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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
|
%global _empty_manifest_terminate_build 0
Name: python-es-pandas
Version: 0.0.22
Release: 1
Summary: Read, write and update large scale pandas DataFrame with ElasticSearch
License: MIT License
URL: https://github.com/fuyb1992/es_pandas
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/8d/fb/d0323116dd231002763468a3f7fb03482a47a8d1f8dd359225b0c9e3b02a/es_pandas-0.0.22.tar.gz
BuildArch: noarch
Requires: python3-pandas
Requires: python3-elasticsearch
Requires: python3-tqdm
Requires: python3-requests
%description
# es_pandas
[](https://travis-ci.org/fuyb1992/es_pandas) <a href="https://996.icu"><img src="https://img.shields.io/badge/link-996.icu-red.svg" alt="996.icu" /></a> [](https://github.com/996icu/996.ICU/blob/master/LICENSE) [](https://pypi.org/project/es-pandas/)
[](https://pepy.tech/project/es-pandas)
Read, write and update large scale [pandas](http://pandas.pydata.org/) DataFrame with [ElasticSearch](https://www.elastic.co/).
## Requirements
This package should work on Python3(>=3.4) and ElasticSearch should be version 5.x, 6.x or 7.x.
Installation
The package is hosted on PyPi and can be installed with pip:
```
pip install es_pandas
```
#### Deprecation Notice
Supporting of ElasticSearch 5.x will by deprecated in future version.
## Usage
```
import time
import pandas as pd
from es_pandas import es_pandas
# Information of es cluseter
es_host = 'localhost:9200'
index = 'demo'
# crete es_pandas instance
ep = es_pandas(es_host)
# Example data frame
df = pd.DataFrame({'Num': [x for x in range(100000)]})
df['Alpha'] = 'Hello'
df['Date'] = pd.datetime.now()
# init template if you want
doc_type = 'demo'
ep.init_es_tmpl(df, doc_type)
# Example of write data to es, use the template you create
ep.to_es(df, index, doc_type=doc_type, thread_count=2, chunk_size=10000)
# set use_index=True if you want to use DataFrame index as records' _id
ep.to_es(df, index, doc_type=doc_type, use_index=True, thread_count=2, chunk_size=10000)
# delete records from es
ep.to_es(df.iloc[5000:], index, doc_type=doc_type, _op_type='delete', thread_count=2, chunk_size=10000)
# Update doc by doc _id
df.iloc[:1000, 1] = 'Bye'
df.iloc[:1000, 2] = pd.datetime.now()
ep.to_es(df.iloc[:1000, 1:], index, doc_type=doc_type, _op_type='update')
# Example of read data from es
df = ep.to_pandas(index)
print(df.head())
# return certain fields in es
heads = ['Num', 'Date']
df = ep.to_pandas(index, heads=heads)
print(df.head())
# set certain columns dtype
dtype = {'Num': 'float', 'Alpha': object}
df = ep.to_pandas(index, dtype=dtype)
print(df.dtypes)
# infer dtype from es template
df = ep.to_pandas(index, infer_dtype=True)
print(df.dtypes)
# use query_sql parameter if you want to do query in sql
# Example of write data to es with pandas.io.json
ep.to_es(df, index, doc_type=doc_type, use_pandas_json=True, thread_count=2, chunk_size=10000)
print('write es doc with pandas.io.json finished')
```
%package -n python3-es-pandas
Summary: Read, write and update large scale pandas DataFrame with ElasticSearch
Provides: python-es-pandas
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-es-pandas
# es_pandas
[](https://travis-ci.org/fuyb1992/es_pandas) <a href="https://996.icu"><img src="https://img.shields.io/badge/link-996.icu-red.svg" alt="996.icu" /></a> [](https://github.com/996icu/996.ICU/blob/master/LICENSE) [](https://pypi.org/project/es-pandas/)
[](https://pepy.tech/project/es-pandas)
Read, write and update large scale [pandas](http://pandas.pydata.org/) DataFrame with [ElasticSearch](https://www.elastic.co/).
## Requirements
This package should work on Python3(>=3.4) and ElasticSearch should be version 5.x, 6.x or 7.x.
Installation
The package is hosted on PyPi and can be installed with pip:
```
pip install es_pandas
```
#### Deprecation Notice
Supporting of ElasticSearch 5.x will by deprecated in future version.
