def push_data_to_elasticsearch(): app_configs = utils.open_json( constants.APP_CONFIG_FILE.format(file_name=constants.APP_CONFIG_FILE_NAME) ) for app_config_file in app_configs: app_config = AppConfig( utils.open_json( app_config_file ) ) # Path where the user reviews were stored after parsing. processed_user_reviews_file_path = constants.PROCESSED_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.processed_data_folder, app_name=app_config.app.name, ) # Loading the reviews reviews = utils.open_json(processed_user_reviews_file_path) # Converting the json object to Review object reviews = [Review.from_review_json(review) for review in reviews] # Filtering out reviews which are not applicable. reviews = filter_utils.filter_reviews_by_time( filter_utils.filter_reviews_by_channel( reviews, filter_utils.filter_disabled_review_channels( app_config ), ), datetime.now(timezone.utc) - timedelta(days=app_config.email_config.email_time_span) ) # We shuffle the reviews. This is because of how elastic search. random.shuffle(reviews) # We first list out all the indices indices = get_indices(app_config.elastic_config.elastic_search_url) if app_config.elastic_config.index not in indices: # Create a new index create_index(app_config.elastic_config.elastic_search_url, app_config.elastic_config.index) # Bulk push the data i = 0 while i * constants.BULK_UPLOAD_SIZE < len(reviews): response = bulk_push_to_elastic( app_config.elastic_config.elastic_search_url, app_config.elastic_config.index, reviews[i * constants.BULK_UPLOAD_SIZE:min((i + 1) * constants.BULK_UPLOAD_SIZE, len(reviews))]) if response.status_code != 200: print( "[Error] push_data_to_elasticsearch :: Got status code : ", response.status_code) print("[Error] push_data_to_elasticsearch :: Response is : ", response.text) i += 1
def parse_reviews(): # Read all the app-config file names app_configs = utils.open_json( constants.APP_CONFIG_FILE.format( file_name=constants.APP_CONFIG_FILE_NAME)) for app_config_file in app_configs: app_config = AppConfig(utils.open_json(app_config_file)) parsed_reviews = [] # We now read the review details for each channel for review_channel in app_config.review_channels: # We parse the channels only if its enabled! if review_channel.is_channel_enabled and review_channel.channel_type != ReviewChannelTypes.BLANK: raw_user_reviews_file_path = constants.RAW_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data. base_folder, dir_name=app_config.fawkes_internal_config.data. raw_data_folder, app_name=app_config.app.name, channel_name=review_channel.channel_name, extension=review_channel.file_type) if review_channel.file_type == constants.JSON: # Parse JSON channel_reviews = parse_json(raw_user_reviews_file_path, review_channel, app_config) elif review_channel.file_type == constants.CSV: # Parse CSV channel_reviews = parse_csv(raw_user_reviews_file_path, review_channel, app_config) else: # Unsupported file format raise ( "Format not supported exception. Check your file-type key in your config." ) parsed_reviews += channel_reviews # Executing custom code after parsing. if app_config.custom_code_module_path != None: custom_code_module = importlib.import_module( app_config.custom_code_module_path, package=None) parsed_reviews = custom_code_module.run_custom_code_post_parse( parsed_reviews) # After parsing the reviews for that all channels, we dump it into a file. # The file has a particular format. # {base_folder}/{dir_name}/{app_name}/parsed-user-feedback.{extension} parsed_user_reviews_file_path = constants.PARSED_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.parsed_data_folder, app_name=app_config.app.name, ) # Create the intermediate folders dir_name = os.path.dirname(parsed_user_reviews_file_path) pathlib.Path(dir_name).mkdir(parents=True, exist_ok=True) utils.dump_json( [parsed_review.to_dict() for parsed_review in parsed_reviews], parsed_user_reviews_file_path)
