Upload 6 files

.gitattributes

@@ -1,35 +1,3 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+project.tar.gz filter=lfs diff=lfs merge=lfs -text
+vector_store/analyze_embeddings.pkl filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,231 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+
+# Distribution / packaging
+logs/*.log
+*.joblib
+data/raw/
+.ipynb_checkpoints/
+.Python
+.vscode/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+csv_files/
+csv_files.zip
+data/datasets/
+# vector_store/*.pkl
+output/
+logs/
+
+# Translations
+*.mo
+*.pot
+# Raw CSVs
+csv_files/
+csv_files.zip
+
+# Processed datasets
+data/datasets/
+
+# Outputs & logs
+output/
+logs/
+
+# Embeddings / binaries
+# vector_store/*.pkl
+*.parquet
+*.feather
+*.xlsx
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+

README.md

@@ -1,17 +1,92 @@
----
-title: EDA Explorer
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 6.5.1
-app_file: app.py
-pinned: false
-hf_oauth: true
-hf_oauth_scopes:
-- inference-api
-license: mit
-short_description: 'Performs EDA Operations '
----
-
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+# 🚀 EDA Explorer – AI-Powered Data Analysis CLI
+
+A lightweight CLI tool that automates exploratory data analysis (EDA) with intelligent insights, feature importance detection, and data quality checks.
+
+Designed to simulate how an **AI Data Analyst** works on real-world datasets used in EDA. 
+
+---
+
+## ⚡ Key Highlights
+
+- 🔍 One-command analysis → `analyze <dataset>`
+- 🧠 Auto target detection for ML-based insights
+- 📈 Feature importance (no manual setup)
+- ⚠️ Smart data warnings (missing, ID columns, constants)
+- 📊 Correlation & outlier detection
+- 📁 Auto report generation (.txt)
+- ⚡ Efficient handling of large datasets (Parquet + sampling)
+
+---
+
+## 🎬 Demo
+
+👉 Full demo: https://github.com/user-attachments/assets/7dff8329-71e8-4bca-ad01-404e75df8314
+
+https://github.com/user-attachments/assets/7dff8329-71e8-4bca-ad01-404e75df8314
+
+---
+
+## 📊 Example Output
+
+Top Correlations:
+- age ↔ income: 0.72
+- tenure ↔ balance: 0.65
+
+⚠️ Data Warnings:
+- customer_id → likely ID column
+- income → 52% missing values
+
+📈 Feature Importance:
+- age: 0.41 (strong signal)
+- tenure: 0.32 (strong signal)
+
+
+---
+
+## 🧠 What Makes It Stand Out
+
+- Automatically identifies **useful vs irrelevant features**
+- No manual preprocessing required
+- Mimics real-world **data analyst reasoning**
+- Built using a **modular agent-based system**
+
+---
+
+## ⚡ Performance
+
+- Parquet-based storage for faster I/O
+- Sampling strategy for large datasets
+
+---
+
+## 🛠️ System Design
+
+- Command handler
+- Dataset registry
+- Modular agents (AnalysisAgent, etc.)
+- Logger integration
+
+---
+
+## 📦 Datasets
+
+- Titanic
+- Customer Churn
+- Credit Card Fraud
+
+---
+
+## 🛠️ Tech Stack
+
+- Python  
+- Pandas, NumPy  
+- Scikit-learn  
+- Parquet  
+
+---
+
+## 🚀 Future Enhancements
+
+- RAG-based EDA advisor  
+- SQL query assistant  
+- Model training pipeline  

app.py

@@ -1,69 +1,83 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = 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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+import os
+import sys
+from rich.console import Console
+from cli_app.command_handler import handle_command
+from utils.logger import logger
+from vector_store.instruction_embedder import embed_analyze_instructions
+import os
+import gradio as gr
+from cli_app.command_handler import handle_command
+from vector_store.instruction_embedder import embed_analyze_instructions
+
+console = Console()
+
+def run_web():
+    """The 'Space Way': A Gradio interface that acts like your CLI."""
+    import gradio as gr
+    
+    def chat_interface(command):
+        # Calls your existing logic exactly like the CLI
+        return handle_command(command)
+
+    demo = gr.Interface(
+        fn=chat_interface,
+        inputs=gr.Textbox(label="EDA Command", placeholder="Type your command here..."),
+        outputs=gr.Code(label="Terminal Output", language="markdown"),
+        title="EDA Explorer",
+        description="Web terminal for EDA Explorer. Type 'help' or your analysis commands."
+    )
+    # HF Spaces uses port 7860
+    demo.launch(server_name="0.0.0.0", server_port=7860)
+
+def run_cli():
+    embed_analyze_instructions() 
+    console.print("\n[bold cyan]EDA Explorer[/bold cyan]")
+    console.print("Type 'exit' to quit\n")
+
+    while True:
+        try:
+            cmd = console.input("[bold yellow]> [/bold yellow]")
+            if cmd.lower() == "exit":
+                break
+            
+            result = handle_command(cmd)
+            if result:
+                console.print(result)
+        except KeyboardInterrupt:
+            break
+        except Exception as e:
+            logger.error(f"CLI error | {e}")
+            console.print(f"Error: {e}")
+
+def run_space_interface():
+    """The 'Space Way' using ChatInterface."""
+    
+    # Pre-embed instructions just like your run_cli() does
+    embed_analyze_instructions()
+
+    def chat_response(message, history):
+        # 'message' is what the user typed in the box
+        # We pass it to your existing handler
+        result = handle_command(message)
+        
+        if result == "exit":
+            return "Session ended. Refresh the page to restart."
+        
+        return str(result) if result else "Command executed with no output."
+
+    # ChatInterface is the closest 'look and feel' to a CLI
+    demo = gr.ChatInterface(
+        fn=chat_response,
+        title="EDA Explorer Terminal",
+        description="Type your EDA commands below. Works just like the CLI version!",
+        examples=["help", "analyze data.csv", "status"] # Optional: suggest commands
+    )
+    
+    demo.launch(server_name="0.0.0.0", server_port=7860)
+
+if __name__ == "__main__":
+    if "SPACE_ID" in os.environ:
+        run_space_interface()
+    else:
+        run_cli()
+

requirements.txt

@@ -0,0 +1,9 @@
+matplotlib==3.10.9
+numpy==2.4.5
+pandas==3.0.3
+plotext==5.3.2
+psutil==7.2.2
+Requests==2.34.2
+rich==15.0.0
+scikit_learn==1.8.0
+sentence_transformers==5.3.0