vsouza

import pandas as pd


data = {'a': [1, 3, 4, 4], 'b': [1, 3, 2, 3]}
df = pd.DataFrame(data=data)
df.to_csv("data/old_data.csv")

data2 = {'a': [1, 3, 5, 4], 'b': [1, 3, 2, 3]}
df2 = pd.DataFrame(data=data2)
df2.to_csv("data/new_data.csv")

vsouza

import Foundation


protocol GQLNodeArgument {}
extension String: GQLNodeArgument {}
extension NSNumber: GQLNodeArgument {}


class GQLNode: StringLiteralConvertible, ArrayLiteralConvertible, Printable, DebugPrintable {
    let name: String?

vsouza

package main

import (
	"fmt"
	"reflect"
)

type Foo struct {
	FirstName string `tag_name:"tag 1"`
	LastName  string `tag_name:"tag 2"`

vsouza

Study

• http://golang.org/ref/spec
• http://golang.org/doc/effective_go.html
• Writing Web Applications
• http://golang.org/doc/cmd
  • http://golang.org/cmd/go/
  • http://golang.org/cmd/cgo/
  • http://godoc.org/code.google.com/p/go.tools/cmd/cover
  • http://golang.org/cmd/fix/
• http://golang.org/cmd/go/

vsouza

import HTTP
import File
import HTTPSClient
import JSON

var url: String?
do {
	let client = try! Client(uri: "https://api.github.com:443")
	var response = try client.get("/repos/vsouza/awesome-ios/git/trees/HEAD")
	let buffer = try response.body.becomeBuffer()

vsouza

spark_context = SparkContext(appName=kinesis_app_name)
spark_streaming_context = StreamingContext(spark_context, spark_batch_interval)
sql_context = SQLContext(spark_context)

kinesis_stream = KinesisUtils.createStream(
    spark_streaming_context, kinesis_app_name, kinesis_stream, kinesis_endpoint,
    aws_region, kinesis_initial_position, kinesis_checkpoint_interval)

py_rdd = kinesis_stream.map(lambda x: json.loads(x))

vsouza

spark_context.saveAsTextFile("s3n://parents/activity_log/01010101.txt")

vsouza

def toRedshift(time, rdd):
    try:

        sqlContext = getSqlContextInstance(rdd.context)
        schema = StructType([
            StructField('user_id', StringType(), True),
            StructField('device_id', StringType(), True),
            StructField('steps', IntegerType(), True),
            StructField('battery_level', IntegerType(), True),
            StructField('calories_spent', IntegerType(), True),

vsouza

spark_streaming_context.start()
spark_streaming_context.awaitTermination()
spark_streaming_context.stop()

vsouza

from __future__ import print_function
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.streaming.kinesis import KinesisUtils, InitialPositionInStream
import datetime
import json
from pyspark.sql import SQLContext, Row
from pyspark.sql.types import *

aws_region = 'us-east-1'