forked from GoogleCloudPlatform/public-datasets-pipelines
-
Notifications
You must be signed in to change notification settings - Fork 0
/
csv_transform.py
137 lines (112 loc) · 4.49 KB
/
csv_transform.py
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
# Copyright 2021 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import json
import logging
import os
import pathlib
import subprocess
import typing
import pandas as pd
import requests
from google.cloud import storage
def main(
source_url: str,
source_file: pathlib.Path,
target_file: pathlib.Path,
chunksize: str,
target_gcs_bucket: str,
target_gcs_path: str,
headers: typing.List[str],
rename_mappings: dict,
pipeline_name: str,
) -> None:
logging.info("Creating 'files' folder")
pathlib.Path("./files").mkdir(parents=True, exist_ok=True)
logging.info(f"Downloading file {source_url}")
download_file(source_url, source_file)
chunksz = int(chunksize)
logging.info(f"Reading csv file {source_url}")
with pd.read_csv(
source_file,
engine="python",
encoding="utf-8",
quotechar='"',
compression="gzip",
chunksize=chunksz,
) as reader:
for chunk_number, chunk in enumerate(reader):
logging.info(f"Processing batch {chunk_number}")
target_file_batch = str(target_file).replace(
".csv", "-" + str(chunk_number) + ".csv"
)
df = pd.DataFrame()
df = pd.concat([df, chunk])
logging.info(" Renaming headers...")
rename_headers(df, rename_mappings)
logging.info("Transform: Reordering headers..")
df = df[headers]
if pipeline_name == "sentinel_2_index":
df["total_size"] = df["total_size"].astype("Int64")
process_chunk(df, target_file_batch)
logging.info(f"Appending batch {chunk_number} to {target_file}")
if chunk_number == 0:
subprocess.run(["cp", target_file_batch, target_file])
else:
subprocess.check_call([f"sed -i '1d' {target_file_batch}"], shell=True)
subprocess.check_call(
[f"cat {target_file_batch} >> {target_file}"], shell=True
)
subprocess.run(["rm", target_file_batch])
logging.info(
f"Uploading output file to.. gs://{target_gcs_bucket}/{target_gcs_path}"
)
upload_file_to_gcs(target_file, target_gcs_bucket, target_gcs_path)
def process_chunk(df: pd.DataFrame, target_file_batch: str) -> None:
logging.info(f"Saving to output file.. {target_file_batch}")
try:
save_to_new_file(df, file_path=str(target_file_batch))
except Exception as e:
logging.error(f"Error saving output file: {e}.")
logging.info("..Done!")
def rename_headers(df: pd.DataFrame, rename_mappings: dict) -> None:
df = df.rename(columns=rename_mappings, inplace=True)
def save_to_new_file(df: pd.DataFrame, file_path) -> None:
df.to_csv(file_path, index=False)
def download_file(source_url: str, source_file: pathlib.Path) -> None:
logging.info(f"Downloading {source_url} into {source_file}")
r = requests.get(source_url, stream=True)
if r.status_code == 200:
with open(source_file, "wb") as f:
for chunk in r:
f.write(chunk)
else:
logging.error(f"Couldn't download {source_url}: {r.text}")
def upload_file_to_gcs(file_path: pathlib.Path, gcs_bucket: str, gcs_path: str) -> None:
storage_client = storage.Client()
bucket = storage_client.bucket(gcs_bucket)
blob = bucket.blob(gcs_path)
blob.upload_from_filename(file_path)
if __name__ == "__main__":
logging.getLogger().setLevel(logging.INFO)
main(
source_url=os.environ["SOURCE_URL"],
source_file=pathlib.Path(os.environ["SOURCE_FILE"]).expanduser(),
target_file=pathlib.Path(os.environ["TARGET_FILE"]).expanduser(),
chunksize=os.environ["CHUNKSIZE"],
target_gcs_bucket=os.environ["TARGET_GCS_BUCKET"],
target_gcs_path=os.environ["TARGET_GCS_PATH"],
headers=json.loads(os.environ["CSV_HEADERS"]),
rename_mappings=json.loads(os.environ["RENAME_MAPPINGS"]),
pipeline_name=os.environ["PIPELINE_NAME"],
)