Commit 742efdac by 20200203063

Replace main.py

parent cd63b2bd
def get_review_summary_for_business(biz_id):
# 获取每一个business的评论总结
# encoding: utf-8
import pandas as pd
import json
from business import Business
import time
def get_review_summary_for_business(biz_id,review_df):
# 获取每一个business的评论总结
business = Business(review_df)
return business.aspect_based_summary()
def main():
bus_ids = [] # 指定几个business ids
review_path = "data/review.json"
reviews = []
with open(review_path,"r",encoding="utf-8") as f:
for line in f.readlines():
if len(line.strip()) == 0:
continue
ele = json.loads(line.strip())
reviews.append(ele)
review_df = pd.DataFrame(reviews)
print(len(review_df))
print(review_df.head())
bus_ids = ["4JNXUYY8wbaaDmk3BPzlWw"] # 指定几个business ids
for bus_id in bus_ids:
print ("Working on biz_id %s" % bus_id)
start = time.time()
summary = get_review_summary_for_business(bus_id)
summary = get_review_summary_for_business(bus_id,review_df[review_df.business_id==bus_id])
# format and print....
print(summary)
print("--------------------------------------------------------")
if __name__ == "__main__":
main()
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment