# Data Cleaning based on Data Analysis using Python & EDA

# Removing the wage outlier row based on EDA observation
crimeData = crimeData[crimeData.county != 185] # very high wser & prob of conviction
crimeData = crimeData[crimeData.county != 115] # prob of arrest > 1

# Removing rows with probability of arrest and conviction > 1
crimeData = crimeData[crimeData['prbarr'] < 1]
crimeData = crimeData[crimeData['prbconv'] < 1]

# The location cannot be both west and central together.
crimeData = crimeData[crimeData['west']+crimeData['central'] <= 1]

# dropping the Year column as it doesn’t help in prediction
crimeData = crimeData.drop('year', axis=1)