Initial commit

app.py

@@ -0,0 +1,93 @@
+import os
+import shutil
+import gradio as gr
+import pandas as pd
+import openai  # Using OpenAI GPT-4 Turbo
+from gradio import Chatbot
+from gradio.data_classes import FileData
+
+# Set OpenAI API Key (Ensure it's in your environment variables)
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+base_prompt = """You are an expert data analyst.
+According to the features you have and the data structure given below, determine which feature should be the target.
+Then list 3 interesting questions that could be asked on this data, for instance about specific correlations with the target variable.
+Then answer these questions one by one, by finding the relevant numbers.
+Meanwhile, plot some figures using matplotlib/seaborn and save them to the folder './figures/'.
+Take care to clear each figure with plt.clf() before doing another plot.
+In your final answer, summarize these correlations and trends.
+After each number, derive real-world insights.
+
+Structure of the data:
+{structure_notes}
+
+The data file is passed to you as a pandas dataframe named `data_file`. You can use it directly.
+DO NOT try to load `data_file`, it is already pre-loaded!
+"""
+
+def get_images_in_directory(directory):
+    image_extensions = {'.png', '.jpg', '.jpeg', '.gif', '.bmp', '.tiff'}
+    image_files = []
+    for root, _, files in os.walk(directory):
+        for file in files:
+            if os.path.splitext(file)[1].lower() in image_extensions:
+                image_files.append(os.path.join(root, file))
+    return image_files
+
+def interact_with_agent(file_input, additional_notes):
+    shutil.rmtree("./figures", ignore_errors=True)
+    os.makedirs("./figures", exist_ok=True)
+
+    data_file = pd.read_csv(file_input)
+    data_structure_notes = f"""- Description (output of .describe()):
+    {data_file.describe()}
+    - Columns with dtypes:
+    {data_file.dtypes}"""
+
+    prompt = base_prompt.format(structure_notes=data_structure_notes)
+    if additional_notes:
+        prompt += "\nAdditional notes on the data:\n" + additional_notes
+    
+    messages = [{"role": "system", "content": "You are an expert data analyst."},
+                {"role": "user", "content": prompt}]
+    
+    yield [gr.ChatMessage(role="assistant", content="⏳ _Starting analysis..._")]
+    
+    response = openai.ChatCompletion.create(
+        model="gpt-4-turbo",
+        messages=messages,
+        max_tokens=1000
+    )
+    
+    assistant_response = response["choices"][0]["message"]["content"]
+    messages.append({"role": "assistant", "content": assistant_response})
+    
+    plot_image_paths = {}
+    for image_path in get_images_in_directory("./figures"):
+        if image_path not in plot_image_paths:
+            plot_image_paths[image_path] = True
+            messages.append(gr.ChatMessage(
+                role="assistant",
+                content=FileData(path=image_path, mime_type="image/png")
+            ))
+    yield messages
+
+# Gradio UI
+demo = gr.Blocks(
+    theme=gr.themes.Soft(
+        primary_hue=gr.themes.colors.yellow,
+        secondary_hue=gr.themes.colors.blue,
+    )
+)
+
+with demo:
+    gr.Markdown("""# GPT-4 Turbo Data Analyst 📊🤖
+Drop a `.csv` file below, add notes if needed, and **GPT-4 Turbo** will analyze it and generate insights with plots!""")
+    file_input = gr.File(label="Upload CSV file")
+    text_input = gr.Textbox(label="Additional notes")
+    submit = gr.Button("Run Analysis!", variant="primary")
+    chatbot = gr.Chatbot(label="Data Analyst Assistant", type="messages")
+    submit.click(interact_with_agent, [file_input, text_input], [chatbot])
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+pandas
+numpy
+matplotlib
+seaborn
+scipy
+smolagents
+huggingface_hub