diff --git b/.gitignore a/.gitignore
new file mode 100644
index 0000000..07f43b8
--- /dev/null
+++ a/.gitignore
@@ -0,0 +1 @@
+data/*
\ No newline at end of file
diff --git b/business.py a/business.py
new file mode 100644
index 0000000..fe4c528
--- /dev/null
+++ a/business.py
@@ -0,0 +1,118 @@
+# encoding: utf-8
+
+from model_training import SentimentModel
+from gen_id2business import id2business
+from tqdm import tqdm
+from sentence import Sentence
+import json
+import pandas as pd
+
+model_path = "model/model.pkl"
+vector_path = "model/vector.pkl"
+SENTIMENT_MODEL = SentimentModel() # 把已经训练好的模型存放在文件里，并导入进来
+
+class Business(object):
+ """
+ 用来表示跟business相关的变量和函数
+ """
+ def __init__(self, review_df):
+ # 初始化变量以及函数
+ self.review_df = review_df
+ self.business_id = self.review_df.iloc[0].business_id
+ self.business_name = id2business[self.business_id]["name"]
+ self.review_nps,self.aspects = self.extract_aspects()
+
+
+ def aspect_based_summary(self,threshold=0.5):
+ """
+ 返回一个business的summary. 针对于每一个aspect计算出它的正面负面情感以及TOP reviews.
+ 具体细节请看给定的文档。
+ """
+ aspect_info = []
+ for aspect in self.aspects:
+ aspect_info.append({
+ "aspect" : aspect,
+ "stars" : [],
+ "pos" : [],
+ "neg" : []
+ })
+ for idx in tqdm(range(len(self.review_df))):
+ review = self.review_df.iloc[idx]
+ text = review.text
+ current_review_nps = self.review_nps[idx]
+ for idx_aspect in range(len(self.aspects)):
+ aspect = self.aspects[idx_aspect]
+ if aspect in current_review_nps:
+ aspect_info[idx_aspect]["stars"].append(review.stars)
+ data = [text]
+ result,score = SENTIMENT_MODEL.predict(data,model_path=model_path,vectorizer_path=vector_path)
+ print(result,score)
+ if score[0][1] >= threshold:
+ aspect_info[idx_aspect]["pos"].append((idx,score[0]))
+ else:
+ aspect_info[idx_aspect]["neg"].append((idx,score[0]))
+
+ business_rating = 0
+ detail = []
+ for idx_aspect in range(len(self.aspects)):
+ aspect = self.aspects[idx_aspect]
+ business_rating += sum(aspect_info[idx_aspect]["stars"])
+ step_pos = len(aspect_info[idx_aspect]["pos"]) // 100 if len(aspect_info[idx_aspect]["pos"]) > 100 else 1
+ step_neg = len(aspect_info[idx_aspect]["neg"]) // 100 if len(aspect_info[idx_aspect]["neg"]) > 100 else 1
+ info = {"aspect":aspect,
+ "rating":sum(aspect_info[idx_aspect]["stars"])/len(aspect_info[idx_aspect]["stars"]),
+ "pos":list(map(lambda y: self.review_df.iloc[y[0]].text,sorted(aspect_info[idx_aspect]["pos"],key=lambda x: x[1])[::step_pos][:5])),
+ "neg":list(map(lambda y: self.review_df.iloc[y[0]].text,sorted(aspect_info[idx_aspect]["neg"],key=lambda x: x[1])[::step_neg][:5]))}
+ detail.append(info)
+
+ business_rating = business_rating/len(self.review_df)
+
+ return {'business_id': self.business_id,
+ 'business_name': self.business_name,
+ 'business_rating': business_rating,
+ 'aspect_summary': detail
+ }
+
+
+ def extract_aspects(self):
+ """
+ 从一个business的review中抽取aspects
+ """
+ np_dict = dict()
+ review_nps = []
+ for idx in tqdm(range(len(self.review_df))):
+ review = self.review_df.iloc[idx]
+ sen = Sentence(review.text)
+ nps = []
+ for np in sen.extract_noun_phrase():
+ print(np)
+ nps.append(np)
+ if np not in np_dict:
+ np_dict[np] = 0
+ np_dict[np] += 1
