Cleared cell outputs
This commit is contained in:
samuelmurira
@@ -0,0 +1,229 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2714fa36",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Week 3 Data Generator With Opensource Models\n",
|
||||
"# Generate synthetic data for Pizza cusromers within Nairobi "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "761622db",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install requests pandas ipywidgets gradio"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cc7347c4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import gradio as gr\n",
|
||||
"from huggingface_hub import InferenceClient\n",
|
||||
"import random\n",
|
||||
"import os\n",
|
||||
"from dotenv import load_dotenv\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f20cd822",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#Load API Key\n",
|
||||
"\n",
|
||||
"load_dotenv(override=True)\n",
|
||||
"HF_API_KEY = os.getenv('HF_TOKEN')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "856cd8cb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\n",
|
||||
"# Define available models with correct Hugging Face model IDs\n",
|
||||
"MODELS = {\n",
|
||||
" \"Mistral-7B\": \"mistralai/Mistral-7B-Instruct-v0.2\",\n",
|
||||
" \"Llama-2-7B\": \"meta-llama/Llama-2-7b-chat-hf\",\n",
|
||||
" \"Phi-2\": \"microsoft/phi-2\",\n",
|
||||
" \"GPT-2\": \"gpt2\"\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"# Nairobi branches\n",
|
||||
"BRANCHES = [\"Westlands\", \"Karen\", \"Kilimani\", \"CBD\", \"Parklands\"]\n",
|
||||
"\n",
|
||||
"# Global variable to store generated data\n",
|
||||
"generated_df = None\n",
|
||||
"\n",
|
||||
"def generate_feedback_data(model_name, num_records):\n",
|
||||
" \"\"\"Generate synthetic pizza feedback data using selected AI model\"\"\"\n",
|
||||
" global generated_df\n",
|
||||
" \n",
|
||||
" try:\n",
|
||||
" # Initialize the Hugging Face Inference Client\n",
|
||||
" model_id = MODELS[model_name]\n",
|
||||
" client = InferenceClient(model=model_id, token=None) # Add your HF token if needed\n",
|
||||
" \n",
|
||||
" feedback_data = []\n",
|
||||
" \n",
|
||||
" for i in range(num_records):\n",
|
||||
" # Random branch\n",
|
||||
" branch = random.choice(BRANCHES)\n",
|
||||
" \n",
|
||||
" # Generate feedback using the AI model\n",
|
||||
" prompt = f\"Generate a brief customer feedback comment about a pizza order from {branch} branch in Nairobi. Make it realistic and varied (positive, negative, or neutral). Keep it under 30 words.\"\n",
|
||||
" \n",
|
||||
" try:\n",
|
||||
" response = client.text_generation(\n",
|
||||
" prompt,\n",
|
||||
" max_new_tokens=50,\n",
|
||||
" temperature=0.8\n",
|
||||
" )\n",
|
||||
" feedback = response.strip()\n",
|
||||
" except Exception as e:\n",
|
||||
" # Fallback to template-based generation if API fails\n",
|
||||
" feedback = generate_fallback_feedback(branch)\n",
|
||||
" \n",
|
||||
" # Generate other fields\n",
|
||||
" record = {\n",
|
||||
" \"Customer_ID\": f\"CUST{1000 + i}\",\n",
|
||||
" \"Branch\": branch,\n",
|
||||
" \"Rating\": random.randint(1, 5),\n",
|
||||
" \"Order_Type\": random.choice([\"Delivery\", \"Dine-in\", \"Takeaway\"]),\n",
|
||||
" \"Feedback\": feedback,\n",
|
||||
" \"Date\": f\"2024-{random.randint(1, 12):02d}-{random.randint(1, 28):02d}\"\n",
|
||||
" }\n",
|
||||
" \n",
|
||||
" feedback_data.append(record)\n",
|
||||
" \n",
|
||||
" # Create DataFrame\n",
|
||||
" generated_df = pd.DataFrame(feedback_data)\n",
|
||||
" \n",
|
||||
