VSM-rocchio-algorithm

Vector space Model implement rocchio algorithm

1. About
2. basic function
3. Quick start
4. Contacts

---

1. About

---

In this project, you will have

800 Queries

2265 Documents

A Background Language Model(BGLM.txt)

Our goal is to implement the VSM model, and inhence by rocchio-algorithm

2. basic function

---

Here are the basic function for this web:

Update_new_query() :

Update query by top_k rocchio-algorithm

cosine_similarity:

Calculator documents and query cosine_similarity

rank_ALL_func:

Get score with each document for each Query

Get_read_data_func :

Read and Get only integer in text

init_subfilename :

Get all subfilename in spec File

init_idf :

Calculator term idf and update idf matrix

update_tf_func :

Calculator term tf in each document and update tf matrix

3. Quick start

---

Download data you need

Edit a、b、k_top for rocchio algorithm you wanted

Run the p.y

Get the result for our query

4. Contacts

---

You can send your suggestions and send them directly to [email protected].