def remove_stop_words(column): '''gets rid of any words that are on the stop word list''' cleaned_responses = [] for response in column: cleaned_response = TextBlob('').words for word in response: if word not in stop_words: cleaned_response.append(word) cleaned_responses.append(cleaned_response) return cleaned_responses
def column_lemmatize(column): '''Lemmatizes down an entire column''' lemmatized_goals = [] for response in column.apply(lambda goal: goal.tags): lemmatized_words = TextBlob('').words for word_and_tag in response: corrected_tag = _penn_to_wordnet(word_and_tag[1]) lemmatized_words.append(word_and_tag[0].lemmatize(corrected_tag)) lemmatized_goals.append(lemmatized_words) return lemmatized_goals
score.sentiment import pandas as pd df = pd.DataFrame() tweets = [] for i in public_tweets: tweets.append(i.text) df['Tweets'] = tweets df sentiment = [] for i in public_tweets: s = (TextBlob(i.text)).sentiment sentiment.append(s) df['Sentiments'] = sentiment df score = [] for i in public_tweets: s = (TextBlob(i.text)).sentiment if s[0] > 0: score.append("Postive") elif s[0] < 0: score.append("Negative") else: score.append("Neutral") df['Score'] = score df
import pandas as pd data = pd.DataFrame() # Extract the 15 tweets tweets = [] for i in public_tweets: tweets.append(i.text) data['Tweets'] = tweets print(data) # Calculating the score for 15 tweets score = [] for i in public_tweets: s = (TextBlob(i.text)).sentiment score.append(s) data['Sentiments'] = score print(data) metrics = [] for i in public_tweets: s = (TextBlob(i.text)).sentiment if s[0] > 0: metrics.append("Positive") elif s[0] < 0: metrics.append("Negative") else: metrics.append("Neutral") data['Metric'] = metrics print(data)