" return generated_df, f\"✓ Successfully generated {num_records} records using {model_name}\"\n",
|
||||
" \n",
|
||||
" except Exception as e:\n",
|
||||
" return pd.DataFrame(), f\"✗ Error: {str(e)}\"\n",
|
||||
"\n",
|
||||
"def generate_fallback_feedback(branch):\n",
|
||||
" \"\"\"Fallback feedback generator if API fails\"\"\"\n",
|
||||
" templates = [\n",
|
||||
" f\"Great pizza from {branch}! Quick delivery and hot food.\",\n",
|
||||
" f\"Pizza was cold when it arrived at {branch}. Disappointed.\",\n",
|
||||
" f\"Excellent service at {branch} branch. Will order again!\",\n",
|
||||
" f\"Average experience. Pizza was okay but nothing special.\",\n",
|
||||
" f\"Long wait time at {branch} but the pizza was worth it.\",\n",
|
||||
" ]\n",
|
||||
" return random.choice(templates)\n",
|
||||
"\n",
|
||||
"def download_csv():\n",
|
||||
" \"\"\"Save generated data as CSV\"\"\"\n",
|
||||
" global generated_df\n",
|
||||
" if generated_df is not None:\n",
|
||||
" generated_df.to_csv('pizza_feedback_data.csv', index=False)\n",
|
||||
" return \"CSV downloaded!\"\n",
|
||||
" return \"No data to download\"\n",
|
||||
"\n",
|
||||
"def download_json():\n",
|
||||
" \"\"\"Save generated data as JSON\"\"\"\n",
|
||||
" global generated_df\n",
|
||||
" if generated_df is not None:\n",
|
||||
" generated_df.to_json('pizza_feedback_data.json', orient='records', indent=2)\n",
|
||||
" return \"JSON downloaded!\"\n",
|
||||
" return \"No data to download\"\n",
|
||||
"\n",
|
||||
"# Create Gradio interface\n",
|
||||
"with gr.Blocks(title=\"Pizza Feedback Data Generator\") as demo:\n",
|
||||
" gr.Markdown(\"\"\"\n",
|
||||
" # 🍕 Pizza Feedback Data Generator\n",
|
||||
" Generate synthetic customer feedback for Nairobi pizza branches using AI models\n",
|
||||
" \"\"\")\n",
|
||||
" \n",
|
||||
" with gr.Row():\n",
|
||||
" with gr.Column():\n",
|
||||
" model_selector = gr.Radio(\n",
|
||||
" choices=list(MODELS.keys()),\n",
|
||||
" label=\"Select AI Model\",\n",
|
||||
" value=list(MODELS.keys())[0]\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" num_records_slider = gr.Slider(\n",
|
||||
" minimum=1,\n",
|
||||
" maximum=50,\n",
|
||||
" value=10,\n",
|
||||
" step=1,\n",
|
||||
" label=\"Number of Records\"\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" generate_btn = gr.Button(\"Generate Feedback Data\", variant=\"primary\")\n",
|
||||
" \n",
|
||||
" with gr.Row():\n",
|
||||
" status_output = gr.Textbox(label=\"Status\", interactive=False)\n",
|
||||
" \n",
|
||||
" with gr.Row():\n",
|
||||
" dataframe_output = gr.Dataframe(\n",
|
||||
" label=\"Generated Feedback Data\",\n",
|
||||
" interactive=False\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" with gr.Row():\n",
|
||||
" csv_btn = gr.Button(\"Download CSV\")\n",
|
||||
" json_btn = gr.Button(\"Download JSON\")\n",
|
||||
" \n",
|
||||
" # Event handlers\n",
|
||||
" generate_btn.click(\n",
|
||||
" fn=generate_feedback_data,\n",
|
||||
" inputs=[model_selector, num_records_slider],\n",
|
||||
" outputs=[dataframe_output, status_output]\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" csv_btn.click(\n",
|
||||
" fn=download_csv,\n",
|
||||
" outputs=status_output\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" json_btn.click(\n",
|
||||
" fn=download_json,\n",
|
||||
" outputs=status_output\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"# Launch the interface\n",
|
||||
"demo.launch()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.12"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user