## Usage
```
import time
import pandas as pd
from es_pandas import es_pandas
# Information of es cluseter
es_host = 'localhost:9200'
index = 'demo'
# crete es_pandas instance
ep = es_pandas(es_host)
# Example data frame
df = pd.DataFrame({'Num': [x for x in range(100000)]})
df['Alpha'] = 'Hello'
df['Date'] = pd.datetime.now()
# init template if you want
doc_type = 'demo'
ep.init_es_tmpl(df, doc_type)
# Example of write data to es, use the template you create
ep.to_es(df, index, doc_type=doc_type, thread_count=2, chunk_size=10000)
# set use_index=True if you want to use DataFrame index as records' _id
ep.to_es(df, index, doc_type=doc_type, use_index=True, thread_count=2, chunk_size=10000)
# delete records from es
ep.to_es(df.iloc[5000:], index, doc_type=doc_type, _op_type='delete', thread_count=2, chunk_size=10000)
# Update doc by doc _id
df.iloc[:1000, 1] = 'Bye'
df.iloc[:1000, 2] = pd.datetime.now()
ep.to_es(df.iloc[:1000, 1:], index, doc_type=doc_type, _op_type='update')
# Example of read data from es
df = ep.to_pandas(index)
print(df.head())
# return certain fields in es
heads = ['Num', 'Date']
df = ep.to_pandas(index, heads=heads)
print(df.head())
# set certain columns dtype
dtype = {'Num': 'float', 'Alpha': object}
df = ep.to_pandas(index, dtype=dtype)
print(df.dtypes)
# infer dtype from es template
df = ep.to_pandas(index, infer_dtype=True)
print(df.dtypes)
# use query_sql parameter if you want to do query in sql
# Example of write data to es with pandas.io.json
ep.to_es(df, index, doc_type=doc_type, use_pandas_json=True, thread_count=2, chunk_size=10000)
print('write es doc with pandas.io.json finished')
```
%package help
Summary: Development documents and examples for es-pandas
Provides: python3-es-pandas-doc
%description help
# es_pandas
[](https://travis-ci.org/fuyb1992/es_pandas) <a href="https://996.icu"><img src="https://img.shields.io/badge/link-996.icu-red.svg" alt="996.icu" /></a> [](https://github.com/996icu/996.ICU/blob/master/LICENSE) [](https://pypi.org/project/es-pandas/)
[](https://pepy.tech/project/es-pandas)
Read, write and update large scale [pandas](http://pandas.pydata.org/) DataFrame with [ElasticSearch](https://www.elastic.co/).
## Requirements
This package should work on Python3(>=3.4) and ElasticSearch should be version 5.x, 6.x or 7.x.
Installation
The package is hosted on PyPi and can be installed with pip:
```
pip install es_pandas
```
#### Deprecation Notice
Supporting of ElasticSearch 5.x will by deprecated in future version.
## Usage
```
import time
import pandas as pd
from es_pandas import es_pandas
# Information of es cluseter
es_host = 'localhost:9200'
index = 'demo'
# crete es_pandas instance
ep = es_pandas(es_host)
# Example data frame
df = pd.DataFrame({'Num': [x for x in range(100000)]})
df['Alpha'] = 'Hello'
df['Date'] = pd.datetime.now()
# init template if you want
doc_type = 'demo'
ep.init_es_tmpl(df, doc_type)
# Example of write data to es, use the template you create
ep.to_es(df, index, doc_type=doc_type, thread_count=2, chunk_size=10000)
# set use_index=True if you want to use DataFrame index as records' _id
ep.to_es(df, index, doc_type=doc_type, use_index=True, thread_count=2, chunk_size=10000)
# delete records from es
ep.to_es(df.iloc[5000:], index, doc_type=doc_type, _op_type='delete', thread_count=2, chunk_size=10000)
# Update doc by doc _id
df.iloc[:1000, 1] = 'Bye'
df.iloc[:1000, 2] = pd.datetime.now()
ep.to_es(df.iloc[:1000, 1:], index, doc_type=doc_type, _op_type='update')
# Example of read data from es
df = ep.to_pandas(index)
print(df.head())
# return certain fields in es
heads = ['Num', 'Date']
df = ep.to_pandas(index, heads=heads)
print(df.head())
# set certain columns dtype
dtype = {'Num': 'float', 'Alpha': object}
df = ep.to_pandas(index, dtype=dtype)
print(df.dtypes)
# infer dtype from es template
df = ep.to_pandas(index, infer_dtype=True)
print(df.dtypes)
# use query_sql parameter if you want to do query in sql
# Example of write data to es with pandas.io.json
ep.to_es(df, index, doc_type=doc_type, use_pandas_json=True, thread_count=2, chunk_size=10000)
print('write es doc with pandas.io.json finished')
```
%prep
%autosetup -n es-pandas-0.0.22
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-es-pandas -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed Apr 12 2023 Python_Bot <Python_Bot@openeuler.org> - 0.0.22-1
- Package Spec generated
|
