prrao87 / fine-grained-sentiment-app

A Flask LIME explainer app for fine-grained sentiment classification.

An Explainer App for Fine Grained Sentiment Classification

This repo contains an initial prototype of an interactive application written in Flask, that explains the results of fine-grained sentiment classification, described in detail in this Medium Series.

A number of classifiers are implemented and their results explained using the LIME explainer. The classifers were trained on the Stanford Sentiment Treebank (SST-5) dataset. The class labels are any of [1, 2, 3, 4, 5], where 1 is very negative and 5 is very positive.

Installation

First, set up virtual environment and install from requirements.txt:

python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt

For further development, simply activate the existing virtual environment.

source venv/bin/activate

Usage

Run the file app.py and then enter a sentence, choose a type of classifier and click on the button Explain results!. We can then observe the features (i.e. words or tokens) that contributed to the classifier predicting a particular class label.

Demo for the front-end

The front-end app takes in a text sample and outputs LIME explanations for the different methods. The app is is deployed using Heroku at this location: https://sst5-explainer.herokuapp.com/

Play with your own text examples as shown below and see the fine-grained sentiment results explained!

NOTE: Because the PyTorch-based models (Flair and the causal transformer) are quite expensive to run inference with (they require a GPU), these methods are not deployed.

fine-grained-sentiment-app's Issues

Lime explainer return empty graph

Hi I have create ML web app for taking input from user and show result to web app.User will fill my form on web app page and then flask will use model to predicted and then model will send result to web app page.Text result working but graph doesn't. Now i want to show explainer using LIME but when i save LIME graph it return empty graph,I already checked my error log.There are no error details

`model = pickle.load(open("./model/hr.pkl", "rb"))
 app = flask.Flask(__name__, template_folder='templates')


 @app.route('/', methods=['GET', 'POST'])
 def main():
 if flask.request.method == 'GET':
 # Just render the initial form, to get input
  return (flask.render_template('main.html'))

  if flask.request.method == 'POST':
  # Extract the input
   TotalWorkingYears = flask.request.form['TotalWorkingYears']
   OverTime_code = flask.request.form['OverTime_code']
    JobInvolvement = flask.request.form['JobInvolvement']
   JobRole_code = flask.request.form['JobRole_code']
   Age = flask.request.form['Age']
   WorkLifeBalance = flask.request.form['WorkLifeBalance']
   Gender_code = flask.request.form['Gender_code']
   DistanceFromHome = flask.request.form['DistanceFromHome']
   MaritalStatus_code = flask.request.form['MaritalStatus_code']
   YearsSinceLastPromotion = flask.request.form['YearsSinceLastPromotion']
   Education = flask.request.form['Education']
   PercentSalaryHike = flask.request.form['PercentSalaryHike']
   TrainingTimesLastYear = flask.request.form['TrainingTimesLastYear']
   JobLevel = flask.request.form['JobLevel']
YearsAtCompany = flask.request.form['YearsAtCompany']
DailyRate = flask.request.form['DailyRate']
YearsWithCurrManager = flask.request.form['YearsWithCurrManager']
MonthlyIncome = flask.request.form['MonthlyIncome']
JobSatisfaction = flask.request.form['JobSatisfaction']
EducationField_code = flask.request.form['EducationField_code']
RelationshipSatisfaction = flask.request.form['RelationshipSatisfaction']
MonthlyRate = flask.request.form['MonthlyRate']
BusinessTravel_code = flask.request.form['BusinessTravel_code']

# Make DataFrame for model
input_variables = pd.DataFrame([[TotalWorkingYears, OverTime_code, JobInvolvement,JobRole_code, Age, WorkLifeBalance,
                                 Gender_code, DistanceFromHome, MaritalStatus_code, YearsSinceLastPromotion,
                                 Education,PercentSalaryHike, TrainingTimesLastYear, JobLevel, YearsAtCompany, DailyRate,
                                 YearsWithCurrManager, MonthlyIncome, JobSatisfaction, EducationField_code,
                                 RelationshipSatisfaction, MonthlyRate, BusinessTravel_code]],
                               columns=['TotalWorkingYears', 'OverTime_code', 'JobInvolvement', 'JobRole_code',
                                        'Age','WorkLifeBalance', 'Gender_code', 'DistanceFromHome','MaritalStatus_code',
                                        'YearsSinceLastPromotion','Education','PercentSalaryHike','TrainingTimesLastYear','JobLevel',
                                        'YearsAtCompany','DailyRate','YearsWithCurrManager','MonthlyIncome','JobSatisfaction',
                                        'EducationField_code','RelationshipSatisfaction','MonthlyRate','BusinessTravel_code'],
                               dtype=float,
                               index=['input'])

# Get the model's prediction
prediction = model.predict(input_variables)[0]
prediction_percentage = model.predict_proba(input_variables)[:,1]

row_to_show = 1
data_for_prediction = input_variables.iloc[1]  # use 1 row of data here. Could use multiple rows if desired
data_for_prediction_array = data_for_prediction.values.reshape(1, -1)

model.predict_proba(data_for_prediction_array)
X_featurenames = input_variables.columns

categorical_features = np.argwhere(np.array([len(set(input_variables.values[0]))]))


predict_fn = lambda x: model.predict_proba(x).astype(float)

explainer = lime.lime_tabular.LimeTabularExplainer(input_variables.values,
feature_names=X_featurenames,
class_names=['Yes','No'],
categorical_features=categorical_features,
verbose=True, mode='classification')

exp = explainer.explain_instance(input_variables.values[0], predict_fn, num_features=5)
fig = exp.as_pyplot_figure()






if os.path.isfile("/home/Domemakarov2013/smart_hr/static/images/shap_graph/graph.svg"):
    os.remove("/home/Domemakarov2013/smart_hr/static/images/shap_graph/graph.svg")

      plt.savefig("/home/Domemakarov2013/smart_hr/static/images/shap_graph/graph.svg",

        dpi = 150,
        bbox_inches = 'tight')
   # plt.savefig('/home/Domemakarov2013/smart_hr/static/images/shap_graph/graph.svg')
else:
   # plt.savefig('/home/Domemakarov2013/smart_hr/static/images/shap_graph/graph.svg')
      plt.savefig("/home/Domemakarov2013/smart_hr/static/images/shap_graph/graph.svg",

        dpi = 150,
        bbox_inches = 'tight')`

Converting lime explainer output to json

is it possible to convert the lime explainer output to json? or suggest any method to predict the final output without using lime framework