Python: Read CSV file without Pandas from S3 bucket [duplicate] - python

I have uploaded an excel file to AWS S3 bucket and now I want to read it in python. Any help would be appreciated. Here is what I have achieved so far,
import boto3
import os
aws_id = 'aws_id'
aws_secret = 'aws_secret_key'
client = boto3.client('s3', aws_access_key_id=aws_id, aws_secret_access_key=aws_secret)
bucket_name = 'my_bucket'
object_key = 'my_excel_file.xlsm'
object_file = client.get_object(Bucket=bucket_name, Key=object_key)
body = object_file['Body']
data = body.read()
What do I need to do next in order to read this data and work on it?

Spent quite some time on it and here's how I got it working,
import boto3
import io
import pandas as pd
import json
aws_id = ''
aws_secret = ''
bucket_name = ''
object_key = ''
s3 = boto3.client('s3', aws_access_key_id=aws_id, aws_secret_access_key=aws_secret)
obj = s3.get_object(Bucket=bucket_name, Key=object_key)
data = obj['Body'].read()
df = pd.read_excel(io.BytesIO(data), encoding='utf-8')

You can directly read xls file from S3 without having to download or save it locally. xlrd module has a provision to provide raw data to create workbook object.
Following is the code snippet.
from boto3 import Session
from xlrd.book import open_workbook_xls
aws_id = ''
aws_secret = ''
bucket_name = ''
object_key = ''
s3_session = Session(aws_access_key_id=aws_id, aws_secret_access_key=aws_secret)
bucket_object = s3_session.resource('s3').Bucket(bucket_name).Object(object_key)
content = bucket_object.get()['Body'].read()
workbook = open_workbook_xls(file_contents=content)

You can directly read excel files using awswrangler.s3.read_excel. Note that you can pass any pandas.read_excel() arguments (sheet name, etc) to this.
import awswrangler as wr
df = wr.s3.read_excel(path=s3_uri)

Python doesn't support excel files natively. You could use the pandas library pandas library read_excel functionality

Related

How to open dataframe stored in pickle in S3 on AWS?

I'm trying to load a dataframe file stored in pickle, and edit the dataframe. I'm opening in linux ubuntu AWS server, loading from S3. I could open by using pd.read_pickle in my environment, but that doesn't seem possibly when loading from S3
I can load and save from and to CSV, and I can also save to pickle, but I can't find a solution to load a pickle file. I tried copying almost every advice i could get on stackoverflow, but none seemed to work.
First, I tried
import pandas as pd
import boto3
import io
s3=boto3.client('s3')
session = boto3.session.Session()
obj = s3.get_object(Bucket = 'mybucket', Key = 'inputfile.pkl')
response = s3.get_object(Bucket=bucket, Key= inputfile)
body_string = response['Body'].read()
pickled = pickle.dumps(body_string)
df=pd.read_pickle(pickled) #embedded null type error
I also tried
import pickle
import boto3
s3 = boto3.resource('s3')
my_pickle = pickle.loads(s3.Bucket('bucket').Object('inputfile').get()['Body'].read())
df = pd.read_pickle(my_pickle) # with open(path, 'rb') as fh:
# return pkl.load(fh) error
Below is the method i used to save to pickle file
s3_resource = boto3.resource("s3")
s3=boto3.client('s3')
obj = s3.get_object(Bucket = bucket, Key = inputfile)
df = pd.read_csv(obj['Body'],index_col = False, low_memory = False)
pickle_buffer = io.BytesIO()
df.to_pickle(outputfile)
s3_resource.Object(bucket, outputfile).put(Body = open(outputfile, 'rb'))
I expect to get a df that i can work on, as I get from df = pd.read_pickle() or df = pd.read_csv()

upload a dataframe as a zipped csv directly to s3 without saving it on the local machine

