import requests
import pandas as pd
def query_foundry_sql(query, token, branch='master', base_url='https://foundry-instance.com') -> (list, list):
"""
Queries the dataproxy query API with spark SQL.
Example: query_foundry_sql("SELECT * FROM `/path/to/dataset` Limit 5000", "ey...")
Args:
query: the sql query
branch: the branch of the dataset / query
Returns: (columns, data) tuple. data contains the data matrix, columns the list of columns
Can be converted to a pandas Dataframe:
pd.DataFrame(data, columns)
"""
response = requests.post(f"{base_url}/foundry-data-proxy/api/dataproxy/queryWithFallbacks",
headers={'Authorization': f'Bearer {token}'},
params={'fallbackBranchIds': [branch]},
json={'query': query})
response.raise_for_status()
json = response.json()
columns = [e['name'] for e in json['foundrySchema']['fieldSchemaList']]
return columns, json['rows']
columns, data = query_foundry_sql("SELECT * FROM `/Global/Foundry Operations/Foundry Support/iris` Limit 5000",
"ey...",
base_url="https://foundry-instance.com")
df = pd.DataFrame(data=data, columns=columns)
df.head(5)
在Foundry中查询数据集有不同的可能性,这取决于数据集的大小和用例。 可能最容易从数据代理查询sql开始,因为您不必担心数据集的底层文件格式
相关问题 更多 >
编程相关推荐