def dump_lifetime_ratings(): app_configs = utils.open_json( constants.APP_CONFIG_FILE.format( file_name=constants.APP_CONFIG_FILE_NAME)) for app_config_file in app_configs: app_config = AppConfig(utils.open_json(app_config_file)) if app_config.elastic_config.lifetime_rating_index != None: time = datetime.strftime(datetime.now() - timedelta(1), constants.TIMESTAMP_FORMAT) playstore_rating = getPlayStoreLifetimeRating(app_config) appstore_rating = getAppStoreLifetimeRating(app_config) # Creating template for uploading lifetime rating playstore_doc = Review( {}, timestamp=time, rating=playstore_rating, app_name=app_config.app.name, channel_name="playstore-lifetime", channel_type="playstore-lifetime", hash_id=utils.calculate_hash(app_config.app.name + ReviewChannelTypes.ANDROID)) appstore_doc = Review( {}, timestamp=time, rating=playstore_rating, app_name=app_config.app.name, channel_name="appstore-lifetime", channel_type="appstore-lifetime", hash_id=utils.calculate_hash(app_config.app.name + ReviewChannelTypes.IOS)) # Deleting document to override elasticsearch.delete_document( app_config.elastic_config.elastic_search_url, app_config.elastic_config.lifetime_rating_index, "_doc", playstore_doc.hash_id) elasticsearch.delete_document( app_config.elastic_config.elastic_search_url, app_config.elastic_config.lifetime_rating_index, "_doc", appstore_doc.hash_id) # Uploading again elasticsearch.create_document( app_config.elastic_config.elastic_search_url, app_config.elastic_config.lifetime_rating_index, "_doc", playstore_doc.hash_id, playstore_doc) elasticsearch.create_document( app_config.elastic_config.elastic_search_url, app_config.elastic_config.lifetime_rating_index, "_doc", appstore_doc.hash_id, appstore_doc)
def parse_keywords_file(keyword_file_name, enable_remove_stop_words=True): # Topics is a dict, key = Topic Name. value = list of words and weights. topics = {} keywords_list = utils.open_json(keyword_file_name) for topic_keyword in keywords_list: topic = {} line = " ".join(keywords_list[topic_keyword]) # Remove all trailing and beginning write spaces line = line.lower() line = line.strip() # We will replace all the non-alphabet charectors with a space cleaned_line = re.sub("[^a-zA-Z]+", " ", line) # Replace multiple spaces with a single space cleaned_line = re.sub(" +", " ", cleaned_line) # Split the line according to space to get the words cleaned_line = cleaned_line.split() # Remove the stopwords. if enable_remove_stop_words: cleaned_line = utils.remove_stop_words(cleaned_line) # For each word assign a weight for word in list(set(cleaned_line)): # Add the word to the topic topic[lmtzr.lemmatize(word.lower())] = 1 topics[topic_keyword] = topic return topics
def parse_json(raw_user_reviews_file_path, review_channel, app_config): """ Parses the JSON files to a Review object """ reviews = utils.open_json(raw_user_reviews_file_path) parsed_reviews = [] for review in reviews: # TODO: Conver this to a standard format like jsonpath message = utils.get_json_key_value( review, review_channel.message_key.split(".")) timestamp = utils.get_json_key_value( review, review_channel.timestamp_key.split(".")) rating = None if review_channel.rating_key != None: rating = utils.get_json_key_value( review, review_channel.rating_key.split(".")) # Add the review object to the parsed reviews parsed_reviews.append( Review( review, message=message, timestamp=timestamp, rating=rating, app_name=app_config.app.name, channel_name=review_channel.channel_name, channel_type=review_channel.channel_type, review_timezone=review_channel.timezone, timestamp_format=review_channel.timestamp_format, )) return parsed_reviews
def generate_keyword_weights(): app_configs = utils.open_json( constants.APP_CONFIG_FILE.format( file_name=constants.APP_CONFIG_FILE_NAME)) for app_config_file in app_configs: app_config = AppConfig(utils.open_json(app_config_file)) # First look at the category keywords. utils.dump_json( parse_keywords_file( app_config.algorithm_config.category_keywords_file), app_config.algorithm_config.category_keywords_weights_file, ) # Then look at the bug-feature keywords utils.dump_json( parse_keywords_file( app_config.algorithm_config.bug_feature_keywords_file, False), app_config.algorithm_config.bug_feature_keywords_weights_file, )
