Now if model doesnt exist it is downloaded from huggingface. Update readme for huggingface deployment

.env.example

@@ -0,0 +1,2 @@
+MODEL_FILENAME = "some_name.h5"
+MODEL_REPOSITORY_NAME = "org/repo_name"

.gitignore

@@ -2,3 +2,4 @@ __pycache__
 *.csv
 .DS_Store
 *.h5
+.env

README.md

@@ -1,3 +1,14 @@
+---
+title: Sentiment classificator
+emoji: 🎭
+colorFrom: blue
+colorTo: red
+sdk: streamlit
+sdk_version: 1.25.0
+pinned: false
+app_file: sentiment_analysis.py
+---
+
 # bert-sentiment-analysis
 
 Prototype that classifies text into positive or negative sentiments using a fine tuned bert model
@@ -8,7 +19,7 @@ Prototype that classifies text into positive or negative sentiments using a fine
 
 ## Usage
 
-1. Download the [trained model](https://drive.google.com/file/d/1yI1yEsAco-U-Ma9uDrJSQV21DnF2n1vU/view?usp=sharing) and move it to the *models* directory
+1. Download the [trained model](https://huggingface.co/rootstrap-org/bert-sentiment-classifier/blob/main/sentiments_bert_model.h5) and move it to the *models* directory
 2. Use the tool:
 * To use it as a **streamlit web app** run:
 

models/models.py

@@ -2,19 +2,29 @@
 Module to load the project models
 """
 import os
-import tensorflow_text
+
 import tensorflow as tf
 import tensorflow_hub as hub
+import tensorflow_text
+from dotenv import load_dotenv
+from huggingface_hub import hf_hub_download
 
-
+load_dotenv()
 CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
+MODEL_FILENAME = os.getenv("MODEL_FILENAME")
+MODEL_REPOSITORY_NAME = os.getenv("MODEL_REPOSITORY_NAME")
 
 
 def load_sentiments_model():
     """
     Load pretrained model
     """
-    model_path = os.path.join(CURRENT_DIR, "sentiments_bert_model.h5")
+    model_path = os.path.join(CURRENT_DIR, MODEL_FILENAME)
+
+    # If model doesnt exist download from huggingface
+    if not os.path.exists(model_path):
+        hf_hub_download(MODEL_REPOSITORY_NAME, MODEL_FILENAME, local_dir=CURRENT_DIR)
+
     model = tf.keras.models.load_model(
         model_path, custom_objects={"KerasLayer": hub.KerasLayer}, compile=False
     )

requirements.txt

@@ -1,3 +1,5 @@
+huggingface_hub
+python-dotenv
 streamlit
 tensorflow
 tensorflow-text

sentiment_analysis.py

@@ -2,6 +2,7 @@
 Sentiment analysis streamlit webpage
 """
 import streamlit as st
+
 from sentiment_classificator import classify_sentiment
 
 
@@ -9,9 +10,9 @@ def get_representative_emoji(sentiment: str) -> str:
     """
     From a sentiment return the representative emoji
     """
-    if sentiment == 'positive':
+    if sentiment == "positive":
         return "😃"
-    elif sentiment == 'negative':
+    elif sentiment == "negative":
         return "😞"
     else:
         return "😐"
@@ -24,7 +25,7 @@ def main() -> None:
     st.title("Sentiment Classification")
 
     # Initialize session state variables
-    if 'enter_pressed' not in st.session_state:
+    if "enter_pressed" not in st.session_state:
         st.session_state.enter_pressed = False
 
     # Input text box and button

sentiment_classificator.py

@@ -2,7 +2,9 @@
 Module to classify text into positive or negative sentiments
 """
 import sys
+
 import tensorflow as tf
+
 from models.models import load_sentiments_model
 
 sentiments_model = load_sentiments_model()
@@ -25,8 +27,7 @@ def classify_sentiment(input_text: str) -> str:
 
 if __name__ == "__main__":
     if len(sys.argv) < 2:
-        print(
-            f"Usage: python {sys.argv[0]} <text to classify>")
+        print(f"Usage: python {sys.argv[0]} <text to classify>")
         sys.exit(1)
     # Get the input string from command line argument
     input_text = sys.argv[1]