g-paras / sentiment-analysis-api

This is a machine learning based sentiment analysis web application using python's nltk library and deployed using flask api on Heroku server.

Sentiment Analysis

This is a sentiment analysis web applications, we have used nltk tweet sample for training model and Naive bais classier and deployed using flask api on heroku server. For training and testing our sentiment analysis model we used Google colaboratory which is an open source platform for machine learning or data science projects. It helps us training the model fast by using virtual GPU. For HTML and CSS we use Microsoft VS Code which is a great code editor with syntax highlighting, emmit abbreviations and much more. Python dependencies used:-

1. Keras
2. Flask 1.2.2
3. TextBlob 0.15.3
4. Gunicorn 20.0.4
5. Numpy 1.9.0
6. Regex 2020.6.8
7. NLTK 3.5

Check it out on https://sentiment-analysis-web-app.herokuapp.com

It might take few seconds to load please give it a try

Files and folder classification

• static folder contains all the images used
• templates folder has all html templates
• requirement.txt contains the python dependencies used in this project
• nltk.txt has the files which need to be downloaded for processing the input text
• Procfile is configuration file for Heroku server
• app.py is the flask application file
• model_nltk.py contains the source code for the Naive Bayes classifer which has been used in the production
• model_keras.py is another source code for model usign keras but we haven't used this in production because of its accuracy.

Updates

• Implemented some async js to make predictions faster and avoid reloading using jquery

• The above mentioned feature is in beta version, you can check it our here

• Added session object to remember admin credentials for short amount of time.

• Now you can upload a test file of reviews and then it will show you the graph of the predicted sentiments. Check it out here

• Implemented custom scroll bar, now it looks kind of cool and now you can use it as a pwa, go to 'add to screen' and then it will be a standalone chrome app

sentiment-analysis-api's Issues

Internal Server Error on making prediction

Website(http://sentiment-analysis-web-app.herokuapp.com/) is not working properly, on submitting form it shows internal server error instead of making prediction.

This issue is recent, website was working properly before. Most probably it is caused by database.

Suggest to loosen the dependency on textblob

Hi, your project sentiment-analysis-api requires "textblob==0.15.3" in its dependency. After analyzing the source code, we found that the following versions of textblob can also be suitable without affecting your project, i.e., textblob 0.9.0, 0.9.1, 0.10.0, 0.11.0, 0.11.1, 0.12.0, 0.13.0, 0.13.1, 0.14.0, 0.15.0, 0.15.1, 0.15.2, 0.16.0, 0.17.0, 0.17.1. Therefore, we suggest to loosen the dependency on textblob from "textblob==0.15.3" to "textblob>=0.9.0,<=0.17.1" to avoid any possible conflict for importing more packages or for downstream projects that may use sentiment-analysis-api.

May I pull a request to further loosen the dependency on textblob?

By the way, could you please tell us whether such dependency analysis may be potentially helpful for maintaining dependencies easier during your development?

---

We also give our detailed analysis as follows for your reference:

Your project sentiment-analysis-api directly uses 1 APIs from package textblob.

textblob.blob.TextBlob.__init__

Beginning from the 1 APIs above, 5 functions are then indirectly called, including 5 textblob's internal APIs and 0 outsider APIs. The specific call graph is listed as follows (neglecting some repeated function occurrences).

[/g-paras/sentiment-analysis-api]
+--textblob.blob.TextBlob.__init__
|      +--textblob.blob.BaseBlob.__init__
|      |      +--textblob.utils.lowerstrip
|      |      |      +--textblob.utils.strip_punc
|      |      +--textblob.blob._initialize_models
|      |      |      +--textblob.blob._validated_param

We scan textblob's versions and observe that during its evolution between any version from [0.9.0, 0.9.1, 0.10.0, 0.11.0, 0.11.1, 0.12.0, 0.13.0, 0.13.1, 0.14.0, 0.15.0, 0.15.1, 0.15.2, 0.16.0, 0.17.0, 0.17.1] and 0.15.3, the changing functions (diffs being listed below) have none intersection with any function or API we mentioned above (either directly or indirectly called by this project).

