AttributeError：“Elasticsearch”对象没有属性“选项”

Question

我正在尝试在 python 中使用 elasticsearch 构建模型，但出现此错误，我能够执行一次，但由于此错误，现在我无法再次运行它

import pandas as pd

df = pd.read_csv("salaries.csv")
df.head()

inputs = df.drop('salary_more_then_100k',axis='columns')

target = df['salary_more_then_100k']

from sklearn.preprocessing import LabelEncoder
le_company = LabelEncoder()
le_job = LabelEncoder()
le_degree = LabelEncoder()

inputs['company_n'] = le_company.fit_transform(inputs['company'])
inputs['job_n'] = le_job.fit_transform(inputs['job'])
inputs['degree_n'] = le_degree.fit_transform(inputs['degree'])

inputs

inputs_n = inputs.drop(['company','job','degree'],axis='columns')

inputs_n

target

from sklearn import tree
model = tree.DecisionTreeClassifier()

model.fit(inputs_n, target)

from eland.ml import MLModel
from elasticsearch import Elasticsearch

es = Elasticsearch(hosts='http://localhost:9200')

es_model = MLModel.import_model(es_client=es,
                                model=model,
                                model_id='salaries-model',
                                feature_names=list(df.columns),
                                es_if_exists='replace'
)

当我运行 es_model 行时，出现此错误 -> AttributeError: 'Elasticsearch' object has no attribute 'options'

我做错了什么，谁能告诉我

Answer 1

opensearch 面临类似问题。

参考链接-https://pydole.tistory.com/entry/Python-Insert-bulk-from-pandas-dataframe-to-elasticsearch

代码-

import pandas as pd
from elasticsearch import Elasticsearch
from elasticsearch.helpers import bulk
from opensearchpy import OpenSearch

# Datetime, String, Interger Example Dataframe 

listDate = ['2020-01-01 00:00:00','2020-01-01 00:01:00','2020-01-01 00:02:00', '2020-01-01 00:03:00']
listStrings = ['a','b','c','d']
listInterger = [1, 2, 3, 4 ]

df = pd.DataFrame([ x for x in zip(listDate,listStrings,listInterger)], columns=['date','string', 'interger'])
df['date'] = pd.to_datetime(df['date'])

host = 'localhost'
port = 9200
auth = ('admin', 'admin') # For testing only. Don't store credentials in code.
# ca_certs_path = '/full/path/to/root-ca.pem' # Provide a CA bundle if you use intermediate CAs with your root CA.

# Optional client certificates if you don't want to use HTTP basic authentication.
# client_cert_path = '/full/path/to/client.pem'
# client_key_path = '/full/path/to/client-key.pem'

# Create the client with SSL/TLS enabled, but hostname verification disabled.

client = OpenSearch(
            hosts = [{'host': host, 'port': port}],
            http_compress = True, # enables gzip compression for request bodies
            http_auth = auth,
        # client_cert = client_cert_path,
        # client_key = client_key_path,
            use_ssl = True,
            verify_certs = False,
            ssl_assert_hostname = False,
            ssl_show_warn = False,
            # ca_certs = ca_certs_path
             )

# Create an index with non-default settings.
index_name = 'bulk'
index_body = {
  'settings': {
    'index': {
      'number_of_shards': 4
    }
  }
}
response = client.indices.create(index_name, body=index_body)
df = pd.DataFrame(data = {'date' : df['date'],
                          'strings': df['string'],
                          'interger' : df['interger']})
 
documents = df.to_dict(orient='records')
print(documents)
bulk(client, documents, index='bulk',doc_type='foo', raise_on_error=True)

错误-

(devenv) E:\env>python bulk.py
[{'date': Timestamp('2020-01-01 00:00:00'), 'strings': 'a', 'interger': 1}, {'date': Timestamp('2020-01-01 00:01:00'), 'strings': 'b', 'interger': 2}, {'date': Timestamp('2020-01-01 00:02:00'), 'strings': 'c', 'interger': 3}, {'date': Timestamp('2020-01-01 00:03:00'), 'strings': 'd', 'interger': 4}]Traceback (most recent call last):
  File "E:\env\bulk.py", line 55, in <module>
    bulk(client, documents, index='bulk',doc_type='foo', raise_on_error=True)
  File "E:\env\devenv\lib\site-packages\elasticsearch\helpers\actions.py", line 524, in bulk
    for ok, item in streaming_bulk(
  File "E:\env\devenv\lib\site-packages\elasticsearch\helpers\actions.py", line 410, in streaming_bulk
    client = client.options()
AttributeError: 'OpenSearch' object has no attribute 'options'

(devenv) E:\env>
(devenv) E:\env>python bulk.py

(devenv) E:\env>python bulk.py
[{'date': Timestamp('2020-01-01 00:00:00'), 'strings': 'a', 'interger': 1}, {'date': Timestamp('2020-01-01 00:01:00'), 'strings': 'b', 'interger': 2}, {'date': Timestamp('2020-01-01 00:02:00'), 'strings': 'c', 'interger': 3}, {'date': Timestamp('2020-01-01 00:03:00'), 'strings': 'd', 'interger': 4}]Traceback (most recent call last):
  File "E:\env\bulk.py", line 55, in <module>
    bulk(client, documents, index='bulk',doc_type='foo', raise_on_error=True)
  File "E:\env\devenv\lib\site-packages\elasticsearch\helpers\actions.py", line 524, in bulk
    for ok, item in streaming_bulk(
  File "E:\env\devenv\lib\site-packages\elasticsearch\helpers\actions.py", line 410, in streaming_bulk
    client = client.options()
AttributeError: 'OpenSearch' object has no attribute 'options'