Upload 4 files

AICodeInit/LlamaCode.py

@@ -0,0 +1,31 @@
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer, pipeline
+# Load the model
+
+def create_pipeline():
+    model = AutoPeftModelForCausalLM.from_pretrained("Moritz-Pfeifer/financial-times-classification-llama-2-7b-v1.3")
+    tokenizer = AutoTokenizer.from_pretrained("Moritz-Pfeifer/financial-times-classification-llama-2-7b-v1.3")
+    prompt = f"""
+            "You are given a news article regarding the greater Boston area.
+            Analyze the sentiment of the article enclosed in square brackets,
+            determine if it is positive, negative or neutral and return the answer as the corresponding sentiment label
+            "positive", "negative", or "neutral"".
+
+            """
+    pipe = pipeline(task="text-generation",
+                        model=model,
+                        tokenizer=tokenizer,
+                        max_new_tokens = 1,
+                        temperature = 0.1,
+                        )
+    return prompt, pipe
+
+def predict_text(text,pipe,prompt):
+    result = pipe((prompt+"\n"+'['+'{'+text+'}'+']'+' '+'='))
+    answer = result[0]['generated_text'].split("=")[-1]
+    if "positive" in answer.lower():
+        return "positive"
+    elif "negative" in answer.lower():
+        return "negative"
+    else:
+        return "neutral"

AICodeInit/__init__.py

@@ -0,0 +1,2 @@
+from .LlamaCode import *
+from .spacy_textblob_functions import *

AICodeInit/spacy_textblob_functions.py

@@ -0,0 +1,57 @@
+from peft import AutoPeftModelForCausalLM
+import spacy
+import pandas as pd
+from textblob import TextBlob
+
+
+def load_model():
+    nlp = spacy.load("en_core_web_sm") 
+    return nlp
+
+def extract_entities(text,nlp):
+    doc = nlp(text)
+    entities = [(ent.text, ent.label_) for ent in doc.ents]
+    return entities
+
+# Function to extract entities context
+def extract_entities_with_context(text, nlp, window=5):
+    doc = nlp(text)
+    entity_context = []
+    for ent in doc.ents:
+        start = max(0, ent.start - window)
+        end = min(len(doc), ent.end + window)
+        context = doc[start:end].text
+        entity_context.append((ent.text, ent.label_, context))
+    return entity_context
+
+def get_sentiment(text):
+    return TextBlob(text).sentiment.polarity
+
+def analyze_entity_sentiments(entity_contexts):
+    sentiments = []
+    for text, label, context in entity_contexts:
+        sentiment = get_sentiment(context)
+        sentiments.append((text, label, sentiment))
+    return sentiments
+
+def analyze_entity_sentiments_score(entity_contexts):
+    sentiments = []
+    for text, label, context in entity_contexts:
+        sentiment = get_sentiment(context)
+        sentiments.append((sentiment))
+    return sentiments
+
+def calculate_avg_score(scores):
+    if scores:
+        return sum(scores) / len(scores)
+    else:
+        return float('inf')
+
+
+def categorize_sentiment(score):
+    if score <= -0.1:
+        return 'Negative'
+    elif score >= 0.1:
+        return 'Positive'
+    else:
+        return 'Neutral'