You have extracted two data series from FRED, namely the U$.$S$.$ Economic Policy Uncertainty Index $($EPU$)$ and the U$.$S$.$ daily implied volatility index $($VIX$),$ using pandas$\_$datareader. Now, you want to perform a logarithmic transformation on both series. Considering the following Python code snippet, which choice correctly explains the purpose of each line of code?

import numpy as np

data$\_$log$\_$transformed $=$ np$.$log$($data$.$dropna$())$

The import numpy as np line imports the NumPy library to use its logarithmic function, and data$\_$log$\_$transformed $=$ np$.$log$($data$.$dropna$())$ applies the log transformation to data after removing all missing values to avoid errors during calculation.

The import numpy as np line imports the NumPy library to use its logarithmic function, and data$\_$log$\_$transformed $=$ np$.$ data.dropna$())$ attempts to transform the missing values to zeros before applying the log transformation, which will result in negative infinity for those entries.

The import numpy as np line imports the pandas library for data manipulation, and data$\_$log$\_$transformed $=$ np$.$ dat$.$dropna$())$ applies a logarithmic transformation which also scales the data to a standard normal distribution.

The import numpy as np line is used to access pandas' internal functions, and data $lo{g}_{{?}_{}}$ transformed $=$ np$.log($data$.$dropna$())$ transforms the zeros in the data to NaN before applying the log transformation.