Is the a way of getting the degree of positiveness

Question

I have been following an example about Sentiment Analysis using Logistic Regression, in which prediction result only gives a 1 or 0 to give positive or negative sentiment respectively.

My challenge is that i want to classify a given user input into one of the four classes (very good, good, average, poor) but my prediction result every time is 1 or 0.

Below is my code sample so far

from sklearn.feature_extraction.text import CountVectorizer
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
from sklearn.metrics import classification_report
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_files
from sklearn.model_selection import GridSearchCV
import numpy as np
import mglearn
import matplotlib.pyplot as plt
# import warnings filter
from warnings import simplefilter
# ignore all future warnings
#simplefilter(action='ignore', category=FutureWarning)

# Get the dataset from http://ai.stanford.edu/~amaas/data/sentiment/

reviews_train = load_files("aclImdb/train/")
text_train, y_train = reviews_train.data, reviews_train.target

print("")
print("Number of documents in train data: {}".format(len(text_train)))
print("")
print("Samples per class (train): {}".format(np.bincount(y_train)))
print("")

reviews_test = load_files("aclImdb/test/")
text_test, y_test = reviews_test.data, reviews_test.target

print("Number of documents in test data: {}".format(len(text_test)))
print("")
print("Samples per class (test): {}".format(np.bincount(y_test)))
print("")


vect = CountVectorizer(stop_words="english", analyzer='word', 
                        ngram_range=(1, 1), max_df=1.0, min_df=1, 
max_features=None)
X_train = vect.fit(text_train).transform(text_train)
X_test = vect.transform(text_test)

print("Vocabulary size: {}".format(len(vect.vocabulary_)))
print("")
print("X_train:\n{}".format(repr(X_train)))
print("X_test: \n{}".format(repr(X_test)))

feature_names = vect.get_feature_names()
print("Number of features: {}".format(len(feature_names)))
print("")

param_grid = {'C': [0.001, 0.01, 0.1, 1, 10]}
grid = 
GridSearchCV(LogisticRegression(penalty='l1',dual=False,max_iter=110, 
solver='liblinear'), param_grid, cv=5)
grid.fit(X_train, y_train)

print("Best cross-validation score: {:.2f}".format(grid.best_score_))
print("Best parameters: ", grid.best_params_)
print("Best estimator: ", grid.best_estimator_)

lr = grid.best_estimator_
lr.predict(X_test)

print("Best Estimator Score: {:.2f}".format(lr.score(X_test, y_test)))
print("")

#creating an empty list for getting overall sentiment
lst = []

# number of elemetns as input
print("")
n = int(input("Enter number of rounds : ")) 

# iterating till the range 
for i in range(0, n):
    temp =[]
ele = input("\n Please Enter a sentence to get a sentiment Evaluation.  
 \n\n")
temp.append(ele)

print("")
print("Review prediction: {}". format(lr.predict(vect.transform(temp))))
print("")
lst.append(ele) # adding the element 

print(lst)
print("")
print("Overal prediction: {}". format(lr.predict(vect.transform(lst))))
print("")

I want to get some values between -0 to 1, like when you use Vader SentimentIntensityAnalyzer's polarity_scores.

Here is a code sample of what i want to achieve using SentimentIntensityAnalyzer's polarity_scores.

# import SentimentIntensityAnalyzer class 
# from vaderSentiment.vaderSentiment module. 
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer 

# function to print sentiments 
# of the sentence.

def sentiment_scores(sentence): 

# Create a SentimentIntensityAnalyzer object. 
sid_obj = SentimentIntensityAnalyzer() 

# polarity_scores method of SentimentIntensityAnalyzer 
# oject gives a sentiment dictionary. 
# which contains pos, neg, neu, and compound scores.

sentiment_dict = sid_obj.polarity_scores(sentence) 

print("")
print("\n Overall sentiment dictionary is : ", sentiment_dict," \n") 
print("sentence was rated as: ", sentiment_dict['neg']*100, "% Negative 
\n") 
print("sentence was rated as: ", sentiment_dict['neu']*100, "% Neutral 
\n") 
print("sentence was rated as: ", sentiment_dict['pos']*100, "% Positive 
\n")

print("Sentence Overall Rated As: ", end = " ") 

# decide sentiment as positive, negative and neutral


if sentiment_dict['compound'] >= 0.5: 
    print("Exellent \n")
elif sentiment_dict['compound'] > 0 and sentiment_dict['compound'] <0.5:
    print("Very Good \n")
elif sentiment_dict['compound'] == 0:
    print("Good \n")
elif sentiment_dict['compound'] <= -0.5:
    print("Average \n")
elif sentiment_dict['compound'] > -0.5 and sentiment_dict['compound']<0:
    print("Poor \n")  

# Driver code 
if __name__ == "__main__" : 

while True:
       # print("")
        sentence= []
        sentence = input("\n Please enter a sentence to get a sentimet 
 evaluation. Enter exit to end progam \n")

        if sentence == "exit":

            print("\n Program End...........\n")
            print("")
            break
        else:
            sentiment_scores(sentence)

Answer 1

You've got a couple options.

1: Label your initial training data with multiple classes according to how negative or positive the example is, instead of just 0 or 1, and perform multi-class classification.

2: As 1 may not be possible, try experimenting with the predict_proba(X), predict_log_proba(X), and decision_function(X) methods and use the results from those to bin your output into the 4 classes according to some hard-coded thresholds. I would recommend using predict_proba as those numbers are directly interpretable as probabilities and is one of the main benefits of logistic regression as opposed to other methods. For example, assuming the 1st (not 0th) column is the "positive" classification

probs = lr.predict_proba(X_test)
labels = np.repeat("very_good", len(probs))
labels[probs[:, 1] <  0.75] = "good"
labels[probs[:, 1] < 0.5] = "average"
labels[probs[:, 1] < 0.25] = "poor"