[PYTHON] I tried using the COTOHA API (there is code on GitHub)

0. Related articles

I tried using the COTOHA API rumored to be easy to handle natural language processing in Python
The result of having COTOHA summarize "Mentos and Go memories". COTOHA with the fastest tutorial

nth decoction

1. Background

~~ Because I learned about Present Planning. ~~

I personally wanted to do text analysis for a long time, so I decided to take this opportunity. However, when I looked it up, there was no official API for various languages. (This article belongs to the author. It's like NTT, but maybe this is the official theory)

So, I will try to make it after studying.

Link to COTOHA API Portal

2. Description of the created API

2.1 Operation confirmed environment

You need requests.

windows

Windows 10 Home
Python 3.7.3

Linux

Ubuntu 18.04.3 LTS
Python 3.6.9

Mac

♰ I don't have ♰

2.2 Quick start

First, register for free at COTOHA API for Developers
Execute the following command

git clone https://github.com/tsuji-tomonori/cotohapy.git
cd cotohapy
pip install -r requirements.txt
# config.Create json
python demo.py
#if,For python3 environment
python3 demo.py
# action!

`config.json looks like this.`



```json
{
    "access_token_publish_url": "",
    "developer_api_base_url": "",
    "clientid": "",
    "clientsecret": ""
}

When you go to the account home, the following page will appear, so please set it based on it. The correspondence table is attached below.

2.3 How to use

GitHub

git clone https://github.com/tsuji-tomonori/cotohapy.git

import

from cotohapy3 import CotohaAPI

The library is all in "cotohapy3". There are other classes besides CotohaAPI, but that will be later ...

Get Access Token

Be sure to go first.

api = CotohaAPI(
    developer_api_base_url=developer_api_base_url, 
    access_token_publish_url=access_token_publish_url
)
api.login(clientid=clientid, clientsecret=clientsecret)

def __init__(self, developer_api_base_url, access_token_publish_url)

argument	Data type	Contents
developer_api_base_url	str	API Base URL
access_token_publish_url	str	Access Token Publish URL

def login(self, clientid, clientsecret)

argument	Data type	Contents
clientid	str	Client ID
clientsecret	str	Client secret

Parsing (https://api.ce-cotoha.com/contents/reference/apireference.html): `parse`

#Execution example
api.parse("I ate yakiniku with my mother in Ginza yesterday")

def parse(self, sentence, **kwargs)

argument	Data type	Contents
sentence	str	Analysis target sentence
**kwargs		Any other parameters(Official reference API reference)

Named entity extraction: `` `ne```

#Execution example
api.ne("I used Tokyo station yesterday.")

def ne(self, sentence, **kwargs)

argument	Data type	Contents
sentence	str	Analysis target sentence
**kwargs		Any other parameters(Official reference API reference)

Resolution analysis: `` `coreference```

#Execution example
api.coreference("Taro is a friend. He ate grilled meat.")

def coreference(self, document, **kwargs)

argument	Data type	Contents
document	str / list	Specify in either of the following formats `str`:Sentence to be analyzed `list`:Sentence to be analyzed集合
**kwargs		Any other parameters(Official reference API reference)

Keyword extraction: `` `keyword```

#Execution example
api.keyword("I had lunch at the restaurant.")

def keyword(self, document, **kwargs)

argument	Data type	Contents
document	str / list	Specify in either of the following formats `str`:Sentence to be analyzed `list`:Sentence to be analyzed集合
**kwargs		Any other parameters(Official reference API reference)

Similarity calculation: `` `similarity```

#Execution example
api.similarity("Where is the restaurant nearby?", "Where are the set meal shops around here?")

def similarity(self, s1, s2, **kwargs)

argument	Data type	Contents
s1	str	Text to be calculated for similarity
s2	str	Text to be calculated for similarity
**kwargs		Any other parameters(Official reference API reference)

Sentence type determination: `` `sentence_type```

#Execution example
api.sentence_type("What is your name?")

def sentence_type(self, sentence, **kwargs)

argument	Data type	Contents
sentence	str	Analysis target sentence
**kwargs		Any other parameters(Official reference API reference)

User attribute estimation (β): `user_attribute`

#Execution example
api.user_attribute("When I went to drink at Tamachi station yesterday, my wife got angry.")

def user_attribute(self, document, **kwargs)

argument	Data type	Contents
document	str / list	Specify in either of the following formats `str`:Sentence to be analyzed `list`:Sentence to be analyzed集合
**kwargs		Any other parameters(Official reference API reference)

Stagnation removal (β): `remove_filler`

#Execution example
api.remove_filler(
    "Well, was that the meeting today? I'm sorry, I have a little urgent need."
)

def remove_filler(self, text, **kwargs)

argument	Data type	Contents
text	str	Text to be analyzed
**kwargs		Any other parameters(Official reference API reference)

Speech recognition error detection (β): `` `detect_misrecognition```

#Execution example
api.detect_misrecognition("Hot spring recognition makes mistakes")

def detect_misrecognition(self, sentence, **kwargs)

argument	Data type	Contents
sentence	str	Analysis target sentence
**kwargs		nothing special(Just in case than the beta version)

Emotion analysis: `` `sentiment```

#Execution example
api.sentiment("Enjoying the spring of life")

def sentiment(self, sentence)

argument	Data type	Contents
sentence	str	Analysis target sentence

Summary (β): `` `summary```

#Execution example
with open("summary.txt", "r", encoding="utf-8") as f:
    document = f.read()
api.summary(document, 1)

`summary.txt`


The front is stagnant over the Pacific Ocean. On the other hand, there is an anticyclone in the sea near Chishima, which gently covers northern and eastern Japan. The Kanto region is sunny and sometimes cloudy, with some rain. Tokyo will be cloudy after sunny and rainy at night due to the effects of moist air and fronts.

def summary(self, document, sent_len, **kwargs)

argument	Data type	Contents
document	str	Input text
sent_len	int	Number of summary sentences
**kwargs		nothing special(Just in case than the beta version)

3. Future plans

I want to put out something I made

Or I want to explain a function that is not explained

reference

pixivpy