprised to found out that I have 9 different values in the column so I had to fix it. I divided the data into two parts one for each region renamed the “Classes” column’s values 0 for “not fire” and 1 for “fire” for each part then I did concave those parts to represent a single unified data set. The instances of the data set were numeric values having a string type s …