def fetch_reviews(): # Read the app-config.json file. app_configs = utils.open_json( constants.APP_CONFIG_FILE.format(file_name=constants.APP_CONFIG_FILE_NAME) ) # For every app registered in app-config.json we for app_config_file in app_configs: # Creating an AppConfig object app_config = AppConfig( utils.open_json( app_config_file ) ) # Each app has a list of review channels from which the user reviews are fetched. for review_channel in app_config.review_channels: if review_channel.is_channel_enabled and review_channel.channel_type != ReviewChannelTypes.BLANK: # Depending on the channel type, we have different "fetchers" to get the data. if review_channel.channel_type == ReviewChannelTypes.TWITTER: reviews = tweets.fetch( review_channel ) elif review_channel.channel_type == ReviewChannelTypes.SALESFORCE: reviews = salesforce.fetch( review_channel ) elif review_channel.channel_type == ReviewChannelTypes.SPREADSHEET: reviews = spreadsheet.fetch( review_channel ) elif review_channel.channel_type == ReviewChannelTypes.CSV: reviews = comma_separated_values.fetch( review_channel ) elif review_channel.channel_type == ReviewChannelTypes.ANDROID: reviews = playstore.fetch( review_channel ) elif review_channel.channel_type == ReviewChannelTypes.IOS: reviews = appstore.fetch( review_channel ) else: continue # After fetching the review for that particular channel, we dump it into a file. # The file has a particular format. # {base_folder}/{dir_name}/{app_name}/{channel_name}-raw-feedback.{extension} raw_user_reviews_file_path = constants.RAW_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.raw_data_folder, app_name=app_config.app.name, channel_name=review_channel.channel_name, extension=review_channel.file_type) # Create the intermediate folders dir_name = os.path.dirname(raw_user_reviews_file_path) pathlib.Path(dir_name).mkdir(parents=True, exist_ok=True) if review_channel.file_type == constants.JSON: utils.dump_json(reviews, raw_user_reviews_file_path) else: with open(raw_user_reviews_file_path) as file: file.write(reviews) # There are lot of use-cases where we need to execute custom code after the data is fetched. # This might include data-transformation, cleanup etc. # This is the right place to do that. if app_config.custom_code_module_path != None: custom_code_module = importlib.import_module(app_config.custom_code_module_path, package=None) reviews = custom_code_module.run_custom_code_post_fetch()
category = review1.derived_insight.category # If the category has not been found, it will be "uncategorized" # All reviews in uncategorized have a score of 0 # So we return True in such cases if category != constants.CATEGORY_NOT_FOUND: return (review2.derived_insight.extra_properties[ constants.CATEGORY_SCORES][category] - review1.derived_insight.extra_properties[ constants.CATEGORY_SCORES][category]) else: return True if __name__ == "__main__": app_configs = utils.open_json( constants.APP_CONFIG_FILE.format( file_name=constants.APP_CONFIG_FILE_NAME)) for app_config_file in app_configs: app_config = AppConfig(utils.open_json(app_config_file)) # Path where the user reviews were stored after parsing. processed_user_reviews_file_path = constants.PROCESSED_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data. processed_data_folder, app_name=app_config.app.name, ) # Loading the reviews reviews = utils.open_json(processed_user_reviews_file_path) # Converting the json object to Review object
