Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -16,16 +16,16 @@ st.set_page_config(
|
|
| 16 |
layout="wide"
|
| 17 |
)
|
| 18 |
|
| 19 |
-
# App title and description
|
| 20 |
-
st.title("π Book Recommendation System")
|
| 21 |
-
st.markdown("Enter a book summary and genres to get personalized book recommendations!")
|
| 22 |
-
|
| 23 |
# GitHub URLs for model files and dataset
|
| 24 |
GITHUB_CSV_URL = "https://media.githubusercontent.com/media/Manithj/bookRecEngine/refs/heads/main/goodreadsV2.csv"
|
| 25 |
GITHUB_KNN_URL = "https://media.githubusercontent.com/media/Manithj/bookRecEngine/refs/heads/main/knn_model.pkl"
|
| 26 |
GITHUB_TFIDF_URL = "https://raw.githubusercontent.com/Manithj/bookRecEngine/main/tfidf_vectorizer.pkl"
|
| 27 |
|
| 28 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
@st.cache_resource
|
| 30 |
def load_models_from_github():
|
| 31 |
try:
|
|
@@ -42,7 +42,7 @@ def load_models_from_github():
|
|
| 42 |
st.error(f"Error loading models: {e}")
|
| 43 |
return None, None
|
| 44 |
|
| 45 |
-
# Load the dataset from GitHub
|
| 46 |
@st.cache_data
|
| 47 |
def load_data_from_github():
|
| 48 |
try:
|
|
@@ -67,9 +67,24 @@ def load_data_from_github():
|
|
| 67 |
st.error(f"Error loading dataset: {e}")
|
| 68 |
return None
|
| 69 |
|
| 70 |
-
#
|
| 71 |
-
|
| 72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
# Recommendation function for out-of-dataset books
|
| 75 |
def recommend_books_knn_out_of_dataset(input_summary, input_genres, top_n=5):
|
|
@@ -96,19 +111,6 @@ def recommend_books_knn_out_of_dataset(input_summary, input_genres, top_n=5):
|
|
| 96 |
|
| 97 |
return recommendations
|
| 98 |
|
| 99 |
-
# Status indicator for loading data
|
| 100 |
-
with st.spinner("Loading models and data from GitHub..."):
|
| 101 |
-
# Load models and data
|
| 102 |
-
tfidf, knn_model = load_models_from_github()
|
| 103 |
-
df_cleaned = load_data_from_github()
|
| 104 |
-
|
| 105 |
-
if tfidf is not None and knn_model is not None and df_cleaned is not None:
|
| 106 |
-
st.success("Models and data loaded successfully!")
|
| 107 |
-
models_loaded = True
|
| 108 |
-
else:
|
| 109 |
-
st.error("Failed to load models or data. Please check the GitHub URLs.")
|
| 110 |
-
models_loaded = False
|
| 111 |
-
|
| 112 |
# Sidebar for inputs
|
| 113 |
st.sidebar.header("Input Parameters")
|
| 114 |
|
|
@@ -186,6 +188,22 @@ st.sidebar.info(
|
|
| 186 |
"""
|
| 187 |
)
|
| 188 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
# Add a footer
|
| 190 |
st.markdown("---")
|
| 191 |
st.markdown("π Book Recommendation System | Created with Streamlit")
|
|
|
|
| 16 |
layout="wide"
|
| 17 |
)
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
# GitHub URLs for model files and dataset
|
| 20 |
GITHUB_CSV_URL = "https://media.githubusercontent.com/media/Manithj/bookRecEngine/refs/heads/main/goodreadsV2.csv"
|
| 21 |
GITHUB_KNN_URL = "https://media.githubusercontent.com/media/Manithj/bookRecEngine/refs/heads/main/knn_model.pkl"
|
| 22 |
GITHUB_TFIDF_URL = "https://raw.githubusercontent.com/Manithj/bookRecEngine/main/tfidf_vectorizer.pkl"
|
| 23 |
|
| 24 |
+
# Define the preprocessing function
|
| 25 |
+
def preprocess_text(text):
|
| 26 |
+
return re.sub(r'[^a-zA-Z0-9\s]', '', text.lower())
|
| 27 |
+
|
| 28 |
+
# Load models from GitHub - using st.cache_resource to load only once
|
| 29 |
@st.cache_resource
|
| 30 |
def load_models_from_github():
|
| 31 |
try:
|
|
|
|
| 42 |
st.error(f"Error loading models: {e}")
|
| 43 |
return None, None
|
| 44 |
|
| 45 |
+
# Load the dataset from GitHub - using st.cache_data to load only once
|
| 46 |
@st.cache_data
|
| 47 |
def load_data_from_github():
|
| 48 |
try:
|
|
|
|
| 67 |
st.error(f"Error loading dataset: {e}")
|
| 68 |
return None
|
| 69 |
|
| 70 |
+
# Load models and data at startup - this happens only once due to caching
|
| 71 |
+
with st.spinner("Loading models and data (this will only happen once)..."):
|
| 72 |
+
tfidf, knn_model = load_models_from_github()
|
| 73 |
+
df_cleaned = load_data_from_github()
|
| 74 |
+
|
| 75 |
+
if tfidf is not None and knn_model is not None and df_cleaned is not None:
|
| 76 |
+
models_loaded = True
|
| 77 |
+
else:
|
| 78 |
+
models_loaded = False
|
| 79 |
+
|
| 80 |
+
# App title and description
|
| 81 |
+
st.title("π Book Recommendation System")
|
| 82 |
+
st.markdown("Enter a book summary and genres to get personalized book recommendations!")
|
| 83 |
+
|
| 84 |
+
if not models_loaded:
|
| 85 |
+
st.error("Failed to load models or data. Please check the GitHub URLs.")
|
| 86 |
+
else:
|
| 87 |
+
st.success("Models and data loaded successfully!")
|
| 88 |
|
| 89 |
# Recommendation function for out-of-dataset books
|
| 90 |
def recommend_books_knn_out_of_dataset(input_summary, input_genres, top_n=5):
|
|
|
|
| 111 |
|
| 112 |
return recommendations
|
| 113 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
# Sidebar for inputs
|
| 115 |
st.sidebar.header("Input Parameters")
|
| 116 |
|
|
|
|
| 188 |
"""
|
| 189 |
)
|
| 190 |
|
| 191 |
+
# Add example inputs for quick testing
|
| 192 |
+
st.sidebar.markdown("---")
|
| 193 |
+
st.sidebar.header("Try these examples")
|
| 194 |
+
|
| 195 |
+
if st.sidebar.button("Example 1: Fantasy Adventure"):
|
| 196 |
+
st.sidebar.text_area("Book Summary",
|
| 197 |
+
value="A young wizard discovers his magical powers and embarks on a journey to defeat a dark lord threatening the world.",
|
| 198 |
+
height=150, key="example1_summary")
|
| 199 |
+
st.sidebar.text_input("Genres", value="fantasy, adventure, magic", key="example1_genres")
|
| 200 |
+
|
| 201 |
+
if st.sidebar.button("Example 2: Mystery Thriller"):
|
| 202 |
+
st.sidebar.text_area("Book Summary",
|
| 203 |
+
value="A detective investigates a series of murders that seem to be connected to an unsolved case from decades ago.",
|
| 204 |
+
height=150, key="example2_summary")
|
| 205 |
+
st.sidebar.text_input("Genres", value="mystery, thriller, crime", key="example2_genres")
|
| 206 |
+
|
| 207 |
# Add a footer
|
| 208 |
st.markdown("---")
|
| 209 |
st.markdown("π Book Recommendation System | Created with Streamlit")
|