+ review_nps.append(nps)
+ sort_np_dict_items_top_5 = sorted(np_dict.items(),key=lambda x: x[1])[:5]
+ aspects = [aspect for aspect,times in sort_np_dict_items_top_5]
+ return review_nps,aspects
+
+if __name__ == "__main__":
+ 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())
+
+ business_ids = ["ujmEBvifdJM6h6RLv4wQIg"]
+ for business_id in business_ids:
+ current_review_df = review_df[review_df.business_id==business_id]
+ print(current_review_df.head())
+ print(len(current_review_df))
+ business = Business(current_review_df)
+ print("Aspects",business.aspects)
+ print(business.aspect_based_summary())
\ No newline at end of file
diff --git b/gen_id2business.py a/gen_id2business.py
new file mode 100644
index 0000000..663a53b
--- /dev/null
+++ a/gen_id2business.py
@@ -0,0 +1,33 @@
+# encoding: utf-8
+import json
+import pickle
+import os
+
+business_path = "data/business.json"
+save_id2business_path = "model/id2business.pkl"
+
+def load_id2business():
+ id2business = None
+ if not os.path.exists(save_id2business_path):
+ id2business = dict()
+ with open(business_path,"r",encoding="utf-8") as f:
+ for line in f.readlines():
+ if len(line.strip()) == 0:
+ continue
+ ele = json.loads(line.strip())
+ business_id = ele["business_id"]
+ if ele["business_id"] in id2business:
+ print("{} duplicated".format(str(business_id)))
+ continue
+ id2business[business_id] = ele
+
+ with open(save_id2business_path,'wb') as f:
+ pickle.dump(id2business,f)
+
+ else:
+ with open(save_id2business_path,'rb') as f:
+ id2business = pickle.load(f)
+ return id2business
+
+
+id2business = load_id2business()
\ No newline at end of file
diff --git b/gen_valid_business_id.py a/gen_valid_business_id.py
new file mode 100644
index 0000000..23d607d
--- /dev/null
+++ a/gen_valid_business_id.py
@@ -0,0 +1,30 @@
+#encoding: utf-8
+import pandas as pd
+import json
+from tqdm import tqdm
+
+review_path = "data/review.json"
+valid_business_id_path = "data/valid_business_id.txt"
+def gen_valid_business_id(review_path,count_citerion=100):
+ valid_business = []
+ count_business_id = dict()
+ reviews = []
+ with open(review_path,"r",encoding="utf-8") as f:
+ for line in tqdm(f.readlines()):
+ if len(line.strip()) == 0:
+ continue
+ ele = json.loads(line.strip())
+ if not ele["business_id"] in count_business_id:
+ count_business_id[ele["business_id"]] = 0
+ count_business_id[ele["business_id"]] += 1
+ reviews.append(ele)
+ review_df = pd.DataFrame(reviews)
+ print("total count of business id in {}: {}".format(len(count_business_id),review_path))
+ for key,value in count_business_id.items():
+ if value >= count_citerion:
+ valid_business.append("{}\t{}".format(str(key),str(value)))
+ return valid_business
+
+valid_business = gen_valid_business_id(review_path,count_citerion=100)
+with open(valid_business_id_path,'w',encoding='utf-8') as f:
+ f.write("\n".join(valid_business))
diff --git b/main.py a/main.py
new file mode 100644
index 0000000..a15bf60
--- /dev/null
+++ a/main.py
@@ -0,0 +1,40 @@
+# 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():
+ 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,review_df[review_df.business_id==bus_id])
+
+ # format and print....
