# -*- coding: utf-8 -*- """gradio.ipynb Automatically generated by Colab. Original file is located at https://colab.research.google.com/drive/1Kn9JCj7NyEmbQZD_QTrBwgMiUd42MH-J """ import gradio as gr print("Gradio version:", gr.__version__) import gradio as gr def add_numbers(a, b): return a + b demo = gr.Interface( fn=add_numbers, inputs=["number", "number"], outputs="number") demo.launch() import gradio as gr def simple_app(name, photo, age, language): greeting = f"Hello {name}!" info = f"You are {age} years old and prefer {language}." return greeting, photo, info demo = gr.Interface( fn=simple_app, inputs=[ gr.Textbox(label="Enter your name"), gr.Image(label="Upload your photo"), gr.Slider(0, 100, label="Your age"), gr.Dropdown(["Python", "JavaScript", "C++"], label="Favorite language"), ], outputs=[ gr.Textbox(label="Greeting"), gr.Image(label="Your Photo"), gr.Textbox(label="Your Info") ], ) demo.launch() import gradio as gr def greet(name): return f"Hello, {name}!" with gr.Blocks() as demo: name = gr.Textbox(label="Enter your name") button = gr.Button("Greet") output = gr.Textbox(label="Greeting") button.click(fn=greet, inputs=name, outputs=output) demo.launch() import gradio as gr def age_alert(age): return "You are", age,"years old!" with gr.Blocks() as demo: age_input = gr.Slider(0, 100, label="Select your age") output = gr.Textbox(label="Age Info") age_input.change(fn=age_alert, inputs=age_input, outputs=output) demo.launch() import gradio as gr import requests def get_joke(): response = requests.get("https://official-joke-api.appspot.com/random_joke") if response.status_code == 200: joke = response.json() return f"{joke['setup']} {joke['punchline']}" else: return "Oops! Could not fetch a joke right now." with gr.Blocks() as demo: btn = gr.Button("Tell me a joke!") output = gr.Textbox(label="Here's your joke") btn.click(fn=get_joke, inputs=None, outputs=output) demo.launch() """Sentiment Analyzer UI""" import gradio as gr from transformers import pipeline sentiment_pipeline = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment") def analyze_sentiment(text): result = sentiment_pipeline(text)[0] label = result['label'] score = result['score'] return f"Sentiment: {label}\nConfidence: {score:.2f}" gr.Interface( fn=analyze_sentiment, inputs=gr.Textbox(lines=3, placeholder="Type your sentence here..", label="Input Text"), outputs=gr.Textbox(label="Sentiment Result"), title="Sentiment Analyzer", description="Enter a sentence and find out its sentiment based on score." ).launch() """Creating Interfaces For Classic ML Models Setup the Project """ pip install scikit-learn gradio pandas """Train a Simple Model""" # Load dataset from sklearn.datasets import fetch_california_housing import pandas as pd from sklearn.model_selection import train_test_split from sklearn.pipeline import make_pipeline from sklearn.preprocessing import StandardScaler from sklearn.ensemble import RandomForestRegressor data = fetch_california_housing(as_frame=True) df = data.frame X = df.drop(columns=["MedHouseVal"]) y = df["MedHouseVal"] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) model = make_pipeline(StandardScaler(), RandomForestRegressor()) model.fit(X_train, y_train) """Create Prediction Function""" def predict_house_price(med_inc, house_age, ave_rooms, ave_bedrooms, population, ave_occup, latitude, longitude): input_data = pd.DataFrame([[ med_inc, house_age, ave_rooms, ave_bedrooms, population, ave_occup, latitude, longitude]], columns=X.columns) prediction = model.predict(input_data)[0] return f"Predicted Price: ${prediction * 100000:.2f}" """Build the Gradio Interface""" import gradio as gr interface = gr.Interface( fn=predict_house_price, inputs=[ gr.Slider(0.0, 20.0, label="Median Income (10k$ units)"), gr.Slider(1, 50, label="House Age"), gr.Slider(1, 10, label="Average Rooms"), gr.Slider(1, 5, label="Average Bedrooms"), gr.Slider(100, 50000, label="Population"), gr.Slider(1, 10, label="Average Occupancy"), gr.Slider(32, 42, label="Latitude"), gr.Slider(-125, -114, label="Longitude"), ], outputs="text", title="California House Price Predictor", description="Enter basic housing info to estimate price", ) interface.launch(share=True) """Deploying Gradio Apps Step 1: Prepare Your Files You’ll need 3 files in your project folder: 1. app.py Save your code in a file called app.py. This is the main app file. Hugging Face Spaces will run this file to launch your Gradio UI. 2. requirements.txt This file tells Hugging Face what Python libraries are needed to run your app. Create a requirements.txt file with this content: gradio pandas scikit-learn Hugging Face installs these packages in the background. If you miss one, your app might crash! 3. README.md (Optional) It is a project description for Hugging Face viewers. Add a README.md with a short intro to your app. Example: California House Price Predictor This Gradio app predicts the median house price in California based on features like income, age, rooms, etc. Built using: - Scikit-learn - Gradio - California Housing Dataset Step 2: Create a Hugging Face Space Go to Hugging Face Space and click on “Create new Space”. Fill the details: Space name: e.g., california-house-predictor Space SDK: Choose Gradio Visibility: Public or Private Click “Create Space” Step 3: Upload Your Files You’ll be taken to the Space repo view. Now: Click “Files” Click “Add file” --> Upload files Upload: app.py, requirements.txt and README.md (optional) Step 4: Wait for Build Once files are uploaded: Hugging Face will automatically install dependencies from requirements.txt Then it will run app.py, which launches the Gradio interface After a few seconds to minutes, your app will be live in the browser! """