def run_algo(): app_configs = utils.open_json( constants.APP_CONFIG_FILE.format(file_name=constants.APP_CONFIG_FILE_NAME) ) for app_config_file in app_configs: app_config = AppConfig( utils.open_json( app_config_file ) ) # Path where the user reviews were stored after parsing. parsed_user_reviews_file_path = constants.PARSED_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.parsed_data_folder, app_name=app_config.app.name, ) # Loading the reviews reviews = utils.open_json(parsed_user_reviews_file_path) # Converting the json object to Review object reviews = [Review.from_review_json(review) for review in reviews] # Filtering out reviews which are not applicable. reviews = filter_utils.filter_reviews_by_time( filter_utils.filter_reviews_by_channel( reviews, filter_utils.filter_disabled_review_channels( app_config ), ), datetime.now(timezone.utc) - timedelta(days=app_config.algorithm_config.algorithm_days_filter) ) # Number of process to make num_processes = min(constants.PROCESS_NUMBER, os.cpu_count()) if constants.CIRCLECI in os.environ: num_processes = 2 # Adding sentiment with Pool(num_processes) as process: reviews = process.map(add_review_sentiment_score, reviews) if app_config.algorithm_config.categorization_algorithm != None and app_config.algorithm_config.category_keywords_weights_file != None: # We read from the topic file first topics = {} topics = utils.open_json(app_config.algorithm_config.category_keywords_weights_file) # Adding text-match categorization with Pool(num_processes) as process: reviews = process.map( partial( text_match_categortization, app_config=app_config, topics=topics ), reviews ) if app_config.algorithm_config.bug_feature_keywords_weights_file != None: # We read from the topic file first topics = {} topics = utils.open_json(app_config.algorithm_config.bug_feature_keywords_weights_file) # Adding bug/feature classification with Pool(num_processes) as process: reviews = process.map( partial( bug_feature_classification, topics=topics ), reviews ) if app_config.algorithm_config.categorization_algorithm == CategorizationAlgorithms.LSTM_CLASSIFICATION: # Load the TensorFlow model model = tf.keras.models.load_model( constants.LSTM_CATEGORY_MODEL_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.models_folder, app_name=app_config.app.name, ) ) # Load the article tokenizer file tokenizer_json = utils.open_json( constants.LSTM_CATEGORY_ARTICLE_TOKENIZER_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.models_folder, app_name=app_config.app.name, ), ) article_tokenizer = tf.keras.preprocessing.text.tokenizer_from_json( tokenizer_json ) # Load the label tokenizer file tokenizer_json = utils.open_json( constants.LSTM_CATEGORY_LABEL_TOKENIZER_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.models_folder, app_name=app_config.app.name, ), ) label_tokenizer = tf.keras.preprocessing.text.tokenizer_from_json( tokenizer_json ) cleaned_labels = {} for review in reviews: label = review.derived_insight.category cleaned_label = re.sub(r'\W+', '', label) cleaned_label = cleaned_label.lower() cleaned_labels[cleaned_label] = label # Adding LSTM categorization reviews = lstm_classification( reviews, model, article_tokenizer, label_tokenizer, cleaned_labels ) # Create the intermediate folders processed_user_reviews_file_path = constants.PROCESSED_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.processed_data_folder, app_name=app_config.app.name, ) dir_name = os.path.dirname(processed_user_reviews_file_path) pathlib.Path(dir_name).mkdir(parents=True, exist_ok=True) utils.dump_json( [review.to_dict() for review in reviews], processed_user_reviews_file_path, )
def train_lstm_model(): app_configs = utils.open_json( constants.APP_CONFIG_FILE.format( file_name=constants.APP_CONFIG_FILE_NAME)) for app_config_file in app_configs: app_config = AppConfig(utils.open_json(app_config_file)) print("[LOG] going through app config ", app_config.app.name) # Path where the user reviews were stored after parsing. processed_user_reviews_file_path = constants.PROCESSED_USER_REVIEWS_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data. processed_data_folder, app_name=app_config.app.name, ) if not (app_config.algorithm_config.categorization_algorithm != None and app_config.algorithm_config.categorization_algorithm == CategorizationAlgorithms.LSTM_CLASSIFICATION): continue # Loading the reviews reviews = utils.open_json(processed_user_reviews_file_path) # Converting the json object to Review object reviews = [Review.from_review_json(review) for review in reviews] # reviews = utils.filter_reviews(reviews, app_config) articles, labels, cleaned_labels = get_articles_and_labels(reviews) trained_model, article_tokenizer, label_tokenizer = train( articles, labels) trained_lstm_categorization_model_file_path = constants.LSTM_CATEGORY_MODEL_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.models_folder, app_name=app_config.app.name, ) dir_name = os.path.dirname(trained_lstm_categorization_model_file_path) pathlib.Path(dir_name).mkdir(parents=True, exist_ok=True) trained_model.save(trained_lstm_categorization_model_file_path) # Saving the tokenizers utils.dump_json( article_tokenizer.to_json(), constants.LSTM_CATEGORY_ARTICLE_TOKENIZER_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.models_folder, app_name=app_config.app.name, ), ) # Saving the tokenizers utils.dump_json( label_tokenizer.to_json(), constants.LSTM_CATEGORY_LABEL_TOKENIZER_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.models_folder, app_name=app_config.app.name, ), )
def test_sanity(self): """ Test for sanity that parsing and algorithms are working """ # First we parse the sample data. parse.parse_reviews() parsed_output = utils.open_json( "data/parsed_data/sample-mint/parsed-user-feedback.json") expected_parsed_output = [{ "message": "I just heard about this budgeting app. So I gave it a try. I am impressed thus far. However I still cant add all of my financial institutions so my budget is kind of skewed. But other that I can say Im more aware of my spending", "timestamp": "2020/03/15 14:13:17", "rating": 5, "app_name": "sample-mint", "channel_name": "appstore", "channel_type": "ios", "hash_id": "de848685d11742dbea77e1e5ad7b892088ada9c9", "derived_insight": { "sentiment": None, "category": "uncategorized", "extra_properties": {} } }] self.assertEqual(parsed_output, expected_parsed_output) # Before running the algorithms, we generate the keyword weights. generate_keyword_weights.generate_keyword_weights() # We run the algorithms on that data algo.run_algo() processed_output = utils.open_json( "data/processed_data/sample-mint/processed-user-feedback.json") expected_processed_output = [{ "message": "I just heard about this budgeting app. So I gave it a try. I am impressed thus far. However I still cant add all of my financial institutions so my budget is kind of skewed. But other that I can say Im more aware of my spending", "timestamp": "2020/03/15 14:13:17", "rating": 5, "app_name": "sample-mint", "channel_name": "appstore", "channel_type": "ios", "hash_id": "6dde3aa82726c0a9e3777623854d839184767571", "derived_insight": { "sentiment": { "neg": 0.0, "neu": 0.928, "pos": 0.072, "compound": 0.4767 }, "category": "Application", "extra_properties": { "category_scores": { "User Experience": 0, "sign-in/sign-up": 0, "Notification": 0, "Application": 1, "ads": 0 }, "bug_feature": "feature" } } }] self.assertEqual(processed_output, expected_processed_output)
sendgrid_api_key): message = Mail(from_email=from_email_address, to_emails=to_email, subject=subject, html_content=html) try: sg = SendGridAPIClient(sendgrid_api_key) response = sg.send(message) print("[LOG] Email to ", to_email, response.status_code) except Exception as e: print(e.message) if __name__ == "__main__": app_configs = utils.open_json( constants.APP_CONFIG_FILE.format(file_name=constants.APP_CONFIG_FILE_NAME) ) for app_config_file in app_configs: app_config = AppConfig( utils.open_json( app_config_file ) ) # Path where the generated email in html format will be stored email_summary_generated_file_path = constants.EMAIL_SUMMARY_GENERATED_FILE_PATH.format( base_folder=app_config.fawkes_internal_config.data.base_folder, dir_name=app_config.fawkes_internal_config.data.emails_folder, app_name=app_config.app.name, ) dir_name = os.path.dirname(email_summary_generated_file_path)