+ print(summary)
+ print("--------------------------------------------------------")
+
+if __name__ == "__main__":
+ main()
+
+
diff --git b/model/README.md a/model/README.md
new file mode 100644
index 0000000..f640b12
--- /dev/null
+++ a/model/README.md
@@ -0,0 +1 @@
+这里存放已经训练好的模型（情感分析模型或者其他模型）。模型方面请提前训练好，然后serialize到一个文件里，运行的时候直接使用即可以。
diff --git b/model/id2business.pkl a/model/id2business.pkl
new file mode 100644
index 0000000..77d2ad1
Binary files /dev/null and a/model/id2business.pkl differ
diff --git b/model/model.pkl a/model/model.pkl
new file mode 100644
index 0000000..bdbc4f9
Binary files /dev/null and a/model/model.pkl differ
diff --git b/model/vector.pkl a/model/vector.pkl
new file mode 100644
index 0000000..f67b569
Binary files /dev/null and a/model/vector.pkl differ
diff --git b/model_training.py a/model_training.py
new file mode 100644
index 0000000..359977b
--- /dev/null
+++ a/model_training.py
@@ -0,0 +1,95 @@
+# encoding: utf-8
+# 此文件包含模型的训练。 给定数据集，训练出情感分类模型，并把模型文件存放在 model文件夹里。
+from sklearn.feature_extraction.text import TfidfVectorizer
+from nltk.tokenize import word_tokenize
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import train_test_split
+import pickle
+import json
+import pandas as pd
+from tqdm import tqdm
+
+class SentimentModel(object):
+ def __init__(self,df_review=None,pos_star=4,neg_star=2):
+ if df_review is not None:
+ self.pos_review = []
+ self.neg_review = []
+ for idx in tqdm(range(len(df_review))):
+ review = df_review.iloc[idx]
+ if review.stars >= pos_star:
+ self.pos_review.append(" ".join([ word for word in word_tokenize(review.text)]))
+ elif review.stars <= neg_star:
+ self.neg_review.append(" ".join([ word for word in word_tokenize(review.text)]))
+ print("样本统计:\n正例: {}\n负例: {}".format(len(self.pos_review),len(self.neg_review)))
+ # print("样本示例:\n正例: {}\n负例: {}".format("\n".join(self.pos_review[:2]),"\n".join(self.neg_review[:2])))
+ self.vectorizer = TfidfVectorizer()
+ corpus = self.pos_review + self.neg_review
+ self.X = self.vectorizer.fit_transform(corpus)
+ self.y = [1] * len(self.pos_review) + [0] * len(self.neg_review)
+ else:
+ self.clf = None
+ self.vectorizer = None
+
+
+ def train(self,test_size=0.25,*args,**kwargs):
+ if kwargs["save_model_path"] is not None:
+ save_model_path = kwargs["save_model_path"]
+ if kwargs["save_vectorizer_path"] is not None:
+ save_vectorizer_path = kwargs["save_vectorizer_path"]
+ self.clf = LogisticRegression(random_state=0,C=10)
+ X_train, X_test, y_train, y_test = train_test_split(self.X, self.y, test_size=test_size, random_state=0)
+ self.clf.fit(X_train,y_train)
+ score = self.clf.score(X_test,y_test)
+ with open(save_model_path,"wb") as f:
+ pickle.dump(self.clf,f)
+ with open(save_vectorizer_path,"wb") as f:
+ pickle.dump(self.vectorizer,f)
+ print("Finish training, score is {}.".format(str(score)))
+
+ def predict(self,*args,**kwargs):
+ if self.clf is None:
+ if kwargs["model_path"] is not None:
+ model_path = kwargs["model_path"]
+ with open(model_path,'rb') as f:
+ self.clf = pickle.load(f)
+ else:
+ raise Exception("model_path missing")
+ if self.vectorizer is None:
+ if kwargs["vectorizer_path"] is not None:
+ vectorizer_path = kwargs["vectorizer_path"]
+ with open(vectorizer_path,'rb') as f:
+ self.vectorizer = pickle.load(f)
+ else:
+ raise Exception("vectorizer_path missing")
+ data = args[0]
+ tmp = []
+ for d in data:
+ tmp.append(" ".join([word for word in word_tokenize(d)]))
+ data = tmp
+ features = self.vectorizer.transform(data)
+ result = self.clf.predict(features)
+ score = self.clf.predict_proba(features)
+ return result,score
+
+if __name__ == "__main__":
+ review_path = "data/review.json"
+ model_path = "model/model.pkl"
+ vector_path = "model/vector.pkl"
+ is_train = False
+ if is_train:
+ 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(review_df.head())
+ model = SentimentModel(review_df)
+ model.train(save_model_path=model_path,save_vectorizer_path=vector_path)
+ else:
+ model = SentimentModel()
+ data = ["Total bill for this horrible service? Over $8Gs. These crooks actually had the nerve to charge us $69 for 3 pills. I checked online the pills can be had for 19 cents EACH! Avoid Hospital ERs at all costs.","kkkkkk"]
+ result,score = model.predict(data,model_path=model_path,vectorizer_path=vector_path)
+ print("\n".join(["{}\t{}\t{}".format(str(label),str(s[label]),d) for label,s,d in zip(result,score,data)]))
diff --git b/requirements.txt a/requirements.txt
new file mode 100644
index 0000000..17e093a
--- /dev/null
+++ a/requirements.txt
@@ -0,0 +1 @@
+# dependency and version
diff --git b/sentence.py a/sentence.py
new file mode 100644
index 0000000..e97b385
--- /dev/null
+++ a/sentence.py
@@ -0,0 +1,79 @@
+# encoding: utf-8
+import nltk
+from nltk.corpus import stopwords
+stopwords = stopwords.words('english')
+# stopwords = []
+grammar = r"""
+ NBAR:
+ {<NN.*|JJ>*<NN.*>} # Nouns and Adjectives, terminated with Nouns
+ NP:
+ {<NBAR>}
+ {<NBAR><IN><NBAR>} # Above, connected with in/of/etc...
