perspective.py 0.3.3

An easy-to-use API wrapper for Perspective API written in Python.

perspective.py

The perspective.py library is an easy-to-use API wrapper written in Python for Perspective API, an API that uses machine learning to identify "toxic" comments.

Installation

Download & install git from https://git-scm.com/ and run below command:

python -m pip install --upgrade git+https://github.com/Yilmaz4/perspective.py.git

Or alternatively, you can install from PyPI (Python Package Index):

pyhton -m pip install --upgrade perspective.py

Getting an API key

You need to get an API key from Google to use Perspective API. Instructions are explained in this article.

Command arguments

text: str The text to analyze

requestedAttributes: list[str] A list of attributes to analyze the text for.

language: str The language of text.

You can use either Attributes.TOXICITY object or simply "TOXICITY" as a string for requestedAttributes argument.

You can specify the language of the text by using language argument. language argument accepts both language codes (such as "en" or "es") and language names (such as "English" or "Spanish"). Small spelling mistakes in language names can also be accepted (such as "Eglish" or "Spamish"). If you set language argument to None, language will be automatically detected.

You can find a list of all attributes and languages each attribute supports in this article.

Example usage

from perspective import Client, Attributes, utils

# Create the Client object which we will use to make requests with the API key
API_KEY = "your_api_key"
client = Client(token = API_KEY)

# Make a request to Perspective API with a text to analyze and the attributes that you want the text to be analyzed for
response = client.analyze(text = "Hey! How are you?", requestedAttributes = [Attributes.TOXICITY, Attributes.INSULT])

# Print the response as a dictionary
print(response)

# Print the score value of TOXICITY attribute
print(response["TOXICITY"]

print("  ")

# Iterate over the response
for attribute, result in response.items():
    print(attribute.capitalize() + ": " + "%.2f" % result + "%")

print("  ")

# Or alternatively, use utils.format_response to print a formatted text of the response which would return almost the same result as the above code
print(utils.format_response(response, align_right=True))

Output

{'TOXICITY': 7.019685000000001, 'INSULT': 3.9963423999999996}
7.019685000000001

Toxicity: 7.02%
Insult: 4.00%

Toxicity: 7.02%
  Insult: 4.00%

As you can see in the output, Client.analyze returns a dictionary with requested attributes and their analysis results as percents. You can get percents of each attribute, or iterate over dictionary.

Example usage for creating a bar chart

from perspective import Client, Attributes, utils

# Create the Client object which we will use to make requests with the API key
API_KEY = "your_api_key"
client = Client(token = API_KEY)

# Make a request to Perspective API with a text to analyze and the attributes that you want the text to be analyzed for
response = client.analyze(text = "Hey! How are you?", requestedAttributes = Attributes.Production) # Attributes.Production includes all production-ready attributes

# Create a horizontal bar chart and show it by popping up a window
utils.show_graph(response=response, title="Sample graph")

# Or alternatively, you can save the chart to an image file
utils.save_graph(response=response, filename="my_chart.png", title="Sample graph")

Output