samiriff

---- Create Pods, Services and Config Maps 
kubectl create -f https://gist.github.com/samiriff/6798254d00b7f42592edbb4311b717fb/raw/ea8a318972896074912457de6716d545d91e9a2b/pgdb-config-map.yml
kubectl create -f https://gist.github.com/samiriff/6798254d00b7f42592edbb4311b717fb/raw/ea8a318972896074912457de6716d545d91e9a2b/web-svc.yml
kubectl create -f https://gist.github.com/samiriff/6798254d00b7f42592edbb4311b717fb/raw/ea8a318972896074912457de6716d545d91e9a2b/pgdb-svc.yml
kubectl create -f https://gist.github.com/samiriff/6798254d00b7f42592edbb4311b717fb/raw/ea8a318972896074912457de6716d545d91e9a2b/web-pod.yml
kubectl create -f https://gist.github.com/samiriff/6798254d00b7f42592edbb4311b717fb/raw/ea8a318972896074912457de6716d545d91e9a2b/pgdb-pod.yml

---- Create default HTTP backend 
kubectl create -f https://gist.github.com/samiriff/6798254d00b7f42592edbb4311b717fb/raw/76cb0baddd0fbbea0a82b8dad7bd5e848f0f85bc/default-http-backend

samiriff

{
   "swagger": "2.0",
   "schemes": [
      "https",
      "http"
   ],
   "host": "ec2.amazonaws.com",
   "basePath": "/",
   "x-hasEquivalentPaths": true,
   "info": {

samiriff

def startsWithDate(s):
    pattern = '^([0-2][0-9]|(3)[0-1])(\/)(((0)[0-9])|((1)[0-2]))(\/)(\d{2}|\d{4}), ([0-9][0-9]):([0-9][0-9]) -'
    result = re.match(pattern, s)
    if result:
        return True
    return False

samiriff

def startsWithAuthor(s):
    patterns = [
        '([\w]+):',                        # First Name
        '([\w]+[\s]+[\w]+):',              # First Name + Last Name
        '([\w]+[\s]+[\w]+[\s]+[\w]+):',    # First Name + Middle Name + Last Name
        '([+]\d{2} \d{5} \d{5}):',         # Mobile Number (India)
        '([+]\d{2} \d{3} \d{3} \d{4}):',   # Mobile Number (US)
        '([+]\d{2} \d{4} \d{7})'           # Mobile Number (Europe)
    ]
    pattern = '^' + '|'.join(patterns)

samiriff

def getDataPoint(line):
    # line = 18/06/17, 22:47 - Loki: Why do you have 2 numbers, Banner?
    
    splitLine = line.split(' - ') # splitLine = ['18/06/17, 22:47', 'Loki: Why do you have 2 numbers, Banner?']
    
    dateTime = splitLine[0] # dateTime = '18/06/17, 22:47'
    
    date, time = dateTime.split(', ') # date = '18/06/17'; time = '22:47'
    
    message = ' '.join(splitLine[1:]) # message = 'Loki: Why do you have 2 numbers, Banner?'

samiriff

parsedData = [] # List to keep track of data so it can be used by a Pandas dataframe
conversationPath = './whatsappcollection/whatsapp_avengers.txt' 
with open(conversationPath, encoding="utf-8") as fp:
    fp.readline() # Skipping first line of the file (usually contains information about end-to-end encryption)
        
    messageBuffer = [] # Buffer to capture intermediate output for multi-line messages
    date, time, author = None, None, None # Intermediate variables to keep track of the current message being processed
    
    while True:
        line = fp.readline() 

samiriff

df = pd.DataFrame(parsedData, columns=['Date', 'Time', 'Author', 'Message'])
df.head()

samiriff

df.describe()

samiriff

author_value_counts = df['Author'].value_counts() # Number of messages per author
top_10_author_value_counts = author_value_counts.head(10) # Number of messages per author for the top 10 most active authors
top_10_author_value_counts.plot.barh() # Plot a bar chart using pandas built-in plotting apis

samiriff

null_authors_df = df[df['Author'].isnull()]
null_authors_df.head()