import os
import time
import boto3
import numpy as np
import pandas as pd
import sagemaker
#from sagemaker import get_execution_role

def get_execution_role():
    return "SageMaker-ExecutionRole-20241030T121452"

sess              = boto3.Session()
sm                = sess.client("sagemaker")
role              = get_execution_role()
sagemaker_session = sagemaker.Session(boto_session=sess)
bucket            = "shared-hs-mlops-bucket" #sagemaker_session.default_bucket()
region            = boto3.Session().region_name


model_package_group_name = "PipelineModelPackageGroup"
prefix                   = "mas-pipeline-model-example"
pipeline_name            = "mas-serial-inference-pipeline"  # SageMaker Pipeline name

raw_dir = os.path.join(os.getcwd(), "data", "raw")

#data_dir = os.path.join(os.getcwd(), "data")
#os.makedirs(data_dir, exist_ok=True)
#raw_dir = os.path.join(os.getcwd(), "data/raw")
#os.makedirs(raw_dir, exist_ok=True)


#########################################################################
## Download Data
s3 = boto3.client("s3")
s3.download_file(
    f"sagemaker-example-files-prod-{region}",
    "datasets/tabular/california_housing/cal_housing.tgz",
    "cal_housing.tgz",
)

#!tar -zxf cal_housing.tgz

columns = [
    "longitude",  "latitude",     "housingMedianAge",
    "totalRooms", "totalBedrooms","population",
    "households", "medianIncome", "medianHouseValue",
]
cal_housing_df = pd.read_csv("CaliforniaHousing/cal_housing.data", names=columns, header=None)
cal_housing_df["medianHouseValue"] /= 500000  # Scaling target down to avoid overcomplicating the example
cal_housing_df.to_csv(f"./data/raw/raw_data_all.csv", header=True, index=False)
rawdata_s3_prefix = "{}/data/raw".format(prefix)

#########################################################################
## Upload to S3
raw_s3 = sagemaker_session.upload_data(
  bucket = bucket,
  path="./data/raw/", 
  key_prefix=rawdata_s3_prefix)
print(raw_s3) #s3://shared-hs-mlops-bucket/mas-pipeline-model-example/data/raw