diff: 0.15.3(original) 0.9.0
['textblob.classifiers.DecisionTreeClassifier', 'textblob.ordereddict.OrderedDict.__ne__', 'textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier.extract_features', 'textblob.classifiers.BaseClassifier', 'textblob.blob.Word.translate', 'textblob.compat.with_metaclass', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.ordereddict.OrderedDict.__iter__', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob.blob.WordList.stem', 'textblob.translate.Translator.detect', 'textblob.translate.Translator.translate', 'textblob.exceptions.NotTranslated', 'textblob._text._read', 'textblob.classifiers.DecisionTreeClassifier.pprint', 'textblob.blob.BaseBlob.ngrams', 'textblob.blob.BaseBlob.translate', 'textblob.classifiers.NLTKClassifier.update', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.ordereddict.OrderedDict.__eq__', 'textblob.ordereddict.OrderedDict.__reduce__', 'textblob.blob.Blobber', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.translate.Translator._get_json5', 'textblob.ordereddict.OrderedDict.__reversed__', 'textblob.en.inflect.singularize', 'textblob.translate.Translator._request', 'textblob.translate.Translator._get_language_from_json5', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob.ordereddict.OrderedDict.__init__', 'textblob.ordereddict.OrderedDict.copy', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.Word.stem', 'textblob.ordereddict.OrderedDict', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.TextBlob', 'textblob.translate._calculate_tk', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.classifiers.DecisionTreeClassifier.pretty_format', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.ordereddict.OrderedDict.__setitem__', 'textblob.ordereddict.OrderedDict.__repr__', 'textblob.blob.WordList.count', 'textblob.ordereddict.OrderedDict.clear', 'textblob.translate._unescape', 'textblob.translate.Translator._get_translation_from_json5', 'textblob.translate.Translator._validate_translation', 'textblob.translate.Translator', 'textblob.ordereddict.OrderedDict.__delitem__', 'textblob.ordereddict.OrderedDict.keys', 'textblob.ordereddict.OrderedDict.popitem', 'textblob.en.np_extractors._is_match', 'textblob.ordereddict.OrderedDict.fromkeys']

diff: 0.15.3(original) 0.9.1
['textblob.ordereddict.OrderedDict.__ne__', 'textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier.extract_features', 'textblob.classifiers.BaseClassifier', 'textblob.blob.Word.translate', 'textblob.compat.with_metaclass', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.ordereddict.OrderedDict.__iter__', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob.blob.WordList.stem', 'textblob.translate.Translator.detect', 'textblob.translate.Translator.translate', 'textblob.exceptions.NotTranslated', 'textblob._text._read', 'textblob.blob.BaseBlob.ngrams', 'textblob.blob.BaseBlob.translate', 'textblob.classifiers.NLTKClassifier.update', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.ordereddict.OrderedDict.__eq__', 'textblob.ordereddict.OrderedDict.__reduce__', 'textblob.blob.Blobber', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.translate.Translator._get_json5', 'textblob.ordereddict.OrderedDict.__reversed__', 'textblob.en.inflect.singularize', 'textblob.translate.Translator._request', 'textblob.translate.Translator._get_language_from_json5', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob.ordereddict.OrderedDict.__init__', 'textblob.ordereddict.OrderedDict.copy', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.Word.stem', 'textblob.ordereddict.OrderedDict', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.TextBlob', 'textblob.translate._calculate_tk', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.ordereddict.OrderedDict.__repr__', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.ordereddict.OrderedDict.__setitem__', 'textblob.blob.WordList.count', 'textblob.ordereddict.OrderedDict.clear', 'textblob.translate._unescape', 'textblob.translate.Translator._get_translation_from_json5', 'textblob.translate.Translator._validate_translation', 'textblob.translate.Translator', 'textblob.ordereddict.OrderedDict.__delitem__', 'textblob.ordereddict.OrderedDict.keys', 'textblob.ordereddict.OrderedDict.popitem', 'textblob.en.np_extractors._is_match', 'textblob.ordereddict.OrderedDict.fromkeys']

diff: 0.15.3(original) 0.10.0
['textblob.ordereddict.OrderedDict.__ne__', 'textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier.extract_features', 'textblob.classifiers.BaseClassifier', 'textblob.blob.Word.translate', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.ordereddict.OrderedDict.__iter__', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob.blob.WordList.stem', 'textblob.translate.Translator.detect', 'textblob.translate.Translator.translate', 'textblob._text._read', 'textblob.blob.BaseBlob.ngrams', 'textblob.blob.BaseBlob.translate', 'textblob.classifiers.NLTKClassifier.update', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.ordereddict.OrderedDict.__eq__', 'textblob.ordereddict.OrderedDict.__reduce__', 'textblob.blob.Blobber', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.translate.Translator._get_json5', 'textblob.en.inflect.singularize', 'textblob.translate.Translator._request', 'textblob.translate.Translator._get_language_from_json5', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob.ordereddict.OrderedDict.__init__', 'textblob.ordereddict.OrderedDict.copy', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.Word.stem', 'textblob.ordereddict.OrderedDict', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.TextBlob', 'textblob.translate._calculate_tk', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.ordereddict.OrderedDict.__repr__', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.ordereddict.OrderedDict.__setitem__', 'textblob.blob.WordList.count', 'textblob.ordereddict.OrderedDict.clear', 'textblob.translate._unescape', 'textblob.translate.Translator._get_translation_from_json5', 'textblob.translate.Translator._validate_translation', 'textblob.translate.Translator', 'textblob.translate.Translator._translation_successful', 'textblob.ordereddict.OrderedDict.__delitem__', 'textblob.ordereddict.OrderedDict.keys', 'textblob.ordereddict.OrderedDict.popitem', 'textblob.ordereddict.OrderedDict.__reversed__', 'textblob.ordereddict.OrderedDict.fromkeys']