How can I upload a data frame as a zipped csv into S3 bucket without saving it on my local machine first?
I have the connection to that bucket already running using:
self.s3_output = S3(bucket_name='test-bucket', bucket_subfolder='')
We can make a file-like object with BytesIO and zipfile from the standard library.
# 3.7
from io import BytesIO
import zipfile
# .to_csv returns a string when called with no args
s = df.to_csv()
with zipfile.ZipFile(BytesIO(), mode="w",) as z:
z.writestr("df.csv", s)
# upload file here
You'll want to refer to upload_fileobj in order to customize how the upload behaves.
yourclass.s3_output.upload_fileobj(z, ...)
This works equally well for zip and gz:
import boto3
import gzip
import pandas as pd
from io import BytesIO, TextIOWrapper
s3_client = boto3.client(
service_name = "s3",
endpoint_url = your_endpoint_url,
aws_access_key_id = your_access_key,
aws_secret_access_key = your_secret_key
# Your file name inside zip
your_filename = "test.csv"
s3_path = f"path/to/your/s3/compressed/file/test.zip"
bucket = "your_bucket"
df = your_df
gz_buffer = BytesIO()
with gzip.GzipFile(
filename = your_filename,
mode = 'w',
fileobj = gz_buffer ) as gz_file:
df.to_csv(TextIOWrapper(gz_file, 'utf8'), index=False)
s3.put_object(
Bucket=bucket, Key=s3_path, Body=gz_buffer.getvalue()
)

Read multiple CSV files from s3 using boto3

The code below reads a CSV file from AWS s3 using Pycham on my local machine.
# Read CSV from s3
import os
import boto3
import pandas as pd
import sys
if sys.version_info[0] < 3:
from StringIO import StringIO # Python 2.x
else:
from io import StringIO
aws_id = 'XXXXXXXXXXXXXXX'
aws_secret = 'XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX'
client = boto3.client('s3', aws_access_key_id=aws_id, aws_secret_access_key=aws_secret)
bucket_name = 'bucket-name'
object_key = 'folder-name/test.csv'
csv_obj = client.get_object(Bucket=bucket_name, Key=object_key)
body = csv_obj['Body']
csv_string = body.read().decode('utf-8')
df = pd.read_csv(StringIO(csv_string))
x = df.head()
print(x)
I would like to be able to read multiple CSV files in the same way. Pretty much anything that is in the folder.
My files are in the following directory:
bucket-name/folder-name/year=2018/month=01/file_032342.csv
bucket-name/folder-name/year=2018/month=02/file_434423.csv
bucket-name/folder-name/year=2018/month=03/file_343254.csv
bucket-name/folder-name/year=2018/month=04/file_544353.csv

How to read a list of parquet files from S3 as a pandas dataframe using pyarrow?

