How to do classification when some information only available only during training stage



I am trying to solve some classification problem while solving it i came across a problem in which some variable only present during only training stage but not present during testing stage .I am not able to solve this type of problem.

Data fields

Dates - timestamp of the crime incident
Category - category of the crime incident (only in train.csv). This is the target variable you are going to predict.
Descript - detailed description of the crime incident (only in train.csv)
DayOfWeek - the day of the week
PdDistrict - name of the Police Department District
Resolution - how the crime incident was resolved (only in train.csv)
Address - the approximate street address of the crime incident
X - Longitude
Y - Latitude



If I am not wrong, this is regarding SF Crime identification challenge on Kaggle. In this challenge, we need to identify the crime category in test dataset and this is the target variable. Other fields like Description and Resolution all are directly related to Crime Category so it is not available in Test dataset.