tomron

import pandas as pd
import numpy as np
from scipy import stats


input_file='advertisement_clicks.csv'

df = pd.read_csv(input_file)

a = df[df['advertisement_id']== 'A']['action'].tolist()

tomron

import pandas as pd
import numpy as np
from scipy import stats


input_file='advertisement_clicks.csv'

df = pd.read_csv(input_file)

a = df[df['advertisement_id']== 'A']['action'].tolist()

tomron

package com.tomron;

import org.apache.spark.sql.Row;
import org.apache.spark.sql.expressions.MutableAggregationBuffer;
import org.apache.spark.sql.expressions.UserDefinedAggregateFunction;
import org.apache.spark.sql.types.DataType;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

tomron

package com.tomron;

import org.apache.spark.sql.Row;
import org.apache.spark.sql.expressions.MutableAggregationBuffer;
import org.apache.spark.sql.expressions.UserDefinedAggregateFunction;
import org.apache.spark.sql.types.DataType;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

tomron

# impor spark, set spark context
from pyspark import SparkContext, SparkConf
from pyspark.sql.context import SQLContext
import sys
import os

if len(sys.argv) == 1:
    sys.stderr.write("Must enter input file to convert")
    sys.exit()
input_file = sys.argv[1]

tomron

import sys
import time

import boto3

def lambda_handler(event, context):
    conn = boto3.client("emr")
    # chooses the first cluster which is Running or Waiting
    # possibly can also choose by name or already have the cluster id
    clusters = conn.list_clusters()

tomron

from __future__ import print_function

import sys
from math import sqrt
import argparse
from collections import defaultdict
from random import randint

from pyspark import SparkContext