deathbladegod020 commited on
Commit
ea49f8e
·
1 Parent(s): fcce4d1

readme updated

Browse files
Files changed (1) hide show
  1. README.md +30 -54
README.md CHANGED
@@ -1,81 +1,57 @@
1
- # Content-Based Book Recommender System
2
-
3
-
4
-
5
- This is a content-based book recommender system built using **Streamlit**. It takes a book title as input and generates up to 5 recommendations based on content similarity. The recommendations combine textual similarity (TF-IDF) and semantic similarity (Sentence Transformers). The system also handles typos and invalid inputs.
6
-
7
-
8
-
 
 
9
  ---
10
 
11
-
12
-
13
- ## Features
14
-
15
-
16
-
17
- 1. **Content-Based Recommendations**:
18
 
19
- - Combines TF-IDF and semantic similarity to recommend books.
20
 
21
- - Handles typos and approximate matches using fuzzy matching.
22
 
23
-
24
 
25
- 2. **Error Handling**:
26
 
27
- - Ensures graceful failure for invalid inputs or system errors.
28
 
29
- - Provides fallback recommendations when similarity scores are insufficient.
 
 
30
 
31
-
 
 
32
 
33
- 3. **Interactive UI**:
 
34
 
35
- - Built with Streamlit for a user-friendly interface.
36
 
37
-
38
-
39
-
40
 
41
  ## Dependencies and Functionality
42
-
43
  1. pandas:
44
-
45
- - Handles data loading, preprocessing, and manipulation.
46
-
47
-
48
 
49
  2. scikit-learn:
50
-
51
- - Provides TF-IDF vectorization and NearestNeighbors for similarity search.
52
-
53
-
54
 
55
  3. sentence-transformers:
56
-
57
- - Generates semantic embeddings for textual data.
58
-
59
-
60
 
61
  4. numpy:
62
-
63
- - Used for numerical computations like handling embeddings and arrays.
64
-
65
-
66
 
67
  5. streamlit:
68
-
69
- - Creates the interactive UI for the application.
70
-
71
-
72
 
73
  6. rapidfuzz:
74
-
75
- - Implements fuzzy matching for typos and approximate title matches.
76
-
77
-
78
 
79
  7. re:
80
-
81
- - Cleans special characters from book titles.
 
1
+ ---
2
+ title: Book Recommender
3
+ emoji: 📉
4
+ colorFrom: gray
5
+ colorTo: blue
6
+ sdk: streamlit
7
+ sdk_version: 1.41.1
8
+ app_file: app.py
9
+ pinned: false
10
+ short_description: A basic book recommender system
11
  ---
12
 
13
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
14
 
 
15
 
16
+ # Content-Based Book Recommender System
17
 
18
+ This is a content-based book recommender system built using **Streamlit**. It takes a book title as input and generates up to 5 recommendations based on content similarity. The recommendations combine textual similarity (TF-IDF) and semantic similarity (Sentence Transformers). The system also handles typos and invalid inputs.
19
 
20
+ ---
21
 
22
+ ## Features
23
 
24
+ 1. **Content-Based Recommendations**:
25
+ - Combines TF-IDF and semantic similarity to recommend books.
26
+ - Handles typos and approximate matches using fuzzy matching.
27
 
28
+ 2. **Error Handling**:
29
+ - Ensures graceful failure for invalid inputs or system errors.
30
+ - Provides fallback recommendations when similarity scores are insufficient.
31
 
32
+ 3. **Interactive UI**:
33
+ - Built with Streamlit for a user-friendly interface.
34
 
 
35
 
 
 
 
36
 
37
  ## Dependencies and Functionality
 
38
  1. pandas:
39
+ Handles data loading, preprocessing, and manipulation.
 
 
 
40
 
41
  2. scikit-learn:
42
+ Provides TF-IDF vectorization and NearestNeighbors for similarity search.
 
 
 
43
 
44
  3. sentence-transformers:
45
+ Generates semantic embeddings for textual data.
 
 
 
46
 
47
  4. numpy:
48
+ Used for numerical computations like handling embeddings and arrays.
 
 
 
49
 
50
  5. streamlit:
51
+ Creates the interactive UI for the application.
 
 
 
52
 
53
  6. rapidfuzz:
54
+ Implements fuzzy matching for typos and approximate title matches.
 
 
 
55
 
56
  7. re:
57
+ Cleans special characters from book titles.