In [5]:

    

import pandas as pd
from datetime import timedelta
import matplotlib.pyplot as plt
import matplotlib

matplotlib.style.use('ggplot') # Look Pretty

#
# INFO: This dataset has call records for 10 users tracked over the course of 3 years.
# Your job is to find out where the users likely live at!


def showandtell(title=None):
  if title != None: plt.savefig(title + ".png", bbox_inches='tight', dpi=300)
  plt.show()
  # exit()

def clusterInfo(model):
  print ("Cluster Analysis Inertia: ", model.inertia_)
  print ('------------------------------------------')
  for i in range(len(model.cluster_centers_)):
    print ("\n  Cluster ", i)
    print ("    Centroid ", model.cluster_centers_[i])
    print ("    #Samples ", (model.labels_==i).sum()) # NumPy Power

# Find the cluster with the least # attached nodes
def clusterWithFewestSamples(model):
  # Ensure there's at least on cluster...
  minSamples = len(model.labels_)
  minCluster = 0
  for i in range(len(model.cluster_centers_)):
    if minSamples > (model.labels_==i).sum():
      minCluster = i
      minSamples = (model.labels_==i).sum()
  print("\n  Cluster With Fewest Samples: ", minCluster)
  return (model.labels_==minCluster)


    

In [ ]:

    

# TODO: Load up the dataset and take a peek at its head
# Convert the date using pd.to_datetime, and the time using pd.to_timedelta
df = pd.read_csv('Datasets/CDR.csv')
df.CallDate = pd.to_datetime(df.CallDate)
df.CallTime = pd.to_datetime(df.CallTime).dt.time[8]
df.head(5)