【NLP】情绪分析与酒店评论

# Drop `Additional_Number_of_Scoring`
df.drop(["Additional_Number_of_Scoring"], axis = 1, inplace=True)
# Replace `Total_Number_of_Reviews` and `Average_Score` with our own calculated values
df.Total_Number_of_Reviews = df.groupby('Hotel_Name').transform('count')
df.Average_Score = round(df.groupby('Hotel_Name').Reviewer_Score.transform('mean'), 1)

# Remove opening and closing brackets
df.Tags = df.Tags.str.strip("[']")
# remove all quotes too
df.Tags = df.Tags.str.replace(" ', '", ",", regex = False)

# Process the Tags into new columns
# The file Hotel_Reviews_Tags.py, identifies the most important tags
# Leisure trip, Couple, Solo traveler, Business trip, Group combined with Travelers with friends, 
# Family with young children, Family with older children, With a pet
df["Leisure_trip"] = df.Tags.apply(lambda tag: 1 if "Leisure trip" in tag else 0)
df["Couple"] = df.Tags.apply(lambda tag: 1 if "Couple" in tag else 0)
df["Solo_traveler"] = df.Tags.apply(lambda tag: 1 if "Solo traveler" in tag else 0)
df["Business_trip"] = df.Tags.apply(lambda tag: 1 if "Business trip" in tag else 0)
df["Group"] = df.Tags.apply(lambda tag: 1 if "Group" in tag or "Travelers with friends" in tag else 0)
df["Family_with_young_children"] = df.Tags.apply(lambda tag: 1 if "Family with young children" in tag else 0)
df["Family_with_older_children"] = df.Tags.apply(lambda tag: 1 if "Family with older children" in tag else 0)
df["With_a_pet"] = df.Tags.apply(lambda tag: 1 if "With a pet" in tag else 0)

df.drop(["Review_Total_Negative_Word_Counts", "Review_Total_Positive_Word_Counts", "days_since_review", "Total_Number_of_Reviews_Reviewer_Has_Given"], axis = 1, inplace=True)

# Saving new data file with calculated columns
print("Saving results to Hotel_Reviews_Filtered.csv")
df.to_csv(r'../data/Hotel_Reviews_Filtered.csv', index = False)

import time
import pandas as pd
import nltk as nltk
from nltk.corpus import stopwords
from nltk.sentiment.vader import SentimentIntensityAnalyzer
nltk.download('vader_lexicon')

# Load the filtered hotel reviews from CSV
df = pd.read_csv('../../data/Hotel_Reviews_Filtered.csv')

# You code will be added here


# Finally remember to save the hotel reviews with new NLP data added
print("Saving results to Hotel_Reviews_NLP.csv")
df.to_csv(r'../data/Hotel_Reviews_NLP.csv', index = False)

from nltk.corpus import stopwords

# Load the hotel reviews from CSV
df = pd.read_csv("../../data/Hotel_Reviews_Filtered.csv")

# Remove stop words - can be slow for a lot of text!
# Ryan Han (ryanxjhan on Kaggle) has a great post measuring performance of different stop words removal approaches
# https://www.kaggle.com/ryanxjhan/fast-stop-words-removal # using the approach that Ryan recommends
start = time.time()
cache = set(stopwords.words("english"))
def remove_stopwords(review):
    text = " ".join([word for word in review.split() if word not in cache])
    return text

# Remove the stop words from both columns
df.Negative_Review = df.Negative_Review.apply(remove_stopwords)   
df.Positive_Review = df.Positive_Review.apply(remove_stopwords)

from nltk.sentiment.vader import SentimentIntensityAnalyzer

# Create the vader sentiment analyser (there are others in NLTK you can try too)
vader_sentiment = SentimentIntensityAnalyzer()
# Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.

# There are 3 possibilities of input for a review:
# It could be "No Negative", in which case, return 0
# It could be "No Positive", in which case, return 0
# It could be a review, in which case calculate the sentiment
def calc_sentiment(review):    
    if review == "No Negative" or review == "No Positive":
        return 0
    return vader_sentiment.polarity_scores(review)["compound"]   

# Add a negative sentiment and positive sentiment column
print("Calculating sentiment columns for both positive and negative reviews")
start = time.time()
df["Negative_Sentiment"] = df.Negative_Review.apply(calc_sentiment)
df["Positive_Sentiment"] = df.Positive_Review.apply(calc_sentiment)
end = time.time()
print("Calculating sentiment took " + str(round(end - start, 2)) + " seconds")

df = df.sort_values(by=["Negative_Sentiment"], ascending=True)
print(df[["Negative_Review", "Negative_Sentiment"]])
df = df.sort_values(by=["Positive_Sentiment"], ascending=True)
print(df[["Positive_Review", "Positive_Sentiment"]])

# Reorder the columns (This is cosmetic, but to make it easier to explore the data later)
df = df.reindex(["Hotel_Name", "Hotel_Address", "Total_Number_of_Reviews", "Average_Score", "Reviewer_Score", "Negative_Sentiment", "Positive_Sentiment", "Reviewer_Nationality", "Leisure_trip", "Couple", "Solo_traveler", "Business_trip", "Group", "Family_with_young_children", "Family_with_older_children", "With_a_pet", "Negative_Review", "Positive_Review"], axis=1)

print("Saving results to Hotel_Reviews_NLP.csv")
df.to_csv(r"../data/Hotel_Reviews_NLP.csv", index = False)