Update app.py

app.py

@@ -1,25 +1,23 @@
-import gradio as gr
-import pandas as pd
-import re
+# Install datasets library
+!pip install -U datasets
+
+# Load Sentiment140 dataset
 from datasets import load_dataset
-from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity
-from transformers import pipeline, set_seed
-import numpy as np
+dataset = load_dataset("sentiment140")
 
-# -------------------------------
-# 1. Load and clean dataset
-# -------------------------------
-@st.cache_resource
-def load_and_prepare_data():
-    dataset = load_dataset("sentiment140")
-    df = dataset["train"].to_pandas()
-    df.dropna(subset=["text", "sentiment"], inplace=True)
-    df["text_length"] = df["text"].apply(len)
-    df = df[(df["text_length"] >= 5) & (df["text_length"] <= 280)]
-    df["clean_text"] = df["text"].apply(clean_text)
-    return df
+# Convert to pandas
+import pandas as pd
+df = dataset["train"].to_pandas()
+df.head()
+# Drop null values in text and sentiment
+df.dropna(subset=["text", "sentiment"], inplace=True)
 
+# Filter tweets with reasonable length
+df["text_length"] = df["text"].apply(len)
+df = df[(df["text_length"] >= 5) & (df["text_length"] <= 280)]
+
+# Clean the text
+import re
 def clean_text(text):
     text = text.lower()
     text = re.sub(r"http\S+", "", text)
@@ -29,32 +27,83 @@ def clean_text(text):
     text = re.sub(r"\s+", " ", text).strip()
     return text
 
-# Load data once
-df = load_and_prepare_data()
+df["clean_text"] = df["text"].apply(clean_text)
+df[["text", "clean_text"]].head()
+# Convert sentiment labels from numbers to text
+def map_sentiment(label):
+    return "negative" if label == 0 else "neutral" if label == 2 else "positive"
+
+df["sentiment_label"] = df["sentiment"].apply(map_sentiment)
+df["sentiment_label"].value_counts()
+# Save for future use
+df[["clean_text", "sentiment_label"]].to_csv("cleaned_sentiment140.csv", index=False)
+print("Cleaned data saved!")
+!pip install -U sentence-transformers
+from sentence_transformers import SentenceTransformer
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Use a small sample for speed (feel free to increase)
 sample_df = df.sample(5000, random_state=42).reset_index(drop=True)
 texts = sample_df["clean_text"].tolist()
 
-# -------------------------------
-# 2. Load models
-# -------------------------------
-embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
-generator = pipeline("text-generation", model="distilgpt2")
-set_seed(42)
-
-# -------------------------------
-# 3. Helper functions
-# -------------------------------
-def get_top3_similarities(text_input):
-    text_embeddings = embedding_model.encode(texts, show_progress_bar=False)
-    input_embedding = embedding_model.encode([text_input])
+# Load 3 different embedding models
+models = {
+    "MiniLM": SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2"),
+    "MPNet": SentenceTransformer("sentence-transformers/all-mpnet-base-v2"),
+    "DistilRoBERTa": SentenceTransformer("sentence-transformers/paraphrase-distilroberta-base-v1")
+}
+# Compute and compare similarity for one test input
+test_input = "I am so happy with this product"
+
+def get_top3_similarities(model, texts, test_input):
+    text_embeddings = model.encode(texts, show_progress_bar=True)
+    input_embedding = model.encode([test_input])
     similarities = cosine_similarity(input_embedding, text_embeddings)[0]
     top_indices = similarities.argsort()[-3:][::-1]
-    return [texts[i] for i in top_indices]
-
-def generate_best_tweet(text_input):
-    synthetic_outputs = generator(
-        text_input,
-        max_length=50,
-        num_return_sequences=10,
-        do_samp_
+    return [(i, texts[i], similarities[i]) for i in top_indices]
+
+# Try each model
+results = {}
+for name, model in models.items():
+    print(f"\n🔎 Top 3 results from: {name}")
+    top3 = get_top3_similarities(model, texts, test_input)
+    for rank, (idx, text, score) in enumerate(top3, start=1):
+        print(f"{rank}. [{score:.4f}] {text}")
+    results[name] = top3
+!pip install -U transformers
+from transformers import pipeline, set_seed
+
+# Load small GPT-2 model for text generation
+generator = pipeline("text-generation", model="distilgpt2")
+set_seed(42)  # reproducible results
+# Example user input
+test_input = "I'm feeling amazing about our product launch!"
+# Generate synthetic tweets
+synthetic_outputs = generator(
+    test_input,
+    max_length=50,
+    num_return_sequences=10,
+    do_sample=True,
+    temperature=0.9
 )
+
+# Extract just the generated text
+generated_tweets = [output["generated_text"].strip() for output in synthetic_outputs]
+for i, tweet in enumerate(generated_tweets, 1):
+    print(f"{i}. {tweet}\n")
+from sentence_transformers import SentenceTransformer
+
+# Load your best model again (MiniLM is a good choice)
+embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+# Embed input and generated tweets
+input_vec = embedding_model.encode([test_input])
+gen_vecs = embedding_model.encode(generated_tweets)
+
+# Compute similarity and select best
+from sklearn.metrics.pairwise import cosine_similarity
+similarities = cosine_similarity(input_vec, gen_vecs)[0]
+top_index = similarities.argmax()
+best_generated = generated_tweets[top_index]
+
+print(f"✅ Best AI-generated tweet:\n[{similarities[top_index]:.4f}] {best_generated}")