Search
 
SCRIPT & CODE EXAMPLE
 
CODE EXAMPLE FOR PYTHON

Remove outliers with median value and Capping

# Removing outliers by standard methods and Plotting graphs:
for col in ['lead_time','adr','days_in_waiting_list']:
  # Using IQR method and capping to define the range of inliners:
  lower_cap, q1, q3, upper_cap, median = df[col].quantile([0.01,0.25,0.75,0.99,0.5])
  lower_limit = q1 - 1.5*(q3-q1)
  upper_limit = q3 + 1.5*(q3-q1)

  # Replacing Outliers with median value and Capping
  new_df[col] = np.where(new_df[col] > upper_limit, median,np.where(
                         new_df[col] < lower_limit,median,np.where(
                         new_df[col] < lower_cap,lower_cap,np.where(
                         new_df[col] > upper_cap,upper_cap,new_df[col]))))
 
PREVIOUS NEXT
Tagged: #Remove #outliers #median #Capping
ADD COMMENT
Topic
Name
2+3 =