Processed and normalized data set to be used as a cvs file.
Dataset Description
The information was obtained from https://afdc.energy.gov/stations/states and downloaded as an excel .xlxs file.
The original excel file was processed and normalized, these were the main tasks performed:
- The 'Year' column was added to identify which year the data belongs to.
- Replacing NaN values with 0.
- Transformation of float64 columns to int64.
- Generation of new columns with new data from 2014: Propane_Primary, Propane_Secondary, Propane_Total, Hydrogen_Retail, Hydrogen_Non_Retail, Hydrogen_Total, Electric_station, Electric_outlets, Electric_Level1, Electric_Level2, Electric_DC_Fast.
- Elimination of repeated columns: Electric, Hydrogen & Propane.
- 'Renewable Diesel' columns applied to all years.
- Comments were removed.
- The rows with the totals ('Total') were also eliminated.
- Rows with NaN values were deleted.
- Replaced values separated by '/' to '|' to be able to process complementary records.
- Thousand separators removed.