diff: 0.15.3(original) 0.11.0
['textblob.ordereddict.OrderedDict.__ne__', 'textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier.extract_features', 'textblob.classifiers.BaseClassifier', 'textblob.blob.Word.translate', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.ordereddict.OrderedDict.__iter__', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob.blob.WordList.stem', 'textblob.translate.Translator.detect', 'textblob.translate.Translator.translate', 'textblob._text._read', 'textblob.blob.BaseBlob.ngrams', 'textblob.blob.BaseBlob.translate', 'textblob.classifiers.NLTKClassifier.update', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.ordereddict.OrderedDict.__eq__', 'textblob.ordereddict.OrderedDict.__reduce__', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.translate.Translator._get_json5', 'textblob.translate.Translator._request', 'textblob.translate.Translator._get_language_from_json5', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob.ordereddict.OrderedDict.__init__', 'textblob.ordereddict.OrderedDict.copy', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.Word.stem', 'textblob.ordereddict.OrderedDict', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.translate._calculate_tk', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.ordereddict.OrderedDict.__repr__', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.ordereddict.OrderedDict.__setitem__', 'textblob.blob.WordList.count', 'textblob.ordereddict.OrderedDict.clear', 'textblob.translate._unescape', 'textblob.translate.Translator._get_translation_from_json5', 'textblob.translate.Translator._validate_translation', 'textblob.translate.Translator', 'textblob.translate.Translator._translation_successful', 'textblob.ordereddict.OrderedDict.__delitem__', 'textblob.ordereddict.OrderedDict.keys', 'textblob.ordereddict.OrderedDict.popitem', 'textblob.ordereddict.OrderedDict.__reversed__', 'textblob.ordereddict.OrderedDict.fromkeys']

diff: 0.15.3(original) 0.11.1
['textblob.ordereddict.OrderedDict.__ne__', 'textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier.extract_features', 'textblob.classifiers.BaseClassifier', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.ordereddict.OrderedDict.__iter__', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob.blob.WordList.stem', 'textblob.translate.Translator.detect', 'textblob.translate.Translator.translate', 'textblob._text._read', 'textblob.blob.BaseBlob.ngrams', 'textblob.classifiers.NLTKClassifier.update', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.ordereddict.OrderedDict.__eq__', 'textblob.ordereddict.OrderedDict.__reduce__', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob.ordereddict.OrderedDict.__init__', 'textblob.ordereddict.OrderedDict.copy', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.Word.stem', 'textblob.ordereddict.OrderedDict', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.translate._calculate_tk', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.ordereddict.OrderedDict.__repr__', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.ordereddict.OrderedDict.__setitem__', 'textblob.blob.WordList.count', 'textblob.ordereddict.OrderedDict.clear', 'textblob.translate._unescape', 'textblob.translate.Translator', 'textblob.ordereddict.OrderedDict.__delitem__', 'textblob.ordereddict.OrderedDict.keys', 'textblob.ordereddict.OrderedDict.popitem', 'textblob.ordereddict.OrderedDict.__reversed__', 'textblob.ordereddict.OrderedDict.fromkeys']

diff: 0.15.3(original) 0.12.0
['textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier.extract_features', 'textblob.classifiers.BaseClassifier', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob._text._read', 'textblob.classifiers.NLTKClassifier.update', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.blob.WordList.count', 'textblob.translate._unescape']

diff: 0.15.3(original) 0.13.0
['textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob._text._read', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob._text.Sentiment.__call__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.WordList.__repr__', 'textblob.classifiers.NLTKClassifier.accuracy', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.classifiers.BaseClassifier.__init__', 'textblob._text.Sentiment', 'textblob.classifiers.NLTKClassifier', 'textblob.blob.WordList.count', 'textblob.translate._unescape']

