酒店评论的情感分析¶

def replace_address(row):
    if "Netherlands" in row["Hotel_Address"]:
        return "Amsterdam, Netherlands"
    elif "Barcelona" in row["Hotel_Address"]:
        return "Barcelona, Spain"
    elif "United Kingdom" in row["Hotel_Address"]:
        return "London, United Kingdom"
    elif "Milan" in row["Hotel_Address"]:        
        return "Milan, Italy"
    elif "France" in row["Hotel_Address"]:
        return "Paris, France"
    elif "Vienna" in row["Hotel_Address"]:
        return "Vienna, Austria" 

# 将所有地址替换为更简短、更有用的形式
df["Hotel_Address"] = df.apply(replace_address, axis = 1)
#  value_counts()的总和应等于评论的总数
print(df["Hotel_Address"].value_counts())

display(df.groupby("Hotel_Address").agg({"Hotel_Name": "nunique"}))

# 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)

# 将标签处理为新列
# 文件Hotel_Reviews_Tags.py识别了最重要的标签
# 休闲旅行、情侣、独自旅行者、商务旅行、与朋友一起旅行的人合并后的团体、
# 带幼儿的家庭、带大孩子的家庭、带宠物
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)

# 保存包含计算列的新数据文件
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')

# 从CSV加载筛选后的酒店评论
df = pd.read_csv('../../data/Hotel_Reviews_Filtered.csv')

# 在此处添加你的代码


# 最后记得保存添加了新NLP数据的酒店评论
print("Saving results to Hotel_Reviews_NLP.csv")
df.to_csv(r'../data/Hotel_Reviews_NLP.csv', index = False)

from nltk.corpus import stopwords

# 从CSV加载酒店评论
df = pd.read_csv("../../data/Hotel_Reviews_Filtered.csv")

# 移除停用词——处理大量文本时可能较慢！
# Ryan Han（Kaggle上的ryanxjhan）发布了一篇很棒的帖子，对比了不同停用词移除方法的性能
# https://www.kaggle.com/ryanxjhan/fast-stop-words-removal # 采用Ryan推荐的方法
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

# 从两个列中移除停用词
df.Negative_Review = df.Negative_Review.apply(remove_stopwords)   
df.Positive_Review = df.Positive_Review.apply(remove_stopwords)

from nltk.sentiment.vader import SentimentIntensityAnalyzer

# 创建vader情感分析器（NLTK中还有其他分析器可供尝试）
vader_sentiment = SentimentIntensityAnalyzer()
# Hutto, C.J. & Gilbert, E.E. (2014). VADER: 一种用于社交媒体文本情感分析的简洁规则模型。第八届网络日志和社交媒体国际会议（ICWSM-14）。美国密歇根州安阿伯，2014年6月。

# 评论的输入有3种可能：
# 可能是"No Negative"（无负面内容），此时返回0
# 可能是"No Positive"（无正面内容），此时返回0
# 可能是一条评论，此时计算其情感得分
def calc_sentiment(review):    
    if review == "No Negative" or review == "No Positive":
        return 0
    return vader_sentiment.polarity_scores(review)["compound"]    

# 添加负面情感和正面情感列
print("计算正面和负面评论的情感列")
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("计算情感耗时" + str(round(end - start, 2)) + "秒")

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"]])

# 重新排列列（仅为美化，方便后续探索数据）
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("将结果保存到Hotel_Reviews_NLP.csv")
df.to_csv(r"../data/Hotel_Reviews_NLP.csv", index = False)