Commiting for the Changes made for config.json and main.py

main.py

@@ -1 +1,83 @@
-print('Hello, Lightning World!')
+import streamlit as st
+import json
+import torch
+from transformers import AutoTokenizer
+from modelling_cnn import CNNForNER, SentimentCNNModel
+
+
+# Load the Yoruba NER model
+ner_model_name = "./my_model/pytorch_model.bin"
+model_ner = "Testys/cnn_yor_ner"
+ner_tokenizer = AutoTokenizer.from_pretrained(model_ner)
+with open("./my_model/config.json", "r") as f:
+    ner_config = json.load(f)
+
+ner_model = CNNForNER(
+                      pretrained_model_name=ner_config["pretrained_model_name"],
+                      num_classes=ner_config["num_classes"]
+                      )
+ner_model.load_state_dict(torch.load(ner_model_name, map_location=torch.device('cpu')))
+ner_model.eval()
+
+# Load the Yoruba sentiment analysis model
+sentiment_model_name = "./sent_model/sent_pytorch_model.bin"
+model_sent = "Testys/cnn_sent_yor"
+sentiment_tokenizer = AutoTokenizer.from_pretrained(model_sent)
+
+with open("./sent_model/config.json", "r") as f:
+    sentiment_config = json.load(f)
+
+sentiment_model = SentimentCNNModel(
+                                    transformer_model_name=sentiment_config["pretrained_model_name"],
+                                    num_classes=sentiment_config["num_classes"]
+                                    )
+
+sentiment_model.load_state_dict(torch.load(sentiment_model_name, map_location=torch.device('cpu')))
+sentiment_model.eval()
+
+
+def analyze_text(text):
+    # Tokenize input text for NER
+    ner_inputs = ner_tokenizer(text, return_tensors="pt")
+
+    # Perform Named Entity Recognition
+    with torch.no_grad():
+        ner_outputs = ner_model(**ner_inputs)
+    
+    ner_predictions = torch.argmax(ner_outputs.logits, dim=-1)
+    ner_labels = [ner_tokenizer.decode(token) for token in ner_predictions[0]]
+
+    # Tokenize input text for sentiment analysis
+    sentiment_inputs = sentiment_tokenizer.encode_plus(text, return_tensors="pt")
+
+    # Perform sentiment analysis
+    with torch.no_grad():
+        sentiment_outputs = sentiment_model(**sentiment_inputs)
+    sentiment_probabilities = torch.softmax(sentiment_outputs.logits, dim=1)
+    sentiment_scores = sentiment_probabilities.tolist()
+
+    return ner_labels, sentiment_scores
+
+def main():
+    st.title("YorubaCNN Models for NER and Sentiment Analysis")
+
+    # Input text
+    text = st.text_area("Enter Yoruba text", "")
+
+    if st.button("Analyze"):
+        if text:
+            ner_labels, sentiment_scores = analyze_text(text)
+
+            # Display Named Entities
+            st.subheader("Named Entities")
+            for label in ner_labels:
+                st.write(f"- {label}")
+
+            # Display Sentiment Analysis
+            st.subheader("Sentiment Analysis")
+            st.write(f"Positive: {sentiment_scores[2]:.2f}")
+            st.write(f"Negative: {sentiment_scores[0]:.2f}")
+            st.write(f"Neutral: {sentiment_scores[1]:.2f}")
+
+if __name__ == "__main__":
+    main()

my_model/config.json

@@ -1 +1,7 @@
-{"model_type": "CNNForYorubaNER", "num_classes": 9, "max_length": 128, "pretrained_model_name": "masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0"}
+{"model_type": "CNNForYorubaNER",
+ "num_classes": 9,
+ "max_length": 128,
+ "pretrained_model_name": "masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0", 
+"id2labels": {"0": "B-DATE", "1": "B-LOC", "2": "B-ORG", "3": "B-PER", "4": "I-DATE", "5": "I-LOC", "6": "I-ORG", "7": "I-PER", "8": "O"},
+"label2id": {"B-DATE": 0, "B-LOC": 1, "B-ORG": 2, "B-PER": 3, "I-DATE": 4, "I-LOC": 5, "I-ORG": 6, "I-PER": 7, "O": 8}
+}

sent_model/config.json

@@ -1 +1 @@
-{"model_type": "CNNForSentimentAnalysis", "num_classes": 2, "max_length": 128, "pretrained_model_name": "Davlan/naija-twitter-sentiment-afriberta-large"}
+{"model_type": "CNNForSentimentAnalysis", "num_classes": 2, "max_length": 128, "pretrained_model_name": "Davlan/naija-twitter-sentiment-afriberta-large", "id2label": {"0": "negative", "1": "positive"}, "label2id": {"negative": 0, "positive": 1}}