diff: 0.15.3(original) 0.13.1
['textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.en.taggers.NLTKTagger.tag', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob._text._read', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.blob.WordList.__iter__', 'textblob.base.BaseTagger', 'textblob.en.taggers.NLTKTagger', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.en.taggers.PatternTagger', 'textblob.blob.BaseBlob', 'textblob.en.taggers.PatternTagger.tag', 'textblob.blob.BaseBlob.correct', 'textblob.blob.WordList.__init__', 'textblob.classifiers.basic_extractor', 'textblob.base.BaseTagger.tag', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.WordList.__repr__', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.classifiers.BaseClassifier.__init__', 'textblob.blob.WordList.count', 'textblob.translate._unescape']

diff: 0.15.3(original) 0.14.0
['textblob.blob.WordList.__str__', 'textblob.classifiers.BaseClassifier', 'textblob.en.sentiments.PatternAnalyzer.analyze', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.WordList.__setitem__', 'textblob.blob.BaseBlob.sentiment_assessments', 'textblob._text._read', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.blob.WordList.__iter__', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.blob.BaseBlob', 'textblob.blob.BaseBlob.correct', 'textblob.blob.WordList.__init__', 'textblob.classifiers.basic_extractor', 'textblob.en.sentiments.PatternAnalyzer', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.WordList.__repr__', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.classifiers.BaseClassifier.__init__', 'textblob.blob.WordList.count', 'textblob.translate._unescape']

diff: 0.15.3(original) 0.15.0
['textblob.blob.WordList.__str__', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.WordList.__setitem__', 'textblob._text._read', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.blob.WordList.__iter__', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__', 'textblob.blob.BaseBlob', 'textblob.blob.BaseBlob.correct', 'textblob.blob.WordList.__init__', 'textblob.blob.Word', 'textblob.blob.WordList.extend', 'textblob.blob.WordList.__repr__', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.Word.lemmatize', 'textblob.blob.Word.lemma', 'textblob.blob.WordList.count']

diff: 0.15.3(original) 0.15.1
['textblob.blob.BaseBlob', 'textblob.blob.BaseBlob.correct', 'textblob.blob.WordList.__str__', 'textblob.blob.WordList', 'textblob.blob.WordList.append', 'textblob.blob.WordList.__init__', 'textblob.blob.WordList.count', 'textblob.blob.BaseBlob.pos_tags', 'textblob.blob.WordList.__iter__', 'textblob.blob.WordList.__setitem__', 'textblob.blob.WordList.extend', 'textblob.blob.WordList.__repr__', 'textblob.tokenizers.SentenceTokenizer', 'textblob._text._read', 'textblob.blob.WordList.__getitem__', 'textblob.blob.WordList.__getslice__']

diff: 0.15.3(original) 0.15.2
['textblob.blob.BaseBlob', 'textblob.tokenizers.SentenceTokenizer', 'textblob.blob.BaseBlob.correct', 'textblob.blob.BaseBlob.pos_tags']

diff: 0.15.3(original) 0.16.0
['textblob.blob.BaseBlob.translate', 'textblob.blob.BaseBlob', 'textblob.blob.Word.translate', 'textblob.blob.Word', 'textblob.blob.BaseBlob.detect_language', 'textblob.blob.Word.detect_language']

diff: 0.15.3(original) 0.17.0
['textblob.blob.BaseBlob.translate', 'textblob.blob.BaseBlob', 'textblob._text.Sentiment', 'textblob._text.Sentiment.__call__', 'textblob.blob.Word.translate', 'textblob.blob.Word', 'textblob.blob.BaseBlob.detect_language', 'textblob.translate.Translator.detect', 'textblob.translate.Translator', 'textblob.translate.Translator.translate', 'textblob.blob.Word.detect_language', 'textblob.translate._calculate_tk']

diff: 0.15.3(original) 0.17.1
['textblob.blob.BaseBlob.translate', 'textblob.blob.BaseBlob', 'textblob._text.Sentiment', 'textblob._text.Sentiment.__call__', 'textblob.blob.Word.translate', 'textblob.blob.Word', 'textblob.blob.BaseBlob.detect_language', 'textblob.translate.Translator.detect', 'textblob.translate.Translator', 'textblob.translate.Translator.translate', 'textblob.blob.Word.detect_language', 'textblob.translate._calculate_tk']

Therefore, we believe that it is quite safe to loose your dependency on textblob from "textblob==0.15.3" to "textblob>=0.9.0,<=0.17.1". This will improve the applicability of sentiment-analysis-api and reduce the possibility of any further dependency conflict with other projects.

Model accuracy is very low

Model accuracy is not so good and can be increased by n-grams or RNN.