Upload 17 files

.gitattributes

@@ -37,7 +37,3 @@ src/Negative[[:space:]]-[[:space:]]Topic[[:space:]]Activities[[:space:]]Over[[:s
 src/Negative[[:space:]]-[[:space:]]Wordcloud.png filter=lfs diff=lfs merge=lfs -text
 src/Positive[[:space:]]-[[:space:]]Topic[[:space:]]Activities[[:space:]]Over[[:space:]]Time.png filter=lfs diff=lfs merge=lfs -text
 src/Positive[[:space:]]-[[:space:]]Wordcloud.png filter=lfs diff=lfs merge=lfs -text
-src/src/Negative[[:space:]]-[[:space:]]Topic[[:space:]]Activities[[:space:]]Over[[:space:]]Time.png filter=lfs diff=lfs merge=lfs -text
-src/src/Negative[[:space:]]-[[:space:]]Wordcloud.png filter=lfs diff=lfs merge=lfs -text
-src/src/Positive[[:space:]]-[[:space:]]Topic[[:space:]]Activities[[:space:]]Over[[:space:]]Time.png filter=lfs diff=lfs merge=lfs -text
-src/src/Positive[[:space:]]-[[:space:]]Wordcloud.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,9 +1,22 @@
 # Hugging Face cache
 .cache/
+hf_cache/
 
-# Streamlit cache
+# NLTK data
+nltk_data/
+
+# Streamlit cache & config
 .streamlit/
+.streamlit/*
 
 # Python bytecode
 __pycache__/
-*.pyc
+*.pyc
+*.pyo
+*.pyd
+
+# Logs & temp
+*.log
+tmp/
+*.sqlite3
+*.db

Dockerfile

@@ -8,8 +8,6 @@ RUN apt-get update && apt-get install -y \
     git \
     && rm -rf /var/lib/apt/lists/*
 
-ENV HF_HOME=/app/.cache/huggingface
-
 COPY requirements.txt ./
 COPY src/ ./src/
 

requirements.txt

@@ -1,16 +1,16 @@
-streamlit==1.44.0
-pandas==2.2.3
-seaborn
-matplotlib
-plotly
-pillow
-numpy
-fastopic==1.0.1
-topmost==1.0.2
-torch==2.6.0
-torchvision==0.21.0
-gensim==4.3.3
-joblib==1.2.0
-scikit-learn==1.6.1
-tensorflow==2.20.0
+streamlit==1.44.0
+pandas==2.2.3
+seaborn
+matplotlib
+plotly
+pillow
+numpy
+fastopic==1.0.1
+topmost==1.0.2
+torchvision==0.21.0
+gensim==4.3.3
+torch==1.11.0
+joblib==1.2.0
+scikit-learn==1.6.1
+tensorflow==2.20.0
 nltk

src/prediction.py

@@ -37,22 +37,35 @@ st.markdown(
 )
 
 # ============================================
-# Hugging Face Hub Repo
+# Hugging Face Hub Repo & Cache Dir
 # ============================================
 repo_id = "BesottenJenny/acre-sentiment-models"
+hf_cache_dir = os.path.join("/tmp", "hf_cache")
 
 # ============================================
 # Cached Loading Functions
 # ============================================
 @st.cache_resource
 def load_sentiment_model():
-    path = hf_hub_download(repo_id=repo_id, filename="best_model.keras")
+    path = hf_hub_download(
+        repo_id=repo_id,
+        filename="best_model.keras",
+        cache_dir=hf_cache_dir
+    )
     return keras.models.load_model(path)
 
 @st.cache_resource
 def load_tokenizer_params():
-    tokenizer_path = hf_hub_download(repo_id=repo_id, filename="tokenizer.pkl")
-    params_path = hf_hub_download(repo_id=repo_id, filename="params.pkl")
+    tokenizer_path = hf_hub_download(
+        repo_id=repo_id,
+        filename="tokenizer.pkl",
+        cache_dir=hf_cache_dir
+    )
+    params_path = hf_hub_download(
+        repo_id=repo_id,
+        filename="params.pkl",
+        cache_dir=hf_cache_dir
+    )
     with open(tokenizer_path, "rb") as f:
         tokenizer = pickle.load(f)
     with open(params_path, "rb") as f:
@@ -61,8 +74,16 @@ def load_tokenizer_params():
 
 @st.cache_resource
 def load_topic_models():
-    neg_path = hf_hub_download(repo_id=repo_id, filename="fastopic_negative_model.pkl")
-    pos_path = hf_hub_download(repo_id=repo_id, filename="fastopic_positive_model.pkl")
+    neg_path = hf_hub_download(
+        repo_id=repo_id,
+        filename="fastopic_negative_model.pkl",
+        cache_dir=hf_cache_dir
+    )
+    pos_path = hf_hub_download(
+        repo_id=repo_id,
+        filename="fastopic_positive_model.pkl",
+        cache_dir=hf_cache_dir
+    )
     neg_model = joblib.load(neg_path)
     pos_model = joblib.load(pos_path)
     return neg_model, pos_model