anna-geller

import logging
import pandas as pd
import awswrangler as wr
from src.timeseries_data_generator import TimeseriesGenerator


def upload_timeseries_data_to_s3(df: pd.DataFrame) -> None:
    result = wr.s3.to_parquet(
        df,
        path=f"s3://data-lake-bronze/timeseries/",

anna-geller

import numpy as np
import pandas as pd


class TimeseriesGenerator:
    def __init__(
        self,
        start_date: str,
        end_date: str,
        frequency: str = "H",

anna-geller

import boto3

sns = boto3.client("sns", region_name="eu-central-1")

# CREATE TOPIC
topic_name = "ge_timeseries_data_test"
create_response = sns.create_topic(Name=topic_name)
topic_arn = create_response.get("TopicArn")

# CREATE SUBSCRIPTIONS

anna-geller

import boto3
import pandas as pd

s3_bucket = "awebsite"
html_file = "sales_report.html"

df = pd.DataFrame([{'year': 2021, 'month': 8, 'order_status': 'unavailable', 'order_count': 48},
                  {'year': 2021, 'month': 8, 'order_status': 'delivered', 'order_count': 7069},
                  {'year': 2021, 'month': 8, 'order_status': 'invoiced', 'order_count': 15},
                  {'year': 2021, 'month': 8, 'order_status': 'shipped', 'order_count': 74},

anna-geller

import boto3
import pandas as pd

s3_bucket = "annageller"
html_file = "sales_report.html"

df = pd.DataFrame([{'year': 2021, 'month': 8, 'order_status': 'unavailable', 'order_count': 48},
                  {'year': 2021, 'month': 8, 'order_status': 'delivered', 'order_count': 7069},
                  {'year': 2021, 'month': 8, 'order_status': 'invoiced', 'order_count': 15},
                  {'year': 2021, 'month': 8, 'order_status': 'shipped', 'order_count': 74},

anna-geller

import boto3
import pandas as pd

s3 = boto3.client("s3")
bucket_name = "annageller"
s3_object = "sales/customers.csv"

obj = s3.get_object(Bucket=bucket_name, Key=s3_object)
df = pd.read_csv(obj["Body"])

anna-geller

import boto3

bucket_name = "annageller"
s3_object = "ted_lasso.txt"
s3_object_body = "Be curious, not judgemental"
s3_resource = boto3.resource("s3")

upload_result = s3_resource.Object(bucket_name, s3_object).put(Body=s3_object_body)
assert upload_result["ResponseMetadata"]["HTTPStatusCode"] == 200

anna-geller

import os
import boto3
import tempfile

S3_BUCKET = "annageller"
S3_PREFIX = "sales/"

with tempfile.TemporaryDirectory() as tempdir:
    s3 = boto3.client("s3")
    response = s3.list_objects_v2(Bucket=S3_BUCKET, Prefix=S3_PREFIX)

anna-geller

import boto3

s3 = boto3.client("s3")
bucket_name = "annageller"
s3_object = "sales/customers.csv"
local_file_path = f"/Users/annageller/Desktop/datasets/{s3_object}"

# Uploading without specifying content type
s3.upload_file(
    local_file_path,

anna-geller

import boto3

s3_resource = boto3.resource("s3")
list(i for i in s3_resource.Bucket("annageller").objects.all()
     if i.get()["ContentType"] == "text/csv")