User Tools

Site Tools

# in sql, it's easy to extract the age in years from the year of birth
EXTRACT (YEAR from age(F.birthdate)) as Age_in_Years
# Create a binning function
def binning(col, cut_points, labels=None):
  #Define min and max values:
  minval = col.min()
  maxval = col.max()
  #create list by adding min and max to cut_points
  break_points = [minval] + cut_points + [maxval]
  #if no labels provided, use default labels 0 ... (n-1)
  if not labels:
    labels = range(len(cut_points)+1)
  #Binning using cut function of pandas
  colBin = pd.cut(col,bins=break_points,labels=labels,include_lowest=True)
  return colBin
#Binning age:
cut_points = [25,35,45,55,65]
labels = ["18 - 25","26 - 35","36 - 45","46 - 55","56 - 65","66 +"]
#apply it to a dataset creating a new column containing the bins
df["bins"] = df(applicata["age_in_years"], cut_points, labels)

Then, group-by counting per age bins, plot the histogram using faceting for unique values contained in another column

frequency_distribution_by_age_bins.txt · Last modified: 2016/11/15 11:33 by vincenzo