maneeshdisodia

def search(text,n):
    '''Searches for text, and retrieves n words either side of the text, which are retuned seperatly'''
    word = r"\W*([\w]+)"
    groups = re.search(r'{}\W*{}{}'.format(word*n,'place',word*n), text).groups()
    return groups[:n],groups[n:]
    
    
t = "The world is a small place, we should try to take care of it."
search(t,3)
#(('is', 'a', 'small'), ('we', 'should', 'try'))

maneeshdisodia

def search(text,n):
    '''Searches for text, and retrieves n words either side of the text, which are retuned seperatly'''
    word = r"\W*([\w]+)"
    groups = re.search(r'{}\W*{}{}'.format(word*n,'place',word*n), text).groups()
    return groups[:n],groups[n:]
    
    
t = "The world is a small place, we should try to take care of it."
search(t,3)
#(('is', 'a', 'small'), ('we', 'should', 'try'))

maneeshdisodia

#create fake data example taken from stackoverflow
df_example = pd.DataFrame({'CG':np.random.randint(0, 5, 100), 'Morph':np.random.choice(['S', 'E'], 100), 'R':np.random.rand(100) * -100})

def my_agg(x):
    x = x.sort_values('R')
    morph = x.head(1)['Morph'].values[0]
    diff = x.iloc[0]['R'] - x.iloc[1]['R']
    diff2 = -2.5*np.log10(sum(10**(-0.4*x['R'])))
    prop = (x['Morph'].iloc[1:] == 'S').mean()
    return pd.Series([morph, diff, diff2, prop], index=['morph', 'diff', 'diff2', 'prop'])

maneeshdisodia

JupyterHub on AWS

EC2 Setup

• Log in to AWS
• Go to a sensible region
• Start a new instance with Ubuntu Trusty (14.04) - compute-optimised instances have a high vCPU:memory ratio, and the lowest-cost CPU time. c4.2xlarge is a decent choice.
• Set security group (firewall) to have ports 22, 80, and 443 open (SSH, HTTP, HTTPS)
• If you want a static IP address (for long-running instances) then select Elastic IP for this VM
• If you want to use HTTPS, you'll probably need a paid certificate, or to use Amazon's Route 53 to get a non-Amazon domain (to avoid region blocking).

maneeshdisodia

import multiprocessing
import pandas as pd
import numpy as np

def _apply_df(args):
    df, func, kwargs = args
    return df.apply(func, **kwargs)

def apply_by_multiprocessing(df, func, **kwargs):
    workers = kwargs.pop('workers')

maneeshdisodia

#!/usr/bin/env python

import os

path = 'data'
os.chdir(path)
files = sorted(os.listdir(os.getcwd()), key=os.path.getmtime)

oldest = files[0]
newest = files[-1]

maneeshdisodia

GCP Dataflow Pipelines

This gist is a detailed walkthrough on how to deploy python Dataflow pipelines in GCP to run without external IPs. Full code samples are available below.

This walkthrough assumes you have a already authenticated with gcloud login commands and have the appropriate IAM privileges to execute these operations.

Step 1 - Gather application dependencies

Since we are planning to use no external IPs on our dataflow worker nodes, we must package up all our application dependencies for an offline deployment. I highly recommend using a virtual environment as your global dependencies will be much more than your single application will require.

Dump your application dependencies into a single file.

maneeshdisodia

import pandas as pd
from google.cloud import firestore

db = firestore.Client()
users = list(db.collection(u'users').stream())

users_dict = list(map(lambda x: x.to_dict(), users))
df = pd.DataFrame(users_dict)

maneeshdisodia

maneeshdisodia

from pyspark.sql.functions import pandas_udf, PandasUDFType

df = spark.createDataFrame(
    [(1, 1.0), (1, 2.0), (2, 3.0), (2, 5.0), (2, 10.0)],
    ("id", "v"))


def my_function(df, by="id", column="v", value=1.0):
    schema = "{} long, {} double".format(by, column)