+"""
+lemmatizer = nltk.WordNetLemmatizer()
+#stemmer = nltk.stem.porter.PorterStemmer()
+
+
+class Sentence(object):
+
+ # WORD_TOKENIZER = MyPottsTokenizer(preserve_case=False)
+
+ # LEMMATIZER = WordNetLemmatizer()
+
+ # 针对于每一句话抽取aspects
+ # ASP_EXTRACTOR =
+
+ def __init__(self,sentence):
+ self.sentence = sentence
+
+
+ # def word_tokenize(self):
+ # return
+
+ # def pos_tag(self):
+ # return
+
+ # def lemmatize(self):
+ # return
+
+ # def contain_aspect(self):
+ # return
+
+ def extract_noun_phrase(self):
+ tree = self.execute()
+ nps = [np for np in self.get_terms(tree)]
+ return nps
+
+
+ def execute(self):
+ # Taken from Su Nam Kim Paper...
+ chunker = nltk.RegexpParser(grammar)
+ #toks = nltk.regexp_tokenize(text, sentence_re)
+ # #postoks = nltk.tag.pos_tag(toks)
+ toks = nltk.word_tokenize(self.sentence)
+ postoks = nltk.tag.pos_tag(toks)
+ tree = chunker.parse(postoks)
+ return tree
+
+ def leaves(self,tree):
+ """Finds NP (nounphrase) leaf nodes of a chunk tree."""
+ for subtree in tree.subtrees(filter=lambda t: t.label() == 'NP'):
+ yield subtree.leaves()
+
+ def normalise(self,word):
+ """Normalises words to lowercase and stems and lemmatizes it."""
+ word = word.lower()
+ # word = stemmer.stem(word)
+ word = lemmatizer.lemmatize(word)
+ return word
+
+ def acceptable_word(self,word):
+ """Checks conditions for acceptable word: length, stopword."""
+ accepted = bool(2 <= len(word) <= 40 and word.lower() not in stopwords)
+ return accepted
+
+ def get_terms(self,tree):
+ for leaf in self.leaves(tree):
+ term = " ".join([self.normalise(w) for w, t in leaf if self.acceptable_word(w)])
+ yield term
+
diff --git b/zhihu_link.txt a/zhihu_link.txt
new file mode 100644
index 0000000..b1081b3
--- /dev/null
+++ a/zhihu_link.txt
@@ -0,0 +1 @@
+# 请填写知乎的链接
diff --git "b/\346\203\205\346\204\237\345\210\206\346\236\220\347\263\273\347\273\237\346\220\255\345\273\272\350\257\264\346\230\216.pdf" "a/\346\203\205\346\204\237\345\210\206\346\236\220\347\263\273\347\273\237\346\220\255\345\273\272\350\257\264\346\230\216.pdf"
new file mode 100644
index 0000000..69a3da1
Binary files /dev/null and "a/\346\203\205\346\204\237\345\210\206\346\236\220\347\263\273\347\273\237\346\220\255\345\273\272\350\257\264\346\230\216.pdf" differ