alecbw

python3
import pandas as pd; import os; files = [f for f in os.listdir('.') if (os.path.isfile(f) and os.path.getsize(f) != 0 and any(x for x in [".csv", ".xlsx"] if x in f))]; print(files); df_tuples = [(f, pd.read_csv(f)) for f in files]; [print(df_tup[0], df_tup[1].shape, df_tup[1].columns, "\n") for df_tup in df_tuples]

alecbw

custom:
  scripts:
    commands:
      hello: This breaks the deploy if env vars aren't set. ${env:FOOBAR}

alecbw

feedbackButtons = document.getElementsByClassName("feedbackButton")

for (i = 0; i < feedbackButtons.length; i++) {
  feedbackButtons[i].addEventListener("click", trackClick);
}

function trackClick(event) {
  var page = window.location.pathname
  var button = event.target.id
  fetch('https://foobar.execute-api.us-west-1.amazonaws.com/prod/feedback?page=' + page + '&button=' + button)

alecbw

import gc

to_delete = []
for name, value in vars().items():
    if isinstance(value, pd.DataFrame):
        to_delete.append(name)

for item in to_delete:
    print(item)
    del item

alecbw

import requests

time_start = '2020-09-01'
time_end = '2020-09-01'
fields = ['website_ctr','reach','adset_name','frequency','action_values','campaign_name','unique_actions','unique_clicks','video_avg_percent_watched_actions','video_p75_watched_actions','spend','cpc','video_p25_watched_actions','canvas_avg_view_time','canvas_avg_view_percent','campaign_id','video_p50_watched_actions','ctr','cpm','cpp','unique_ctr','video_avg_time_watched_actions','ad_name','impressions','labels','video_p95_watched_actions','cost_per_10_sec_video_view','ad_id','adset_id','clicks','website_purchase_roas','location','actions','cost_per_unique_click']
fields = "['" + "','".join(fields) + "']"

api_url =  'https://graph.facebook.com/v8.0/' + os.environ['FB_ACCOUNT_ID'] + "/insights?"

api_url += "level=ad"

alecbw

import boto3

def get_row_count_of_s3_csv(bucket_name, path):
    sql_stmt = """SELECT count(*) FROM s3object """
    req = boto3.client('s3').select_object_content(
        Bucket=bucket_name,
        Key=path,
        ExpressionType="SQL",
        Expression=sql_stmt,
        InputSerialization = {"CSV": {"FileHeaderInfo": "Use", "AllowQuotedRecordDelimiter": True}},

alecbw

import hashlib
import requests
import os
import json


"""
Docs: https://mailchimp.com/developer/guides/organize-contacts-with-tags/#label-a-contact-with-a-tag
Emails must be MD5 hashed before sending the call (such is done so below)
The API returns 204 No Content no matter if the input is valid or invalid

alecbw

{
    "Statement": [
        {
            "Action": [
                "s3:ListBucket",
                "s3:GetBucketLocation"
            ],
            "Effect": "Allow",
            "Resource": [
                "arn:aws:s3:::bucket-your-data-is-in",

alecbw

{
    "Statement": [
        {
            "Action": [
                "s3:ListBucket",
                "s3:GetBucketLocation"
            ],
            "Effect": "Allow",
            "Resource": [

alecbw

import awswrangler as wr
import pandas as pd

get current IAM role/user
name = wr.sts.get_current_identity_name()
arn = wr.sts.get_current_identity_arn()

# Reading files
df = wr.s3.read_csv(f"s3://sample-bucket/sample.csv") #you can optionally select a subset of columns with names=['col_name1'] and parse date cols with: parse_dates=["col_name2"]
df = wr.s3.read_json(f"s3://sample-bucket/sample.json")