s3-utils-python/s3.py at master · ostwalprasad/s3-utils-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
"""
Util functions for S3
"""

from .config import *
import boto3
import joblib
import pandas as pd

class s3_utils():
	"""
	Utilities to IO operations on Amazon S3.
	This library assumes that credentials are stored locally or class is being called from lambda.
	"""
	def __init__(self,prod=False):
		"""
		Connect to S3 when object is created
		"""
		self.S3 = boto3.client('s3', region_name=AWS_S3_HOST)
		if prod is True:
			self.folder = LAMBDA_TEMP_FOLDER
		else:
			self.folder = LOCAL_TEMP_FOLDER

	def load_file(self,file:"string",bucket:"bucketname")->"bytes":
		"""

		Args:
			file: filename that has to be loaded
			bucket: bucketname

		Returns:
			Bytes containing data of file.

		Example:
			s3.load_file("learn.txt",BUCKET_NAME)

		"""
		response = self.S3.get_object(Bucket=bucket, Key=file)
		return response['Body'].read()

	def store_file(self,filesource:"filename",filedestination:"filename",bucket:"bucketname")->"response":
		"""

		Args:
			filesource: Filename with path and extension
			filedestination: filename with path and extension
			bucket: bucketname

		Returns:
			Not defined yet

		Example:
			s3.store_file("learn.txt","learn.txt",BUCKET_NAME)

		"""
		self.S3.upload_file(filesource, bucket,filedestination)

	def delete_file(self,file:"filename",bucket:"bucketname")->"response": #TODO: Not checked yet
		"""

		Args:
			file: filname that exists in bucket
			bucket: bucketname

		Returns:
			Not defined yet

		Example:
			s3.delete_file("learn.txt",BUCKET_NAME)

		"""
		self.S3.delete_object(Bucket=bucket,Key=file)

	def load_pickle_model(self,file:'string',bucket:'bucketname') -> 'Model Object' :
		"""

		Args:
			file: filename of pickled object that exists in bucket
			bucket: bucketname

		Returns:
			Object extracted from picked file

		Example:
			myobj = s3.load_pickle_model("Regression.pkl",BUCKET_NAME)
			myobj.predict(x)

		"""
		data = self.load_file(file=file,bucket=bucket)
		myfile = open(f"{self.folder}{file}", "wb")
		myfile.write(data)
		with open(f"{self.folder}{file}", 'rb') as myfile:
			model = joblib.load(myfile)
		return model

	def store_pickle_model(self,model_object:'Model Object',file:"filename",bucket:'bucketname')->'response':
		"""

		Args:
			model_object: Object that needs to be pickled and stored into S3
			file: filename for object
			bucket: bucketname

		Returns:
			Not defined yet

		Example:
			from sklearn.linear_model import LinearRegression
			lm = LinearRegression()
			s3.store_pickle_model(lm,"Regression.pkl",BUCKET_NAME)
		"""
		joblib.dump(model_object,f"{self.folder}{file}")
		self.store_file(filesource=f"{self.folder}{file}",bucket=bucket,filedestination=file)

	def load_csvdataframe(self,file:"filename",bucket:'bucketname')->'Pandas Dataframe':
		"""

		Args:
			file: filename of csv file
			bucket: bucketname

		Returns:
			Pandas DataFrame


		Example:
			data = s3.load_csvdataframe("myfile.csv",BUCKET_NAME)
		"""
		data = self.load_file(file=file,bucket=bucket)
		return pd.read_csv(io.BytesIO(data))

	def store_csvdataframe(self,dataframe:'pandas dataframe',file:'filename',bucket:'bucketname'):
		"""

		Args:
			dataframe: Pandas dataframe
			file: filename
			bucket: bucketname

		Returns:
			Not yet defined

		Example:

			s3.store_csvdataframe(dataframe,"data.csv",BUCKET_NAME)

		"""
		dataframe.to_csv(f"{self.folder}{file}")
		self.store_file(filesource=f"{self.folder}{file}",filedestination=file,bucket=MODEL_BUCKET_NAME)