prefix_result_pdd.ipynb

#ipython notebook prefix_result_pdd.ipynb

import pandas as pd
import numpy as np
from os import listdir
from os.path import isfile, join

filename = "10-14T05-00_10-14T20-17-014.csv"
print filename

cdrs = pd.read_csv(filename)
print len(cdrs)
print type(cdrs)

#print cdrs
grouped = cdrs.groupby(['Terminating number','Hangup code'])
print type(grouped)

#[0:6]

# single out what you need
trimmed = cdrs[['Terminating number','Hangup code','PDD(sec)']]
# trim to get prefix
trimmed['Terminating number'] = trimmed['Terminating number'].astype(str).str[0:7]

len(trimmed.columns)
trimmed

def mean_col(input_trimmed):
    input_trimmed['Mean PDD'] = input_trimmed['PDD(sec)'].mean()
    return input_trimmed

print trimmed.groupby(['Terminating number','Hangup code']).apply(mean_col)
trimmed = trimmed.groupby(['Terminating number','Hangup code']).apply(mean_col)

# does the main logic, the counts
trimmed.groupby(['Terminating number','Hangup code','Mean PDD'],as_index=False).size()
#print len(trimmed.groupby(trimmed.columns.tolist(),as_index=False).size())

#trimmed.to_csv("prefix_results.csv")

trimmed.groupby(['Terminating number','Hangup code','Mean PDD'],as_index=False).size().to_csv("prefix_results_pdd.csv")