def nlp_sentiment_analysis(movies, movies_data):
"""
This function creates a dictionary to store the normalized sentiment data for each movie
"""
sentiment_analysis = {}
for movie in movies:
reviews = movies_data[movie]
sentiment_data = {}
for review in reviews:
review_text = review["reviewText"]
review_anaylsis = SentimentIntensityAnalyzer().polarity_scores(
review_text)
for key in review_anaylsis.keys():
if key in sentiment_data:
sentiment_data[key] += review_anaylsis[key]
else:
sentiment_data[key] = review_anaylsis[key]
normalize_sent_data = normalize_sentiment(sentiment_data, len(reviews))
sentiment_analysis[movie] = normalize_sent_data
visualize_sentiment(sentiment_analysis)
return sentiment_analysis
def polarity(dataframe, review_column):
"""
Takes a dataframe and the column name containing text to calculate the
sentiment polarity of. Calculates polarity then appends to existing
dataframe to return.
:params dataframe dataframe:
:params review_column string:
:returns dataframe:
"""
# Datatype checks
if not isinstance(dataframe, pd.DataFrame):
raise ValueError('dataframe is not a pandas dataframe')
if not isinstance(review_column, str):
raise ValueError('review_column is not a string')
if not review_column in dataframe:
raise ValueError('review_column is not in the dataframe')
dataframe = dataframe.dropna()
rows = dataframe.shape[0]
scores_array = np.zeros([rows, 4])
keys = []
index_1 = 0
for review in dataframe[review_column]:
scores = SentimentIntensityAnalyzer().polarity_scores(review)
scores_array[index_1] = list(scores.values())
if index_1 == 0:
keys = list(scores.keys())
index_1 += 1
index_2 = 0
for k in keys:
dataframe[k] = scores_array[:, index_2]
index_2 += 1
return dataframe
