fix(data): 更新数据文件路径- 将 GoogleProducts.csv 和 AmazonProducts.csv 替换为 Google.csv 和 Amazon.csv

- 确保代码能够正确加载数据文件
This commit is contained in:
fly6516 2025-04-16 09:45:22 +08:00
parent 4233cfc792
commit 4c79cad322

4
3-1.py
View File

@ -42,8 +42,8 @@ if __name__ == "__main__":
stopwords = load_stopwords(sc)
# 加载数据
google = sc.textFile("hdfs://master:9000/user/root/GoogleProducts.csv")
amazon = sc.textFile("hdfs://master:9000/user/root/AmazonProducts.csv")
google = sc.textFile("hdfs://master:9000/user/root/Google.csv")
amazon = sc.textFile("hdfs://master:9000/user/root/Amazon.csv")
# 提取内容
google_rdd = google.map(lambda line: extract_info(line, "google")) \