I have a hacky way of achieving this using boto3 (1.4.4), pyarrow (0.4.1) and pandas (0.20.3).
First, I can read a single parquet file locally like this:
import pyarrow.parquet as pq
path = 'parquet/part-r-00000-1e638be4-e31f-498a-a359-47d017a0059c.gz.parquet'
table = pq.read_table(path)
df = table.to_pandas()
I can also read a directory of parquet files locally like this:
import pyarrow.parquet as pq
dataset = pq.ParquetDataset('parquet/')
table = dataset.read()
df = table.to_pandas()
Both work like a charm. Now I want to achieve the same remotely with files stored in a S3 bucket. I was hoping that something like this would work:
dataset = pq.ParquetDataset('s3n://dsn/to/my/bucket')
But it does not:
OSError: Passed non-file path: s3n://dsn/to/my/bucket
After reading pyarrow's documentation thoroughly, this does not seem possible at the moment. So I came out with the following solution:
Reading a single file from S3 and getting a pandas dataframe:
import io
import boto3
import pyarrow.parquet as pq
buffer = io.BytesIO()
s3 = boto3.resource('s3')
s3_object = s3.Object('bucket-name', 'key/to/parquet/file.gz.parquet')
s3_object.download_fileobj(buffer)
table = pq.read_table(buffer)
df = table.to_pandas()
And here my hacky, not-so-optimized, solution to create a pandas dataframe from a S3 folder path:
import io
import boto3
import pandas as pd
import pyarrow.parquet as pq
bucket_name = 'bucket-name'
def download_s3_parquet_file(s3, bucket, key):
buffer = io.BytesIO()
s3.Object(bucket, key).download_fileobj(buffer)
return buffer
client = boto3.client('s3')
s3 = boto3.resource('s3')
objects_dict = client.list_objects_v2(Bucket=bucket_name, Prefix='my/folder/prefix')
s3_keys = [item['Key'] for item in objects_dict['Contents'] if item['Key'].endswith('.parquet')]
buffers = [download_s3_parquet_file(s3, bucket_name, key) for key in s3_keys]
dfs = [pq.read_table(buffer).to_pandas() for buffer in buffers]
df = pd.concat(dfs, ignore_index=True)
Is there a better way to achieve this? Maybe some kind of connector for pandas using pyarrow? I would like to avoid using pyspark, but if there is no other solution, then I would take it.
You should use the s3fs module as proposed by yjk21. However as result of calling ParquetDataset you'll get a pyarrow.parquet.ParquetDataset object. To get the Pandas DataFrame you'll rather want to apply .read_pandas().to_pandas() to it:
import pyarrow.parquet as pq
import s3fs
s3 = s3fs.S3FileSystem()
pandas_dataframe = pq.ParquetDataset('s3://your-bucket/', filesystem=s3).read_pandas().to_pandas()
Thanks! Your question actually tell me a lot. This is how I do it now with pandas (0.21.1), which will call pyarrow, and boto3 (1.3.1).
import boto3
import io
import pandas as pd
# Read single parquet file from S3
def pd_read_s3_parquet(key, bucket, s3_client=None, **args):
if s3_client is None:
s3_client = boto3.client('s3')
obj = s3_client.get_object(Bucket=bucket, Key=key)
return pd.read_parquet(io.BytesIO(obj['Body'].read()), **args)
# Read multiple parquets from a folder on S3 generated by spark
def pd_read_s3_multiple_parquets(filepath, bucket, s3=None,
s3_client=None, verbose=False, **args):
if not filepath.endswith('/'):
filepath = filepath + '/' # Add '/' to the end
if s3_client is None:
s3_client = boto3.client('s3')
if s3 is None:
s3 = boto3.resource('s3')
s3_keys = [item.key for item in s3.Bucket(bucket).objects.filter(Prefix=filepath)
if item.key.endswith('.parquet')]
if not s3_keys:
print('No parquet found in', bucket, filepath)
elif verbose:
print('Load parquets:')
for p in s3_keys:
print(p)
dfs = [pd_read_s3_parquet(key, bucket=bucket, s3_client=s3_client, **args)
for key in s3_keys]
return pd.concat(dfs, ignore_index=True)
Then you can read multiple parquets under a folder from S3 by
df = pd_read_s3_multiple_parquets('path/to/folder', 'my_bucket')
(One can simplify this code a lot I guess.)
It can be done using boto3 as well without the use of pyarrow
import boto3
import io
import pandas as pd
# Read the parquet file
buffer = io.BytesIO()
s3 = boto3.resource('s3')
object = s3.Object('bucket_name','key')
object.download_fileobj(buffer)
df = pd.read_parquet(buffer)
print(df.head())
Probably the easiest way to read parquet data on the cloud into dataframes is to use dask.dataframe in this way:
import dask.dataframe as dd
df = dd.read_parquet('s3://bucket/path/to/data-*.parq')
dask.dataframe can read from Google Cloud Storage, Amazon S3, Hadoop file system and more!
Provided you have the right package setup
$ pip install pandas==1.1.0 pyarrow==1.0.0 s3fs==0.4.2
and your AWS shared config and credentials files configured appropriately
you can use pandas right away:
import pandas as pd
df = pd.read_parquet("s3://bucket/key.parquet")
In case of having multiple AWS profiles you may also need to set
$ export AWS_DEFAULT_PROFILE=profile_under_which_the_bucket_is_accessible
so you can access your bucket.
If you are open to also use AWS Data Wrangler.
import awswrangler as wr
df = wr.s3.read_parquet(path="s3://...")
You can use s3fs from dask which implements a filesystem interface for s3. Then you can use the filesystem argument of ParquetDataset like so:
import s3fs
s3 = s3fs.S3FileSystem()
dataset = pq.ParquetDataset('s3n://dsn/to/my/bucket', filesystem=s3)
Using pre-signed URLs
s3 =s3fs.S3FileSystem(key='your_key',secret='your_secret',client_kwargs={"endpoint_url":'your_end_point'})
df = dd.read_parquet(s3.url('your_bucket' + 'your_filepath',expires=3600,client_method='get_object'))
I have tried the #oya163 solution and it works but after little bit change
import boto3
import io
import pandas as pd
# Read the parquet file
buffer = io.BytesIO()
s3 = boto3.resource('s3',aws_access_key_id='123',aws_secret_access_key= '456')
object = s3.Object('bucket_name','myoutput.parquet')
object.download_fileobj(buffer)
df = pd.read_parquet(buffer)
print(df.head())

