Upload app.py

app.py

@@ -1,64 +1,114 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.ensemble import RandomForestClassifier
+import matplotlib.pyplot as plt
+from wordcloud import WordCloud
+from matplotlib.font_manager import FontProperties
+import os
+
+# Function to generate word cloud for cleaned_text
+def plot_wordcloud(text_data, stopwords, width=500, height=500, background_color="White", collocations=True, min_font_size=5):
+    """Generates a word cloud for cleaned text."""
+    wordcloud = WordCloud(
+        width=width,
+        height=height,
+        background_color=background_color,
+        stopwords=stopwords,
+        collocations=collocations,
+        min_font_size=min_font_size
+    ).generate(text_data)
+
+    plt.figure(figsize=(10, 10))
+    plt.imshow(wordcloud, interpolation="bilinear")
+    plt.axis("off")
+    plt.title("Word Cloud")
+    plt.show()
+
+# Function to process uploaded file and predict sentiment
+def analyze_sentiment(file):
+    try:
+        # Load CSV
+        df = pd.read_csv(file.name)
+
+        # Ensure the required column exists
+        if 'cleaned_text' not in df.columns or 'sentiment_label' not in df.columns:
+            return "Error: The uploaded CSV must contain 'cleaned_text' and 'sentiment_label' columns."
+
+        # Extract text and labels
+        X = df['cleaned_text']
+        y = df['sentiment_label']
+
+        # Vectorize text using TF-IDF
+        vectorizer = TfidfVectorizer()
+        X_vectorized = vectorizer.fit_transform(X)
+
+        # Train Random Forest Classifier on the entire dataset
+        model = RandomForestClassifier(random_state=42)
+        model.fit(X_vectorized, y)
+
+        # Predict sentiment for the entire dataset
+        df['predicted_sentiment'] = model.predict(X_vectorized)
+
+        # Generate sentiment distribution histogram
+        plt.figure(figsize=(8, 6))
+        sentiment_counts = df['predicted_sentiment'].value_counts(normalize=True) * 100
+        sentiment_counts.sort_index().plot(kind='bar', color=['blue', 'orange', 'green'], alpha=0.7)
+        plt.title("Predicted Sentiment Distribution")
+        plt.xlabel("Sentiment Labels")
+        plt.ylabel("Percentage")
+        plt.xticks(ticks=[0, 1, 2], labels=["Negative (0)", "Positive (1)", "Neutral (2)"], rotation=45)
+        plt.grid(axis="y", linestyle="--", alpha=0.7)
+
+        # Save the histogram as an image
+        histogram_path = "sentiment_histogram.png"
+        plt.tight_layout()
+        plt.savefig(histogram_path)
+        plt.close()
+
+        # Generate a word cloud for cleaned_text
+        text_data = " ".join(X.astype(str))
+        stopwords = set()
+
+        # Plot and save the word cloud
+        plot_wordcloud(text_data, stopwords)
+
+        wordcloud_path = "wordcloud.png"
+        plt.savefig(wordcloud_path)
+        plt.close()
+
+        # Display summary
+        positive_percentage = sentiment_counts.get(1, 0)
+        negative_percentage = sentiment_counts.get(0, 0)
+        neutral_percentage = sentiment_counts.get(2, 0)
+
+        summary = (f"Sentiment Summary:\n"
+                   f"Positive: {positive_percentage:.2f}%\n"
+                   f"Negative: {negative_percentage:.2f}%\n"
+                   f"Neutral: {neutral_percentage:.2f}%")
+
+        # Display results
+        return (
+            summary,
+            histogram_path,
+            wordcloud_path
+        )
+
+    except Exception as e:
+        return f"Error processing the file: {str(e)}"
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Sentiment Analysis Chatbot")
+    gr.Markdown("Please upload a CSV file with 'cleaned_text' and 'sentiment_label' columns.")
+
+    file_input = gr.File(label="Upload CSV File", file_types=[".csv"])
+    output_text = gr.Textbox(label="Message", lines=5)
+    output_histogram = gr.Image(label="Sentiment Histogram")
+    output_wordcloud = gr.Image(label="Word Cloud")
+
+    analyze_button = gr.Button("Analyze Sentiment")
+    analyze_button.click(analyze_sentiment, inputs=file_input, outputs=[output_text, output_histogram, output_wordcloud])
+
+# Save as app.py
+demo.launch()