Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
CHATBOT/textclassify.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
58 lines (50 sloc)
1.61 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
''' | |
Text Classifier | |
available classifiers in Texblob.classifies: | |
DecisionTreeClassifier | |
MaxEntClassifier | |
NaiveBayesClassifier | |
PositiveNaiveBayesClassifier | |
''' | |
#dataset from : https://www.kaggle.com/marklvl/sentiment-labelled-sentences-data-set/home | |
''' | |
def format_data(): | |
#---This funtion is used to label sentences and should be ran once | |
import pandas as pd | |
import pickle | |
training_data=[] | |
dataset =pd.read_csv('data.csv') | |
content=dataset['content'] | |
value=dataset['value'] | |
text_list=[] | |
value_list=[] | |
training_data=[] | |
for text in content: | |
text_list.append(text) | |
for review in value: | |
value_list.append(str(review)) | |
n=0 | |
while n<len(text_list): | |
training_data.append((text_list[n],value[n])) #-- Creating turples | |
#-- because textblob classify want require them in this form | |
n=n+1 | |
pickle.dump(training_data,open('training_data.p','wb')) | |
return training_data | |
''' | |
from textblob.classifiers import NaiveBayesClassifier | |
import pickle | |
def classify_text(text_to_classify): | |
train=pickle.load(open('training_data.p','rb')) | |
TESS_classify=NaiveBayesClassifier(train) | |
sentiment=(TESS_classify.classify(text_to_classify)) | |
return sentiment | |
while True: | |
user=input('Enter some text and i will tell you if it is positive or not. Bear in mind i do not understand sarcasm yet > ').lower() | |
if user=='q': | |
print('exiting') | |
break | |
else: | |
if classify_text(user)==1: | |
print('positive sentence') | |
elif classify_text(user)==0 : | |
print('negative sentence') | |