How to read a csv file from an s3 bucket using Pandas in Python

I am trying to read a CSV file located in an AWS S3 bucket into memory as a pandas dataframe using the following code:
import pandas as pd
import boto
data = pd.read_csv('s3:/example_bucket.s3-website-ap-southeast-2.amazonaws.com/data_1.csv')
In order to give complete access I have set the bucket policy on the S3 bucket as follows:
{
"Version": "2012-10-17",
"Id": "statement1",
"Statement": [
{
"Sid": "statement1",
"Effect": "Allow",
"Principal": "*",
"Action": "s3:*",
"Resource": "arn:aws:s3:::example_bucket"
}
]
}
Unfortunately I still get the following error in python:
boto.exception.S3ResponseError: S3ResponseError: 405 Method Not Allowed
Wondering if someone could help explain how to either correctly set the permissions in AWS S3 or configure pandas correctly to import the file. Thanks!
Using pandas 0.20.3
import boto3
import pandas as pd
import sys
if sys.version_info[0] < 3:
from StringIO import StringIO # Python 2.x
else:
from io import StringIO # Python 3.x
client = boto3.client('s3')
bucket_name = 'my_bucket'
object_key = 'my_file.csv'
csv_obj = client.get_object(Bucket=bucket_name, Key=object_key)
body = csv_obj['Body']
csv_string = body.read().decode('utf-8')
df = pd.read_csv(StringIO(csv_string))
Based on this answer that suggested using smart_open for reading from S3, this is how I used it with Pandas:
import os
import pandas as pd
from smart_open import smart_open
aws_key = os.environ['AWS_ACCESS_KEY']
aws_secret = os.environ['AWS_SECRET_ACCESS_KEY']
bucket_name = 'my_bucket'
object_key = 'my_file.csv'
path = 's3://{}:{}#{}/{}'.format(aws_key, aws_secret, bucket_name, object_key)
df = pd.read_csv(smart_open(path))
You don't need pandas.. you can just use the default csv library of python
def read_file(bucket_name,region, remote_file_name, aws_access_key_id, aws_secret_access_key):
# reads a csv from AWS
# first you stablish connection with your passwords and region id
conn = boto.s3.connect_to_region(
region,
aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key)
# next you obtain the key of the csv you want to read
# you will need the bucket name and the csv file name
bucket = conn.get_bucket(bucket_name, validate=False)
key = Key(bucket)
key.key = remote_file_name
data = key.get_contents_as_string()
key.close()
# you store it into a string, therefore you will need to split it
# usually the split characters are '\r\n' if not just read the file normally
# and find out what they are
reader = csv.reader(data.split('\r\n'))
data = []
header = next(reader)
for row in reader:
data.append(row)
return data
hope it solved your problem,
good luck!
:)
I eventually realised that you also need to set the permissions on each individual object within the bucket in order to extract it by using the following code:
from boto.s3.key import Key
k = Key(bucket)
k.key = 'data_1.csv'
k.set_canned_acl('public-read')
And I also had to modify the address of the bucket in the pd.read_csv command as follows:
data = pd.read_csv('https://s3-ap-southeast-2.amazonaws.com/example_bucket/data_1.csv')
You can use AWS SDK for Pandas, a library that extends Pandas to work smoothly with AWS data stores, such as S3.
import awswrangler as wr
df = wr.s3.read_csv("s3://bucket/file.csv")
Without pandas (it's a big dependency just to read a csv file folks):
client = boto3.client("s3", region_name="eu-west-2")
data = client.get_object(Bucket=bucket, Key=_file)
reader = csv.DictReader(StringIO(data['Body'].read().decode('utf-8')))

Categories

Resources